CN110084416A - A kind of complex product production line performance optimization method based on genetic algorithm - Google Patents
A kind of complex product production line performance optimization method based on genetic algorithm Download PDFInfo
- Publication number
- CN110084416A CN110084416A CN201910317787.7A CN201910317787A CN110084416A CN 110084416 A CN110084416 A CN 110084416A CN 201910317787 A CN201910317787 A CN 201910317787A CN 110084416 A CN110084416 A CN 110084416A
- Authority
- CN
- China
- Prior art keywords
- complex product
- feature
- production line
- manufacturing
- process route
- 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
Classifications
-
- 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"
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06316—Sequencing of tasks or work
Abstract
The present invention provides a kind of complex product production line performance optimization method based on genetic algorithm, analyzes each parts machining process route of complex product, specifies the part machining feature of all completions of per pass manufacturing procedure；According to the constraint of each machining feature optional equipment collection, generates the machining process route of Facing to Manufacturing node and encoded；Optimality criterion is carried out to the Process matrix of complex product processing to be decoded if meeting needs according to mapping relations, generates the parts machining process route that performance has optimized.The present invention uses genetic algorithm, using integer coding model, intersection and mutation operation is carried out in the range of the optional equipment collection according to defined by manufacturing feature, realizes the search and selection of process route.The method of the present invention comprehensively considers two problems of reliability and balance of complex product production line, seeks optimal solution in huge solution space, so that optimum results are relatively reliable.
Description
Technical field
The invention belongs to manufacture system Performance Optimization technique fields, and in particular to a kind of complex product based on genetic algorithm
Production line performance optimization method.
Background technique
Complex product generally comprises that zero component is numerous, structural relation is complicated, manufacturing process is complicated, the accuracy of manufacture and reliability
It is required that high and processing cost is huge, typical complex product such as spacecraft, aircraft, automobile, Complex Mechatronic Products, weapon system
Deng.This kind of product is usually directed to machinery, control, electronics, software, hydraulic and pneumatic etc. multidisciplinary field.The manufacture of complex product
Processing, often relates to a large amount of human and material resources, financial resources, the manufacture for complex product is undoubtedly challenging.
In complex product production line, large number of process equipment is frequently included, and the process amount that distinct device undertakes
Often there is very big difference, it is possible to cause the load factor of distinct device in production line operation very unbalanced, be easy to appear certain set
The phenomenon that standby idle, and certain equipment are blocked by a large amount of semi-finished product, influence entire manufacturing system efficiency.Meanwhile it producing
In the process, since there are the reliabilities that many enchancement factors influence manufacture system, such as equipment downtime, tool wear, interim order
Addition etc., so as to cause production line blocking, interrupt it is even a wide range of the catastrophic collapse such as shut down, that is, cause to manufacture
The lower reliability of system.Therefore, it is necessary to the performance of the production line of complex product in terms of balance with reliability two
It is analyzed, and identifies the influence factor for influencing the two performance indicators of complex product production line, and then targetedly carry out
Optimization achievees the purpose that improve complex product manufacturing system.
Summary of the invention
(1) the technical issues of solving
The main object of the present invention is the reliability and balance in order to solve the problems, such as complex product production line, provides one kind
It is raw to comprehensively consider complex product by using genetic algorithm for complex product production line performance optimization method based on genetic algorithm
The reliability and balance of producing line, seek optimal solution in solution space, to show that the complex product that performance has optimized is raw
Producing line process route.
(2) technical solution
In order to achieve the above object, the present invention is achieved by the following technical programs:
A kind of complex product production line performance optimization method based on genetic algorithm, comprising the following steps:
S1, each parts machining process route of complex product is analyzed, specifies the zero of all completions of per pass manufacturing procedure
Part machining feature；
S2, according to the constraint of each machining feature optional equipment collection, generate the machining process route of Facing to Manufacturing node simultaneously
It is encoded；
S3, to complex product processing Process matrix carry out optimality criterion, if meeting needs, according to mapping relations into
Row decoding generates the parts machining process route that performance has optimized.
