DE29723632U1 - Computer controlled hydraulic resistance device for a prosthesis and other devices - Google Patents

Description

SCHROETER FLEUCHAUS LEHMANN & dALLCJ *!

PATENT ATTORNEYS · EUROPEAN PATENT ATTORNEYS
WOLFRATSHAUSER STR. 145 ■ D-81479 MUNICH

New German utility model application

Mauch, Inc. September 14, 1998

Our reference: jx-ma-10 AL/ho/pe

Computer-controlled hydraulic resistance device
for a prosthesis and other devices

Background of the invention

The present invention is ideally suited for use with an artificial leg or prosthesis worn by a above-the-knee amputee, but also allows for other applications and uses. Typically, this type of prosthesis comprises an artificial knee joint having a socket for receiving and gripping the user's stump, a knee brace rigidly connected to the socket, and a frame extending downward from the brace and pivotally connected to the brace by a horizontal shaft. A trunk and an artificial foot are connected to the base of the frame, and a control unit is connected to lock the knee joint to prevent it from collapsing under load in the stance or posture phase of a step and to release the knee joint in the swing phase of the step. Preferably, the prosthesis controls the knee joint in such a way that the amputee can walk with a normal or natural-appearing gait. This gait is characterized by almost identical movements performed by both lower limbs at varying walking speeds.

The biological or natural knee joint is powered by the actions of muscles. Each muscle develops an active force through contraction and also allows for variable stiffness or resistance. It has not been possible to imitate muscle contraction in leg prostheses due to the weight and

jx-ma-10 - 2 -

volumes that would be required to mimic this function. Research has focused on applying a stiffness or resistance to rotation of the knee joint. Typically, this involves switching the knee joint into one of two modes, namely locked or free to rotate. The locked mode occurs during the stance phase of the walking cycle, and the free to rotate mode occurs during the swing phase of the walking cycle. The stance phase is when the prosthetic foot is on the ground, and the swing phase is when the prosthetic foot is off the ground.

Much of the research in recent years has sought improvements in the control of an artificial knee joint in ways that improve gait and enable the amputee to cope with situations such as descending stairs or ramps or lowering into a sitting position. If a knee joint is considered a simple joint, there are two distinct processes that occur. During flexion, the upper and lower sections move closer together as the knee joint rotates. During extension, the leg straightens and the sections move apart. In order for a prosthetic knee joint to replicate a biological knee, it is necessary to independently and variably control the resistance to rotation in each direction. This resistance to rotation during the swing phase can be accomplished by a mechanical damper or friction device, a pneumatic damper, or a hydraulic damper. It is generally accepted in prosthetics that a hydraulic damper provides the smoothest operation over a wider range of walking speeds.

The stance phase control must provide very high resistance to bending or completely lock any rotation against bending. The stance control is usually accomplished by a weight-activated mechanical locking brake mechanism or a position-activated polycentric linkage system or a position-activated hydraulic damper. Mechanical brake mechanisms can be difficult to keep correctly adjusted and can cause the amputee to walk with a somewhat unnatural gait. Position-activated polycentric mechanisms require more concentration and can be difficult for amputees to use in certain situations. Hydraulic dampers require more concentration and training from the amputee while allowing a more natural gait.

jx-ma-10

-3 -

U.S. Patents 5,405,409 and 5,443,521, issued to the assignee of the present invention, disclose a linear type hydraulic damper for controlling an above-the-knee prosthesis. This hydraulic damper has an independently adjustable and variable resistance in flexion and extension during the swing phase of the walking cycle. Due to the turbulent flow of hydraulic fluid during the swing phase, this damper can accommodate a wide range of walking speeds. The control damper has a single damping rate in the stance phase that can be manually adjusted to suit the needs of each individual amputee. When the knee joint is fully extended, the damper enters a non-stance resistance mode of operation. This position-activated stance phase may initially require additional walking training and concentration on the part of the amputee to obtain the full benefit of the damper.

More recently, electronics have been introduced into lower limb prosthetics in an attempt to make walking easier for the amputee. For example, US patents 5,062,856, 5,383,939 and 5,571,205 disclose two systems that use microprocessor control to adjust the resistance in a pneumatic or hydraulic cylinder during the swing phase in an attempt to provide control of the rotation of the knee joint over a wider range of walking speeds than is possible with conventional pneumatic or friction dampers.

A further improvement in the amputee's gait could come from a mechanism that would allow a small amount of knee flexion at the beginning of the stance phase and then lock against further flexion while allowing knee extension as the leg extends due to body motion. Such a mechanism is described by Siegmar et al. in "Design Principles, Biomechanical Data and Clinical Experience with a Polycentric Knee Offering Controlled Stance Phase Knee Flexion: A Preliminary Report", Journal of Prosthetics and Orthotics, Vol. 9, No. 1, pp. 18-24, Winter 1997, and by Popvic et al. in "Optimal Control for an Above-knee Prosthesis with Two Degrees of Freedom", J. Biomechanics, Vol. 28, No. 1, pp. 89-98, 1995.

An amputee requires a different resistance to knee flexion when going down stairs than is required when sitting down in a chair. It is therefore desirable for a control device to be able to automatically provide these different resistances to knee flexion. The control

jx-ma-10 - 4 -

The device should also provide vibration resistance over a wide range of walking speeds. All of this should be automatic so that the amputee can walk without having to think about his prosthesis.

The same type of computer-controlled hydraulic damping system that can be used in amputees can also be used in other applications, such as robotic systems, braking systems, and exercise equipment. These applications differ only in the size of the actuator to control the maximum resistance applied. They can all use the same sensors, microprocessor-controlled electronics, and valve technology. Computer-controlled exercise equipment is disclosed in U.S. Patents 4,354,676, 4,711,450, 4,919,418, 5,230,672, and 5,397,287. However, in any such device it is desirable to be able to maintain an accurately applied resistance over a wide range of temperature and manufacturing tolerances. It is also desirable to have an appropriate feedback control and a hydraulic valve and regulator designed for relatively low operating speeds.

Summary of the invention

The present invention is directed to a computer controlled closed-loop electromechanical resistance device. One application of the device is to provide vibration resistance for the knee unit of a lower limb prosthesis as worn by an above-the-knee amputee. Other applications of the invention include rehabilitation devices, exercise equipment, braking devices, or various other dampening applications.

According to a preferred embodiment of this invention, the device comprises a rotary vane or blade rotor or drive. When the rotary vane is rotated, hydraulic fluid is forced through an electronically controlled valve from one side of the impeller to the opposite side of the impeller. When rotation is reversed, the direction of the hydraulic fluid is reversed and it flows back through the same valve. Computer control of the valve causes a variable pressure differential from one side of the rotary vane to the other side. The variable pressure differential is received as a variable resistance on the rotary vane. However, the resistance device of the invention can also be applied with equal effectiveness to a linear type drive.

jx-ma-10 . - 5 -

The valve used in the device is a proportionally controlled, solenoid operated, balanced spool or control valve. The shape of the spool or barrel is such that flow across the face of the spool has little or no effect on spool movement, thus eliminating any possibility of unbalanced flow induced forces. The valve spool is also pressure balanced to eliminate any possibility of hydraulic locking. The magnetic core of the valve is designed to produce a nearly constant force in the duty cycle of the spool when constant power is supplied. The valve control includes a high frequency dither signal to prevent spool lag and proportional control is provided to minimize any large wear rate normally associated with pulse width modulated control.

