[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN114453809A - Cavity welding positioning method - Google Patents

Cavity welding positioning method Download PDF

Info

Publication number
CN114453809A
CN114453809A CN202210266974.9A CN202210266974A CN114453809A CN 114453809 A CN114453809 A CN 114453809A CN 202210266974 A CN202210266974 A CN 202210266974A CN 114453809 A CN114453809 A CN 114453809A
Authority
CN
China
Prior art keywords
sampling point
sampling
point
positioning
initial
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210266974.9A
Other languages
Chinese (zh)
Other versions
CN114453809B (en
Inventor
刘飞香
李鹏
戴熙礼
李肖
蒲英钊
马金琦
汪雷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Railway Construction Heavy Industry Group Co Ltd
Original Assignee
China Railway Construction Heavy Industry Group Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Railway Construction Heavy Industry Group Co Ltd filed Critical China Railway Construction Heavy Industry Group Co Ltd
Priority to CN202210266974.9A priority Critical patent/CN114453809B/en
Publication of CN114453809A publication Critical patent/CN114453809A/en
Application granted granted Critical
Publication of CN114453809B publication Critical patent/CN114453809B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K37/00—Auxiliary devices or processes, not specially adapted to a procedure covered by only one of the preceding main groups
    • B23K37/02—Carriages for supporting the welding or cutting element
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
    • B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Robotics (AREA)
  • Physics & Mathematics (AREA)
  • Optics & Photonics (AREA)
  • Laser Beam Processing (AREA)
  • Numerical Control (AREA)

Abstract

The invention discloses a cavity welding and positioning method, which comprises the following steps: step S1: sampling point collection is carried out at the initial position and the end position of a welding line to be welded to obtain a total initial sampling point set; step S2: carrying out optimization processing on the initial sampling point set to obtain a sampling point truth value set; step S3: processing the sampling point truth value set by using a BA algorithm to obtain an available sampling point set; step S4: distinguishing and processing available sampling points related to the initial position and the end position of a welding seam to be welded in the available sampling point set to obtain optimal positioning sampling points of the initial point and the end point of the welding seam; step S5: the executing mechanism completes positioning according to the optimal positioning sampling point; after the cavity welding positioning method is used for sampling, the reference is set to remove abnormal sampling points, then smoothing is carried out to obtain a sampling point truth value set, then the sampling point truth value set is optimized and calculated by using a BA algorithm, and the positioning result accuracy is high.

