CN113447022A - Path planning method and system for workpiece detection - Google Patents
Path planning method and system for workpiece detection Download PDFInfo
- Publication number
- CN113447022A CN113447022A CN202010212405.7A CN202010212405A CN113447022A CN 113447022 A CN113447022 A CN 113447022A CN 202010212405 A CN202010212405 A CN 202010212405A CN 113447022 A CN113447022 A CN 113447022A
- Authority
- CN
- China
- Prior art keywords
- detection
- path
- module
- mutation
- total distance
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 206
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000035772 mutation Effects 0.000 claims abstract description 69
- 239000011159 matrix material Substances 0.000 claims abstract description 35
- 238000005457 optimization Methods 0.000 claims abstract description 28
- 241000283153 Cetacea Species 0.000 claims abstract description 25
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 15
- 238000007689 inspection Methods 0.000 claims description 42
- 238000004364 calculation method Methods 0.000 claims description 20
- 230000003044 adaptive effect Effects 0.000 claims description 17
- 238000010586 diagram Methods 0.000 description 8
- 238000005259 measurement Methods 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 description 1
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005295 random walk Methods 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention provides a path planning method and a path planning system for workpiece detection. The path planning method for workpiece detection is used for planning the optimal detection path of the workpiece detected by the measuring machine. And establishing a coordinate relation matrix according to the plurality of moving modes of the detection points by using the moving mode of the ray detection measuring machine between the two detection points. The path optimization step encodes each detection point, then arranges the detection points in a plurality of random sequences to form a plurality of detection paths, and sorts the detection paths according to the total distance value. And (3) generating a mutation detection path by evolution according to a whale algorithm, wherein the mutation detection path comprises a mutation total distance value, comparing the total distance value with the mutation total distance value, and selecting the minimum value to be kept to form the optimal detection path. Thereby, a fast and safe optimal path for workpiece detection is generated.
Description
Technical Field
The present invention relates to a path planning method and system, and more particularly, to a path planning method and system for workpiece inspection.
Background
In the precision manufacturing process, after the workpiece is machined, a measuring machine is required to measure the workpiece to ensure that the precision of the machined workpiece is within a reasonable range. When the number of detection points to be detected is increased, a user cannot plan a measurement path smoothly by experience, so that the production efficiency can be remarkably improved if the path planning problem can be effectively solved.
The current path planning uses the following methods: (1) the time measured in a Coordinate Measuring Machine (CMM) is reduced by minimizing the trace, and the search is performed using an ant colony algorithm. (2) The measurement sequence is planned by nearest neighbor method and refinement method, and the optimized sequence is used to complete the whole measurement process. The above path planning method still has many problems, such as too fast convergence speed, long time required for solving, easy to fall into the optimal solution of the area, and large amount of calculation, which needs to be completed by using a large amount of memory. Therefore, a path planning method and a system thereof which have slow convergence, short solution time and are not easy to fall into the optimal solution of the area are lacking in the market, so that all related companies seek the solution.
Disclosure of Invention
The invention aims to provide a path planning method for workpiece detection and a system thereof, which firstly detect the moving mode among detection points and generate a coordinate relation matrix, code and randomly sort the detection points into a plurality of detection paths, calculate the total distance value of each detection path, sort the detection paths according to the total distance value, and further group and select the leader in each group. And generating mutation detection paths and total mutation distances by a whale algorithm, and selecting the path with the minimum total distance value from all leader and mutation detection paths to be the optimal detection path so as to solve the problem of easy falling into the optimal solution of the area in the known path planning technology.
According to an embodiment of the present invention, a method for planning a path for workpiece inspection is provided, the method for planning an optimal inspection path for an inspection machine to inspect a workpiece, the inspection path includes a plurality of inspection points, and the method for planning a path for workpiece inspection includes a coordinate relation matrix establishing step and a path optimizing step. And a coordinate relation matrix establishing step of driving the ray detection measuring machine to move between two detection points and establishing a coordinate relation matrix according to a plurality of moving modes of the detection points. The path optimization step comprises an initialization coding step, an adaptive value sorting step, a dynamic grouping step, a mutation step, a selection step and an iteration number judgment step. The initialization encoding step encodes each detection point, and then the detection points are arranged in a random order for a plurality of times to form a plurality of detection paths. And the adaptive value sorting step is to calculate the total distance value of each detection path according to the coordinate relation matrix and each detection path and sort the detection paths according to the total distance value. The dynamic grouping step groups the detection paths into a plurality of groups according to the total distance value, the difference value of the plurality of total distance values of the plurality of detection paths of any group is less than or equal to a preset difference value, and the minimum value of the total distance values in each group is regarded as a leader. And in the mutation step, the leaders of the groups are evolved according to a whale algorithm to generate mutation detection paths, and the mutation detection paths comprise mutation total distance values. And the selection step compares the total distance value and the mutation total distance value of the leaders in each group with the optimal detection path after the previous iteration and selects and reserves the minimum one to become the optimal detection path. An iteration number judging step of judging whether the execution number of the mutation step is equal to a preset number; if not, the mutation step and the selection step are executed again; if yes, ending the path optimization step.