The valve control used in the device is a microprocessor-based, closed-loop, adaptive control. The microprocessor receives the pressure differential across the drive or rotor impeller, the rotor position, an auxiliary force, and a pressure differential error at 1 ms intervals (1,000 Hz). The microprocessor calculates the rotor position, the rotor speed, and the rotor direction at 10 ms intervals (100 Hz). Based on this information, the microprocessor calculates the required rotor resistance (pressure differential) based on state equations, thereby creating an automatically adjusting resistance device. If the difference between the actual and the required pressure differential is large, the microprocessor changes the valve in large steps to compensate for this large error. If the difference between the actual and the required pressure differential is small, the microprocessor changes the valve in small steps to compensate for this small error. By using pressure feedback for the closed loop, the control system is able to compensate for machining tolerances, valve solenoid resistance changes, varying fluid viscosity, temperature effects and wear. Constants in the equations of state adjust for adaptive control with changes in the system operating environment.

When the device according to the invention is used as a knee control unit for a person with an above-the-knee amputation, the control unit determines five significant points in a typical walking cycle. The two main areas of a walking cycle are the stance or posture phase and the swing phase. The posture phase is the time period in which the prosthesis is in contact with the ground. The swing phase is the time period in which the prosthesis is not in contact with the ground. The first

jx-ma-10

-6-

The main point considered is the heel strike, which is the beginning of the stance phase. This is the point at which the prosthesis first touches the ground and no longer swings in the air. At this point the prosthesis must be stable so that it does not collapse when the amputee's weight is transferred to the other leg.

A yielding stance is ideal for this situation, where a great deal of resistance is applied to support the amputee, but the prosthesis is allowed to flex slightly. Ideally, the prosthesis should flex 10° so that the amputee does not have to jump over a fully extended prosthesis. This 10° flexure during the stance is the second point of consideration. At this point, the prosthesis begins to extend as the amputee moves himself forward. During this forward movement, the prosthesis fully extends. After the forward movement, the third point is the initiation of flexion, where the amputee begins to move the prosthesis forward by flexing the hip. The fourth point is when the toe is removed, with the prosthesis leaving the ground. This is the beginning of the swing phase.

During the swing phase, the knee control unit provides a significant amount of resistance to limit the swing speed and amount of angular movement of the lower portion of the prosthesis. Ideally, the knee should not bend more than 65° during the swing phase. This can be accomplished by applying a large amount of resistance to limit the amount of heel lift. Due to the kinetic energy of the prosthesis, the knee control unit begins to extend as it swings through the air. The fifth point to consider is the final deceleration. This occurs just before heel strike during the last few degrees of extension, during which a large amount of resistance must be applied to limit any hard knee strike as the prosthesis rests the extension stops.

To control the knee control unit, the microprocessor of the invention records the pressure differential on the rotor impeller, knee position, pressure differential error and prosthetic force at 1 ms intervals (1,000 Hz). The microprocessor calculates knee position, knee velocity, knee direction and records user settings (1-10) for flexion and extension at 10 ms intervals (100 Hz). The user settings for flexion and extension form a range of use and the adaptive control fine-tunes the unit from this baseline.

jx-ma-10 - 7 -

Based on this information, the microprocessor calculates the required knee resistance (pressure differential) based on state equations, creating an automatically adjusting knee control unit.

Constants in the state equations are able to adapt to changes in the system operating environment. If the difference between the actual and the required pressure differential is large, the microprocessor changes the valve in large increments to compensate for this large error. If the difference between the actual and the required pressure differential is small, the microprocessor changes the valve in smaller increments to compensate for this small error. As the knee angle extends and approaches full extension, the microprocessor begins to close the valve to create a large resistance and slow the prosthesis in the extension direction. As the knee angle flexes and approaches the ideal heel lift, the microprocessor begins to close the valve to create a large resistance and slow the prosthesis in the flexion direction. The measured prosthetic force allows the microprocessor to distinguish between heel strike, mid-stance or toe-off states. This assists the amputee in descending stairs by creating a large knee resistance and lowering the amputee to the next step using his or her own weight.

Trip recovery is accomplished by recording force and knee pivot speed. If the force sensors indicate a stance phase and knee velocity is high, this could indicate a trip condition, so the system applies a large amount of resistance to help the amputee regain control. In the event of prolonged non-use of more than five seconds, the microprocessor returns to a sleep state where all components except the knee angle sensor circuit are turned off. This conserves battery power, but allows the control system to resume operation if the knee angle changes. The control system is powered by four 3.6-volt lithium-ion batteries in a removable battery pack that is rechargeable to 90% capacity in two hours. Battery life is approximately 30 hours between full recharges.

The knee control unit preferably works with a rotary vane rotor which is arranged inside a rotor housing on the knee axis, wherein the knee clamp with

·

·♦···♦

jx-ma-10 - 8 -

connected to the rotary impeller. When the knee is flexed, the impeller rotates, forcing hydraulic fluid out of the housing through the solenoid control valve, which in turn controls fluid flow and pressure. This control of fluid flow and pressure provides the resistance available at the knee axis. Fluid exiting the solenoid control valve flows through a weight-operated position valve. This valve limits fluid flow whenever a weight is applied to the prosthesis. The position valve is adjustable to allow different levels of compliance depending on the weight or desire of the amputee. Fluid exiting the position valve enters an extension bias cylinder. This cylinder consists of a spring-loaded piston that is compressed when the knee control unit is flexed. Fluid on the opposite side of the biasing piston is directed to the opposite side of the rotating impeller, closing the fluid path. During extension, the flow is reversed, with the stored potential energy of the spring-loaded piston available to contribute to the extension of the prosthesis.

Further features and advantages of the invention will become apparent from the following description, the accompanying drawings and the appended claims.

Short description of the drawings

Figure 1 is a side view of a lower limb prosthesis for up to

the knee amputee, comprising a resistance device or knee control unit constructed according to the invention;

Figure 2 is an enlarged fragmentary side view of the device shown in Figure 1.

knee control unit;

Figure 3 is the front view of the knee control unit;

Figure 4 is the rear view of the knee control unit;

Figure 5 is a section taken substantially along line 5-5 of Figure 3, wherein

components inside are shown;

jx-ma-10 - 9 -

Figure 6 is a partial sectional view taken substantially along line 6-6 of Figure 3, wherein

the knee angle sensor mechanism is shown;

Figure 7 is a section taken substantially along line 7-7 of Figure 2, wherein the

resistance rotor and the rotor housing are shown;

Figure 8 is a section taken substantially along line 8-8 of Figure 2, with the

Extension pressure sensor is shown;

Figure 9 is a plan view of the solenoid control valve;

Figure 10 is an axial section of the solenoid control valve shown in Figure 9;

Figure 1IA is an exploded sectional view of the capacitance pressure sensor shown in Figure 8;

Figure HB is an axial section of the assembled sensor;

Figures 12A to 12D are views of the capacitance force sensor used in the knee control unit;

Figures 13A to 13C are views of the resistance rotor shown in Figures 5 and 7;

Figure 14 is a block diagram of the hydraulic circuit for the knee control unit;

Figure 15 is an overall block diagram of a computer controlled electromechanical closed loop resistance device constructed in accordance with the invention;

Figure 16 is a block diagram illustrating an application of the device to a training or robotic or cushioning device;

Figure 17 is a block diagram illustrating an application of the device for a knee control prosthesis for an amputee;

jx-ma-10 - 10 -

Figure 18 is a circuit diagram of the electronics for controlling the solenoid control valve in the resistance device;

Figure 19 is a circuit diagram for the Hall position sensor electronics in the resistive device;

Figure 20 is a circuit diagram for the force sensors of the knee control unit; Figure 21 is a gait-nod angle diagram for the knee control unit;

Figure 22 is a block diagram of a main software program for the knee control unit;

Figure 23 is a block diagram for the 1 ms interrupt software program for the knee control unit; and

Figures 24A and 24B show the block diagram for the 10 ms interrupt software program for the knee control unit.