Description

Cavity welding positioning method
Technical Field
The invention relates to the field of welding automation, in particular to a cavity welding positioning method.
Background
The position is sought to artifical location, mechanical positioning, high pressure commonly used in current welding seam initial point location, but to steel structure cavity (steel structure cavity) location, the problem that current steel structure cavity welding position exists is: 1. the internal space of the steel structure cavity is narrow, the manual construction difficulty is high, the traditional steel structure cavity is mostly welded on site by a welder with skillful technology during machining, the vertical welding and overhead welding work difficulty is high, and great difficulty is brought to the construction of the welder; 2. the mechanical positioning tool in the steel structure cavity cannot be accurately positioned under the influence of machining errors in machining, assembling, riveting and other links; high pressure is sought to be located and is needed the welding wire touch work piece inner wall in the welder, but steel structure cavity welding seam initial point position accessibility is poor, and welder usually is difficult to reach.
In view of the above, a cavity welding positioning method is urgently needed to solve the problem of difficult welding positioning in the prior art.
Disclosure of Invention
The invention aims to provide a cavity welding positioning method to solve the problem of difficult welding positioning in the prior art, and the specific technical scheme is as follows:
a cavity welding positioning method comprises the following steps:
step S1: sampling point collection is carried out at the initial position and the end position of a welding line to be welded to obtain a total initial sampling point set;
step S2: optimizing the initial sampling point set to obtain a sampling point truth value set;
step S3: processing the sampling point truth value set by using a BA algorithm to obtain an available sampling point set;
step S4: distinguishing and processing available sampling points related to the initial position and the end position of a welding seam to be welded in the available sampling point set to obtain optimal positioning sampling points of the initial point and the end point of the welding seam;
step S5: and the executing mechanism completes positioning according to the optimal positioning sampling point.
Preferably, in step S1, the laser sensor is used to detect the initial position and the final position of the weld jointThe positions of the sampling points are n to obtain an initial sampling point set { x }i}；xiRepresenting the ith sample in the initial set of samples.
Preferably, in the above technical solution, the step S2 includes a step S2.1, specifically, the initial sampling point set { x ] is subjected to equation 1)iFiltering to obtain an initial sample point set after filtering, and formula 1) is as follows:
Figure BDA0003552222080000011
wherein x isiRepresenting the ith sample point in the initial sample point set; x is the number ofmedianRepresenting the median of the initial set of samples; sigmamedianIs a comparative reference; y isiA standard function representing the ith sample in the initial set of samples when yiWhen the sampling point is greater than Q, the sampling point is rejected, and when y is greater than QiIf the sampling point is less than or equal to Q, the sampling point is reserved in the initial sampling point set; q is a constant.
Preferably, in step S2.1, σmedian＝1.4826{|xi-xmedian|}；Q＝2.5。
Preferably, in the above technical solution, step S2 further includes step S2.2, specifically, smoothing the filtered initial sample point set by using equation 2) to obtain a sample point truth value set
Figure BDA0003552222080000021
Formula 2) is as follows:
Figure BDA0003552222080000022
wherein,
Figure BDA0003552222080000023
representing the ith sample point in the sample point truth value set; x is the number ofiRepresenting the ith sample point in the initial sample point set; m is the smoothing order; and L is the total number of sampling points in the sampling point truth value set.
The above technical scheme is optimizedSaid step S3 includes a step S3.1 for global exploration, using equation 3) for the set of sample truth values
Figure BDA0003552222080000024
Iterating the sample points to obtain iterated sample points, and generating a first random distribution number rand1According to rand1The sample point is judged as a local solution
Figure BDA0003552222080000025
Or eliminating the sample point, equation 3) is as follows:
Figure BDA0003552222080000026
wherein, the directional movement of a certain bat i in a D-dimensional space is set, and the position of the bat i in the space in the t-th iteration is the position of the bat i in the t-th iteration
Figure BDA0003552222080000027
The location of the location; the bat i has a unique movement frequency f at the t-th iterationiAnd the running speed vi，
Figure BDA00035522220800000212
Representing the speed of the bat i after t iterations; f. ofminRepresents the minimum frequency of the bat i during the movement; f. ofmaxRepresents the maximum frequency of the bat i during the movement;
Figure BDA0003552222080000028
representing the position of the bat i after t iterations;
Figure BDA0003552222080000029
representing the optimal solution of all bats at present; gamma is a correction factor; beta is a random value of (-1, 1) and follows a uniform distribution.
Preferably, the technical scheme also comprises a step 3.2 of local exploration,
first, the local solution obtained in step S3.1 is solved using equation 4)
Figure BDA00035522220800000210