Therefore, the path planning method for workpiece detection disclosed by the invention escapes the optimal solution of the region through the dynamic clustering step and the whale algorithm, so as to solve the problem that the known path planning method is easy to fall into the optimal solution of the region due to the over-high convergence speed.
Other examples of the foregoing embodiments are as follows: in the coordinate relation matrix establishing step, if a workpiece exists between the two detection points, the moving mode is nonlinear moving. If no workpiece exists between the two detection points, the moving mode is linear moving.
Other examples of the foregoing embodiments are as follows: the dynamic clustering step includes a similarity calculation step and a clustering step. And a similarity calculation step of calculating a fitness threshold and a distance threshold of the detection path. And the grouping step calculates the fitness difference and the distance difference between each detection path and the leader, and groups the detection paths according to the fitness threshold and the distance threshold.
Other examples of the foregoing embodiments are as follows: the whale algorithm comprises a surrounding step, a hunting step and a random searching step. And the surrounding step updates the optimal detection path after the previous iteration and finds the minimum of the total distance values of all leaders in a shrink surrounding mode. The hunting step finds the minimum of the total distance values of the collars and the sleeves in a spiral motion mode. The random search step arranges the detection points in a random order to generate a mutation detection path.
Other examples of the foregoing embodiments are as follows: the method for planning the workpiece detection path further comprises a recoding step of converting the code of the optimal detection path into a measuring machine code used by the measuring machine.
According to an embodiment of the present invention, a path planning system for workpiece inspection is provided to plan an optimal inspection path of a workpiece inspected by a metrology machine, the path planning system for workpiece inspection includes a coordinate relationship matrix establishing module and a path optimizing module. The coordinate relation matrix building module drives the ray detection measuring machine to move between the two detection points so as to generate a coordinate relation matrix. The path optimization module is in signal connection with the coordinate relation matrix building module and comprises an initialization coding module, an adaptive value sorting module, a dynamic grouping module, a mutation module, a selection module and an iteration number judgment module. The initialization coding module is used for coding each detection point and then driving the detection points to be randomly arranged for a plurality of times to generate a plurality of detection paths. And the adaptive value sorting module is in signal connection with the initialization coding module, generates a total distance value of each detection path according to the coordinate relation matrix and each detection path, and sorts the detection paths according to the size of the total distance value. And the dynamic grouping module is in signal connection with the adaptive value sorting module and groups the detection paths into a plurality of groups according to the total distance value, and the difference value of the total distance values of the plurality of detection paths of any group is less than or equal to a preset difference value. And the mutation module is in signal connection with the dynamic grouping module, and the leaders of the group generate mutation detection paths through the whale calculation unit, wherein the mutation detection paths comprise mutation total distance values. And the selection module is in signal connection with the mutation module, compares the total distance value and the mutation total distance value of the leaders in each group with the optimal detection path after the previous iteration, and selects and reserves the minimum one to form the optimal detection path. The iteration frequency judging module is in signal connection with the selecting module and the mutation module and judges whether the execution frequency of the mutation module is equal to the preset frequency or not; if not, the mutation module and the selection module are executed again; if so, the path optimization module terminates execution.
Therefore, the path planning system for workpiece detection disclosed by the invention escapes the optimal solution of the region through the dynamic clustering module and the whale calculation unit, so that the problem that the known path planning system is easy to fall into the optimal solution of the region due to too high convergence speed is solved.
Other examples of the foregoing embodiments are as follows: in the coordinate relation matrix building module, if a workpiece exists between the two detection points, the moving mode is nonlinear moving. If no workpiece exists between the two detection points, the moving mode is linear moving.
Other examples of the foregoing embodiments are as follows: the dynamic clustering unit comprises a similarity meter operator module and a clustering submodule. And the similarity operator module calculates a fitness threshold and a distance threshold of the detection path. And the grouping sub-module is connected with the similarity meter operator module through signals to calculate the fitness difference and the distance difference between each detection path and the leader, and is divided into groups according to the fitness threshold and the distance threshold.
Other examples of the foregoing embodiments are as follows: the whale calculation unit comprises a surrounding submodule, a hunting submodule and a random search submodule. And the surrounding submodule updates the optimal detection path after the previous iteration and finds out the minimum of the total distance values of all leaders. And the hunting sub-module is in signal connection with the surrounding sub-module and finds out the minimum of the total distance values of all the leaders. And the random search submodule is in signal connection with the hunting submodule and generates a sudden change detection path by arranging the detection points in a random sequence.
Other examples of the foregoing embodiments are as follows: the path planning system for workpiece detection further comprises a recoding module connected with the iteration number judging module through signals, wherein the recoding module is used for converting the code of the optimal detection path into the code of the measuring machine used by the measuring machine.