Description of the preferred embodiments

Referring to Figure 1, a typical lower limb prosthesis for a above-the-knee amputee includes a residual limb socket 1 which acts as an interface between the amputee and the prosthesis, a knee control assembly or unit 2 which allows knee rotation and resistance to assist walking, an attachment stem 3, and a foot 4. The components 1, 3 and 4 are known and commercially available.

The knee control assembly or unit 2 is described in connection with Figures 2 to 14 and comprises a frame assembly 5 and a knee bracket 6 in the shape of an inverted U which is secured to the receiver 1. The knee bracket 6 has a retaining plate 7 on the right hand side and a retaining plate 8 on the left hand side. The knee bracket 6 slides over a rotor shaft 9 (Figure 5) which has parallel surfaces at each end to lock the shaft to the bracket. The side retaining plates 7 and 8 are secured to the bracket 6 by screws and the shaft 9 rotates with the

jx-ma-10 - 11 -

knee bracket 6 relative to the frame 5. The left side retaining plate 8 also has an external cam surface (Figure 6) to actuate a knee angle sensing mechanism.

Figure 6 shows the knee angle sensor mechanism which consists of a roller 10 attached to a knee angle lever arm 12 by a pin 11. The knee angle lever arm 12 pivots about a cross pin 13 which is pressed into a housing 15. A magnet 14 is attached to the lower end of the knee angle lever arm 12 by an adhesive. As the knee bracket 6 rotates relative to the housing 15 and frame 5, the roller 10 moves on the cam surface of the left side support plate 8. A spring 16 causes the lever arm 12 to pivot on the pin 13 which in turn changes the distance between the magnet 14 and a Hall effect sensor 18 mounted on a PC board assembly 17. When this distance is changed, the output of the Hall effect sensor 18 changes to indicate the actual knee angle of the frame 5 and the housing 15 relative to the bracket 6. Power is supplied to the PC board 17 by a pack 19 of several batteries.

Figure 5 shows the internal components of the knee control unit or assembly 2. Hydraulic fluid is the working fluid that provides the knee control resistance. Resistance is applied to the knee bracket 6 via the rotor shaft 9 (Figure 7) and a vane-like rotor 20 (Figures 5, 7, 13A to 13C) attached to the rotor shaft via two cross pins 21. The rotor chamber is defined by a rotor cap 22 on the right side (Figure 7) and a rotor cap 23 on the left side. Two endless Teflon seals 24 seal the rotor 20 against the rotor caps 22 and 23, forming two separate rotor chambers 25 and 26 (Figure 5). As shown in Figure 7, the rotor shaft 9 is supported by roller bearings 27 to support the weight of the amputee, while lateral axial loads are taken up by flat Teflon thrust washers between the caps 22 and 23 and the sides or legs of the bracket 6. The rotor shaft 9 is sealed against hydraulic fluid leakage by means of spring-loaded lip seals 28 adjacent to the bearings 27.

During flexion, the rotor 20 is rotated with the knee clamp 6 and the rotor shaft 9, forcing hydraulic fluid out of the rotor chamber 26 (Figure 5) and through a curved passage 29 located between the rotor caps 22 and 23 and the housing 15. From the passage 29, the hydraulic fluid is forced into passages 30a and 30b. The passage 30a forms a connection to a flexure

jx-ma-10 - 12 -

pressure sensor 31 sealed by an O-ring and held in place by a retaining ring. The passage 30b leads into a valve cavity. The fluid passages 30a and 30b and the valve cavity are machined into the housing 15. From the passage 30b, the hydraulic fluid passes through a solenoid control valve 32 which electronically controls the flow and pressure of the hydraulic fluid in the working chambers 25 and 26. The hydraulic fluid exits the solenoid control valve 32 and enters a fluid passage 33 (Figure 8).

The passage 33 extends to a stretch pressure sensor 34 (Figures 5 and 8) which is also sealed in the housing 15 by an O-ring and held in place by a retaining ring. The passage 33 is also connected to a bias tube 35 (Figure 4) and the hydraulic fluid passes through the bias tube 35 and into a cavity 36 (Figure 5) machined in an upper bias cap 37. The hydraulic fluid then passes through a position valve tube 38 and a tubular position valve element 39 into a chamber 40. The fluid flowing into the chamber 40 exerts pressure on an annular seal 41 and an adjacent annular piston 42 which moves upward to compress a bias spring 43 mounted against a spring seat member 44 secured to the cap 37. The spring 43 is disposed in an oil chamber 45 defined by a cylinder 46 secured to a lower cap member 47 which carries a position valve piston 48 for axial movement.

An annular support 50 defines the chamber 40 and forms a bottom seat for the annular seal 41 and the piston on the position valve tube 38, having an upper end pressed into a socket in the spring seat member 44. Leakage of the preload cylinder is controlled by a series of O-rings (Figure 5) and the hydraulic fluid is forced upwardly out of the chamber 45 in response to upward movement of the annular piston 42. The fluid passes through openings in the spring seat member 44 and the top cap 37, through a return tube 57 (Figure 4) and passages 58 and 59 into the rotor chamber 25, thereby forming a flow circuit. The passage 58 is machined into the resistor housing 15, and the curved passage 59 is defined by the rotor caps 22 and 23 and the resistor housing 15 and sealed by suitable O-rings. A spring-loaded pressure relief valve (not shown) may be incorporated into the upper bias cap 37 to allow hydraulic flow from the bias tube 35 directly to the return tube 57 in the event that an extremely high pressure is generated due to rapid flexure.

jx-ma-10

- 13 -

high fluid pressure occurs. During extension, the flow is reversed due to the rotor 20, directing the hydraulic fluid out of the chamber 25 and back through the system. In this case, the bias spring 43 helps to move the flow from below the piston 42 to the chamber 26, thereby ensuring full extension of the prosthesis.

During the stance or posture phase of the walking cycle, the amputee's weight is applied to the bottom of the knee control unit 2 by the trunk 3 and foot 4 at a base plate 64 (Figure 5). The base plate 64 is held in place by tubular sleeves 66 and screws 67. The base plate 64 is also supported by a force sensor 68 and an elastomeric pad 74. The elastomeric pad 74 deforms, causing the base plate 64 and a position adjustment screw 69 to move vertically a small distance. The elastomeric pad 74 can be effectively replaced by springs, disc springs or wave washers, but maintaining the same actuation characteristics. The position adjustment screw 69 actuates the position valve piston 48 which presses on a position valve cap 70 to move the position valve 39 upwardly into the position valve tube 38 to close the radial openings in the position valve 39. When these openings are closed, the knee control unit is restricted from any flexion movement.