Carry out random disturbance to obtain new solution
Figure BDA00035522220800000211
Second, using the new solution
Figure BDA0003552222080000031
Equation 3) and equation 5) are iterated and a second random distribution number rand is generated2According to a second random distribution number rand2And judging that the iterated sampling point is taken as one of the available sampling points or the sampling point is eliminated, wherein a plurality of available sampling points obtain an available sampling point set, and the following formulas 4) and 5) are as follows:
Figure BDA0003552222080000032
Figure BDA0003552222080000033
wherein,
Figure BDA0003552222080000034
for solving a local solution
Figure BDA0003552222080000035
A new solution generated after random disturbance; ε is [ -1, 1]A random value of (a);
Figure BDA0003552222080000036
represents the average of all batloudness at the t-th iteration;
Figure BDA00035522220800000312
representing the loudness value of bat i at the t-th iteration;
Figure BDA0003552222080000037
representing bati at the t-th iterationA wavelength;
Figure BDA0003552222080000038
represents the wavelength of the bat i when not iterated; both α and γ are constants.
Preferably, in the step 3.1, the correction factor is
Figure BDA0003552222080000039
Wherein b is a random number obeying a beta distribution; t is the number of iterations; t ismaxIs the maximum iteration number; e is a natural constant.
Preferably, in the above technical solution, the step S4 includes a step S4.1 and a step S4.2;
step S4.1:
first, using equation 6) to obtain a set of available samples { p }jInverse solution of each sample point in (6) } as follows:
Figure BDA00035522220800000310
wherein p isjRepresenting the jth sample point in the available sample point set;
Figure BDA00035522220800000311
representing an inverse solution of a jth sample point in the available sample point set; a is the upper limit of the optimized value; d is the lower limit of the optimized value;
second, determine whether to collect the available sampling points { p) according to equation 7)jReplacing the sampling point in the positioning sample point set with the inverse solution corresponding to the sampling point to obtain a positioning sample point set, wherein the formula 7) is as follows:
Figure BDA0003552222080000041
wherein, represents Δ pjRepresents the optimal solution of the jth sampling point in the available sampling point set and all current bats
Figure BDA0003552222080000042
The absolute value of the difference of (a);
Figure BDA0003552222080000043
representing the inverse solution of the jth sampling point in the available sampling point set and the optimal solution of all current bats
Figure BDA0003552222080000044
The absolute value of the difference of (a); when in use
Figure BDA0003552222080000045
When the current sampling point is included in the positioning sampling point set, when the current sampling point is included in the positioning sampling point set
Figure BDA0003552222080000046
Taking the inverse solution corresponding to the current sampling point and incorporating the inverse solution into a positioning sampling point set;
step S4.2:
firstly, distinguishing sampling points in a positioning sampling point set to obtain M positioning sampling points at the initial point position of a welding line to be welded and K positioning sampling points at the final point position of the welding line to be welded;
secondly, taking the arithmetic mean value of the M positioning sampling points to obtain the optimal positioning sampling point of the initial position of the welding seam; and taking the arithmetic mean value of the K positioning sampling points to obtain the optimal positioning sampling point of the end point position of the welding seam.
Preferably, in the step S5, the optimal positioning sampling point is substituted into the inverse kinematics formula to obtain an action parameter of the actuator, and the actuator is positioned to the welding start point or the welding end point according to the action parameter.
The technical scheme of the invention has the following beneficial effects:
(1) after the cavity welding positioning method is used for sampling, the reference is set to remove abnormal sampling points, then smoothing is carried out to obtain a sampling point truth value set, then the sampling point truth value set is optimized and calculated by using a BA algorithm, and the positioning result accuracy is high.
(2) The invention uses the laser sensor to position, and the accessibility is good; whole module easy dismounting carries out the steel structure when changing outfit production, can remove whole module, also can remove the work piece and produce.
(3) According to the method, during global exploration, correction factors are introduced to correct the step length during global exploration, so that the accuracy of a positioning result is ensured; in the correction factor of the invention, b is a random number obeying beta distribution, so that in the iteration process, (2b-1) approaches to 1 and floats up and down, and e is a natural constant, so that in the initial iteration, the correction factor approaches to 4, and in the final iteration, the correction factor approaches to 1, therefore, the correction factor of the invention can be updated more quickly in the early stage of speed updating, and the speed updating is slowed down when approaching a target point, thereby improving the searching precision.
(4) When the optimal positioning sampling point is confirmed, the inverse solution concept is introduced to optimize the sampling point, and the positioning precision is improved.