Drawings
FIG. 1 is a flow chart illustrating a path planning method for workpiece inspection according to a first embodiment of the present invention;
FIG. 2 is a flow chart illustrating a path optimization step of the path planning method for workpiece inspection of FIG. 1;
FIG. 3 is a flow chart illustrating a dynamic clustering step of the path optimization step of FIG. 2;
FIG. 4 is a schematic flow chart illustrating a whale algorithm of a path planning method for workpiece detection according to a first embodiment of the present invention;
FIG. 5 is a block diagram illustrating a path planning system for workpiece inspection according to a second embodiment of the present invention;
FIG. 6 is a block diagram illustrating a path optimization module of the path planning system for workpiece inspection of FIG. 5;
FIG. 7 is a block diagram of a dynamic clustering module of the path optimization module of FIG. 6; and
FIG. 8 is a block diagram of a whale calculation unit of a path planning system for workpiece inspection according to a second embodiment of the present invention.
[ notation ] to show
100 path planning method for workpiece detection
152 whale algorithm
S110. coordinate relation matrix establishing step
S112, route optimization step
S114, recoding step
S120, initializing the coding step
S130, an adaptive value sorting step
S140, dynamic grouping step
S142, calculating similarity
S144, grouping step
S150 mutation step
S154 surrounding step
S156 hunting step
S158, random search step
S160, a selection step
S170, iteration frequency judging step
200 path planning system for workpiece detection
210 coordinate relation matrix establishing module
212 route optimization Module
214 recoding module
220 initializing the coding module
230 adaptive value ordering module
240 dynamic grouping module
242 similarity calculation operator module
244 grouping submodule
250 mutation module
252 whale calculation unit
254 surrounding sub-module
256 hunting sub-module
258 random search submodule
260 selection module
270 iteration frequency judging module
Detailed Description
Referring to fig. 1 and fig. 2 together, fig. 1 is a flow chart illustrating a path planning method 100 for workpiece detection according to a first embodiment of the present invention; fig. 2 is a flowchart illustrating the path optimization step S112 of the path planning method 100 for workpiece inspection in fig. 1. As shown, the method 100 for planning a path for workpiece inspection is used to plan an optimal inspection path for a workpiece inspected by a measuring machine, where the inspection path includes a plurality of inspection points. The method 100 for planning a path for workpiece inspection includes a coordinate relationship matrix establishing step S110, a path optimizing step S112, and a recoding step S114.
The coordinate relation matrix establishing step S110 is to drive the radiation detection measuring machine to move between two detection points, and establish a coordinate relation matrix according to the movement of the detection points. If a workpiece exists between the two detection points, the moving mode is non-linear moving; if no workpiece exists between the two detection points, the moving mode is linear moving. In detail, whether the radiation detection probe can move between the two detection points in a linear manner is divided into '0' and '1' according to the moving manner between the points, wherein '0' represents that the two points can move in a linear manner, and '1' represents that the two points cannot move in a linear manner, and the safety movement of the Z axis needs to be increased to avoid collision, and the moving manner between the two detection points is established as a coordinate relation matrix.
The path optimization step S112 includes an initialization encoding step S120, an adaptive value sorting step S130, a dynamic clustering step S140, a mutation step S150, a selection step S160, and an iteration number determination step S170. In other words, the path optimization step S112 is used to list the detection points in a plurality of arrangements and find the best detection path.
The initialization encoding step S120 encodes each detection point, and then arranges the detection points in a random order a plurality of times to form a plurality of detection paths. In other words, the initialization encoding step S120 encodes the coordinates of the detection points and generates a plurality of detection paths arranged in a random order.
Referring to the first table, the adaptive value sorting step S130 is to calculate a total distance value of each detection path according to the coordinate relationship matrix and each detection path, sort the detection paths according to the total distance value, and preset the group of each detection path to 0. The total distance value is Fitness, and each detection path is In. Will InAccording to their Fitness, ordered from minimum to maximum, I1For the smallest total distance value, INPThe Group is the Group with the maximum total distance.
Watch 1
| Fitness | Best | Worst | |||||||
| In | I1 | I2 | … | Ii-1 | Ii | Ii+1 | … | INP-1 | INP |
| Group | 0 | 0 | 0 | 0 | 0 | 0 | … | 0 | 0 |
Referring to fig. 3, fig. 3 is a flowchart illustrating the dynamic clustering step S140 of the path optimization step S112 of fig. 2. The dynamic grouping step S140 groups the detection paths into a plurality of groups according to the total distance values, the difference between the total distance values of the plurality of detection paths of any group is less than or equal to a preset difference, and the smallest of the total distance values in each group is regarded as the leader. The dynamic clustering step S140 includes a similarity calculation step S142 and a clustering step S144. The similarity calculation step S142 is to calculate a fitness threshold and a distance threshold of the detected path.
In detail, the step S142 of calculating the similarity calculates the fitness threshold and the distance threshold of the detection paths, and the calculation method of the step S142 of calculating the similarity satisfies the following formula:
wherein DISgIs the distance difference of the g-th group, n is the total number of detected paths, D is the total number of detected points, g is the group,
is the collar-sleeve of the group g,
for the ith detection path, NC is the total number of detection paths of the current group,
is the distance threshold of the g-th group. FITgFit (τ) is the fitness difference of group gg) Fitness value of the g-th set of collars, Fit (X)i) For the fitness value, ψ, of the ith detection pathgIs the fitness threshold of group g.