By adjusting the position adjustment screw 69, the radial openings in the position valve 39 can be adjusted to limit the closing of the openings during the position phase, allowing controlled leakage in the direction of flexion, giving the amputee a compliant position. Due to a Belleville spring 71 over a position control valve disc 72 covering axial openings in the position valve cap 70, extension during the position phase is not affected. When extension is performed during the position phase, the hydraulic flow lifts the position disc 72 while compressing the Belleville spring 71 to open the axial openings in the position valve cap 70. When flexure is attempted during the stance phase, hydraulic pressure forces the stance disk 72 to cover the holes in the stance valve cap 70, thereby preventing flexure flow from moving through the stance valve end cap 70. When the load is removed from the base plate 64, the stance valve 39 is urged to the open position (Figure 5) by a return spring 73 within the tube 38 to allow flow to continue through the chamber 40.

jx-ma-lO - 14 -

A block diagram for a general illustration of the hydraulic system is shown in Figure 14. By rotating the rotor 20 clockwise within the housing 15, hydraulic fluid is forced from the chamber 26 through an opening to the solenoid control valve 32. The solenoid control valve 32 is electronically operated to variably change the flow area of the fluid path. By reducing the flow area in the valve 32, the hydraulic flow is reduced while increasing a reverse pressure. This is felt as rotational resistance on the rotor shaft 9. The fluid exits the solenoid control valve 32 through a passage leading to the position valve element 39.

The position valve element 39 is actuated when an external force is applied. Parallel to the position valve 39 is the control valve element 72 which prevents flow during clockwise rotation of the rotor 20 when the position valve element 39 is actuated, but allows flow during counterclockwise rotation. Also parallel to the position valve element 39 is an adjustable orifice 78 which allows a small regulated flow during clockwise rotation when the position valve element 39 is actuated. The hydraulic fluid exits the position valve element 39 through the radial orifices, allowing the fluid to move or actuate the piston 42.

The piston 42 separates two chambers 40 and 45 in the cylinder 46. When fluid enters the chamber 40, the piston 42 compresses the spring 43. The piston then forces the fluid in the chamber 45 to exit the cylinder 46. This flow returns to the rotor chamber 25 to rotate the rotor clockwise. When the clockwise rotation of the rotor 20 and shaft 9 is released, the bias spring 43 and the piston 42 force the hydraulic fluid out of the chamber 40 through the position valve 39 and back through the solenoid control valve 32 and into the chamber 26, resulting in a counterclockwise rotation of the rotor 20 and rotor shaft 9.

Figures 13A through 13C show the rotor 20 and its construction. The rotor 20 has two endless grooves 82 and 83 for receiving the endless seals 24. The seals 24 of choice are extruded, machined, Teflon coated seals, although molded, elastomeric lip seals provide similar results. Each endless seal is seamless and surrounds the full circumference of the rotor 20. This type of seal has the advantage of double wiping the seal surface and acts as a pre-seal to the

jx-ma-10 - 15 -

Seals 28 (Figure 7) around the shaft 9 near the legs of the bracket 6 to minimize any external leakage. Two holes 84 (Figures 13A and 13B) are provided in the center of the rotor 20 to receive the pins 21 which secure the rotor 20 to the rotor shaft 9.

An external view of the solenoid control valve 32 is shown in Figure 9 and a cross-sectional view of the solenoid control valve 32 is shown in Figure 10. A coil spool 100 is wound with a wire coil 101 with a radial step (Figure 10). The number of turns of the coil wire 101 depends on the desired electrical and magnetic properties required for operation of the valve. Lead wires 102 are attached to the coil wires and epoxy 103 is provided for strain relief. A flux core 104 is inserted through the center of the spool 100 and a metallic cup-like casing 105 houses the spool 100, coil 101 and flux core 104. An adjusting screw 106 is threaded into the center of the flux core 104 and is sealed with an O-ring 107.

A valve element or valve coil 108 is seated on top of a return spring 109, and a tubular coil seat 110 rests on the flux core 104 and is held in place by a tubular sleeve 111. The coil seat 110 limits the displacement or axial movement of the coil 108. A sleeve plug 112 is pressed into the sleeve 111, which is threaded into the shell 105. A magnetic material, such as low carbon steel, is used for the flux core 104, the shell 105, the adjusting screw 106 and the coil 108. These metal parts are preferably hyper-annealed for best efficiency. A non-magnetic material, such as 300 series stainless steel, is used for the coil seat 110, the sleeve plug 112 and the sleeve 111.

The solenoid control valve 32 is normally open when no power is supplied to the coil 101. When power is supplied, the coil 101 generates a magnetic flux which draws the coil 108 further into the flux core 104 against the increasing force of the spring 109. The special shape of the flux core 104 and the coil 108 together with the spring constant of the spring 109 is such that the coil movement is proportional to the power supplied, which translates into proportional flow control. When hydraulic fluid enters the passage 30b from the chamber 29, the fluid is directed from the opening 113 to the opening 114 formed by the sleeve 111 and the sleeve sleeve 112. When the coil 101 is fully energized, the coil 108 will open the

jx-ma-lO - 16 -

ings 113, 117, 114 and 116 will close off and the flow will cease. If the coil 101 is partially energized or de-energized, the flow will then enter the coil chamber 115, flow around the coil 108 and exit through the opening 114 and the passage 34 to the tube 35.

The pair of ports 113 and 117 and the pair of ports 114 and 116 are located at the same height, with the ports of each pair spaced 180° apart, and with each pair of ports spaced 90° from the other pair. The solenoid control valve 32 has two inlet ports 113 and 117 and two outlet ports 114 and 116, although more ports may be used if desired. Although ports 113 and 117 are described as inlet and ports 114 and 116 as outlet, the flow may be unidirectional or bidirectional with the same results. The shape of the spool 108 in the flow region 115 provides for balancing of any fluid forces that may tend to open or close the spool. An axial bore or hole passes through the center of the coil 108 to prevent hydraulic jamming. The advantages of an optimized magnetic flux to match the spring rate and an optimized coil to match the fluid forces significantly reduce the energy required to operate the valve. Leakage between the inlet and outlet ports is controlled by an O-ring 120 attached to the sleeve 111. External leakage of the hydraulic fluid is controlled by O-rings 121 and 122. Although the solenoid control valve 32 is preferably proportionally controlled, it can also be operated with pulse width modulation.

As mentioned above, the computer controlled hydraulic resistance device according to the invention has a variety of applications, such as the knee control described above for above-the-knee amputees, advanced training systems using computer controlled resistance, and robotic or cushioning applications. While a full application of electronic knee control is disclosed here, the use of the device in other applications is obvious.

Figure 15 shows the control diagram of the overall system, which relates to all the above applications. The system is controlled by a conventional microprocessor 200, which includes a RAM memory, a program memory, timers and interrupt controllers, multi-channel analog-digital converters and input/output control lines.

J * * J J···» t»·» I

jx-ma-10 - 17 -

The microprocessor uses an external clock pulse generated by a timing generator 201. For production testability of the internal circuitry and for data transfer to other devices, a system block 202 contains serial, asynchronous and synchronous ports as well as a port for a real-time background mode of operation.

