Automatic layout and optimization method for engineering machinery assembly workshop based on logistics simulation and genetic algorithm

Abstract

The invention relates to an engineering machinery assembly workshop automatic layout and optimization method based on logistics simulation and a genetic algorithm, and belongs to the field of logistics simulation and genetic algorithms. According to the invention, the genetic algorithm module, the data processing and storage module, the simulation module, the evaluation analysis module and the visualization module are integrated on the logistics simulation platform, so that automatic layout and optimization of the discrete assembly workshop are realized. The method specifically comprises the steps that a genetic algorithm module is used for encoding functional areas and generating samples, a data processing and storage module is used for converting sample encoding information into coordinates needed by simulation, a simulation module is used for simulating operation and outputting index data, an evaluation analysis module is used for calculating sample fitness values, and a simulation result is obtained. And the genetic algorithm module performs selection, crossover and mutation operations according to the fitness value, and performs iterative optimization to obtain an optimal layout scheme. And the visualization module is used for displaying the simulation process and result. The optimization efficiency of the complex production system is improved, and the limitation of the prior art is overcome.

Description

Technical Field

[0001] The invention belongs to the field of logistics simulation and genetic algorithm, and relates to an automated layout and optimization method for an engineering machinery assembly workshop based on logistics simulation and genetic algorithm. Background Art

[0002] At present, the layout optimization of construction machinery assembly workshops mainly relies on experience and manual design, and there are the following problems:

[0003] Existing logistics simulation technology mainly focuses on the simulation and verification of existing solutions. It is unable to automatically generate optimization solutions and relies on the experience and subjective judgment of designers. It is inefficient and prone to errors.

[0004] The optimization modules usually provided in logistics simulation software mostly adopt enumeration method, which is limited to non-continuous optimization, making it difficult to cope with complex and changeable practical problems, and the optimization efficiency is low.

[0005] As a powerful optimization algorithm, genetic algorithm has the advantages of strong search capability, good parallelism and robustness. However, when dealing with complex problems in multi-dimensional and multi-factor coupled space, it has problems such as complex solution, high time cost and difficulty in convergence.

[0006] Therefore, in view of the shortcomings of the prior art, the present invention proposes an automated layout and optimization method for an engineering machinery assembly workshop based on logistics simulation and genetic algorithm, aiming to achieve automated layout, improve optimization efficiency, and overcome the limitations of genetic algorithms on complex problems. Summary of the invention

[0007] In view of this, the purpose of the present invention is to provide an automated layout and optimization method for an engineering machinery assembly workshop based on logistics simulation and genetic algorithm, which is used to solve the problems of difficult layout optimization of complex production systems, weak optimization of logistics simulation software, and the inability of genetic algorithms to solve problems in multi-dimensional and multi-factor coupled spaces.

[0008] In order to achieve the above object, the present invention provides the following technical solutions:

[0009] An automated layout and optimization method for an engineering machinery assembly workshop based on logistics simulation and genetic algorithm, the method comprising the following steps:

[0010] Step 1: Use the genetic algorithm module to genetically encode the functional areas divided by the workshop and randomly generate samples;

[0011] Step 2: Use the data processing and storage module to grid the layout space, convert the location information of each partition in the sample, that is, the genetic code, into the location coordinate information required for simulation and store it;

[0012] Step 3: Use the simulation module to read the location information of each functional area, establish the logical relationship and operation process between modules, run the model and output the transportation distance, logistics efficiency and logistics cost indicator data;

[0013] Step 4: Use the evaluation and analysis module to calculate and output the fitness value of the current sample solution layout based on the output indicator data;

[0014] Step 5: Use the genetic algorithm module to perform selection, crossover and mutation operations according to the fitness value of each sample to obtain a new generation of sample population;

[0015] Step 6: Repeat steps 2 to 5 until the fitness value converges and no longer changes, and obtain the optimal layout solution under the current input;

[0016] Step 7: Use the visualization module to display the current iteration number, simulation layout, simulation run characteristic indicators, and the fitness value of the current solution.

[0017] Furthermore, the functional areas include unloading areas, storage areas, material picking areas, production areas and material distribution points.

[0018] Furthermore, the simulation module is one of Plant Simulation, DELMIA, FlexSim, VisualComponents, Simio, Arena, AutoMod, SIMUL8, AnyLogic, AutoMod, ExtendSim or Demo3d.