In the grouping step S144, fitness difference and distance difference between each detection path and the leader are calculated and are grouped according to fitness threshold and distance threshold. The grouping step S144 corresponds to the following formula:
Fiti＝|Fit(τg)-Fit(Xi)| (6)。
wherein DisiFor the distance difference of the ith detection path, FitiIs the fitness difference of the ith detection path, D is the total number of detection points,
is the collar-sleeve of the group g,
for the ith detectionPath, Fit (τ)g) Fitness value of the g-th set of collars, Fit (X)i) Is the fitness value of the ith detection path. When in use
And Fiti<ψgIn this case, the ith detection path is similar to the g-th group leader, the ith detection path is classified into the g-th group, and the grouping step S144 is stopped after all detection paths are classified.
Referring to fig. 4, fig. 4 is a schematic flow chart illustrating the whale algorithm 152 of the path planning method 100 for workpiece detection according to the first embodiment of the invention. In the mutation step S150, the leaders of the group are evolved according to the whale algorithm 152 to generate mutation detection paths, and the mutation detection paths include total mutation distance values. Whale algorithm 152 includes a surrounding step S154, a hunting step S156, and a random search step S158.
The bounding step S154 is to update the optimal detection path after the previous iteration and find the minimum total distance value of each leader in a shrink-wrapping manner. The surrounding step S154 conforms to the following equation:
where t is the current iteration number, X (t) is the current optimal detection path, X*(t) is the position space of the detection path, XτgLeader of group g, A, C coefficient, and calculation method thereofThe method is expressed by the following expressions (9) and (10), wherein a is a vector linearly decreasing from 2 to 0 when iteration is performed, and r represents a random number between 0 and 1. In other words, the step S154 is enclosed to load the minimum of the optimal detection path and the total distance value of each leader after the previous iteration.
Judging whether the value of the random number p is less than 0.5, if so, executing the surrounding step S154 again; if not, the hunting step S156 is executed. The hunting step S156 is to find the minimum of the total distance values of the sleeves by the spiral motion. The hunting step S156 corresponds to the following equation:
where p is a random number between 0 and 1, b is a constant used to define the spiral shape, and l is a random number between 1 and-1. When p is less than 0.5, finding out a detection path with the minimum total distance value of each leader in a shrink wrapping mode; when p is greater than 0.5, finding out the detection path with the minimum total distance value in each leader in a spiral motion mode.
The random search step S158 is to arrange the detection points in a random order to generate a mutation detection path. The random search step S158 corresponds to the following equation:
wherein XrandIs a vector of randomly generated detection paths,
the expression multiplication, the generation of the D vector, and the introduction of the Levy flight strategy, which provides random walk from the probability distribution provided, enables the whale algorithm 152 to jump off the optimal solution of the region. When A is more than or equal to 1, a mutation detection path is randomly generated, and the mutation detection path comprises mutationThe total distance value.
The selection step S160 is to compare the total distance value of the leaders in each group, the mutation total distance value, and the optimal detection path after the previous iteration, and select the remaining one as the optimal detection path. The selection step S160 corresponds to the following equation:
wherein
For the best detection path after the previous iteration,
the mutation detection path generated in step S158 is randomly searched. Selection step S160 judgment
Is compared with the total distance value of
More preferably, if so, then
Substitution
Becoming the best detection path; if not, the optimal detection path after the previous iteration is reserved to the next generation.
The iteration number judging step S170 is to judge whether the execution number of the mutation step S150 is equal to a preset number; if not, re-executing the mutation step S150 and the selection step S160; if yes, the path optimization step S112 is ended. In other words, when the iteration is performed to the preset number, the obtained optimal detection path is the optimal detection path obtained by the path planning method for workpiece detection 100.
The re-encoding step S114 is to convert the code of the best detection path into the code of the measuring machine used by the measuring machine. In detail, the measuring machine may be a Numerical Control (CNC) machine, and the measuring machine code used by the measuring machine may be a G/M code.
Therefore, the path planning method 100 for workpiece inspection of the present invention escapes the optimal solution of the region through the dynamic clustering step S140 and the whale algorithm 152, so as to solve the problem that the conventional path planning method is easy to fall into the optimal solution of the region due to too fast convergence speed.
Referring to fig. 1 to 6, fig. 5 is a block diagram illustrating a path planning system 200 for workpiece inspection according to a second embodiment of the present invention, and fig. 6 is a block diagram illustrating a path optimization module 212 of the path planning system 200 for workpiece inspection shown in fig. 5. As shown, the workpiece inspection path planning system 200 uses the workpiece inspection path planning method 100 to plan the optimal inspection path for inspecting the workpiece by the metrology machine. The path planning system 200 for workpiece inspection includes a coordinate relationship matrix building module 210, a path optimization module 212, and a recoding module 214.
The coordinate relation matrix establishing module 210 executes the coordinate relation matrix establishing step S110, which is a moving manner of driving the radiation detection measuring machine between the two detection points to generate the coordinate relation matrix. If a workpiece exists between the two detection points, the moving mode is non-linear moving; if no workpiece exists between the two detection points, the moving mode is linear moving.