In all applications of the device, the microprocessor 200 executes its program, which requires both sensing and closed-loop control. The system programs cause a resistance to be applied to the device depending on the sensed position and speed. Using a hydraulic fluid system, the resistance is applied by a hydraulic actuator 211, which can be either a rotary impeller such as rotor 20 or a piston linearly movable within a cylinder. The resistance is applied by limiting the flow in a closed fluid system by a solenoid control valve 210, such as valve 32, which is operated by the microprocessor 200 and its control circuit 207. The mechanical resistance is applied to a device 215 through a coupler 214. The device being acted upon may, for example, be a knee joint of a prosthesis or a part of a training device or a robotic platform that requires a limitation of movement and/or speed.

The position of the actuated device is sensed by a sensor 216 which may be a potentiometer, a distance detector or a linear Hall effect sensor such as sensor 18. The output of the position sensor is a signal conditioned and scaled by circuit 204. The analog position signal leaving circuit 204 is converted to an 8-16 bit digital number by the microprocessor's A/D converter or an external A/D device for use in the main program. The position is sampled in time at fixed intervals. The difference in position between the fixed time intervals divided by the time sampling period is the speed of movement of the device, which must also be used by the main program, as well as the direction of movement.

In order to produce the calculated desired resistance applied to the device in a reproducible manner and independent of manufacturing tolerances, fluid viscosity and/or temperature variations, a closed-loop control is used and the internal fluid pressures 212 and 213 of the rotating or linear hydraulic

jx-ma-10 - 18 -

Actuator 211 are received. In a closed hydraulic system, actuator 211 creates a high and low pressure on opposite sides of the rotary impeller or piston when the control valve is actuated to restrict fluid flow. When the direction is reversed, the high and low pressure sides are reversed. The received pressures 212 and 213 are signal conditioned and scaled to a usable analog level by circuit 206. The processed analog hydraulic pressures are converted to a usable 8-16 bit digital valve signal by microprocessor 200 or an external A/D converter. In the above applications, logical branching of the program state control into different sections of the main program as well as different variations in the calculations in the application dependent program 209 are accomplished by additional analog force sensors and/or digital switches or buttons 208 and 224 using additional sensing. In an exercise machine or robot application, the additional sensing is accomplished by a user keyboard and/or by remote control switches. In the knee control prosthesis application case, the additional sensing function uses two body weight sensors and two 16-position rotation selector switches.

Figures 16 and 17 show the application of the control system of the invention to prosthetic devices, exercise machines and robotic devices. The device of the invention can also be used as a computerized cushioning device, such as for a truck seat bumper, which would use the control and component diagram of Figure 16. Due to the high resolution microprocessor control provided by the sensors and hydraulic actuator and control valve of the invention, the same type of implemented exerciser can be used for medical rehabilitation purposes, programmed to make small increments of applied weight changes in increments as small as 45.4 grams (0.1 pound) to a total of 226.8 kilograms (500 pounds). The additional input function tells the main program to limit or reduce the load on the patient as he becomes exhausted from the exercise. The block diagram shown in Figure 16 is very similar to the block diagram of the entire invention shown in Figure 15 and shows the application of the device to a training device, a robotic device or a computerized dampening device. The application shows a microprocessor 200, communication and test circuits 202, a timing generator 201, a reset circuit 219, a valve control circuit 207, as well as a solenoid control valve 210, a position sensor 226 and a circuit 204, a

jx-ma-10 - 19 -

Hydraulic internal force sensor circuit 206 and power supply circuits 203.

Figure 17 discloses the components of the application for the electronic knee control prosthesis. The microprocessor 200 executes its application program, which requires both sensing and closed-loop control, as described above in connection with Figure 15. The microprocessor used in this typical application is a Motorola MC68HC912B32 embedded 16-bit signal chip processor. The application software executed by the microprocessor 200 proportionally controls the resistance to be applied to the prosthesis knee joint during a patient's walking cycle, using the valve control circuit 207 to control the proportional solenoid-operated valve 210 or 32. A pulse width modulation technique works equally well in most applications. The proportional control valve restricts the closed system hydraulic flow generated by the patient's moving knee and the hydraulic rotary vane actuator 211 connected to the knee joint 215 by a connection 214. The application software algorithm initially predicts what level of control current to apply to the solenoid valve 210 or 32 given the position, direction and speed of the knee joint. The exact resistance error is determined in a closed loop manner using the sensed high and low pressure hydraulic sides 212 and 213 to be conditioned and scaled by the circuit 206 and is then converted to a digital valve signal relative to the control level by the microprocessor 200. The inner loop of the microprocessor senses the high and low hydraulic pressures on opposite sides of the rotor 20 and updates the voltage level applied across the control solenoid at a rate of 1,000 times per second. The main control loop of the program operates at a rate of 100 times per second.

The knee position sensor 216 is implemented by a linear Honeywell Hall effect sensor 18 that measures the change in the magnetic field relative to the sensor. The magnet 14 is moved relative to the sensor 18 or 216 in proportion to the knee angle of the prosthesis. The output of the sensor 216 is conditioned, shifted and scaled by the sensor circuit 204. The microprocessor 200 converts this 0 to 5 volt analog level to an 8-bit digital value. The application program samples the position sensor at a rate of 1,000 times per second. The application program determines information about the knee direction and the speed of travel at this rate.

jx-ma-10 - 20 -

The exact speed is determined at the control rate of 100 times per second. For differences between patients in their size, weight and walking characteristics, the prosthetist adjusts the 16-position rotary auxiliary switches 224 for flexion and extension. Other auxiliary circuits used for program state control are the two weight force sensors 220 and 221, which are modulated, conditioned, demodulated and scaled by the circuit 206. These weight force sensors are located in the bottom of the prosthesis (Figures 5 and 12A-12D) to measure the force distribution applied during the walking cycle to determine when the toe-off, flat foot and heel strike states, along with their variations, are present. This information is used in the adaptive closed-loop algorithm with knee position, knee velocity, knee direction, and learned characteristics of a previous walking cycle to monitor instantaneous resistance control over changing terrain.

Since this knee prosthesis is worn on the body, the control system is powered by four rechargeable lithium-ion batteries 218 or 19 that provide 14.4 volts. The power is split into two voltages applied to the circuitry of 7.2 volts to power the system logic and 14.4 volts to power the proportional control solenoid control circuits. The raw voltage is monitored by low battery detection circuitry 222, which scales the battery voltage to a 0 to 5 volt level to be received by microprocessor 200 using its A/D converter. The microprocessor and associated logic circuits require 5 volts, which is set by power supply circuitry 203 from the 7.2 volt input signal, which comprises a conventional low dropout three-terminal integrated regulator circuit. The lithium-ion batteries are recharged over a period of two hours and then switched to a trickle charge mode by an LM3420-16.8 integrated circuit manufactured by National Semiconductor.