In addition to the objects, features and advantages described above, other objects, features and advantages of the present invention are also provided. The present invention will be described in further detail below with reference to the drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention.
In the drawings:
FIG. 1 is a schematic structural diagram of a cavity welding positioning method according to the present embodiment;
fig. 2 is a flowchart of step S3 in the cavity welding positioning method of the present embodiment;
wherein, 1, a steel cavity is formed; 2. an actuator; 3. a laser sensor.
Detailed Description
Embodiments of the invention will be described in detail below with reference to the drawings, but the invention can be implemented in many different ways, which are defined and covered by the claims.
Example (b):
a cavity welding positioning method, as shown in fig. 1 and 2, specifically includes the following steps:
first, as shown in fig. 1, an actuator 2 (e.g., a welding robot) performs rough positioning by mechanical assembly, and performs subsequent laser sampling based on local positioning;
secondly, classifying welding seams to be welded of the steel structure cavity 1, and classifying the welding seams into three types of horizontal welding, vertical welding and overhead welding according to a welding method, wherein each type of four welding seams (respectively a horizontal welding seam a 1-a 4, a vertical welding seam b 1-b 4 and an overhead welding seam c 1-c 4) are provided, a sampling point is located on any one of two plate surfaces where the welding seams to be welded are located, the distance between the sampling position and the initial point and the distance between the sampling position and the final point of the welding seams to be welded are appropriate (the specific distance is determined according to actual conditions), and the specific positioning steps are as follows:
step S1: sampling point collection is respectively carried out at the initial position and the end position of a welding line to be welded by utilizing the laser sensor 3 on the actuating mechanism, the total number of sampling points sampled at two positions is n (for example, 100 and 200), and a total initial sampling point set { x-iIn which xiRepresents the ith sample point in the initial sample point set, wherein the value of i is 1-n.
Step S2: for the initial sampling point set { xiCarrying out optimization processing to obtain a sampling point truth value set
Figure BDA0003552222080000051
The method comprises the following specific steps:
step S2.1 (filtering), initial sampling point set { x) is processed by formula 1iRemoving abnormal sample points or unavailable sample points in the data to obtain a filtered initial sample point set, wherein the formula 1) is as follows:
Figure BDA0003552222080000061
wherein x isiRepresenting the ith sampling point in the initial sampling point set; x is a radical of a fluorine atommedianRepresenting the median of the initial set of samples; sigmamedianIs a comparative reference; y isiA standard function representing the ith sample in the initial set of samples when yiWhen the sampling point is greater than Q, the sampling point is rejected, and when y is greater than QiAnd if not more than Q, keeping the sampling point in the initial sampling point set, thereby obtaining the filtered initial sampling point set.
Preferably, in this embodiment, the reference σ is comparedmedian＝1.4826{|xi-xmedianI, the constant Q is 2.5, σ is selected in this embodimentmedianQ can ensure the filtering precision, and invalid sample points can be removed quickly and accurately;
step S2.2, smoothing the filtered initial sample point set (namely, filling the removed invalid sample points in the initial sample point set and optimizing the sample points in the filtered initial sample point set) by using the formula 2) to obtain a sample point truth value set
Figure BDA0003552222080000062
Formula 2) is as follows:
Figure BDA0003552222080000063
wherein,
Figure BDA0003552222080000064
representing the ith sample point in the sample point truth value set; x is the number ofiRepresenting the ith sample point in the initial sample point set; m is a smoothing order, and m is a natural number more than or equal to 1; l is the total number of sampling points in the sampling point truth value set, preferably L is equal to n (n is the total number of sampling points of the initial sampling, i.e. the total number of sampling points in the initial sampling point set); i denotes the ith.
Step S3: as shown in fig. 2, sample truth sets
Figure BDA0003552222080000065
Utilizing BA algorithm (namely bat algorithm) to carry out post-processing to obtain available sampling point set { pjSpecifically, it is assumed that a bat i moves directionally in a D-dimensional space, and the spatial position of the bat i at the t-th iteration is the position of the bat i
Figure BDA0003552222080000066
The location of the location; the bat i has a unique movement frequency f at the t-th iterationiAnd the running speed viThe method comprises the following steps:
step S3.1 (global exploration): as shown in fig. 2, the sampling points are true using equation 3)Set of values
Figure BDA0003552222080000067
After iteration is performed on the sampling points in (1), a first random distribution number rand is generated1According to rand1Judging to use the iterated sampling point as a local solution
Figure BDA0003552222080000068
Or eliminating the sample point, equation 3) is as follows:
Figure BDA0003552222080000071
wherein, the spatial position of the bat i in the t-th iteration is
Figure BDA0003552222080000072
The location of the location; the bat i has a unique movement frequency f at the t-th iterationiAnd the running speed vi，