[0019] An automated layout and optimization system for an engineering machinery assembly workshop based on logistics simulation and genetic algorithm, the system comprising:

[0020] Genetic algorithm module, used to genetically encode the functional areas divided by the workshop and randomly generate samples;

[0021] The data processing and storage module is used to perform grid processing on the layout space, convert the position information of each partition in the sample, that is, the genetic code, into the position coordinate information required for simulation and store it;

[0022] The simulation module is used to read the location information of each functional area, establish the logical relationship and operation process between modules, run the model and output the indicator data of transportation distance, logistics efficiency and logistics cost;

[0023] An evaluation and analysis module is used to calculate and output the fitness value of the current sample solution layout based on the output indicator data;

[0024] Visualization module, used to display the current iteration number, simulation layout, simulation operation characteristic indicators and the fitness value of the current solution;

[0025] The genetic algorithm module is connected to the data processing and storage module, and transmits the generated samples to the data processing and storage module for subsequent grid processing and coordinate information conversion;

[0026] The data processing and storage module is connected to the simulation module, and transmits the functional area coordinate information to the simulation module for establishing a simulation model and performing simulation operation;

[0027] The simulation module is connected to the evaluation and analysis module, and the indicator data is passed to the evaluation and analysis module for calculating the fitness value of the sample; the simulation module is connected to the visualization module, and the simulation operation results are passed to the visualization module for displaying the simulation layout and operation characteristic indicators;

[0028] The evaluation and analysis module is connected to the genetic algorithm module, and transmits the fitness value to the genetic algorithm module for performing selection, crossover and mutation operations; the evaluation and analysis module is connected to the visualization module, and is used to display the fitness value of the current layout scheme;

[0029] The visualization module is connected to the genetic algorithm module, and obtains the current iteration number and sample information from the genetic algorithm module; the visualization module is connected to the simulation module, and obtains the simulation operation characteristic indicators and layout scheme from the simulation module; the visualization module is connected to the evaluation and analysis module, and obtains the fitness value of the current scheme from the evaluation and analysis module.

[0030] The beneficial effects of the present invention are:

[0031] (1) Combining genetic algorithms with logistics simulation technology, the automatic generation and optimization of layout plans is realized, which avoids manual design and reliance on experience and improves efficiency and accuracy.

[0032] (2) Through the parallel search capability and iterative optimization mechanism of the genetic algorithm, the optimal layout solution can be quickly found, effectively shortening the optimization time and improving the optimization efficiency.

[0033] (3) Logistics simulation technology provides genetic algorithms with modeling tools in multi-dimensional and multi-factor coupling space, enabling them to effectively handle complex problems and overcome the limitations of genetic algorithms in dealing with complex problems.

[0034] (4) The visualization module can clearly display the simulation process and results, making it easier for users to understand and evaluate layout plans and improving decision-making efficiency.

[0035] (5) The present invention can be applied to the layout optimization of various engineering machinery assembly workshops and has strong versatility.

[0036] Other advantages, objectives and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below in conjunction with the accompanying drawings, wherein:

[0038] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0039] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0040] Among them, the drawings are only used for illustrative explanations, and they only represent schematic diagrams rather than actual pictures, and should not be understood as limitations on the present invention. In order to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of actual products. For those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0041] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "front", "rear", etc. indicate the orientation or position relationship, they are based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, the terms describing the position relationship in the drawings are only used for illustrative purposes and cannot be understood as limiting the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0042] like Figure 1As shown, the present invention proposes an automated layout and optimization method for an engineering machinery assembly workshop based on logistics simulation and genetic algorithm. The logistics simulation model and genetic algorithm model involved in the method are both established on a logistics simulation platform. The logistics simulation platform includes: a genetic algorithm module, a data processing and storage module, a simulation module, an evaluation and analysis module, a visualization module, etc.

[0043] Optionally, the genetic algorithm module is responsible for genetically encoding the functional areas divided into the workshop, such as unloading area, storage area, material picking area, production area, material distribution point, etc., and randomly generates 100 samples.

[0044] Optionally, the divided functional areas can be increased, reduced or adjusted according to actual needs and are not limited to the above needs; the solution space of 100 samples is an empirical value and can be adjusted according to the actual situation of the project.

[0045] Optionally, the data processing and storage module is responsible for gridding the layout space, dividing it into square grids with specific side lengths according to the size of the space, each grid having its own number and position, and then the data processing and storage module converts the position information of each partition in each sample into the position coordinate information required for simulation and stores it.

[0046] Optionally, the simulation module reads the location information of each functional area, establishes the logical relationship and operation process between the modules, runs the model and outputs indicator data such as transportation distance, logistics efficiency, and logistics cost.

[0047] Optionally, the evaluation and analysis module calculates and outputs the fitness value of the current sample solution layout based on the output indicator data.

