EP0341244A4

EP0341244A4 - Nondestructive measurement of composite materials

Info

Publication number: EP0341244A4
Application number: EP19870907889
Authority: EP
Inventors: Carlos A. Salvado; Bruce E. Wade
Original assignee: Expert System Technologies Inc
Current assignee: Expert System Technologies Inc
Priority date: 1987-11-10
Filing date: 1987-11-10
Publication date: 1991-04-10
Also published as: AU8277687A; AU620023B2; WO1989004524A1; JPH02502669A; EP0341244A1

Abstract

An apparatus (110) for performing ultrasonic measurements of compliant material specimens (18) includes a pair of facing (114, 116) but spaced apart ultrasonic transducers between which the specimen (18) is placed, and which transmits signals (114) into the specimen and receives signals (116) from the specimen, a structure (124) which presses the transducers against the opposite surfaces of the specimen with a reproducibly controllable force so that the same compressive force may be applied for successive measurements, a gauge (125) that measures the separation of the two transducers, and a controller (122) which drives the transmitting transducer and receives the signals from the receiving transducer. Using this apparatus, the weight fractions of the phases of a composite material working specimen are determined nondestructively by first performing a sufficient number of nondestructive and destructive calibration measurements on the properties of calibration specimens. The information learned from the calibration specimens is used in combination with similar nondestructive measurements of the working specimen to determine the fractions of the phases therein, without damaging the working specimen.

Description

NONDESTRUCTIVE MEASUREMENT OF COMPOSITE MATERIALS

BACKGROUND OF THE INVENTION

This invention relates to testing of mixtures and composite materials, and, more specifically, to nondestructively measuring the fractions of the phases of working specimens.

Many of the materials used in modern technology, particularly those used for their structural properties, are mixtures of several phases which generally retain their inherent character within the mixture. One important class of such mixtures is composite materials, wherein at least two distinct phases are bonded together to form a single material. In a typical structural composite material used in aerospace applications, oriented, high-strength, low ductility graphite, carbon, Kevlar or glass reinforcement fibers are embedded in a resin matrix which binds and protects the fibers. The properties of the resulting composite material reflect the high strength and elastic properties of the reinforcement fibers, yet the composite material is formable and usable in a variety of applications.

One of the most important parameters characterizing such a composite material is the weight (or, equivalently, the volume) fractions of the phases. That is, such a composite material can be described as containing a particular weight fraction of a first phase, another particular weight fraction of a second phase, and so forth, so that the weight fractions of all the phases total 1.0. The greater the amount of a particular phase present in the composite material, the greater is its influence on the overall or total composite material properties.

Once a composite material has been designed to have a particular combination of properties, it must be manufactured to the design speci ications and inspected to be certain that the manu acturing process actually resulted in the desired material. After manufacture and during service, the composite material must be inspected periodically to ensure that its properties have not changed during use. For example, absorption of moisture by the nonmetallic matrix, due to environmental exposure, can seriously degrade the composite properties. In both types of inspection procedures, measurement of the weight fractions of the phases is necessary because the properties of the composite material depend directly upon the weight or volume fractions of the phases. The measurement of the weight fractions of the phases in the final composite material is not easy to perform, because portions of the phases are buried inside the composite material and are not readily visible to the naked eye nor measurable by external instruments. The most common approach to the measurement of the fractions of the phases during manufacturing is to section random samples of the material so that the internal structure can be inspected and the volume fraction determined (which then can be converted to a weight fraction, if desired), or to remove the matrix phase and weigh the amount of the fiber reinforcement phase to calculate a weight fraction

(which then can be converted to a volume fraction, if desired, with knowledge of the densities of all of the phases of the composite material and the density of the composite material itself). In either event, the specimen that is investigated is destroyed and cannot be reused. A destructive testing program of this type usually requires a cost expenditure of about $40 to $150 per specimen examined, which cost tends to reduce the number of specimens tested and the reliability of the testing program. The testing procedure requires about 1/2 to about 3 hours, preventing real time control of the manufacturing process based upon the measurements.

Service determinations of weight or volume fraction are even more difficult, since the composite material is usually bonded into a structure which cannot be sectioned or dissolved. The composite material will also have been subjected to various changes during its service lifetime, which may influence its properties. One cannot therefore assume that the composite material in service has phase fractions and phase properties within acceptable limits, simply because the original material was acceptable.

Various types of measurement techniques have been developed to gain information about the internal structure of mixtures and composite materials, including the destructive techniques described above. However, all suffer from the shortcoming that quick, accurate, and inexpensive measurements of the phase fractions of working specimens cannot be made in a nondestructive fashion. Accordingly, there exists a need for a new technique for measuring the weight or volume fractions of the phases of a mixture, such as composite materials and the many other types of mixtures whose structures must be understood and characterized. The present invention fulfills this need, and further provides related advantages. SUMMARY OF THE INVENTION

The present invention provides a process for determining the weight or volume fractions of the phases in a working specimen mixture, such as a composite material, in a rapid, nondestructive manner. The approach utilizes actual calibration data gained from measurements of mixtures of the same type as the working specimen, to maximize the accuracy of the measurements and to minimize the errors that might result from a purely theoretical treatment wherein there could be a deviation from theory for particular specimens. The method is generally applicable to mixtures and composites of an arbitrary number of phases, with those mixtures having more phases requiring that more information be known or gained from measurements of calibration specimens. The approach is readily applied both to repetitive nondestructive measurements of large numbers of specimens in a factory fabrication inspection procedure, and also to field measurements of working specimens in service or mixtures found in the field.