Figure BDA0003552222080000073
Representing the speed of the bat i after t iterations; f. ofminRepresents the minimum frequency of the bat i during the movement; f. ofmaxRepresents the maximum frequency of the bat i during the movement;
Figure BDA0003552222080000074
representing the position of the bat i after t iterations;
Figure BDA0003552222080000075
representing the optimal solution of all bats at present; gamma is a correction factor; beta is a random value of (-1, 1) and is subject to uniform distribution;
preferably, the correction factor
Figure BDA0003552222080000076
Wherein b is a random number obeying a beta distribution; t is the number of iterations; t ismaxIs the maximum iteration number; e is a natural constant;
in step S3.1, a set of truth values of the sample points
Figure BDA0003552222080000077
As input and generates a first random distribution number rand after performing the iteration by equation 3)1According to rand1First pulse emissivity r of bat iiThe relationship judgment of (1) is to use the iterated sampling points as local solutions
Figure BDA0003552222080000078
Or eliminating the sampling points, and judging the rule as follows:
when rand1＜riTaking the iterated sampling points as local solutions
Figure BDA0003552222080000079
And enter local exploration (i.e., random perturbation is performed);
when rand1≥riThen, the current sampling point is eliminated, and the sampling point truth value set
Figure BDA00035522220800000710
The next sample point in (3) is iterated further according to equation 3) of step S3.1;
step S3.2 (local exploration): the method comprises a first step and a second step, and specifically comprises the following steps:
first, local solution using equation 4)
Figure BDA00035522220800000711
Carrying out random disturbance to obtain a new solution
Figure BDA00035522220800000712
Second, using the new solution
Figure BDA0003552222080000081
Equation 3) and equation 5) are followed and a second random distribution number rand is generated2According to a second random distribution number rand2Determining the iterated samples as available samplesOne or eliminate the sample point, multiple available sample points get available sample point set { pj}, formula 4) and formula 5) are as follows:
Figure BDA0003552222080000082
Figure BDA0003552222080000083
wherein,
Figure BDA0003552222080000084
for solving a local solution
Figure BDA0003552222080000085
A new solution generated after random disturbance; ε is [ -1, 1]A random value of (a);
Figure BDA0003552222080000086
represents the average of all batloudness at the t-th iteration;
Figure BDA0003552222080000087
representing the loudness value of bat i at the t-th iteration;
Figure BDA0003552222080000088
represents the wavelength of the bat i at the t-th iteration;
Figure BDA0003552222080000089
represents the wavelength of the bat i when not iterated; both α and γ are constants; exp represents an exponential function with a natural constant e as the base;
in step S3.2, by solving the local
Figure BDA00035522220800000810
Random perturbation is performed (as shown in equation 4) to generate a new solution
Figure BDA00035522220800000811
And to solve the new solution
Figure BDA00035522220800000812
Performing border crossing treatment and reusing new solution
Figure BDA00035522220800000813
Loudness and wavelength of bat i (i.e., equation 5) and equation 3) for subsequent iterations; for new solutions after perturbation calculation
Figure BDA00035522220800000814
Generating rand2According to rand2The second pulse emissivity r of bat ij(rjAnd r in step S3.1iBoth randomly generated) is to include the iterated sample points into the set of available sample points { p }jWhether the sampling point is taken as one of the available sampling points or eliminated, the specific judgment rule is as follows:
when rand2＜rjThen, the iterated sampling points are included in the available sampling point set { p }jAs one of the available samples;
when rand2≥rjThen, the sampling points are removed;
the above rand2And rjAfter the determination of (2), the sampling point truth value set
Figure BDA00035522220800000815
The next sample point in (3) continues the iteration according to equation 3) in step S3.1.
Step S4: distinguishing and processing available sampling points related to the initial position and the end position of a welding seam to be welded in the available sampling point set to obtain optimal positioning sampling points of the initial point and the end point of the welding seam, wherein the method specifically comprises the following steps:
step S4.1, comprising a first step and a second step,
first, using equation 6) to obtain a set of available samples { p }jInverse solution of each sample point in (6) } as follows:
Figure BDA0003552222080000091
wherein p isjRepresenting the jth sample in the available set of samples (i.e., the positive solution);
Figure BDA0003552222080000092
representing an inverse solution of a jth sample point in the available sample point set; a is the upper limit of the optimized value; d is an optimized value lower limit, the optimized value upper limit and the optimized value lower limit are selected according to the actual situation, and the selection of a and d meets the following conditions: a. d ∈ R × pjAnd p isjE (a d), R is a real number.
Second, according to equation 7) it is determined that the set of available samples { p } isjReplacing the sample point in the positioning sample point with the inverse solution corresponding to the sample point or directly using the sample point (i.e. using the positive solution), so as to obtain a positioning sample point set, and equation 7) as follows:
Figure BDA0003552222080000093
wherein, represents Δ pjRepresents the optimal solution of the jth sampling point in the available sampling point set and all current bats
Figure BDA0003552222080000094
The absolute value of the difference of (a);
Figure BDA0003552222080000095
representing the inverse solution of the jth sampling point in the available sampling point set and the optimal solution of all current bats
Figure BDA0003552222080000096
The judgment rule of the absolute value of the difference value is as follows:
when in use
Figure BDA0003552222080000097
When the current sampling point is directly used (namely, the current sampling point is brought into the positioning sampling point set), when the current sampling point is directly used
Figure BDA0003552222080000098
Then, the current sampling point is takenThe corresponding inverse solution is brought into a positioning sampling point set;
step S4.2, comprising a first step and a second step,
firstly, distinguishing positioning sampling points belonging to the initial point position and the end point position of a to-be-welded seam in a positioning sampling point set, wherein the distinguishing can be manually distinguished or can be finished by referring to the prior art, M positioning sampling points of the initial point position of the to-be-welded seam and K positioning sampling points of the end point position of the to-be-welded seam are obtained after the distinguishing, and M + K is equal to the total number of the sampling points in the positioning sampling point set;
secondly, taking the arithmetic average value of M positioning sampling points at the initial position of the welding seam to be welded to obtain the optimal positioning sampling point at the initial position of the welding seam to be welded; and obtaining the optimal positioning sampling point of the end point position of the welding line to be welded by taking the arithmetic average value of the K positioning sampling points of the end point position of the welding line to be welded.
Step S5: the executing mechanism completes positioning according to the optimal positioning sampling point, and specifically comprises the following steps: and substituting the optimal positioning sampling point into an inverse kinematics formula to obtain an action parameter of the actuating mechanism, and positioning the actuating mechanism to the welding starting point or the welding terminal point according to the action parameter. This step can be done with reference to the prior art.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A cavity welding positioning method is characterized by comprising the following steps:
step S1: sampling point collection is carried out at the initial position and the end position of a welding line to be welded to obtain a total initial sampling point set;
step S2: optimizing the initial sampling point set to obtain a sampling point truth value set;
step S3: processing the sampling point truth value set by using a BA algorithm to obtain an available sampling point set;
step S4: distinguishing and processing available sampling points related to the initial position and the end position of a welding seam to be welded in the available sampling point set to obtain optimal positioning sampling points of the initial point and the end point of the welding seam;
step S5: and the executing mechanism completes positioning according to the optimal positioning sampling point.
2. The cavity welding positioning method according to claim 1, wherein in step S1, n sampling points are sampled at the start position and the end position of the weld joint by the laser sensor to obtain an initial sampling point set { x }i}；xiRepresenting the ith sample in the initial set of samples.
3. The cavity welding positioning method of claim 1, wherein the step S2 includes a step S2.1, specifically, using formula 1) to initial sampling point set { x }iFiltering to obtain an initial sample point set after filtering, and formula 1) is as follows:
Figure FDA0003552222070000011
wherein x isiRepresenting the ith sample point in the initial sample point set; x is the number ofmedianRepresenting the median of the initial set of samples; sigmamedianIs a comparative reference; y isiA standard function representing the ith sample in the initial set of samples when yiWhen the sampling point is greater than Q, the sampling point is rejected, and when y is greater than QiIf the sampling point is less than or equal to Q, the sampling point is reserved in the initial sampling point set; q is a constant.
4. The cavity weld positioning method according to claim 3, wherein, in the step S2.1, σ ismedian＝1.4826{|xi-xmedian|}；Q＝2.5。
5. The cavity welding positioning method of claim 3, wherein the step S2 further includes a step S2.2, specifically, smoothing the filtered initial sampling point set by using the formula 2),obtaining a truth value set of sampling points
Figure FDA0003552222070000013
Formula 2) is as follows:
Figure FDA0003552222070000012
wherein,
Figure FDA0003552222070000021
representing the ith sample point in the sample point truth value set; x is the number ofiRepresenting the ith sample point in the initial sample point set; m is the smoothing order; and L is the total number of sampling points in the sampling point truth value set.
6. The cavity welding positioning method of claim 5, wherein the step S3 includes a step S3.1 of global exploration using equation 3) for sample truth set
Figure FDA0003552222070000022
Iterating the sample points to obtain iterated sample points, and generating a first random distribution number rand1According to rand1The sample point is judged as a local solution
Figure FDA0003552222070000023