An embodiment according to the present invention in the step S2, specifically comprises the following steps:
S2.1, the process route based on machining feature is handled first, is a processing by each genetic marker
Feature, and each machining feature can be completed by different manufacturing equipments；
S2.2, then, intersects, mutation operation re-encodes manufacture node for convenience, so that each machining feature
The coding continuous arrangement of corresponding manufacture node, is arranged the mapping relations of gene and device coding, determines each machining feature
The bound of corresponding manufacture nodes encoding, defines the range that corresponding gene intersects or makes a variation, guarantees in all evolutionary process
Obtained solution is all feasible solution；
S2.3, it is integrated into chromosome finally, the process route of all parts is encoded, after the completion of evolution, according to mapping
Relationship decodes the process route after being optimized accordingly.
An embodiment according to the present invention, the step S2.2 uses integer coding model in code Design, according to system
It makes and carries out in the range of optional equipment collection defined by feature intersecting and mutation operation, realize the search and selection of process route.
An embodiment according to the present invention, the step S2.3 indicate the process route of m kind part due to chromosome, so
The length of chromosome isGene in chromosome represents the volume of manufacture node serial number optional for position machining feature
Code.
An embodiment according to the present invention in the step S3, specifically comprises the following steps:
S3.1, objective function and fitness function design: being raw to complex product from two angles of reliability and balance
Producing line is improved, and the target of this model optimization is to keep the degree of process distribution deviation equilibrium state on manufacture node minimum,
I.e.
In formula, PK0Indicate total process amount of complex product processing, kViIndicate manufacture node ViThe process amount undertaken, k
(V) indicate complex product production line network in manufacture node sum, D indicate production line in manufacturing process distribution variance and；
S3.2, due to process distribution departure function value it is smaller, illustrate that the balance of production line is got over reliability standard
Height, and departure function be each node manufacturing process distribution variance and, perseverance be positive value, therefore, set fitness function as
Fitness=1/D (2)
S3.3, crossover operation: as chromosome encryption algorithm in each based on according to defined by corresponding manufacturing feature
Manufacturing equipment collection randomly selects, therefore carries out gene recombination using two-point crossover method, and the individual of generation is still feasible solution；
S3.4, mutation operation: it to guarantee the feasible solution not yet of the individual after genetic mutation, also needs to limit in mutation algorithm
Value range after determining genetic mutation is still optional manufacturing equipment collection defined by corresponding position manufacturing feature；
S3.5, finally, by setting Population Size, evolutionary generation, intersection and variation probability, execute evolution；It has evolved
Cheng Hou, obtaining the highest chromosome of fitness is optimal solution, according to above-mentioned mapping relations decoding after, can be obtained reliability with
The process route of the higher complex product manufacture processing of balance.
(3) beneficial effect
Beneficial effects of the present invention: a kind of complex product production line performance optimization method based on genetic algorithm, with something lost
Propagation algorithm is intersected and is made a variation in the range of the optional equipment collection according to defined by manufacturing feature using integer coding model
Operation, realizes the search and selection of process route；The method of the present invention comprehensively considers the reliability and balance of complex product production line
Two problems of property, seek optimal solution, to obtain the complex product production line that performance has optimized in huge solution space
Process route, so that optimum results are relatively reliable.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the method for the present invention flow chart；
Fig. 2 is chromosome design diagram；
Fig. 3 is that each manufacture node in embodiment optimization front and back undertakes process amount comparison diagram；
Fig. 4 is that front and back production line reliability comparison diagram is transformed in embodiment.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
In conjunction with Fig. 1, a kind of complex product production line performance optimization method based on genetic algorithm, comprising the following steps:
S1, each parts machining process route of complex product is analyzed, specifies the zero of all completions of per pass manufacturing procedure
Part machining feature.
S2, according to the constraint of each machining feature optional equipment collection, generate the machining process route of Facing to Manufacturing node simultaneously
It is encoded.