The path optimization module 212 is in signal connection with the coordinate relationship matrix establishing module 210, and performs the path optimization step S112, wherein the path optimization module 212 includes an initialization encoding module 220, an adaptive value sorting module 230, a dynamic clustering module 240, a mutation module 250, a selection module 260, and an iteration number determining module 270. The initialization encoding module 220 executes the initialization encoding step S120 to encode each detection point, and then drives the detection points to randomly arrange a plurality of times to generate a plurality of detection paths.
The adaptive value sorting module 230 is in signal connection with the initialization encoding module 220, and executes the adaptive value sorting step S130, wherein the adaptive value sorting module 230 generates the total distance value of the detection paths according to the coordinate relationship matrix and each detection path and sorts the detection paths according to the size of the total distance value.
Referring to fig. 7, fig. 7 is a block diagram illustrating the dynamic clustering module 240 of the path optimization module 212 of fig. 6. As shown, the dynamic clustering module 240 is in signal connection with the adaptive value sorting module 230 for performing the dynamic clustering step S140, and clusters the detection paths into a plurality of groups according to the total distance value, wherein the difference between the total distance values of the plurality of detection paths of any group is less than or equal to a preset difference. The dynamic clustering module 240 includes a similarity operator module 242 and a clustering submodule 244. The similarity operator module 242 executes the similarity calculation step S142, which is to calculate a fitness threshold and a distance threshold of the detection path. The clustering sub-module 244 is in signal connection with the similarity operator module 242, and is configured to perform the clustering step S144, in which the fitness difference and the distance difference between each detection path and the leader are calculated and classified according to the fitness threshold and the distance threshold.
Referring to fig. 8, fig. 8 is a block diagram illustrating a whale calculation unit 252 of a path planning system 200 for workpiece detection according to a second embodiment of the present invention. The mutation module 250 is in signal connection with the dynamic clustering module 240 for performing the mutation step S150, wherein the leader of each of the groups generates a mutation detection path through the whale calculation unit 252, and the mutation detection path includes a mutation total distance value. Whale calculation unit 252 includes a bounding sub-module 254, a hunting sub-module 256, and a random search sub-module 258. The surrounding submodule 254 is used to perform the surrounding step S154, which is to update the optimal detection path after the previous iteration and find the minimum of the total distance values of the leaders. The hunting submodule 256 is in signal connection with the surrounding submodule 254 for executing the hunting step S156 to find the minimum of the total distance values of the respective collar-sleeves. The random search sub-module 258 is in signal connection with the hunting sub-module 256 for performing the random search step S158 to arrange the detection points in a random order to generate a sudden change detection path.
The selection module 260 is in signal connection with the mutation module 250, and is configured to perform the selection step S160, compare the total distance value of the leader in each group, the mutation total distance value, and the optimal detection path after the previous iteration, and select the remaining minimum to become the optimal detection path.
The iteration number judging module 270 is in signal connection with the selecting module 260 and the mutation module 250, and the iteration number judging module 270 is configured to execute the iteration number judging step S170 to judge whether the execution number of the mutation module 250 is equal to a preset number; if not, the mutation module 250 and the selection module 260 are executed again; if so, the path optimization module 212 terminates execution.
The re-encoding module 214 is in signal connection with the iteration number determining module 270, and the re-encoding module 214 is used to perform the re-encoding step S114, which is to convert the code of the optimal detection path into the code of the measuring machine used by the measuring machine.
Therefore, the path planning system 200 for workpiece inspection of the present invention escapes the optimal solution of the area through the dynamic clustering module 240 and the whale calculation unit 252, so as to solve the problem that the conventional path planning system is easy to fall into the optimal solution of the area due to too fast convergence speed.
Although the present invention has been described with reference to the above embodiments, it should be understood that various changes and modifications can be made therein by those skilled in the art without departing from the spirit and scope of the invention.
Claims (10)
1. A path planning method for workpiece inspection is used for planning an optimal inspection path of a workpiece inspected by an inspection machine, wherein the optimal inspection path comprises a plurality of inspection points, and the path planning method for workpiece inspection comprises the following steps:
a coordinate relation matrix establishing step, namely driving a ray to detect a moving mode of the measuring machine between two detection points, and establishing a coordinate relation matrix according to a plurality of moving modes of the detection points; and
a path optimization step, comprising:
an initialization coding step, which is to code each detection point and then make the detection points become a plurality of detection paths through a plurality of times of random sequence arrangement;
an adaptive value sorting step, which is to calculate a total distance value of each detection path according to the coordinate relation matrix and each detection path and sort the detection paths according to the total distance values;
a dynamic grouping step, grouping the detection paths into a plurality of groups according to the total distance values, wherein the difference value of the total distance values of the detection paths of any group is less than or equal to a preset difference value, and the minimum value of the total distance values in each group is regarded as a leader;
a mutation step, which evolves the leaders of the groups according to a whale algorithm to generate a mutation detection path, wherein the mutation detection path comprises a mutation total distance value;
a selection step, comparing the total distance value of the leader in each group, the mutation total distance value and the optimal detection path after the previous iteration, and selecting the minimum one to be kept as the optimal detection path; and
an iteration number judging step, which is to judge whether the execution number of the mutation step is equal to a preset number; if not, re-executing the mutation step and the selection step; if yes, the path optimization procedure is ended.