The present invention provides an apparatus and procedure for performing such ultrasonic measurements on specimens in a reproducible, precise manner that permits accurate determinations of physical properties and also permits comparisons of data taken from different specimens, from different areas of a single specimen, and from the same specimen at different times. The apparatus is operable with compliant materials, whose deformation can interfere with obtaining reproducible measurements. When compliant materials are evaluated, the specimen under study is not contaminated with couplants made of foreign matter, but coupling is achieved in a fully reproducible fashion. When rigid specimens are evaluated, minimal amounts of volatile couplants, or a compliant transducer, may be utilized. The apparatus and procedure can be used for composite prepreg, cured composite, and a wide variety of other types of materials, both in a laboratory environment and also in a factory or even a service environment, with reproducibility and precision maintained throughout the variety of tests.

In accordance with the invention, a process for performing a nondestructive determination of the fractions ,of the phases present in a working specimen of a mixture comprises the steps of selecting a series of nondestructively measurable properties of the phases of' the mixture, each of which properties vary with the weight fractions of the individual phases in a known way and are summed over the phases to define a total mixture value for that property, thereby forming a system of simultaneous equations for the mixture properties as a function of the sum of products of a coefficient of variation times the weight fraction of each phase; measuring each of the measurable mixture properties on a sufficient number of calibration specimens having different weight fractions of the phases, and then destructively determining the weight fractions of the phases for the calibration specimens, thereby determining the coefficients of variation of the system of equations; and nondestructively measuring each of the measurable mixture properties on the working specimen of unknown weight fractions, and solving the system of equations for the weight fractions of the phases present in the working specimen. Equivalently, the same procedure may be performed using volume fractions rather than weight fractions, if that approach is more convenient in the circumstances, because the weight fractions are related to the volume fractions in a known, single-valued way through the densities of the phases and the composite material. As used herein, a mixture is a heterogeneous mechanical blend of two or more phases which retain their physical identities in the mixture. In such a mixture, the phases are identifiable on a macro scale. In a mixture, as that term is used here, there may or may not be bonding between the phases. Where bonding occurs, the mixture is termed a composite material. While under some definitions of the term "mixture" a composite material would not be a mixture because ^"the phases are bonded, it is intended that the term not be so narrowly interpreted here. As used herein, a composite material is one type of mixture.

The present approach is further illustrated by an exemplary embodiment involving the determination of the fractions of the phases in a composite material having a fiber of known properties and coefficient of variation of a particular property, ultrasonic slowness, a matrix whose coefficient of variation of the same property, ultrasonic slowness, may vary when the matrix is incorporated into the composite material, and wherein volume is conserved. Such a situation may arise in practice because the elastic properties of the fiber do not change when the fiber is incorporated into the matrix, but the elastic properties of the matrix may vary due to a stress state, uneven curing, unexpected chemical reactions, or the like.

In such an approach, a process for performing a nondestructive determination of the weight fractions of the phases of a composite material working specimen having as phases an elastic fiber and a resin matrix, wherein the slowness of an ultrasonic wave propagated through the fiber is known, and wherein the in-situ slowness of an ultrasonic wave propagated through the matrix may differ from that measured when the matrix material is not incorporated into the working specimen, comprises the steps of determining the in-situ slowness of an ultrasonic wave propagating through the matrix, by the steps of measuring the slowness of an ultrasonic wave in a composite calibration specimen, destructively determining the volume fractions of the fiber and matrix for the calibration specimen, and calculating the in-situ slowness of an ultrasonic wave in the matrix as the reciprocal of the volume fraction of the matrix, times the difference between the slowness of an ultrasonic wave in the working specimen less the product of the slowness of an ultrasonic wave in the fiber times the volume fraction of the fiber, all determined for the calibration specimen; measuring the slowness of an ultrasonic wave in the working specimen, which is not destroyed in the measurement; and calculating the volume fraction of the matrix in the working specimen as the slowness of the ultrasonic wave in the working specimen, less the known slowness of the ultrasonic wave in the fiber, divided by the difference between the slowness of the ultrasonic wave in the matrix, as determined from the calibration specimen, less the known slowness of the ultrasonic wave in the fiber. The measurements of composite properties of both the calibration and working specimens are preferably made by an ultrasonic technique, which is readily adapted to rapid, automated, nondestructive testing of numbers of specimens. The ultrasonic test measures, among other things, "slowness" of an ultrasonic wave in the specimens, which is the reciprocal of velocity. The process of the preferred approach can be accomplished using automated test apparatus for sequentially testing series of working specimens, once the calibration tests have been performed. As an example, the process can be arranged to test large numbers of prepreg specimens for volume fraction as the prepreg is manufactured. Each test is performed in a time of on the order of 1 second, and a running record and fabrication evaluation can be maintained. That is, the fractions of the phases can be evaluated nearly continuously just after the product is manufactured, and manufacturing process adjustments can be made to correct deviations discovered by the preferred process. This type of feedback control has not heretofore been possible.

The present process finds immediate application in evaluation of composite materials, an important class of mixtures. However, the process also finds important applications in other areas where mixtures must be evaluated, such as blending control of aggregates used in concrete manufacture, determination of the amount of reinforcement wire in automobile tires, determination of mineral fractions in ores, and the like, to name a few. The process in its general form is highly flexible and adaptable to measuring many different types of materials. Ultrasonic measurements are only one technique that may be used in the evaluations. Light, electrical, magnetic, electromagnetic, and other forms of waves and radiation may likewise be used as properties to determine the weight and volume fractions of the phases, once the functional dependence of the composite property on phase fraction is known.

In accordance with the invention, apparatus for performing ultrasonic measurements on a solid specimen comprises measurement means for introducing a first ultrasonic signal into the specimen and for receiving a second ultrasonic signal from the specimen, compression means for forcing the measurement means against the surface of the specimen with a reproducibly controllable constant compressive force, so that the same compressive force may be applied on successive measurements, and control means for controlling said measurement means.