In the step S2, specifically comprise the following steps:
S2.1, the process route based on machining feature is handled first, is a processing by each genetic marker
Feature, and each machining feature can be completed by different manufacturing equipments；
S2.2, then, intersects, mutation operation re-encodes manufacture node for convenience, so that each machining feature
The coding continuous arrangement of corresponding manufacture node is arranged the mapping relations of gene and device coding, thus may be used as shown in table 1
The bound that nodes encoding is manufactured as corresponding to each machining feature of determination defines the range that corresponding gene intersects or makes a variation,
Guarantee that obtained solution is all feasible solution in all evolutionary process.Integer coding model is used in code Design, according to manufacture
Intersection and mutation operation are carried out in the range of optional equipment collection defined by feature, realize the search and selection of process route.
The mapping relations of table 1 gene and device coding
S2.3, it is integrated into chromosome finally, the process route of all parts is encoded, is completed as shown in Fig. 2, evolving
Afterwards, according to the mapping relations decoding in table 1 thus the process route after being optimized accordingly.Since chromosome indicates m kind zero
The process route of part, so the length of chromosome isGene in chromosome represents optional for position machining feature
The coding of node serial number is manufactured, such as first coding 22 indicates equipment of the first procedure of first part by being encoded to 22
CKQ61100 is processed.
S3, to complex product processing Process matrix carry out optimality criterion, if meeting needs, according to mapping relations into
Row decoding generates the parts machining process route that performance has optimized.
In the step S3, specifically comprise the following steps:
S3.1, objective function and fitness function design: being raw to complex product from two angles of reliability and balance
Producing line is improved, and the target of this model optimization is to keep the degree of process distribution deviation equilibrium state on manufacture node minimum,
I.e.
In formula, PK0Indicate total process amount of complex product processing, kViIndicate manufacture node ViThe process amount undertaken, k
(V) indicate complex product production line network in manufacture node sum, D indicate production line in manufacturing process distribution variance and.
S3.2, due to process distribution departure function value it is smaller, illustrate that the balance of production line is got over reliability standard
Height, and departure function be each node manufacturing process distribution variance and, perseverance be positive value, therefore, set fitness function as
Fitness=1/D (2)
S3.3, crossover operation: as chromosome encryption algorithm in each based on according to defined by corresponding manufacturing feature
Manufacturing equipment collection randomly selects, therefore carries out gene recombination using two-point crossover method, and the individual of generation is still feasible solution.
S3.4, mutation operation: it to guarantee the feasible solution not yet of the individual after genetic mutation, also needs to limit in mutation algorithm
Value range after determining genetic mutation is still optional manufacturing equipment collection defined by corresponding position manufacturing feature.
S3.5, finally, by setting Population Size, evolutionary generation, intersection and variation probability, execute evolution.It has evolved
Cheng Hou, obtaining the highest chromosome of fitness is optimal solution, according to above-mentioned mapping relations decoding after, can be obtained reliability with
The process route of the higher complex product manufacture processing of balance.
In certain aero-engine casing part production line network model, with 81 kinds of parts, the work of 40 flexible apparatus composition
Skill route is encoded, according to optional equipment collection E corresponding to each manufacturing featureijConstraint, random generate includes 100 individuals
Initial population, with crossover probability for 0.9, mutation probability is 0.04 to execute evolutional operation, and algebra is set as 1000, calculates target
Functional value and fitness function value draw the comparison diagram of optimization front and back for balance and reliability, as shown in Figure 3 and Figure 4.
Wherein as seen from Figure 3, some scripts need to undertake the process in the equipment of many manufacturing operations and are shared
In other equipment, so that the distribution of process is more balanced in the aircraft engine parts production line after optimization.It can be seen by Fig. 4
Out, the aircraft engine parts production line network is when removing manufacture node by node strength size after optimization, residue manufacture system
The effectiveness decrease speed of system slows down, and so that production line effectiveness is dropped to same degree and needs more equipment failures；In addition, after optimization
Workload that the most manufacture node of task amount is undertaken is undertaken than having dropped 61.3% before optimizing, and according to the research of scholar,
Undertake that delay machine occurs in the less equipment of task amount or the probability of blocking is lower.Therefore, for these two aspects, pass through technique road
Line optimization, so that the performance of complex product production line is improved.