2. The method for path planning of workpiece inspection according to claim 1, wherein in the coordinate relationship matrix establishing step,
if the workpiece exists between the two detection points, the moving mode is nonlinear movement; and
if the workpiece does not exist between the two detection points, the moving mode is linear movement.
3. The method of claim 1, wherein the dynamically clustering step comprises:
a step of calculating similarity, which is to calculate a fitness threshold and a distance threshold of the detection paths; and
and a grouping step, namely calculating a fitness difference and a distance difference between each detection path and the leader, and dividing the detection paths into the groups according to the fitness threshold and the distance threshold.
4. The method of claim 1, wherein the whale algorithm comprises:
a surrounding step, which is to update the optimal detection path after the previous iteration and find the minimum of the total distance value of each leader in a shrinkage surrounding way;
a hunting step, finding out the minimum of the total distance value of each collar-sleeve in a spiral motion mode; and
a random search step for generating the mutation detection path by arranging the detection points in a random order.
5. The method for path planning for workpiece inspection according to claim 1, further comprising:
a re-encoding step, converting the code of the optimal detection path into a code of the measuring machine used by the measuring machine.
6. A path planning system for workpiece inspection, for planning an optimal inspection path of a workpiece inspected by an inspection machine, the path planning system comprising:
a coordinate relation matrix establishing module for driving a ray to detect a moving mode of the measuring machine between two detection points so as to generate a coordinate relation matrix; and
a path optimization module in signal connection with the coordinate relation matrix building module, the path optimization module comprising:
an initialization coding module for coding each detection point and then driving the detection points to randomly arrange for a plurality of times to generate a plurality of detection paths;
an adaptive value sorting module, which is in signal connection with the initialization coding module, generates a total distance value of each detection path according to the coordinate relation matrix and each detection path, and sorts the detection paths according to the total distance values;
a dynamic grouping module, which is in signal connection with the adaptive value sorting module and groups the detection paths into a plurality of groups according to the total distance values, wherein the difference value of the total distance values of the detection paths of any group is less than or equal to a preset difference value;
a mutation module, the signal of which is connected with the dynamic grouping module, the leaders of the groups generate a mutation detection path through a whale calculation unit, and the mutation detection path comprises a mutation total distance value;
a selection module, which is in signal connection with the mutation module, compares the total distance value of the leader in each group, the mutation total distance value and the optimal detection path after the previous iteration, and selects the minimum one to be reserved to become the optimal detection path; and
the iteration frequency judging module is in signal connection with the selecting module and the mutation module and judges whether the execution frequency of the mutation module is equal to a preset frequency or not; if not, the mutation module and the selection module are executed again; if so, the path optimization module terminates execution.
7. The system of claim 6, wherein in the coordinate relationship matrix creation module,
if the workpiece exists between the two detection points, the moving mode is nonlinear movement; and
if the workpiece does not exist between the two detection points, the moving mode is linear movement.
8. The system of claim 6, wherein the dynamic clustering unit comprises:
a similarity operator module for calculating a fitness threshold and a distance threshold of the detection paths; and
and the grouping submodule is in signal connection with the similarity meter operator module, calculates a fitness difference and a distance difference between each detection path and the leader, and divides the detection paths into the groups according to the fitness threshold and the distance threshold.
9. The system for path planning for workpiece inspection of claim 6, wherein the whale calculation unit comprises:
a surrounding submodule for updating the optimal detection path after the previous iteration and finding out the minimum of the total distance value of each leader;
a hunting sub-module, which is in signal connection with the surrounding sub-module and is used for finding out the minimum value of the total distance value of each leader; and
and the random search submodule is in signal connection with the hunting submodule and generates the mutation detection path by arranging the detection points in a random sequence.