Figure 18 shows the circuitry 207 for the solenoid control valve drive 210 or 32. The proportional solenoid control valve requires only very low power, 1 watt maximum. The drive of the solenoid is a type of constant current over a range of 0 to 83 milliamps. The resolution in this application of the level of 0 to 83 milliamps is one part in 255 or 0.325 milliamps per step using the 8-bit digital potentiometer 243. This circuit AD8400AR10 is an integrated circuit manufactured by Analog Devices. The microprocessor 200 updates this device level at a rate of 1,000 times per second. The reference to the

■ · • ·

jx-ma-10 - 21 -

digital potentiometer is the logic supply of 5 volts. When the level is adjusted in the 256 levels, the output of the wiper changes from 0 to 4.9 volts. The voltage signal is converted to a constant current drive by the op-amp Ul, transistor Ql and three resistors Rl, R2, R3, R4 and R5. The output of the digital potentiometer seen by a differential input op-amp with a gain of 0.169 is seen by resistors Rl, R2, R3 and R4. The NPN transistor Ql is used as a current amplifier in an emitter follower mode. The diode Dl is used in the circuit to eliminate the reverse EMF effects of the solenoid control valve coil. An electrolytic capacitor C2 is used as part of a low-pass filter with the solenoid coil to reduce the high frequency bandwidth of the circuit. Cl is used as a high frequency power supply bypass.

When the digital potentiometer voltage is increased, the circuit applies a voltage across the solenoid coil. The current through the coil is in series with the 10 ohm sense resistor R5. This constant current circuit increases or decreases the output voltage of the op-amp until the voltage seen at the tip of the sense resistor is equal to the controlled voltage. Thus, to apply a control current of 0 to 83 milliamps to the solenoid coil, an input voltage of 0 to 4.9 volts is required. The constant current circuit automatically compensates for manufacturing variations and temperature effects of the coil resistance.

Referring to Figure 19, the circuitry for the linear Hall effect position sensor 216 or 18 is conditioned, offset and amplified with respect to the signal by the knee position circuitry 204. A magnet 228 or 14 is attached to the lever arm 12 which is pivoted by a cam surface on the support plate 8 so that the lever arm 12 moves in direct proportion to the knee angle. As the magnet 14 moves toward or away from the sensor 18, the Honeywell SS94A1B sensor 216 or 18 changes its output voltage in response to the north or south magnetic field. The sensor 18 outputs a 2.5 volt signal which depends on the amplitude of the magnetic field and the magnet polarity. In this application, the polarity of the magnet is chosen such that decreasing the distance until the magnet touches the sensor produces 0 volts, and completely removing the magnet from the sensor produces an output of 2.5 volts. The minimum distance at 0° knee extension is 2.54 mm (0.10 inches), which produces a minimum voltage of 1 volt. In Figure 19, block 229 buffers and low-pass filters

jx-ma-10 - 22 -

the Hall position signal from 1 to 2.5 volts at a corner frequency of 100 Hz to remove any high frequency components. The second stage operational amplifier 230 increases the signal level by 3.33 times, removing the 1 volt offset from the reference 231, to provide an output signal of 0 to 5 volts. This analog output signal is then converted to a digital output signal for use by the main program by the microprocessor 200.

Figure 20 shows the force sensor 232 or 68 and its associated circuitry. As shown in Figure 17, the weight sensor circuit 206 is used for closed loop control of the proportional solenoid control valve 210 or 32. The weight force sensor 220 and 221 (Figure 12A) and the weight sensor circuit 206 are used for program state control. The circuitry is identical except for the final amplification of U4, R3 and R4 in Figure 20. This represents an improved version of a capacitance sensor. Figures 12A and B show the actual sensors 220 and 221 used in the knee control application. The enlarged sensor 232 (Figure 12D) is constructed from two double-sided printed circuit boards and an elastomeric spacer. When a force is applied to compress the plates together, the signal applied to one side of the elastomer is proportionally coupled to the plate on the other side. As the force is increased, the reference signal level transmitted to the second plate is amplified by the increase in capacitance between the plates. The amount of force that can be measured by the sensor is a function of the elastomer density used and the gain of the demodulation circuit. The stiffer the elastomer, the more force can be applied before the plates are fully compressed. Too much stiffness in the elastomer reduces the dynamic range of the sensor. An elastomer with a specific hardness is selected for each application.

In Figure 20, the sensor application uses the microprocessor 200 to generate a 100 kHz square wave reference signal. This signal is buffered by the operational amplifier Ul. The emitter side of the sensor with increased capacitance is formed on a double-sided printed circuit board. A conductive reflector 236 is on the outside and a conductive reference surface 238 is on the other side. The isolated printed circuit board 237 is made of epoxy glass. The 100 kHz reference signal is coupled via the elastomer 239 to the receiver plate 240 on another board 237 which is protected from external radiation by another shield plate 236. The received, coupled 100 kHz signal is proportional to the grain

jx-ma-10 - 23 -

pression of the plates and is applied across the resistor Rl. The signal is then buffered by the operational amplifier U2. The received signal is converted to a proportional DC level by the RMS converter circuit, which consists of Dl, R2, Cl and the operational amplifier U3. The DC level is scaled to a maximum level of 5 volts by the operational amplifier U4 and R3 and R4. The microprocessor 200 converts this analog signal into a usable digital signal by its on-board analog-to-digital converter.

In the knee control application (Figure 17), two configurations of this sensor technology are shown. These are the hydraulic oil pressure sensors 206 and the body weight sensors 208. Figures HA and B show one of the two oil pressure sensors 206 or 31 or 34 used for closed-loop control of the proportional adjustment of the solenoid control valve. Oil ports 30a and 30b within the housing 15 are in pressure communication with chambers 25 and 26 on opposite sides of the hydraulic vane rotor 20. Internal pressure changes are communicated to each sensor 206 through an end cap 243 (Figures HA and HB) and a diaphragm 242. The diaphragm pressure compresses the printed reference circuit board 237, which contains the reference plate 240 and the reflector plate 236, against the elastomer 239. The signal is coupled to the receiver plate 238 and a shield plate 236 on another circuit board 237. The assembly is housed in the sensor closure container 241 and operates with its associated circuitry as described above.

Referring to Figures 12A through 12D, the body weight force sensor 208 or 68 of the knee control application is constructed of two 50.8 mm by 50.8 mm (2 inches by 2 inches) double-sided printed circuit boards 237 separated by an elastomer layer 239. The capacitance plates 220 and 221 are 12.7 mm by 31.75 mm (0.5 inches by 1.25 inches) and two reference plates and receiver plates 238 and 240 are used to form a weight distribution sensor 68. This sensor 208 or 68 is located in the base of the knee control. From the compression in the front, middle or rear force distributions, the system software can determine toe-off, flat foot or heel strike conditions for program state control. This arrangement with its associated circuitry also works as described above.

In the knee control application (Figure 17), the system software is written in assembly code for a microprocessor 200 of the type Motorola MC68HC912B32. This

jx-ma-10 - 24 -

Microprocessor 200 includes a 16-bit CPU, an interrupt controller, an 8-channel 8-bit A/D converter, a 1 kilobyte RAM, 32 kilobytes of EPROM program short-term storage, a 756-byte EEPROM, a real-time timer interrupt, 6 timer counters, a supervisory circuit, and an array of communications facilities for interaction with other systems such as an RS-232 serial peripheral, a synchronous serial peripheral, a synchronous BDLC serial peripheral, and a real-time background mode interface.