In conclusion the embodiment of the present invention, the complex product production line performance optimization method based on genetic algorithm, with something lost
Propagation algorithm is intersected and is made a variation in the range of the optional equipment collection according to defined by manufacturing feature using integer coding model
Operation, realizes the search and selection of process route；The method of the present invention comprehensively considers the reliability and balance of complex product production line
Two problems of property, seek optimal solution, to obtain the complex product production line that performance has optimized in huge solution space
Process route, so that optimum results are relatively reliable.
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to the foregoing embodiments
Invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each implementation
Technical solution documented by example is modified or equivalent replacement of some of the technical features；And these modification or
Replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (5)
1. a kind of complex product production line performance optimization method based on genetic algorithm, it is characterised in that: the following steps are included:
S1, each parts machining process route of complex product is analyzed, the part for specifying all completions of per pass manufacturing procedure adds
Work feature；
S2, according to the constraint of each machining feature optional equipment collection, generate the machining process route of Facing to Manufacturing node and progress
Coding；
S3, the Process matrix progress optimality criterion of complex product processing is solved if meeting needs according to mapping relations
Code generates the parts machining process route that performance has optimized.
2. a kind of complex product production line performance optimization method based on genetic algorithm according to claim 1, feature
It is: in the step S2, specifically comprises the following steps:
S2.1, the process route based on machining feature is handled first, is a machining feature by each genetic marker,
And each machining feature can be completed by different manufacturing equipments；
S2.2, then, intersects, mutation operation re-encodes manufacture node for convenience, so that each machining feature institute is right
The coding continuous arrangement for the manufacture node answered, is arranged the mapping relations of gene and device coding, determines that each machining feature institute is right
The bound that nodes encoding should be manufactured defines the range that corresponding gene intersects or makes a variation, and guarantees gained in all evolutionary process
To solution be all feasible solution；
S2.3, it is integrated into chromosome finally, the process route of all parts is encoded, after the completion of evolution, according to mapping relations
Decode the process route after being optimized accordingly.
3. a kind of complex product production line performance optimization method based on genetic algorithm according to claim 2, feature
Be: the step S2.2 uses integer coding model, the optional equipment collection according to defined by manufacturing feature in code Design
In the range of carry out intersect and mutation operation, realize the search and selection of process route.
4. a kind of complex product production line performance optimization method based on genetic algorithm according to claim 2, feature
Be: the step S2.3 indicates the process route of m kind part due to chromosome, so the length of chromosome isDye
Gene in colour solid represents the coding of manufacture node serial number optional for position machining feature.
5. a kind of complex product production line performance optimization method based on genetic algorithm according to claim 1, feature
It is: in the step S3, specifically comprises the following steps:
S3.1, objective function and fitness function design: for from two angles of reliability and balance to complex product production line
Improved, the target of this model optimization is to keep the degree of process distribution deviation equilibrium state on manufacture node minimum, i.e.,
In formula, PK0Indicate total process amount of complex product processing, kViIndicate manufacture node ViThe process amount undertaken, k (V) are indicated
In complex product production line network manufacture node sum, D indicate production line in manufacturing process distribution variance and；
S3.2, due to process distribution departure function value it is smaller, illustrate that the balance of production line and reliability standard are higher, and
Departure function be each node manufacturing process distribution variance and, perseverance be positive value, therefore, set fitness function as
Fitness=1/D (2)
S3.3, crossover operation: as chromosome encryption algorithm in each based on being manufactured according to defined by corresponding manufacturing feature
Equipment collection randomly selects, therefore carries out gene recombination using two-point crossover method, and the individual of generation is still feasible solution；
S3.4, mutation operation: it to guarantee the feasible solution not yet of the individual after genetic mutation, also needs to limit base in mutation algorithm