10. The system for path planning for workpiece inspection according to claim 6, further comprising:
a recoding module in signal connection with the iteration number judging module, wherein the recoding module converts the code of the optimal detection path into a measuring machine code used by the measuring machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010212405.7A CN113447022A (en) | 2020-03-24 | 2020-03-24 | Path planning method and system for workpiece detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010212405.7A CN113447022A (en) | 2020-03-24 | 2020-03-24 | Path planning method and system for workpiece detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113447022A true CN113447022A (en) | 2021-09-28 |
Family
ID=77807422
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010212405.7A Pending CN113447022A (en) | 2020-03-24 | 2020-03-24 | Path planning method and system for workpiece detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113447022A (en) |
Citations (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4009377A (en) * | 1975-11-07 | 1977-02-22 | Ronald Duane Elms | Positioning determining method and apparatus |
| JPS63204301A (en) * | 1987-02-19 | 1988-08-24 | Yokogawa Electric Corp | Method for deciding optimum packing route of nc packing machine |
| EP0504755A2 (en) * | 1991-03-22 | 1992-09-23 | Firma Carl Zeiss | Method and arrangement to detect edges and bores with an optical sensing head |
| US5272638A (en) * | 1991-05-31 | 1993-12-21 | Texas Instruments Incorporated | Systems and methods for planning the scheduling travel routes |
| JP2002141943A (en) * | 2000-11-06 | 2002-05-17 | Ntt Communications Kk | Path search method and system |
| WO2004010759A1 (en) * | 2002-07-23 | 2004-01-29 | Matsushita Electric Industrial Co., Ltd. | Component mounting order optimization method, component mounting order optimization program, recording medium for the program, and component mounting apparatus using the method |
| JP2006270677A (en) * | 2005-03-25 | 2006-10-05 | Oki Electric Ind Co Ltd | Optimum path arrangement searching apparatus and optimum path arrangement searching method |
| WO2009028680A1 (en) * | 2007-08-30 | 2009-03-05 | Nec Corporation | Optimum pseudo random sequence determining method, position detecting system, position detecting method, transmitter, and receiver |
| US20100125414A1 (en) * | 2008-11-19 | 2010-05-20 | Fujitsu Limited | Apparatus and method for calculating absolute movement path and recording medium |
| WO2011096327A1 (en) * | 2010-02-05 | 2011-08-11 | 株式会社日立製作所 | Processing path generation method and device for same |
| WO2011131232A1 (en) * | 2010-04-20 | 2011-10-27 | Hamilton Bonaduz Ag | Position detecting device and method for producing a marking arrangement for a position detecting device |
| CN106156893A (en) * | 2016-07-14 | 2016-11-23 | 陕西科技大学 | A kind of Pheromone update method based on ant group algorithm |
| TWI571761B (en) * | 2016-03-08 | 2017-02-21 | 國立勤益科技大學 | Optimization method for sequence of printed circuit board assembly process |
| CN106841206A (en) * | 2016-12-19 | 2017-06-13 | 大连理工大学 | Untouched online inspection method is cut in heavy parts chemical milling |
| TW201807423A (en) * | 2016-08-29 | 2018-03-01 | 樹德科技大學 | Circuit board inspection method with inspection route optimization function |
| CN107909228A (en) * | 2017-12-23 | 2018-04-13 | 深圳大学 | Based on mould because of the dynamic vehicle shipping and receiving paths planning method and device of calculating |
| WO2019042295A1 (en) * | 2017-08-31 | 2019-03-07 | 广州小鹏汽车科技有限公司 | Path planning method, system, and device for autonomous driving |
| CN109579753A (en) * | 2018-12-13 | 2019-04-05 | 广州优里贸易有限公司 | A kind of effective on-line detecting system |
| CN110110930A (en) * | 2019-05-08 | 2019-08-09 | 西南交通大学 | A kind of Recognition with Recurrent Neural Network Short-Term Load Forecasting Method improving whale algorithm |
| CN110531716A (en) * | 2019-08-12 | 2019-12-03 | 陕西科技大学 | The method for solving low-carbon Job-Shop problem based on discrete whale algorithm |
| CN110530373A (en) * | 2019-09-30 | 2019-12-03 | 山东大学 | A kind of robot path planning method, controller and system |
| CN110802601A (en) * | 2019-11-29 | 2020-02-18 | 北京理工大学 | Robot path planning method based on fruit fly optimization algorithm |
| US20200061824A1 (en) * | 2018-08-27 | 2020-02-27 | Teradyne, Inc. | System and method for multi-goal path planning |
-
2020
- 2020-03-24 CN CN202010212405.7A patent/CN113447022A/en active Pending
Patent Citations (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4009377A (en) * | 1975-11-07 | 1977-02-22 | Ronald Duane Elms | Positioning determining method and apparatus |
| JPS63204301A (en) * | 1987-02-19 | 1988-08-24 | Yokogawa Electric Corp | Method for deciding optimum packing route of nc packing machine |
| EP0504755A2 (en) * | 1991-03-22 | 1992-09-23 | Firma Carl Zeiss | Method and arrangement to detect edges and bores with an optical sensing head |
| US5272638A (en) * | 1991-05-31 | 1993-12-21 | Texas Instruments Incorporated | Systems and methods for planning the scheduling travel routes |
| JP2002141943A (en) * | 2000-11-06 | 2002-05-17 | Ntt Communications Kk | Path search method and system |
| WO2004010759A1 (en) * | 2002-07-23 | 2004-01-29 | Matsushita Electric Industrial Co., Ltd. | Component mounting order optimization method, component mounting order optimization program, recording medium for the program, and component mounting apparatus using the method |
| JP2006270677A (en) * | 2005-03-25 | 2006-10-05 | Oki Electric Ind Co Ltd | Optimum path arrangement searching apparatus and optimum path arrangement searching method |