Coupling of the transducers to the specimen is accomplished by compressing the transducers against the surface with a precise, reproducible force such as, for example, dead-weight loading, spring loading, or controlled loading by a device such as a robotic arm. The extent of coupling is the same for every specimen for which the same compressive force is used. The nature of the coupling can be understood for each type of specimen material as a function of the amount of compressive force applied. The ultrasonic wave velocity calculation is affected primarily by the deformation of the material, and therefore simultaneous measurement is required. Amplitude of the ultrasonic wave, and therefore measurements of wave attenuation, is affected primarily by the amount of contact, which is dependent upon the applied compression. While the compression does tend to deform the materials such as prepreg slightly, the deformation is uniform, constant, and readily measured by a deformation gauge optionally provided with the apparatus. Consequently, it is possible to compensate for such compression in the calculations of the ultrasonic attenuation, time of flight, or other parameters derived from the data taken.

Either one or two transducers may be used. If a single transducer is used both to introduce ultrasonic pulses into the specimen and to receive the modified pulses back from the specimen, that transducer is pressed against one flat surface uniformly during operation. If two transducers are used, one to transmit and the other to receive the ultrasonic signals, then the transducers are oriented in a facing but spaced apart relationship along an axis so that the specimen is sandwiched between the two transducers under the controlled compression force. The uniform, reproducible compressive loading results in a constant degree of coupling between the transducer or transducers and the specimen, which can be duplicated for different areas of a specimen or for different specimens. The constant degree of coupling is highly significant for the accurate measuring of velocity and attenuation of the ultrasonic signal within the specimen. Variations in coupling lead to varying boundary losses as the signal is introduced into and extracted from the specimen, resulting in uncontrollable variation between tests. Applying the same pressure reduces or eliminates the variation, by causing a constant degree of coupling. The high pressure also helps to minimize coupling variations to non-metallic matrix composites by compressively reducing local surface irregularities that can sometimes appear and vary between successive tests of the same region of a specimen. Such reproducible coupling cannot be achieved by conventional coupling methods such as the application of grease between the transducer and the specimen.

The displacement gauge permits measurement of the actual thickness of the specimen as the ultrasonic measurements are taken. The two transducers are touched together along their facing surfaces when no specimen is present to establish a zero point. (When one transducer is used, it is contacted to the surface supporting the specimen to establish the zero point.) Then the specimen is inserted so that the transducers fit solidly against the opposite surfaces, and the displacement from the zero point measured. The distance between the transducers is reduced as the compressive pressure rises. This distance is the actual path traversed by the ultrasonic signal. For very thin specimens, even a small change or error in measuring the path length can be significant in making accurate measurements. For example, a typical ply of a non-metallic matrix thermoset composite prepreg is about .008 inches thick, so that an undetected .001 inch thickness variation error results in a 12# error in the measured thickness value, with a corresponding error in the computed ultrasonic velocity. The approach of the present invention avoids this source of error, resulting in more precise measurements that are reproducible. It will now be appreciated that the present invention provides an important advance in the field of nondestructive testing of mixtures, including composite materials. Once the functional dependence of a particular property with phase fraction is known, the coefficients of variation can be determined from either known information or by testing a sufficient number of calibration specimens. With proper selection of the properties to be measured, the process is readily adapted to automated testing of working specimens. Other features and advantages of the invention will be apparent from the following more detailed description, taken in conjunction with the accompanying drawings, which description illustrates, by way of- example, the principles of the invention.

BRIEF DESCRIPTION OF THE DRAWINGS

Figure 1 is a side elevational view of a preferred apparatus;

Figure 2 is an enlarged detail of Figure 1, illustrating the deformation of the specimen under the compressive forces;

Figure 3 is a side sectional view of a portion of Figure 1, illustrating an alternative approach using a single transducer;

Figure 4 is a block diagram of the control system for the apparatus;

Figure 5 is a side elevational view of a portable apparatus, with portions broken away for clarity;

Figure 6 is a process flow chart for a preferred embodiment of the invention; and Figure 7 is a side sectional view of an apparatus for practicing the invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT

The present invention is embodied in an apparatus 10, illustrated in Figure 1. The apparatus 10 includes a rigid base 12 and an upright frame 14 set thereupon. The frame 14 conveniently is formed of two vertical uprights 16 spaced apart by a distance that permits insertion of a specimen 18 therebetween. The frame 14 is stiffened by horizontal stiffeners 20 extending between the uprights 16. The total forces involved in the apparatus 10 are not more than a few hundred pounds at most, typically less than one hundred pounds, and as a result the frame 14 need not be constructed to withstand high forces. However, rigidity is important, and the frame 14 is therefore preferably constructed of steel.

Intermediate the uprights 16 is a vertical support rod 22 that extends parallel to the uprights 16 but is free to move vertically along its axis. The support rod 22 is preferably supported in a pair of bearings 24 mounted to two of the horizontal stiffeners 20. These bearings 24 are preferably teflon sleeves, but can be roller bearings or other type of bearing. The bearings 24 provide sideways support and stability, and at the same time permit the support rod 22 to slide upwardly and downwardly. The support rod 22 does not move great distances or at high rates, so that the bearings 24 need not be selected with such complications in mind. A first ultrasonic transducer 26 is mounted to the base 12 with its active surface facing upwardly. A second ultrasonic transducer 28 is mounted to the bottom end of the support rod 22, with its active surface facing downwardly. The first and second transducers 26 and 28 are positioned to be in facing relationship to each other, so that ultrasonic signals emitted from one are received by the other. The specimen 18 is positioned between the two facing transducers 26 and 28, and therefore the vertical movement of the support rod 22 must be great enough to allow specimens of differing thicknesses to be placed between the transducers. When the specimen 18 is so placed, and the support rod 22 relaxed under the force of gravity, the specimen 18 is lightly pressed between the two transducers 26 and 28.