Because the value range after variation is still optional manufacturing equipment collection defined by corresponding position manufacturing feature；
S3.5, finally, by setting Population Size, evolutionary generation, intersection and variation probability, execute evolution；After the completion of evolution,
Obtaining the highest chromosome of fitness is optimal solution, and after the decoding of above-mentioned mapping relations, reliability and balance can be obtained
Property the manufacture processing of higher complex product process route.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910317787.7A CN110084416A (en) | 2019-04-19 | 2019-04-19 | A kind of complex product production line performance optimization method based on genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910317787.7A CN110084416A (en) | 2019-04-19 | 2019-04-19 | A kind of complex product production line performance optimization method based on genetic algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110084416A true CN110084416A (en) | 2019-08-02 |
Family
ID=67415635
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910317787.7A Pending CN110084416A (en) | 2019-04-19 | 2019-04-19 | A kind of complex product production line performance optimization method based on genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110084416A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852705A (en) * | 2019-10-23 | 2020-02-28 | 太原科技大学 | Manufacturing task driven cutter combination recommendation method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080140499A1 (en) * | 1999-11-22 | 2008-06-12 | Barnard Ray F | System and method for ongoing supporting a procurement and accounts payable system |
| CN106611232A (en) * | 2016-02-04 | 2017-05-03 | 四川用联信息技术有限公司 | Layered optimization algorithm for solving multi-technical-route workshop scheduling |
-
2019
- 2019-04-19 CN CN201910317787.7A patent/CN110084416A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080140499A1 (en) * | 1999-11-22 | 2008-06-12 | Barnard Ray F | System and method for ongoing supporting a procurement and accounts payable system |
| CN106611232A (en) * | 2016-02-04 | 2017-05-03 | 四川用联信息技术有限公司 | Layered optimization algorithm for solving multi-technical-route workshop scheduling |
Non-Patent Citations (1)
| Title |
|---|
| 卢素伟: ""基于有向加权图的复杂产品生产线性能分析与优化"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852705A (en) * | 2019-10-23 | 2020-02-28 | 太原科技大学 | Manufacturing task driven cutter combination recommendation method |
| CN110852705B (en) * | 2019-10-23 | 2022-06-10 | 太原科技大学 | Manufacturing task driven cutter combination recommendation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tang et al. | Diversity-adaptive parallel memetic algorithm for solving large scale combinatorial optimization problems | |
| Pholdee et al. | Hybridisation of real-code population-based incremental learning and differential evolution for multiobjective design of trusses | |
| KR20130101548A (en) | Improving reliability in distributed environments | |
| CN108460463B (en) | High-end equipment assembly line production scheduling method based on improved genetic algorithm | |
| CN104122796B (en) | A kind of Intelligent assembly Sequence Planning method | |
| CN110084416A (en) | A kind of complex product production line performance optimization method based on genetic algorithm | |
| CN102213767A (en) | Positioning control method for closed region of vehicle-mounted GPS (Global Positioning System) | |
| CN107832586A (en) | The individual combination Relationship iden- tification method and device of one kind three | |
| CN103955410A (en) | Interruption control method based on multiple interrupt source priority ordering | |
| Al-Janan et al. | Path optimization of CNC PCB drilling using hybrid Taguchi genetic algorithm | |
| CN105116795A (en) | Distributed control method for automatic manufacturing system with assembly operation | |
| CN103645961A (en) | Anomaly detection method and system for calculating intensive parallel tasks | |
| Zhu et al. | Improved evolutionary generation of test data for multiple paths in search-based software testing | |
| CN113987938A (en) | Process parameter optimization method, device, equipment and storage medium | |
| CN106326005A (en) | Automatic parameter tuning method for iterative MapReduce operation | |
| CN116578558A (en) | Data processing method, device, equipment and storage medium | |
| CN110110158A (en) | A kind of the memory space division methods and system of three-dimensional mesh data | |
| CN106599411B (en) | Aircraft system redundancy configuration optimization method | |
| Barkat Ullah et al. | Handling equality constraints with agent-based memetic algorithms | |
| Allmendinger et al. | Efficient discovery of chromatography equipment sizing strategies for antibody purification processes using evolutionary computing | |
| CN105446808B (en) | A kind of method that combined task completes complex task | |
| Hua et al. | New knowledge-based genetic algorithm for excavator boom structural optimization | |
| CN115130985A (en) | Production control method and related apparatus, storage medium, and program product | |
| CN110147804B (en) | Unbalanced data processing method, terminal and computer readable storage medium | |
| CN103034698B (en) | Date storage method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190802 |