[0048] Optionally, the genetic algorithm module is also responsible for performing operations such as selection, crossover, and mutation according to the fitness value of each sample to obtain a new generation of sample populations. After several iterations and evolutions, until the fitness value converges and no longer changes, the optimal layout solution under the current input can be obtained.

[0049] Optionally, the visualization module is responsible for acquiring data from the genetic algorithm module, the simulation module, and the evaluation and analysis module, and clearly displays the current iteration number, simulation layout, simulation operation characteristic indicators, and the fitness value of the current solution.

[0050] Optionally, the logistics simulation platform is one of Plant Simulation, DELMIA, FlexSim, VisualComponents, Simio, Arena, AutoMod, SIMUL8, AnyLogic, AutoMod, ExtendSim, and Demo3d.

[0051] Example

[0052] Problem description: A construction machinery assembly workshop adopts the traditional layout method, which has problems such as long material transportation distance, low logistics efficiency, and high cost, and requires automated layout optimization.

[0053] Step 1: Functional area division

[0054] The workshop is divided into the following functional areas:

[0055] Unloading area (1)

[0056] Warehouse area (2)

[0057] Material picking area (3)

[0058] Production area (4)

[0059] Material distribution points (5)

[0060] Step 2: Genetic Algorithm Coding

[0061] The genetic algorithm module is used to encode the functional areas. Each functional area is represented by a set of genes to represent its position coordinates (x, y). For example, the coordinates of the unloading area are (1010, 1010), the coordinates of storage area 1 are (10100, 1010), the coordinates of storage area 2 are (11110, 1010), the coordinates of material picking area 1 are (101000, 1010), the coordinates of material picking area 2 are (110010, 1010), the coordinates of material picking area 3 are (111100, 1010), the coordinates of production area 1 are (1000110, 1010), and the coordinates of production area 2 are (1010000, 1010). ), the coordinates of production area 3 are (1011010,1010), the coordinates of production area 4 are (1100100,1010), the coordinates of material distribution point 1 are (1101110,1010), the coordinates of material distribution point 2 are (1111000,1010), the coordinates of material distribution point 3 are (10000010,1010), the coordinates of material distribution point 4 are (10001100,1010), and the coordinates of material distribution point 5 are (10010110,1010).

[0062] Step 3: Generate samples

[0063] 100 samples are randomly generated, each of which represents a layout plan. For example, the layout plan of sample 1 is: unloading area (1010, 1010), storage area 1 (10100, 1010), storage area 2 (11110, 1010), material picking area 1 (101000, 1010), material picking area 2 (110010, 1010), material picking area 3 (111100, 1010), production area 1 (1000110, 1010), production area 2 (1010000, 1 010), production area 3 (1011010,1010), production area 4 (1100100,1010), material distribution point 1 (1101110,1010), material distribution point 2 (1111000,1010), material distribution point 3 (10000010,1010), material distribution point 4 (10001100,1010), material distribution point 5 (10010110,1010). The layout plan of sample 2 is: unloading area (1111, 10100), storage area 1 (11110, 1010), storage area 2 (110010, 101000), material picking area 1 (10100, 100011), material picking area 2 (10100, 101000), material picking area 3 (10100, 110010), production area 1 (1000110, 110010), production area 2 (1011010, 110010) ), production area 3 (1011010, 110111), production area 4 (1100100, 111100), material distribution point 1 (1100100, 1000001), material distribution point 2 (1101110, 111100), material distribution point 3 (1111000, 111100), material distribution point 4 (10000111, 111100), material distribution point 5 (10010001, 111100).

[0064] Step 4: Meshing

[0065] The workshop layout space is divided into square grids with a side length of 1 meter, and each grid has a number and location information. Then the genetic code representing the location information of each functional area is converted into coordinate information that can be recognized by the simulation module. For example, the genetic code of the unloading area is (1010,1010), and the location coordinates after conversion by the data processing and storage module are (10,10).

[0066] Step 5: Simulation

[0067] Use the simulation module to read the functional area coordinate information of the sample, establish the logical relationship and operation process between the modules, run the model and output the indicator data such as transportation distance, logistics efficiency, logistics cost, etc. For example, the transportation distance of sample 1 is 500 meters, the logistics efficiency is 80%, and the logistics cost is 1,000 yuan.

[0068] Step 6: Fitness value calculation

[0069] The evaluation and analysis module is used to calculate the fitness value of each sample based on the output index data. The higher the fitness value, the better the layout solution. For example, the fitness value of sample 1 is 0.8, and the fitness value of sample 2 is 0.9.