It has been found that the compression force applied to the specimen 18 through the transducers 26 and 28 should be constant but controllable to differing levels to provide optimization of this parameter for different specimen materials and con igurations. However, once that optimal point has been reached, the force should be maintained precisely constant between different measurements of that specimen, and between different measurements that are to be compared with each other. A preferred approach to achieve this feature is to use dead-weight loading of the support rod 22, which eliminates the need for a force gauge and a means to control the force. For this purpose, a weight box 30 is attached to the support rod 22 at its upper end. The weight box 30 is a simple container into which weights 32 may be added to increase the compressive force applied to the specimen 18 through the support rod 22. Figure 2 is an enlarged view of the specimen 18 and the transducers 26 and 28, with weight applied. The transducers 26 and 28 act as punches to locally reduce the thickness of the specimen 18 in a central region 34 thereof, while the remainder of the specimen 18 retains its original thickness. The ultrasonic signals pass through the central region 34, and it is important to know the local through-thickness dimension in the central region 34. As indicated earlier, the thickness of a prepreg is typically .008 inches, and a .001 inch reduction in thickness could result in a 1056 error in the determination of ultrasonic velocity, if such error is undetected. The local dimension in the central region

34 is determined using a displacement gauge 36 that measures the movement of the support rod 22. The frame 14 and support rod 22 can be considered rigid, so that any movement of the support rod 22 is due to the thickness of the specimen 18. The local thickness of the specimen 18 is determined by placing the transducers 26 and 28 face to face without the specimen 18 present, and obtaining a displacement reading from the gauge 36. The specimen 18 is then inserted between the transducers 26 and 28, and the displacement of the gauge 36 is then read again. The difference between the two readings is the local through thickness dimension of the specimen 18 in the central region 34. The through thickness dimension of the specimen 18 in the region without any applied compressive loading can be similarly determined, if that is of interest, by making the second displacement measurement as the transducer 28 first touches the upper surface of the specimen 18 when the support rod 22 is lowered. With the transducers 26 and 28 in place and compressively forced against the specimen 18, the ultrasonic measurements can be taken under the control of a controller 38, illustrated in Figure 4. The nature of these measurement depends upon the data required. In a preferred system, pulsed ultrasonic signals are emitted by transducer 28 under the control of a pulser 40. The pulser 40 sends a transmission pulse to the transducer 28, which transmits a corresponding signal into the specimen 18. The ultrasonic signal propagated through the specimen 18 and received by the transducer 26 is provided to the pulser 40. The waveform is digitized by a digitizer 42 and provided to a computer 44, which also receives the displacement signal from the displacement gauge 36o The information in the computer 44 can then be used to calculate the desired properties such as velocity and attenuation as necessary, that in turn characterize the material.

Ultrasonic measurements are taken using the apparatus 10 by raising the support rod 22 to separate the transducers 26 and 28, and inserting a specimen 18 into the gap between the transducers. For compliant specimens, no separate couplant is used. For rigid specimens, a drop of a completely volatile liquid couplant such as alcohol or water can be placed on the surface of each side of the specimen 18 in the region where the transducers 26 and 28 contact the specimen. The support rod 22 is lowered to permit the upper transducer 28 to rest against the specimen 18, and the measurement is taken. A manual switch may be used to indicate that a measurement is to be taken, or the controller 38 may control this function automatically. The support rod 22 is raised, and the process may be repeated with another area of the specimen 18 or another specimen. It will be appreciated that this apparatus 10 is well suited to an automated measurement operation, wherein a mechanism is provided to raise and lower the support rod 22 at the appropriate times, and wherein another mechanism translates specimens into position between the transducers.

In this preferred embodiment, the transducers 26 and 28 are Panametrics Model A109-S transducers which operate at 5 MHz, with a relatively broad band width that minimizes ringing of the transducer when used with a narrow specimen. The pulser 40 is a Panametrics Pulser Receiver Model 5052 PR. The digitizer 42 is a Tektronix Model 336 digitizing oscilloscope. The computer 44 is a Hewlett Packard Integral PC. The displacement gauge 36 is a Sylvac P25 capacitance device sensitive to .0001 millimeter. A variation of the apparatus 10 is illustrated in Figure 3. Here the transducer 26 is omitted, and a single transducer 28 both transmits and receives the ultrasonic signal. The path length traversed by the signal is twice the local thickness of the specimen 18. The specimen 18 is supported by a support block 50, which has an aperture 51 therethrough below the specimen to provide optimal reflective properties for the reflected ultrasonic wave. This apparatus of Figure 3 is preferred for use when only one side of the specimen is accessible.

Figure 5 illustrates a preferred portable apparatus 60 which may be used in field testing of materials by ultrasonic means. The apparatus 60 is in the form of a hand-held gun, having a barrel 62 and a handgrip 64 for easy manipulation. A rigid, removable skirt 65 extends outwardly from the end of the barrel 62 to steady the barrel against lateral tipping when placed against a surface of a specimen. A transducer 66 is mounted on an extendible rod 68 that extends outwardly from the end of the barrel 62. The interior end of the rod 68 is attached to a spring 70 which biases the rod 68 and the transducer 66 to extend outwardly from the barrel 62. The other end of the spring 70 is contacted by a plunger 72 supported on a threaded rod 74 that may be turned by a screw 76 on the end of the barrel 62 remote from the transducer 66, to move the plunger 72 so as to apply greater or lesser force on the end of the spring 70. A scale 78 on the outside of the barrel 62 indicates the force applied to the transducer 66 in the following manner.