Or eliminating the sample point, equation 3) is as follows:
Figure FDA0003552222070000024
wherein, the directional movement of a certain bat i in a D-dimensional space is set, and the spatial position of the bat i in the t-th iteration is the position of the bat i in the space
Figure FDA0003552222070000025
The location of the location; the bat i has a unique movement frequency f at the t-th iterationiAnd the running speed vi，
Figure FDA0003552222070000026
Representing the speed of the bat i after t iterations; f. ofminRepresents the minimum frequency of the bat i during the movement; f. ofmaxRepresents the maximum frequency of the bat i during the movement;
Figure FDA0003552222070000027
representing the position of the bat i after t iterations;
Figure FDA0003552222070000028
representing the optimal solution of all bats at present; gamma is a correction factor; beta is a random value of (-1, 1) and follows a uniform distribution.
7. The cavity weld positioning method of claim 6, further comprising step 3.2 for local exploration,
first, the local solution obtained in step S3.1 is solved using equation 4)
Figure FDA0003552222070000029
Carry out random disturbance to obtain new solution
Figure FDA00035522220700000210
Second, using the new solution
Figure FDA00035522220700000211
Formula 3) and formula 5) are iterated, and a second random distribution number rand is generated2According to a second random distribution number rand2And judging that the iterated sampling point is taken as one of the available sampling points or the sampling point is eliminated, wherein a plurality of available sampling points obtain an available sampling point set, and the following formulas 4) and 5) are as follows:
Figure FDA00035522220700000212
Figure FDA0003552222070000031
wherein,
Figure FDA0003552222070000032
for solving a local solution
Figure FDA0003552222070000033
A new solution generated after random disturbance; ε is [ -1, 1]A random value of (a);
Figure FDA0003552222070000034
represents the average of all batloudness at the t-th iteration;
Figure FDA0003552222070000035
representing the loudness value of bat i at the t-th iteration;
Figure FDA0003552222070000036
represents the wavelength of the bat i at the t-th iteration;
Figure FDA0003552222070000037
represents the wavelength of the bat i when not iterated; both α and γ are constants.
8. Cavity welding positioning method according to claim 6 or 7, characterized in that in step 3.1, the correction factor
Figure FDA0003552222070000038
Wherein b is a random number obeying a beta distribution; t is the number of iterations; t ismaxIs the maximum iteration number; e is a natural constant.
9. The cavity welding positioning method according to claim 8, wherein the step S4 includes steps S4.1 and S4.2;
step S4.1:
first, using equation 6) to obtain a set of available samples { p }jInverse solution of each sample point in (6) } as follows:
Figure FDA0003552222070000039
wherein p isjRepresenting the jth sample point in the available sample point set;
Figure FDA00035522220700000310
representing an inverse solution of a jth sample point in the available sample point set; a is the upper limit of the optimized value; d is the lower limit of the optimized value;
second, determine whether to collect the available sampling points { p) according to equation 7)jReplacing the sampling point in the positioning sample point set with the inverse solution corresponding to the sampling point to obtain a positioning sample point set, wherein the formula 7) is as follows:
Figure FDA00035522220700000311
wherein, represents Δ pjRepresents the optimal solution of the jth sampling point in the available sampling point set and all current bats
Figure FDA0003552222070000041
The absolute value of the difference of (a);
Figure FDA0003552222070000042
representing the inverse solution of the jth sampling point in the available sampling point set and the optimal solution of all current bats
Figure FDA0003552222070000043
The absolute value of the difference of (a); when in use
Figure FDA0003552222070000044
When the current sampling point is included in the positioning sampling point set, when the current sampling point is included in the positioning sampling point set
Figure FDA0003552222070000045
Taking the inverse solution corresponding to the current sampling point and incorporating the inverse solution into a positioning sampling point set;
step S4.2:
firstly, distinguishing sampling points in a positioning sampling point set to obtain M positioning sampling points at the initial point position of a welding line to be welded and K positioning sampling points at the final point position of the welding line to be welded;
secondly, taking the arithmetic mean value of the M positioning sampling points to obtain the optimal positioning sampling point of the initial position of the welding seam; and taking the arithmetic mean value of the K positioning sampling points to obtain the optimal positioning sampling point of the end point position of the welding seam.
10. The cavity welding positioning method according to claim 9, wherein in step S5, the optimal positioning sampling point is substituted into an inverse kinematics formula to obtain an action parameter of the actuator, and the actuator is positioned to the welding start point or the welding end point according to the action parameter.
CN202210266974.9A 2022-03-17 2022-03-17 Cavity welding positioning method Active CN114453809B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210266974.9A CN114453809B (en) 2022-03-17 2022-03-17 Cavity welding positioning method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210266974.9A CN114453809B (en) 2022-03-17 2022-03-17 Cavity welding positioning method