[0070] Step 7: Genetic algorithm iterative optimization

[0071] Genetic algorithm modules are used to perform selection, crossover, mutation and other operations according to the fitness value to generate a new generation of sample populations. For example, samples with higher fitness values ​​are selected for crossover to generate new samples, and they are mutated to increase the diversity of samples.

[0072] Step 8: Visualization

[0073] Use the visualization module to display the current iteration number, simulation layout, simulation operation characteristic indicators and the fitness value of the current solution.

[0074] Step 9: Repeat

[0075] Repeat steps 5 to 8 until the fitness value converges and no longer changes, and obtain the optimal layout solution under the current input.

[0076] After multiple iterations of optimization, the optimal layout solution was finally obtained, which placed the material distribution points close to the production area, shortened the material transportation distance, improved logistics efficiency, and reduced logistics costs. For example, the optimal solution had a transportation distance of 300 meters, a logistics efficiency of 90%, and a logistics cost of 800 yuan.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution, which should be included in the scope of the claims of the present invention.

Claims

1. An automated layout and optimization method for an engineering machinery assembly workshop based on logistics simulation and genetic algorithm, characterized by: The method comprises the following steps: Step 1: Use the genetic algorithm module to genetically encode the functional areas divided by the workshop and randomly generate samples; Step 2: Use the data processing and storage module to grid the layout space, convert the location information of each partition in the sample, that is, the genetic code, into the location coordinate information required for simulation and store it; Step 3: Use the simulation module to read the location information of each functional area, establish the logical relationship and operation process between modules, run the model and output the transportation distance, logistics efficiency and logistics cost indicator data; Step 4: Use the evaluation and analysis module to calculate and output the fitness value of the current sample solution layout based on the output indicator data; Step 5: Use the genetic algorithm module to perform selection, crossover and mutation operations according to the fitness value of each sample to obtain a new generation of sample population; Step 6: Repeat steps 2 to 5 until the fitness value converges and no longer changes, and obtain the optimal layout solution under the current input; Step 7: Use the visualization module to display the current iteration number, simulation layout, simulation run characteristic indicators, and the fitness value of the current solution.

2. The method for automatic layout and optimization of an engineering machinery assembly workshop based on logistics simulation and genetic algorithm according to claim 1 is characterized in that: The functional areas include unloading area, storage area, material picking area, production area and material distribution point.

3. The method for automatic layout and optimization of an engineering machinery assembly workshop based on logistics simulation and genetic algorithm according to claim 1 is characterized in that: The simulation module is one of Plant Simulation, DELMIA, FlexSim, VisualComponents, Simio, Arena, AutoMod, SIMUL8, AnyLogic, AutoMod, ExtendSim or Demo3d.

4. An automated layout and optimization system for an engineering machinery assembly workshop based on logistics simulation and genetic algorithm, characterized in that: The system comprises: Genetic algorithm module, used to genetically encode the functional areas divided by the workshop and randomly generate samples; The data processing and storage module is used to perform grid processing on the layout space, convert the position information of each partition in the sample, that is, the genetic code, into the position coordinate information required for simulation and store it; The simulation module is used to read the location information of each functional area, establish the logical relationship and operation process between modules, run the model and output the indicator data of transportation distance, logistics efficiency and logistics cost; An evaluation and analysis module is used to calculate and output the fitness value of the current sample solution layout based on the output indicator data; Visualization module, used to display the current iteration number, simulation layout, simulation operation characteristic indicators and the fitness value of the current solution; The genetic algorithm module is connected to the data processing and storage module, and transmits the generated samples to the data processing and storage module for subsequent grid processing and coordinate information conversion; The data processing and storage module is connected to the simulation module, and transmits the functional area coordinate information to the simulation module for establishing a simulation model and performing simulation operation; The simulation module is connected to the evaluation and analysis module, and the indicator data is passed to the evaluation and analysis module for calculating the fitness value of the sample; the simulation module is connected to the visualization module, and the simulation operation results are passed to the visualization module for displaying the simulation layout and operation characteristic indicators; The evaluation and analysis module is connected to the genetic algorithm module, and transmits the fitness value to the genetic algorithm module for performing selection, crossover and mutation operations; the evaluation and analysis module is connected to the visualization module, and is used to display the fitness value of the current layout scheme; The visualization module is connected to the genetic algorithm module, and obtains the current iteration number and sample information from the genetic algorithm module; the visualization module is connected to the simulation module, and obtains the simulation operation characteristic indicators and layout scheme from the simulation module; the visualization module is connected to the evaluation and analysis module, and obtains the fitness value of the current scheme from the evaluation and analysis module.

Images