Prior to a measurement, the transducer 66 extends from the end of the barrel 62. To make a measurement, the transducer 66 is pressed against "the surface of the specimen to be measured, forcing the extendible rod 68 back into the barrel 62 and compressing the spring 70. When the transducer 66 is forced against the surface of the specimen so that the end 80 of the barrel 62 contacts the specimen, no further travel is possible. The spring force is measured by the position of an indicator 79 mounted to the plunger 72 in relation to the scale 78. If the spring force is other than the desired amount, the spring force is adjusted by turning the screw 76 to reach a desired force applied against the surface of the specimen through the transducer. Such adjustment is typically required for testing the first specimen of a group, but then readjustment is not required as long as the desired force is unchanged. This force is exactly and readily reproduced on successive specimens by forcing the transducer 66 down against the surface until the end 80 prevents further movement. The thickness of the specimen, if required, is measured by other means such as a separate gauge. Alternatively, the apparatus 60 could be constructed with an integral thickness gauge.

In the design illustrated in Figure 5, spaced ultrasonic pulses are continuously transmitted to the specimen 18. The received pulse is sent to the controller 38 through a line 84 only when a trigger 82 is depressed to indicate that the proper force level is reached.

The portable apparatus may be used to collect ultrasonic data in a laboratory or factory environment, but is also operable in a service environment. That is, if a composite material is built into a structure such as an aircraft, the portable apparatus may be taken to the aircraft and contacted to the composite piece to quickly and accurately determine the ultrasonic parameters. The measurement is taken by forcing the transducer 66 against the surface of the composite piece until the end 80 of the barrel 62 touches the surface, adjusting the screw 76 until the proper force level is indicated on the scale 78, and depressing the trigger 82. The measurement is recorded in the controller, and the next area may be measured.

The apparatus just described, in either its stationary or portable forms, is preferably used in conjunction with measurements of the amounts of phases in a composite material. In the preferred approach, measurements of composite ultrasonic slowness are used to determine phase fractions. The preferred embodiment is one case of the more general approach of the invention, and it is helpful to outline the general approach before proceeding to the preferred embodiment. Many physical properties of a mixture depend upon the nature and volume fraction of the phases making up the mixture. In general terms,

'm sum (Ci x fu(Pi)),

where C_m is the mixture property of interest, fu indicates a general functional variation, P is the volume fraction of a phase expressed in the appropriate physical terms, C± is the coefficient of variation, and the summation is made over the n total phases of the mixture. Even if the coefficients of variation Ci are known, a single eaurement of a composite property is not sufficient to calculate the unknown phase fractions P, for n greater than unity.

However, if a series of j equations of the above general form is written for j measurable properties or characteristics of the mixture, then it is possible to determine the phase fractions P by first finding the values of C^ from known information or from measurements of calibration specimens, and then measuring the j properties for a single working specimen:

C_2m - sum (C₂i x fu(P_±))

C_jm - sum (C_ji x fu(Pi))

The value of j must be at least as great as n for a solution of the equations. If j is equal to n, the system of equations is said to be determined. If j is greater than n, the system of equations is said to be overdetermined, there is redundance in the solution, and a solution in a least squares sense is possible. If j is less than n, more information is required to reach a unique solution.

The above set of equations is sufficient for a solution, but it is desirable that for simplicity in solution the equations be linear in P, so that

fu(Pi) - Pi.

It is also desirable that the properties P be readily determined in measurements of specimens, and not be affected significantly by interfaces within the mixture, inasmuch as the present invention is used to determine volume fractions, not interfacial characteristics.

In addition to measurable properties, according to the principle of conservation of mass, the sum of the weight fractions is unity:

1 - sum (Pi,_w)

where w denotes a weight fraction.

The coefficients of variation C^ are determined in one of two ways. For some phases, ~~1 i"⁰¹* the in-situ phase is the same as the property measured in bulk, and the selection of measurable properties is made with this consideration in mind. This is the case for most hard, strong, elastic fiber reinforcement materials used in composite materials. If the in-situ values of Ci are the same as the bulk properties for all of the properties required, then the coefficients are determined and there is no need to do testing of calibration specimens. For many phases of interest and measurable properties, however, the value of C is not necessarily identical to the comparable bulk property. One important practical example is the resin matrix of a fiber reinforcement/resin matrix composite material. The resin matrix may absorb moisture or be in an unknown state of cure when present as the matrix of the composite, and in certain cases it is not possible to assume that the in-situ property is identical to the comparable bulk property.

In such cases, the coefficient of variation for the property Is determined by measuring a number of calibration specimens sufficient for the determination. Where there are n phases whose phase fractions are eventually to be determined and r of the properties are such that all of the coefficients of variation of the phases are previously known or can be determined from the bulk data, then the number of calibration specimens that must be tested to determine the remaining coefficients of variation is (n-r). Each of the properties of interest for each of the calibration specimens is measured. The phase fraction of each of the phases of each of the calibration specimens is measured, typically by destructively sectioning or removing portions of the calibration specimens.

With this information derived from the calibration specimens, namely all of the composite properties, all of the phase fractions, and all of the known coefficients of variation, the above equations can be solved for the remaining unknown coefficients of variation. Where the equations are linear, the solution is readily accomplished by matrix techniques. A system of linear equations is preferred, and the properties to be measured are chosen with this consideration in mind. However, when this is not possible, nonlinear properties and equations may be used and the system of equations is solved with greater difficulty.

Once all of the coefficients of variation Ci are known, including those which vary in an in-situ manner, the fractions of the phases of working specimens may be determined by measuring composite properties of the working specimens, and without destroying the working specimens. Each of the measurable composite properties is measured, and the equations (whose coefficients of variation were previously supplied or determined) are solved for volume or weight fractions of the phases. Once either the volume or weight fractions are known, the other can be calculated, according to the equation:

Pi,v - Pi,w (D_c/Di)

wherein P is the fraction of the phase, D is density, i is the ith phase, v is by volume, w is by weight, and c refers to the composite.