The knee control software application includes subroutines common to robotic applications and training devices. Referring to the general block diagram of Figure 15, the microprocessor 200 provides a signal to a valve control circuit 207 to operate the proportional solenoid control valve 210, such as valve 32, which in turn applies resistance by limiting the fluid actuator 211, such as rotor 20. Two pressure sensors 212 and 213, such as sensors 31 and 34, are incorporated by the microprocessor 200 for use in its closed-loop control of the valve to maintain a correct force applied to the device coupled to the actuator, regardless of manufacturing tolerances, temperature variations, and fluid viscosities. The pressure sensors measure the differential pressure across the actuator, regardless of the direction of movement of the actuator. The device 215 to which the resistor is applied includes a position sensor 216, such as sensor 18, which allows the system software to close the external control loop in determining the position, velocity, acceleration and direction of movement of the device. In most cases, the system software also uses an additional analog circuit 208 and switch inputs 224 for program state control.

Referring to the knee control software discussed above in connection with Figure 17, the system software executing in the microprocessor 200 provides the required 8-bit control valve level to the valve control circuitry 207. The digital potentiometer uses three I/O pins of the microprocessor. The low level driver routine of the software generates the required synchronous 10-bit serial connection that sets the required input drive of 0 to 4.9 volts for the constant current valve control amplifier. The fluid pressure force sensors 212 and 213, such as sensors 31 and 34, are analog processed by the fluid pressure sensor circuitry 208.

jx-ma-10 - 25 -

and scaled. The demodulated 0 to 5 volt proportional signal is read by the microprocessor 200 using the low level A/D fluid sensor driver routine. All fluid pressure and weight sensors use a 100 kHz square wave reference signal generated by the counter timers located on the microprocessor board and initialized in the software power reset routine. This signal is buffered by the hardware and sent to the sensors.

The external loop feedback is achieved by the linear Hall effect position sensor 216, such as sensor 18, attached to the movable knee joint housing 15. The analog output of the Hall effect sensor 18 is non-linear. Part of the linearization is accomplished by the cam surface on the support plate 8 (Figure 6). Most of the position interpretation is accomplished by a software look-up table driver routine that converts the raw position to an actual knee angle in degrees and tenths. The raw position information is scaled and offset by the position sensor circuit 204, which is read by the microprocessor 200 using the A/D position driver software routine.

Two types of auxiliary program decision state control functions are used. One of these is analog and the other is digital. The analog program state sensors 220 and 221 form the dual body weight sensor 68 which is attached to the base of the knee control frame 5. The sensors 220 and 221 sense the weight of the amputee applied to the toe or flat foot or heel to assist the main software program control. The two sensors 220 and 221 also use the 100 kHz reference signal. The resulting demodulated and scaled analog signals are read by the microprocessor 200 via A/D software drivers. Variations in the amputee's height, weight, age and strength are accommodated by setting ten levels of flexion and ten levels of extension profiles. These settings are made by the prosthetist during the knee control fitting. The master micro printed circuit board contains two miniature sixteen-position digital hexadecimal rotary switches. The first ten positions are used for the prosthetic settings of flexion and extension, and the other six positions are used for special modes of operation tailored for sports and geriatrics. The two 4-bit auxiliary switch inputs 224 are read directly by the microprocessor using the switch's software driver input routine and the I/O input pins and associated internal resistors to step up the voltage. The input signals are

jx-ma-10 - 26 -

normally seen as a digital upper TTL level unless they are grounded through the switch.

Since this knee control application is battery powered, additional low level software drivers are required for this application. The battery pack 218, like the battery pack 19, is conditioned and split into 5, 7.2 and 14.4 volts by the power supply circuits 203. The battery level is monitored by the microprocessor 200 through the conditioned battery sensed signal 222. The analog filtered level of 0 to 5 volts is read by the microprocessor 200 through the low level software A/D battery driver routine. When the programs determine that the battery is within 30 minutes of a minimum safe operating level, the two safety software routines are activated to cause a vibrator circuit 226 to generate a warning signal to give the user notice of an impending shutdown. The connection to or from the outside world to the knee controller is made through internal microprocessor communication ports and a hardware interface circuit 202. The asynchronous (SCI) and synchronous (SPI) serial data ports are used for the acquisition and control of special clinical data. The background mode (BDM) port is used as a test interface during the manufacturing process and during software development for the factory. The main programming of the 32 kilobyte short-term memory is done through the BDM port.

Figure 22 shows the knee control main program software. When the microprocessor 200 is powered, the microprocessor is passed to the reset (RESET) subroutine. This routine initializes the programmable data ports and peripherals to the desired analog and digital level, such as the two weight sensors and the two fluid pressure sensors, which require their 100 kHz reference signal for proper operation. The proportional control valve drive level is set to zero until required to be changed by the application program. Once the system is initialized, a test program built into the system is executed to determine if the knee control electronics are operating according to the manufacturer's specifications. If not, the system vibrator is activated on for half a second and off for one second to warn the user that the system has encountered a fault and that it is not safe to use. Until the error is corrected, execution of a normal system application is disabled. During normal operation, determination of system control and operating mode

jx-ma-lO - 27 -

accomplished by the two interrupt routines that occur at a rate of 100 and 1,000 times per second.

The main program checks for low battery and external communication link conditions during system idle time, during which the interrupt driven adaptive closed loop time dependent application is not running. The main program checks for two low level battery conditions, one of which is when the level is at less than 30 minutes of safe operation, and the other of which is when the battery is in a state with less than 10 minutes of safe operation remaining. The user is notified of the immediate loss of system use due to a low battery by either a vibration that is on for one second and off for ten seconds for the 30 minute case, or one second on and one second off for the 10 minute case. With normal use, the lithium ion battery pack lasts 22 to 30 hours before needing to be recharged. Typically, the knee control prosthesis is recharged by the user each night. If necessary, the user can recharge the battery pack to 90% of its level in two hours during operation.

Figure 23 shows the knee control unit's 1 millisecond software interrupt routine. This routine takes the raw sensor data and updates the valve control at a rate of 1,000 times per second. The raw sensor data is read from the individual A/D channels. These 8-bit valve signals are converted by the low-level software driver routines using lookup conversion tables and numerical calculations to actual scaled fluid pressures in psi, to front and rear amputee weight distributions in pounds, and to knee angle in degrees. The valve is also controlled in a closed-loop manner at this rate of 1,000 times per second by calculating a new control level to be written into the solenoid control valve electronic circuit. A calculation is made from the error difference between the required force and the received hydraulic fluid pressure. This difference is used in a non-linear gain equation and a look-up table to determine the next best estimate at the valve level control to achieve the desired instantaneous resistance with the least error or delay. The obtained control byte values are written to the digital potentiometer by the low level driver software routine, converting the bytes into the required 10-bit serial

jx-ma-lO - 28 -

data is converted and the clock pulse and the activation bits are controlled in a bit-by-bit manner.

Referring to Figures 24A and 24B, the knee control unit has a 10 millisecond interrupt routine that is the main control loop in which the majority of the calculations and program control are performed. This routine operates at a rate of 100 times per second. The software application requires knee position, knee velocity, knee direction, patient switch settings for extension and flexion, and anterior and posterior body weight distribution. The recording of the position is the most important parameter. To obtain smooth and accurate position information, the ten 1 millisecond interrupt position samples are stored in a group. These ordered samples are time weighted and averaged in a slice to obtain the system's used knee position. The previous old position is subtracted from the new position and divided by 10 milliseconds to calculate a short term knee velocity.

The new position is also subtracted from an old position 50 milliseconds ago and divided by 50 milliseconds to calculate a long-term knee velocity. The short-term knee velocity is used to determine knee direction. The long-term knee velocity is used to determine the knee resistance to be applied. The applied knee resistance calculations are based on the mathematical transfer function of a non-electronic hydraulic knee controller obtained through extensive engineering characterization. A set of tables and equations are used to calculate the required applied resistance, expressed in PSI, for each instantaneous knee position, knee velocity, knee direction, and patient switch setting for flexion or extension. Once the normal swing phase calculations have been performed, the normal swing phase resistance is stored in RAM for later use.

The program flow then determines if additional modes of operation need to be performed. The first decision path involves a terminal deceleration (T.D.). As the prosthetic knee approaches full extension, the system software applies an additional large resistance at less than 10° to prevent hyperextension of the knee. Similarly, another routine is used to slow the prosthetic knee during flexion. This is called flexion deceleration

·

·

• f

jx-ma-10 - 29 -

(Flexion Decelaration = F.D.). This routine is used to prevent the knee from bending too much. The F.D. routine increases resistance proportionally beyond 65° of flexion and terminates knee control completely at 70°. Other additional modes include stair descent detection and trip detection. The stair descent mode is determined by the knee angle and weight distribution as sensed by the two weight force sensors 220 and 221. The electronic controller extends the decaying position mode of the mechanical portion of the controller. When trip arrest is required, it applies a large resistance to the knee controller for a period of time and then decelerates it to zero. This mode attempts to protect the patient from falling and is sensed by knee speed, knee angle and weight force distribution.

When the resistance software sequence is complete, the desired force level to be applied is stored in a RAM variable. The application software calculates the best valve control level based on the knee speed, knee direction, hydraulic characteristics, and valve characteristics. This level is written to a RAM variable location for use by the 1 millisecond interrupt routine mentioned previously.

A summary of the walking cycle of the knee control application is shown in Fig. 21. The knee angle of the walking cycle is represented by curve 248. The swing phase is active when the knee control is off the ground, with the knee bending as it bends or extends. The swing phase begins at the toe-off position 252 and is completed by the time the heel is just about to touch down at position 253. The electronic control is active at any time the knee is at an angle greater than zero, except when it detects that the knee has not moved for more than five seconds. The stance phase consists of a heel-off position 249, a loading position 250 where all weight is supported, and a position 251 where the toe is almost off the ground but still touching the ground.

While the method and form of apparatus described herein represent a preferred embodiment of the invention, it is to be understood that the invention is not limited solely to the method and form of apparatus described,

jx-ma-10 - 30 -

and that changes may be made therein without departing from the scope of the invention as defined in the appended claims.

Claims (16)

SCHROETER FLEUCHAUS LEHMANN & GALLO: · : : ··· PATENTANWÄLTE · EUROPEAN PATENT ATTORNEYS WOLFRATSHAUSER STR. 145 · D-81479 MUNICH New German utility model application Mauch, Inc. September 14, 1998 Our reference: jx-ma-10 AL/pe/ho PROTECTION CLAIMS 1. Apparatus for producing a controlled, variable resistance for an apparatus having a first member movable relative to a second member, the apparatus comprising: means comprising a hydraulic actuator for connecting the first member to the second member, the actuator comprising a housing enclosing a movable member for applying a resistance separating within the housing a first chamber from a second chamber, a hydraulic fluid within the chambers, means defining passages for the hydraulic fluid connected to the chambers, a solenoid controlled valve arranged to regulate the flow of the hydraulic fluid through the passages, means for independently sensing the hydraulic fluid pressure within each of the first and second chambers, and a computer control system responsive to the pressure sensing means to actuate the valve to precisely regulate the flow of fluid through the valve and into and out of the first and second chambers and to detect changes in the device and the fluid viscosity. 2. The device of claim 1, including a position sensor for sensing the position of the first member relative to the second member, connected to the control system to apply a predetermined resistance profile to the device. 3. The device of claim 1, including means for biasing the flow of hydraulic fluid through the valve from the first chamber to the second chamber. imstOOO3acn oe000547 jx-ma-lO - 2 - 4. The device of claim 1, comprising means for connecting the first member to the portion of a leg of an amputee and means for connecting the second member to an artificial foot for the amputee. 5. The device of claim 4, wherein the control system includes sensors to separately sense the forces exerted on the toe and heel of the artificial foot as the amputee walks. 6. The apparatus of claim 1, wherein the resistance applying member comprises a rotating shaft supporting a vane rotor within the housing, and a flexible sealing member extending around the rotor and engaging the housing. 7. The apparatus of claim 1, wherein the solenoid valve comprises a metal valve element supported for axial movement within a metal core element having an annular shoulder, a wire coil surrounding the core element and having an annular step receiving the shoulder. 8. The apparatus of claim 1, wherein the means for sensing hydraulic fluid pressure comprises a capacitive sensor connected to the control system and comprising a set of metal circuit boards separated by a slightly elastic layer of non-metallic material, a set of insulated reflector plates attached to the circuit boards. 9. Apparatus for producing a controlled, variable resistance for a prosthesis having a first member pivotally connected to a second member, the apparatus comprising: means comprising a rotatable hydraulic actuator for connecting the first member to the second member, the actuator comprising a housing enclosing a vane rotor for applying a resistance separating a first chamber from a second chamber within the housing, a hydraulic fluid within the chambers, means defining passages for the hydraulic fluid connected to the chambers, a solenoid controlled valve arranged to regulate the flow of the hydraulic fluid through the passages, means for independently receiving the hydraulic fluid pressure within each of the first and · ix jx-ma-lO - 3 - second chambers on opposite sides of the rotor, and a computer control system responsive to the pressure sensing means for actuating the valve to precisely control the flow of fluid through the valve and into and out of the first and second chambers and to compensate for changes in the device and fluid viscosity. 10. The device of claim 9, including a position sensor for sensing the angular position of the first member relative to the second member, connected to the control system to apply a predetermined resistance profile to the device. 11. The apparatus of claim 9, including means for biasing the flow of hydraulic fluid through the valve from the first chamber to the second chamber. 12. The device of claim 9, comprising means for connecting the first member to the portion of a leg of an amputee and means for connecting the second member to an artificial foot for the amputee. 13. The apparatus of claim 12, wherein the control system includes sensors to separately sense the forces exerted on the toe and heel of the artificial foot as the amputee walks. 14. The apparatus of claim 13, wherein the sensors comprise a capacitive sensor connected to the control system and comprising a set of metal circuit boards separated by a slightly elastic layer of non-metallic material, with a set of electrically insulated reflector plates attached to the circuit boards. 15. The apparatus of claim 9, wherein the rotor defines at least one endless groove extending around the rotor, and wherein an endless, flexible sealing element extends within the groove and engages the housing. 16. The apparatus of claim 1, wherein the means for sensing hydraulic fluid pressure comprises a capacitive sensor connected to the control system. jx-ma-10 - 4 - and comprising a set of metal circuit boards separated by a slightly elastic layer of non-metallic material, a set of electrically insulated reflector plates attached to the circuit boards, and a flexible membrane arranged between the capacitive sensor and the oil in the first chamber. F^