| WO2009028680A1 (en) * | 2007-08-30 | 2009-03-05 | Nec Corporation | Optimum pseudo random sequence determining method, position detecting system, position detecting method, transmitter, and receiver |
| US20100125414A1 (en) * | 2008-11-19 | 2010-05-20 | Fujitsu Limited | Apparatus and method for calculating absolute movement path and recording medium |
| WO2011096327A1 (en) * | 2010-02-05 | 2011-08-11 | 株式会社日立製作所 | Processing path generation method and device for same |
| WO2011131232A1 (en) * | 2010-04-20 | 2011-10-27 | Hamilton Bonaduz Ag | Position detecting device and method for producing a marking arrangement for a position detecting device |
| TWI571761B (en) * | 2016-03-08 | 2017-02-21 | 國立勤益科技大學 | Optimization method for sequence of printed circuit board assembly process |
| CN106156893A (en) * | 2016-07-14 | 2016-11-23 | 陕西科技大学 | A kind of Pheromone update method based on ant group algorithm |
| TW201807423A (en) * | 2016-08-29 | 2018-03-01 | 樹德科技大學 | Circuit board inspection method with inspection route optimization function |
| CN106841206A (en) * | 2016-12-19 | 2017-06-13 | 大连理工大学 | Untouched online inspection method is cut in heavy parts chemical milling |
| WO2019042295A1 (en) * | 2017-08-31 | 2019-03-07 | 广州小鹏汽车科技有限公司 | Path planning method, system, and device for autonomous driving |
| CN107909228A (en) * | 2017-12-23 | 2018-04-13 | 深圳大学 | Based on mould because of the dynamic vehicle shipping and receiving paths planning method and device of calculating |
| US20200061824A1 (en) * | 2018-08-27 | 2020-02-27 | Teradyne, Inc. | System and method for multi-goal path planning |
| CN109579753A (en) * | 2018-12-13 | 2019-04-05 | 广州优里贸易有限公司 | A kind of effective on-line detecting system |
| CN110110930A (en) * | 2019-05-08 | 2019-08-09 | 西南交通大学 | A kind of Recognition with Recurrent Neural Network Short-Term Load Forecasting Method improving whale algorithm |
| CN110531716A (en) * | 2019-08-12 | 2019-12-03 | 陕西科技大学 | The method for solving low-carbon Job-Shop problem based on discrete whale algorithm |
| CN110530373A (en) * | 2019-09-30 | 2019-12-03 | 山东大学 | A kind of robot path planning method, controller and system |
| CN110802601A (en) * | 2019-11-29 | 2020-02-18 | 北京理工大学 | Robot path planning method based on fruit fly optimization algorithm |
Non-Patent Citations (3)
| Title |
|---|
| FLISBERG, P.等: "Route selection for best distances in road databases based on drivers’ and customers’ preferences", CANADIAN JOURNAL OF FOREST RESEARCH-REVUE CANADIENNE DE RECHERCHE FORESTIERE, vol. 42, no. 6, pages 1126 - 1140 * |
| XINYOU LIN等: "AER adaptive control strategy via energy prediction for PHEV", IET INTELLIGENT TRANSPORT SYSTEM, vol. 13, no. 12, pages 1822 - 1831, XP006088198, DOI: 10.1049/iet-its.2018.5582 * |
| 曹二保, 赖明勇, 李董辉: "基于混合差分进化算法的模糊需求车辆路径问题", 系统工程理论与实践, vol. 29, no. 2, pages 106 - 113 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20060269144A1 (en) | Data division apparatus, data division method and program | |
| CN113051683B (en) | Numerical control machine tool life prediction method, system, equipment and storage medium | |
| CN112085368A (en) | Equipment energy production configuration and layout optimization method based on immune genetic algorithm | |
| Lu et al. | Genetic algorithm modelling and solution of inspection path planning on a coordinate measuring machine (CMM) | |
| CN112116952A (en) | Gene selection method of wolf optimization algorithm based on diffusion and chaotic local search | |
| CN110579201A (en) | Flatness evaluation method based on differential evolution algorithm | |
| CN113447022A (en) | Path planning method and system for workpiece detection | |
| CN117149615A (en) | Method and corresponding device for generating test case execution path | |
| CN112733451A (en) | Key inspection characteristic identification and extraction method of MBD model | |
| Tseng | A genetic algorithm for assessing flatness in automated manufacturing systems | |
| CN113985899B (en) | Underwater robot global path planning method based on interval multi-objective optimization | |
| CN110348575A (en) | A kind of impeller reverse engineering approach based on genetic algorithm | |
| CN115741703A (en) | Method suitable for multi-station multi-robot optical measuring point task allocation | |
| CN110674915B (en) | Irregular pipeline defect inversion method based on improved particle swarm optimization | |
| TWM601358U (en) | System of workpiece inspection in path planning | |
| Gao et al. | Flow shop scheduling with variable processing times based on differential shuffled frog leaping algorithm | |
| CN113345005A (en) | Finite random search method suitable for target ball center resolving | |
| CN109115161A (en) | A kind of sphericity assessment method shunk based on spatial orientation and improve cuckoo searching algorithm | |
| CN111553087A (en) | Measuring field optimization method based on three-dimensional real-time perception | |
| CN114646313A (en) | User track positioning method, electronic equipment and computer storage medium | |
| Majeed Ahmad AL-Hadad | Corridor Based Horizontal Highway Alignment Optimization Using GIS and Genetic Algorithms | |
| CN110070620A (en) | Three-dimensional grid surface model global approximation axial symmetry decision algorithm based on genetic algorithm | |
| CN116901386B (en) | Product detection and intelligent injection molding production method and system based on 3D scanning technology | |
| CN113204482B (en) | Heterogeneous defect prediction method and system based on semantic attribute subset division and metric matching | |
| Safari et al. | Optimum NURBS curve fitting for geometry parameterization of gas turbine blades’ sections: Part I—evolutionary optimization techniques |
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 |