In an application of these principles, the properties of a composite material having four phases is determined from the assumption . of conservation of volume, and measurements of ultrasonic slowness S, which is the reciprocal of velocity of an ultrasonic wave, ultrasonic attenuation A, which is the reduction of amplitude of an ultrasonic wave, and density D, using the following linear equation, expressed in matrix form. Such a situation of the need to determine four phases can arise because the composite includes a matrix, a fiber, a moisture phase, and a paper separation material.

The leftmost matrix, a 4 x 4 matrix termed g, contains the coefficients of variation for the 4 x 1 volume fraction vector, termed M. The 1 composite properties vector, d, is the rightmost matrix of the equation. Because the coefficients of variation for one property, volume fraction, are known from the assumption of conservation of volume, there remain three properties whose coefficients of variation are not knowno Therefore, the S, A, and D properties must be measured nondestructively for three calibration specimens, and the V values measured destructively for each of those specimens. The slowness properties S and the ultrasonic attenuation properties A are measured by ultrasonic wave propagation, and the density property D is measured by a liquid displacement technique, or by a more sophisticated technique such as gamma ray or beta ray emission. The equation can then be solved for all the remaining terms of g. Once g is known, nondestructive measurements of the components of the d vector on a working specimen permits the equation to be solved for the M vector for the working specimen, by a direct matrix transformation:

M (gTg)-l_gT_d.

This matrix transformation is a general form applicable to a determined or overdetermined system, which can be simplified, for the usual case of a square n x n matrix, to

M ■= g-ld

In the presently preferred embodiment of the invention, the volume fractions of a working specimen of a two-phase composite material, having an elastic fiber reinforcement phase f and a resin matrix phase m, are evaluated. The determinations are based upon two experimental observations for such materials: that the sum of the volume fractions of the phases is unity (i.e., conservation of volume), and that the sum of the ultrasonic slowness of the fiber (Sf) times the volume fraction of fiber (Pf) plus the ultrasonic slowness of the matrix (S_m) times the volume fraction of the matrix (P_m) being the ultrasonic slowness of the composite material (S_c). The slowness of an ultrasonic wave in the composite is independent of, or at most very weakly dependent upon, the nature of the interfaces in the composite material. Slowness can be readily measured in a nondestructive manner on working specimens. These measurements may be performed by apparatus that operates in an automated manner.

There are three possible cases of interest in applying this approach to the testing of actual composite measurements. In the first case, the values of the coefficients of variation S and S_m are known for the in situ properties from measurements of bulk properties. This case is found for a number of practical composite materials of interest. No measurements of calibration specimens are required, and the volume fractions of the phases of the working specimen can be determined from a single measurement of the composite slowness of that specimen.

In the second case, the in situ properties of one phase (specifically, the matrix) are different from the bulk properties, and measurements of a calibration specimen are required. This case may arise because the matrix cures unevenly due to the proximity of the fibers, for example. The determinations required for this second case are illustrated in Figure 1. The slowness of the ultrasonic wave in the fiber depends upon the elastic modulus and the density of the fiber, both of which do not change when the fiber Is incorporated into the matrix. The in situ coefficient of variation of fiber slowness is therefore equal to the bulk slowness, which is often readily available for a particular fiber choice. Only one coefficient of variation, matrix slowness, must therefore be determined from measurements of a calibration specimen. The matrix slowness Is determined by measuring the composite slowness of a calibration specimen. Preferably, the calibration specimen is chosen so that the volume fraction of the phases therein is about that of the working specimen to be subsequently measured, so that the stress and cure states of the two specimens are about the same. The calibration specimen is then sectioned and examined microscopically to determine the volume fractions of the phases. Alternatively, the matrix of the calibration specimen may be dissolved away, and the remaining fiber reinforcement material weighed and converted mathematically to a volume fraction of reinforcement. The volume fraction of matrix Is unity minus the fiber volume fraction (assuming that volume is conserved). The coefficient of variation of the ultrasonic wave in the matrix is the reciprocal of the volume fraction of the matrix, times the difference between the slowness of the ultrasonic wave in the working specimen, less the product of the slowness of the ultrasonic wave in the fiber times the volume fraction of the fiber. With this calculation complete, all of the coefficients of variation are known.

Next, the slowness of the ultrasonic wave in the working specimen of the composite material is measured. Only a single measurement on the working specimen is required, and the working specimen is not destroyed or otherwise physically altered. The ultrasonic measurement requires on the order of about one second to perform, using apparatus to be described subsequently. The volume fraction of the matrix is then calculated as the measured slowness of the ultrasonic wave in the working specimen, less the known slowness of the ultrasonic wave in the fiber, this difference being divided by the difference between the slowness of the ultrasonic wave in the matrix, as determined from the calibration specimen, less the known slowness of the ultrasonic wave In the fiber reinforcement. The volume fraction of fiber reinforcement is unity minus the volume fraction of the matrix.

In the third case, neither the fiber nor the matrix coefficient of variation of slowness is known. Measurements of ultrasonic slowness must be performed on two calibration specimens, and those calibration specimens must be sectioned or must have the matrix removed to determine the phase fractions. Once this information is determined, the coefficients of variation for the calibration specimens 1 and 2 are found by solving the equation:

(To have a meaningful solution, the phase fractions of the two calibration specimens should be sufficiently different. Alternatively stated, the product of P ,l times Pf,2 should be different from the product of Pm,2 times ^pf,l«) ^By solving this equation for the coefficients of variation S_m and S , and then using these coefficients in conjunction with the measurement of composite slowness for a working specimen in the manner previously described, the volume fraction values of P_m and Pf for the working specimen are determined.

In this two-phase system, under the assumption that ^"the volume fractions of the phases add to unity, only a single type of measurement is required for the determination of volume fraction of the phases. Ultrasonic slowness has been chosen as the preferred quantity to be determined, as it is defined by a linear function, is not affected significantly by interface characteristics, and can be measured quickly and accurately for both working specimens and calibration specimens.

If the assumption of conservation of volume is not applicable, then two types of measurements would be required. For example, any t o of ultrasonic slowness, ultrasonic a11enuation, and density could be used as the basis for the determination of the phase fractions. Other composite properties such as optical, electrical, magnetic, electromagnetic, or the like could also serve as the basis for this determination. Returning to the preferred embodiment wherein volume is conserved and a measurement of slowness is used, Figure 7 illustrates an apparatus 110 for measuring composite slowness of specimens 18. The specimen 18 is contacted on one surface by a transmitter transducer 114, which transmits into the specimen 18 pulsed ultrasonic signals of proper frequency, such as from about 10⁵ to about 10⁷ Hertz. A receiver transducer 116 contacts the other side of the specimen 18 in a facing relation to the transmitter transducer 114, and receives the transmitted ultrasonic wave. A pulse generator 118 sends a pulsing signal to the transmitter transducer 114, and receives the transmitted signal from the receiver transducer 116. The waveform is digitized in a digitizer 121. The thickness or sonic path of the specimen is measured by a thickness gauge 120, and the thickness is provided to a minicomputer 122, along with the waveform and transit time from the digitizer 121. The slowness is the transit time divided by the thickness. This apparatus can be provided with a mechanism 124 upon which the transducers 114 and 116 are mounted, and a mechanism 125 upon which the thickness gauge 120 is mounted. The mechanisms 124 and 125 can open to permit a specimen 18 to be placed therein, closed for a measurement, and then open to allow extraction of the specimen 18 and insertion of a new specimen. The mechanisms 124 and 125 can be made to operate very rapidly, so that measurements of a series of working specimens can be accomplished rapidly, with each measurement requiring less than one second using automated apparatus. The highly automated apparatus just described is particularly useful in performing production line measurements of composite materials as they are fabricated. For example, graphite fiber/resin matrix composites are typically fabricated as thin sheets of "prepreg", which is a loosely bound, uncured sheet about .004-.008 inches thick and containing the fiber reinforcement and the matrix material, the matrix being in an uncured state. It is important to determine the weight fractions of the phases during production of the prepreg, since the prepreg is sold to a specification requiring particular weight fractions of the phases. In the art, the usual method of measuring the weight fractions of the phases on the production line has been to select working specimens on a periodic basis for destructive testing for weight fraction. The specimens were taken to a laboratory, where the matrix was dissolved away and the remaining fiber material weighed and converted to a volume fraction through calibration tables. Each such test costs about $40-$150 to perform, and requires about 1/2-3 hours to perform. The high cost reduces the number of specimens measured, and the time delay does not permit real time control of the fabrication process. The present invention, on the other hand, yields a weight fraction determination in only a few seconds, at a cost of less than $1 per test. Many tests can be performed and trends observed. If a trend from the desired weight fractions is observed, the manufacturing process can be adjusted accordingly.

The present approach can, of course, also be used on finished composites, before they are joined into structures, as a quality control check after the structure has been joined together, and even after the structure has been in service, as a check for deterioriation. In the latter application, it is not uncommon for one phase, particularly the resin matrix, to absorb moisture during service. The absorbed moisture causes deterioriation of composite properties. The present approach permits inspection of the weight fractions of the phases of a part in service. Such inspection is sufficiently accurate to identify the change in weight fraction of a phase due to absorbed moisture, and even the appearance of a new phase, containing bubbles of moisture. The following example is presented to illustrate aspects of the invention, and should not be taken as limiting the scope of the invention in any way.

Example A commercial sheet of prepreg was obtained from the manufacturer. The sheet was composed of graphite fibers in an epoxy matrix, and had dimensions of about 12 inches by 12 inches by .005 inches thick. The sheet was cut into pieces 4 inches by 4 inches, and each of these pieces was cut into specimens 2 inches by 2 inches. The 2 inch by 2 inch samples from a 4 inch by 4 inch piece were stacked and evaluated by the process of the invention. They were then evaluated by the conventional procedure of dissolving the matrix and weighing the remaining fibers. Four such comparative tests were made, and the resin contents by weight of the samples are summarized in the following table:

The resin contents as determined by the two approaches are reasonably consistent, with at most 156 difference between the two measurements. It is also apparent that the resin contents between areas of the piece of prepreg vary by several percent,c even as measured by either of the two techniques. Consequently, it cannot be concluded that either of the techniques gives more accurate or more dependable results than the other. The prior art process has a number of sources of error, and the approach of the present invention may in fact be more accurate. However, the approach of the Invention definitely yields the results more quickly and inexpensively than the conventional approach, and detects the variations between areas of several percent.

It will now be appreciated that the approach of the present invention can be used to determine volume fractions of multi-phase systems quickly and accurately. Calibration data is first obtained on a limited number of calibration specimens, and then this data is used in conjunction with test data to determine volume or weight fractions of the phases in working specimens. Although a particular embodiment of the invention has been described in detail for purposes of illustration, various modifications may be made without departing from the spirit and scope of the invention. Accordingly, the invention is not to be limited except as by the appended claims.

Claims

What is claimed is:

1. A process for performing a nondestructive determination of the fractions of the phases present in a working specimen of a mixture, comprising the steps of: selecting a series of nondestructively measurable properties of the phases of the mixture, each of which properties varies with the fractions of the individual phases in a known way and are summed over the phases to define a total mixture value for that property, thereby forming a system of simultaneous equations for the mixture properties as a function of the sum of products of a coefficient of variation times the fraction of each phase; measuring each of the measurable mixture properties on a sufficient number of calibration specimens having different fractions of the phases, and then destructively determining the fractions of the phases for the calibration specimens, thereby determining the coefficients of variation of the system of equations; and nondestructively measuring each of the measurable mixture properties on the working specimen of unknown phase fractions, and solving the system of equations for the fractions of the phases present in the working specimen.

2. The process of claim 1, wherein at least some of the measurable properties are measured by ultrasonic measurements. 3. The process of claim 1, wherein said step of nondestructively measuring is performed by an apparatus comprising: measurement means for introducing a first ultrasonic signal into the specimen and for receiving a second ultrasonic signal from the specimen; compression means for forcing said measurement means against the surface of the specimen with a reproducibly controllable constant compressive force, so that the same compressive force may be applied on successive measurements; and control means for controlling said measurement means.

4. The process of claim 1, wherein the mixture is a bonded composite material.

5. The process of claim 1, wherein at least one phase is an elastic fiber.

6c The process of claim 1, wherein at least one phase Is a nonmetallic matrix.

7. A process for performing a nondestructive determination of the volume fractions of the phases of a composite material working specimen having as phases an elastic fiber and a resin matrix, wherein the slowness of an ultrasonic wave propagated through the fiber is known, and wherein the in-situ slowness of an ultrasonic wave propagated through the matrix may differ from that measured when the matrix material is not incorporated into the working specimen, comprising the steps of: determining the in-situ slowness of an ultrasonic wave propagating through the matrix, by the steps of measuring the slowness of an ultrasonic wave in a composite calibration specimen, destructively measuring the volume fractions of the fiber and matrix for the calibration specimen, and calculating the in-situ slowness of an ultrasonic wave in the matrix as the reciprocal of the volume fraction of the matrix, times the difference between the slowness of an ultrasonic wave in the working specimen, less the product of the slowness of an ultrasonic wave in the fiber times the volume fraction of the fiber, all determined for the calibration specimen; measuring the slowness of an ultrasonic wave in the working specimen, which is not destroyed in the measurement; and calculating the volume fraction of the matrix in the working specimen as the slowness of the ultrasonic wave in the working specimen, less the known slowness of the ultrasonic wave in the fiber, divided by the difference between the slowness of the ultrasonic wave in the matrix, as determined from the calibration specimen, less the known slowness of the ultrasonic wave in the fiber, whereupon the volume fraction of the fiber in the working specimen can be determined as one minus the volume fraction of matrix in the working specimen.

8. The process of claim 7, wherein said step of measuring the slowness is performed by an apparatus comprising: measurement means for introducing a first ultrasonic signal into the specimen and for receiving a second ultrasonic signal from the specimen; compression means for forcing said measurement means against the surface of the specimen with a reproducibly controllable constant compressive force, so that the same compressive force may be applied on successive measurements; and control means for controlling said measurement means.

9. The process of claim 7, wherein said step of measuring is performed by an apparatus comprising: a pair of ultrasonic transducers disposed in a facing but spaced apart relationship to each other along a vertical axis, so that a specimen may be placed between said ultrasonic transducers; a frame which supports said two ultrasonic transducers, said frame including a support rod movable in the vertical direction within said frame and to which one of said transducers is fixed, so that said transducer is movable along the vertical axis and is forced toward the other of said transducers under the dead, loading weight of said support rod, thereby compressing the specimen between said transducers under a constant, reproducible force; a displacement gauge that measures the relative position along the vertical axis of the support rod with respect to said frame; and a controller that drives one of said transducers and receives a signal from the other of said transducers. 10. Apparatus for performing ultrasonic measurements on a solid specimen, comprising: measurement means for introducing a first ultrasonic signal into the specimen and for receiving a second ultrasonic signal from the specimen; compression means for forcing said measurement means against the surface of the specimen with a reproducibly controllable constant compressive force, so that the same compressive force may be applied on successive measurements; and control means for controlling said measurement means.

11. The apparatus of claim 10, wherein said measurement means includes a pair of ultrasonic transducers in a facing but spaced apart relationship along an axis and adapted for contacting opposing surfaces of the specimen.

12. The apparatus of claim 10, wherein said measurement means includes a single ultrasonic transducer which both transmits a signal into the specimen and receives a signal back from the specimen.

13. The apparatus of claim 10, wherein said compression means includes a frame for supporting said measurement means in contact with the surface of the compliant specimen, and loading means for applying a dead-weight load to said measurement means to force it against the surface of the compliant specimen. 14. The apparatus of claim 10, wherein said compression means includes adjustable spring biasing means for applying a constant force to the measurement means.

15. The apparatus of claim 10, further including locating means for measuring the position of said measurement means.

16. Apparatus for performing ultrasonic measurements on a solid specimen, comprising: an ultrasonic transducer adapted for contacting to the surface of the specimen; a compression loader for forcing said ultrasonic transducer against the surface of the specimen with a reproducibly controllable constant force; and a controller that receives a signal from said transducer.

17. The apparatus of claim 16, wherein said compression loader forces said transducer against the surface of the specimen by a dead-weight load.

18. The apparatus of claim 16, wherein said compression loader includes a frame for supporting said ultrasonic transducer in contact with the surface of the specimen, and loading means for applying a dead-weight load to said transducer means to force it against the surface of the specimen. 19. The apparatus of claim 16, further including locating means for measuring the position of said transducer means parallel to the direction of application of the compressive force.

20. Apparatus for performing ultrasonic measurements on a solid specimen, comprising: a pair of ultrasonic transducers disposed in a facing but spaced apart relationship to each other along a vertical axis, so that a specimen may be placed between said ultrasonic transducers; a frame which supports said two ultrasonic transducers, said frame including a support rod movable in the vertical direction within said frame and to which one of said transducers is fixed, so that said transducer is movable along the vertical axis and is forced toward the other of said transducers under the dead loading weight of said support rod, thereby compressing the specimen between said transducers under a constant, reproducible force; a displacement gauge that measures the relative position along the vertical axis of the support rod with respect to said frame; and a controller that drives one of said transducers and receives a signal from the other of said transducers.