Publications (2)

Publication Number Publication Date
CN114453809A true CN114453809A (en) 2022-05-10
CN114453809B CN114453809B (en) 2024-07-09

Family

ID=81416947

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210266974.9A Active CN114453809B (en) 2022-03-17 2022-03-17 Cavity welding positioning method

Country Status (1)

Country Link
CN (1) CN114453809B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115716268A (en) * 2022-12-05 2023-02-28 中国电力科学研究院有限公司 Method and device for correcting welding path of node welding point and node welding path of power transmission tower
CN117884818A (en) * 2024-02-03 2024-04-16 江苏科钛机器人有限公司 Welding robot with accurate positioning function

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5597498A (en) * 1994-07-29 1997-01-28 Hitachi Zosen Corporation Method for welding corrugate portions by means of welding robot for corrugation lap joint
CN103521965A (en) * 2012-07-03 2014-01-22 通用电气公司 Automatic welding system and method
CN109035204A (en) * 2018-06-25 2018-12-18 华南理工大学 A kind of weld seam target real-time detection method
CN109397294A (en) * 2018-12-05 2019-03-01 南京邮电大学 A kind of robot cooperated localization method based on BA-ABC converged communication algorithm
WO2020206071A1 (en) * 2019-04-02 2020-10-08 Brain Corporation Systems, apparatuses, and methods for cost evaluation and motion planning for robotic devices
CN113793344A (en) * 2021-08-31 2021-12-14 无锡砺成智能装备有限公司 Impeller weld joint positioning method based on three-dimensional point cloud

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5597498A (en) * 1994-07-29 1997-01-28 Hitachi Zosen Corporation Method for welding corrugate portions by means of welding robot for corrugation lap joint
CN103521965A (en) * 2012-07-03 2014-01-22 通用电气公司 Automatic welding system and method
CN109035204A (en) * 2018-06-25 2018-12-18 华南理工大学 A kind of weld seam target real-time detection method
CN109397294A (en) * 2018-12-05 2019-03-01 南京邮电大学 A kind of robot cooperated localization method based on BA-ABC converged communication algorithm
WO2020206071A1 (en) * 2019-04-02 2020-10-08 Brain Corporation Systems, apparatuses, and methods for cost evaluation and motion planning for robotic devices
CN113793344A (en) * 2021-08-31 2021-12-14 无锡砺成智能装备有限公司 Impeller weld joint positioning method based on three-dimensional point cloud

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
徐小明;张华;: "局部环境焊缝初始位置图像识别方法", 焊接技术, no. 11, 28 November 2011 (2011-11-28), pages 10 - 13 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115716268A (en) * 2022-12-05 2023-02-28 中国电力科学研究院有限公司 Method and device for correcting welding path of node welding point and node welding path of power transmission tower
CN117884818A (en) * 2024-02-03 2024-04-16 江苏科钛机器人有限公司 Welding robot with accurate positioning function

Also Published As

Publication number Publication date
CN114453809B (en) 2024-07-09

Similar Documents

Publication Publication Date Title
CN114453809A (en) Cavity welding positioning method
CN105345237A (en) Device and process method for automatically controlling welding seam shape in longitudinal submerged arc welding
US11914339B2 (en) Datum selection methods and systems for minimizing hole position errors in group hole machining of large components
CN114227054B (en) Automatic detection method for tube plate welding seam based on 3D point cloud
CN113762410B (en) Key welding process parameter prediction method based on machine learning
CN114170176B (en) Automatic detection method for welding seam of steel grating based on point cloud
CN116402866A (en) Point cloud-based part digital twin geometric modeling and error assessment method and system
CN105739440A (en) Adaptive machining method of wide-chord hollow fan blade
CN113435086B (en) Automatic planning method and system for increase and decrease alternation process facing material increase and decrease composite manufacturing
CN116309556B (en) Steel member finished product quality management method based on machine vision technology
CN113751429B (en) High-precision positioning and motion compensation method for mechanical arm assisted laser processing
CN109598761B (en) Curve measurement positioning method
CN109359360B (en) Structural stress processing method based on local features
CN115464669B (en) Intelligent optical perception processing system based on intelligent welding robot and welding method
CN110222454A (en) The process design method of Milling Process precision consistency
CN112924065A (en) Measuring method for measuring residual stress of curved surface based on blind hole method
CN106682773A (en) Human-machine welding time prediction method based on simulation annealing algorithm
CN118023791B (en) Welding method and system for precise shell
CN117592223B (en) Intelligent design method of hole machining tool for aerospace materials
CN114003003A (en) Technological parameter optimization and stability control method in laser cladding process
KR20200014019A (en) Image analysis system and method for post processing of a workpiece
CN112872114B (en) Three-dimensional interference detection method in metal plate bending process
CN109765843B (en) Thin-wall part machining error compensation method based on mirror image method and cubic spline interpolation
CN113673166A (en) Digital twin model working condition self-adaption method and system for machining quality prediction
CN115847398B (en) Robot intelligent machining method and system based on region

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant