Pipelined quadratic optimization design method and system, electronic terminal and storage medium
By using a pipeline optimized by a genetic algorithm, complex technical problems that are difficult to solve efficiently in existing technologies are solved. A secondary optimization design method for pipelines, systems, electronic terminals, and storage media are realized. Specifically, the secondary optimization design method for pipelines, systems, electronic terminals, and storage media are involved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NAVAL UNIV OF ENG PLA
- Filing Date
- 2026-06-09
- Publication Date
- 2026-07-10
AI Technical Summary
In the secondary design of production lines, how to minimize the required site area while maintaining production line performance and ensuring stable and reliable design quality is a challenge that existing technologies rely on manual experience to achieve efficiently.
Genetic algorithms are used to optimize the parallel processes of the pipeline. By collecting the site area and process time of the parallel processes, the individuals in the genetic algorithm population are used to perform global optimization, calculate the fitness, and select the optimal design scheme to achieve secondary optimization of the pipeline.
It achieves a significant reduction in site area without significantly increasing process time, with stable and reliable design quality, and completes the secondary design of the production line quickly and efficiently without relying on human experience.
Smart Images
Figure CN122367080A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of pipeline design technology, specifically to a pipeline secondary optimization design method, system, electronic terminal, and storage medium. Background Technology
[0002] In manufacturing, repair, and other fields, assembly lines are a highly efficient way to process batches of products. When adding a new assembly line, sometimes the available space is insufficient to build a 100% replica. In such cases, it's necessary to redesign the existing assembly line from a space-saving perspective. The main task of this redesign is to make localized adjustments to the existing assembly line.
[0003] Actual production lines are often extremely complex, frequently involving multiple parallel processes. These parallel processes only occupy space when in operation; their space usage when not in operation is negligible. Combining multiple originally parallel processes into a new process (where the new process executes these previously parallel processes sequentially within the same area) is an effective method for addressing space constraints in production line redesign, but it may increase the total time to complete all processes. The degree of space reduction and the increase in time to complete all processes will vary depending on the sequential processing method. Minimizing the required space while maintaining production line performance has always been a challenge in production line redesign. Currently, good redesign solutions largely rely on the experience of frontline production line managers; their optimization ideas and methods often vary from person to person, making it difficult to achieve high-quality and stable production line optimization redesign. Summary of the Invention
[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:
[0005] A method for secondary optimization design of a pipeline includes the following steps:
[0006] Collect the area required for each parallel process in the production line and the process time, where the process time refers to the average time to complete one process.
[0007] All parallel processes are numbered in ascending order of their processing time. The area required for process i is denoted as . The process time is recorded as i = 1, 2, ..., n, where n is the number of parallel processes;
[0008] For parallel processes with numbering ranging from 1 to n-1, a secondary optimization design of the pipeline is performed based on a genetic algorithm.
[0009] Furthermore, when performing secondary optimization design of pipelines based on genetic algorithms, each individual in the genetic algorithm population corresponds to a design method for the user to choose from.
[0010] Furthermore, for any individual X, its fitness is calculated as follows:
[0011] The n original parallel processes are called the original processes. The design method corresponding to individual X is: m new parallel processes are generated from the n-1 original parallel processes with a number range of 1 to n-1. Each new process is composed of one or more original processes in series.
[0012] The area required for each new process is denoted as . The process time is recorded as j=1,2,…,m;
[0013] For any new process, if Then the characteristic value of the new process for:
[0014] ;
[0015] Otherwise, let the characteristic value of the new process be... ;
[0016] The fitness Y of individual X is calculated using the following formula:
[0017] .
[0018] Furthermore, when the genetic algorithm terminates, it also outputs the total area corresponding to each individual and the average time of each new process. The user selects the individual with the lowest fitness from the population under the site constraints of the pipeline to determine the secondary optimization design scheme of the pipeline.
[0019] Furthermore, in the genetic algorithm, for any individual X, individual X is a set containing n-1 elements, and each element is a natural number with a value in the range of 1 to n-1. If the value of any a-th element in individual X is equal to that of the b-th element, it means that in the design method corresponding to individual X, the a-th original process and the b-th original process are included in the same new process in a serial manner.
[0020] Another aspect of the present invention provides a pipeline secondary optimization design system, which employs the above-described pipeline secondary optimization design method and includes:
[0021] The data collection module is used to collect the area required for each parallel process in the production line and the process time, and to number all parallel processes in ascending order of process time.
[0022] The optimization design module is used to perform secondary optimization design of the pipeline based on the data collected by the data collection module and a genetic algorithm.
[0023] Another aspect of the present invention provides an electronic terminal, including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the electronic terminal performs the above-described pipeline secondary optimization design method.
[0024] In another aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the processor performs the above-described pipeline secondary optimization design method.
[0025] Compared with existing technologies, the pipeline secondary optimization design method, system, electronic terminal and storage medium provided by the present invention no longer rely on human experience, but are based on genetic algorithms for global optimization. They can efficiently obtain the optimal or near-optimal serialized scheme in a complex solution space, thereby completing the secondary design work quickly and efficiently, with stable and reliable design quality and strong universality. Attached Figure Description
[0026] Figure 1 A flowchart illustrating a secondary optimization design method for a pipeline provided by the present invention;
[0027] Figure 2 This is a schematic diagram of a pipeline after secondary optimization design in a case study.
[0028] Figure 3 This is a schematic diagram of the pipeline after secondary optimization design in another specific case;
[0029] Figure 4 This is a diagram showing the performance comparison of the pipeline before and after the secondary optimization design. Detailed Implementation
[0030] To make the technical means, creative features, objectives and effects of this invention easier to understand, the following description, in conjunction with the accompanying drawings and specific embodiments, further explains how this invention is implemented.
[0031] Reference Figure 1 As shown, the present invention provides a secondary optimization design method for pipelines, comprising the following steps:
[0032] S1. Collect the area and time required for each parallel process in the production line, whereby the process time refers to the average time to complete one process.
[0033] S2. Number all parallel processes in ascending order of their process times. The area required for process i is denoted as . The process time is recorded as , i=1,2,…,n, where n is the number of parallel processes.
[0034] S3. For parallel processes numbered from 1 to n-1, a secondary optimization design of the pipeline is performed based on a Genetic Algorithm (GA). GA is an algorithm based on the evolutionary laws of biological populations, capable of efficiently finding the optimal solution in a complex solution space. Each individual in the GA population corresponds one-to-one with a solution in the problem's solution space, and the individuals are generated by the GA itself. In this embodiment, each individual in the genetic algorithm population corresponds to a design method for the user to choose from.
[0035] This invention only processes parallel processes numbered from 1 to n-1, while parallel processes numbered n are left in their original state by default, which helps to improve the running efficiency of the genetic algorithm.
[0036] For any individual X, the n original parallel processes are called the original processes. The design method corresponding to individual X is: m new parallel processes are generated from the n-1 original parallel processes with numbers ranging from 1 to n-1. Each new process is composed of one or more original processes in series.
[0037] Furthermore, individual X is a set containing n-1 elements, and each element is a natural number with a value in the range of 1 to n-1. If the value of any a-th element in individual X is equal to that of the b-th element, it means that in the design method corresponding to individual X, the a-th original process and the b-th original process are included in the same new process in a serial manner.
[0038] Taking a production line with 5 original processes as an example, GA only processes the original processes numbered 1 to 4. Each individual is a set containing 4 elements, and each element is a natural number in the range of 1 to 4. Assume that the individual If the first element is equal to the second element, and the third element is equal to the fourth element, then process 1 (representing the original process numbered 1, hereinafter the same) and process 2 are included in the same new process in a sequential manner, and processes 3 and 4 are included in the same new process in a sequential manner. The unprocessed process 5 remains in its original state. (Refer to...) Figure 2 As shown.
[0039] In addition, each individual in GA has a fitness value, which is used to evaluate the individual's quality. GA uses the fitness values of all individuals to perform evolutionary operations such as "heredity" and "mutation" to ultimately achieve optimization. In this embodiment, it is agreed that the lower the fitness value, the better the individual.
[0040] Specifically, for any individual X, its fitness is calculated as follows:
[0041] The area required for each new process is denoted as . The process time is recorded as Let j = 1, 2, ..., m. Understandably, if the new process contains only one of the original processes, then... , The site area and process time are the same as the original process. If the new process includes multiple original processes, since the new process involves sequentially executing multiple original processes in the same location, the corresponding area for the new process is... The area required for the new process is determined by the maximum area required in the original process it includes. It is determined by the sum of the process times of all the original processes it contains.
[0042] For any new process, if Then the characteristic value of the new process for:
[0043] ;
[0044] Otherwise, let the characteristic value of the new process be... ;
[0045] The fitness Y of individual X is calculated using the following formula:
[0046] .
[0047] When the genetic algorithm terminates, it also outputs the total area (i.e., the total required site area) for each individual and the average time to complete each new process once. The user selects the individual with the lowest fitness from the population that meets the site constraints of the pipeline to determine the secondary optimization design scheme for the pipeline. It is understandable that in reality, the site may be limited, i.e., the area cannot exceed a certain threshold. In this case, the individual with the lowest fitness is selected from the individuals whose total area does not exceed that threshold.
[0048] In a specific case, a branch line of a product production line has 10 parallel processes. The required area and processing time for each process are shown in Table 1. Using the method described above, these parallel processes are redesigned.
[0049] Table 1 Information on parallel processes
[0050]
[0051] After collecting the required site area and process time for each parallel process, the process times were sorted in ascending order. The sorting results for all processes are shown in Table 2.
[0052] Table 2. Sorted Process Information
[0053]
[0054] Based on a genetic algorithm, a secondary optimization design of the pipeline is performed for parallel processes numbered 1 to 9 (i.e., process number 10, named G7, is not processed by the genetic algorithm). In this embodiment, the optimized pipeline is as follows: Figure 3 As shown.
[0055] Based on the unoptimized production line in Table 1, its occupied area is 44 m². 2 Simulating the production line processing 100 products, the average time was 19,366 minutes. However, using... Figure 3 The production line occupies a space of only 30 square meters. 2 The simulation showed that the production line processed 100 products, with an average processing time of 19,607 minutes. The optimized production line occupied only 68.2% of the floor space of the baseline production line, and the time to complete a batch of products increased by only 1.2% compared to the baseline production line. Figure 4 The simulations extensively examined the completion time distribution of two different production lines processing 100 products, showing little difference between them. This achieved the goal of "minimizing the reduction of production line performance while maximizing the reduction of site area." Numerous simulation results demonstrate that this method can quickly and efficiently complete secondary design work.
[0056] Another aspect of the present invention provides a pipeline secondary optimization design system, which employs the above-described pipeline secondary optimization design method and includes:
[0057] The data collection module is used to collect the area required for each parallel process in the production line and the process time, and to number all parallel processes in ascending order of process time.
[0058] The optimization design module is used to perform secondary optimization design of the pipeline based on the data collected by the data collection module and a genetic algorithm.
[0059] In summary, the pipeline secondary optimization design method provided by this invention no longer relies on human experience, but instead uses a genetic algorithm for global optimization. It can efficiently obtain the optimal or near-optimal serialization scheme in a complex solution space, thereby completing the secondary design work quickly and efficiently, with stable and reliable design quality and strong universality.
[0060] Another aspect of the present invention provides an electronic terminal, including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the electronic terminal performs the above-described pipeline secondary optimization design method.
[0061] In another aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the processor performs the above-described pipeline secondary optimization design method.
[0062] The system, electronic terminal, and computer-readable storage medium described in the embodiments of the present invention can be found in the detailed description of the above-mentioned pipeline secondary optimization design method and its beneficial effects, which will not be repeated here.
[0063] Generally, the computer instructions used to implement the method of the present invention can be carried by any combination of one or more computer-readable storage media. Any storage medium can be temporary or non-temporary, and can include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any combination thereof.
[0064] Computer-readable storage media can be any tangible medium containing a stored program, and more specific examples (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.
[0065] This program can be used, or combined with, an instruction execution system, apparatus, or device, and is written in one or more programming languages or a combination thereof to perform the operations of this invention. The programming languages include object-oriented programming languages—such as Java, Smalltalk, and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages. In particular, Python, suitable for neural network computation, and platform frameworks such as TensorFlow and PyTorch can be used. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet according to an Internet service provider).
[0066] Finally, it should be noted that the above description is only an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.
Claims
1. A method for secondary optimization design of a pipeline, characterized in that, Includes the following steps: Collect the area required for each parallel process in the production line and the process time, wherein the process time refers to the average time to complete one process. All parallel processes are numbered in ascending order of their processing time. The area required for process i is denoted as . The process time is recorded as i = 1, 2, ..., n, where n is the number of parallel processes; For parallel processes with numbering ranging from 1 to n-1, a secondary optimization design of the pipeline is performed based on a genetic algorithm; When performing secondary optimization design of pipelines based on genetic algorithms, each individual in the genetic algorithm population corresponds to a design method for the user to choose from. For any individual X, its fitness is calculated using the following method: The n original parallel processes are called the original processes. The design method corresponding to individual X is: m new parallel processes are generated from the n-1 original parallel processes with a number range of 1 to n-1. Each new process is composed of one or more original processes in series. The area required for each new process is denoted as . The process time is recorded as j=1,2,…,m; For any new process, if Then the characteristic value of the new process for: ； Otherwise, let the characteristic value of the new process be... ; The fitness Y of individual X is calculated using the following formula: 。 2. The secondary optimization design method for production lines according to claim 1, characterized in that, When the genetic algorithm terminates, it also outputs the total area corresponding to each individual and the average time of each new process. The user selects the individual with the lowest fitness from the population under the site constraints of the pipeline to determine the secondary optimization design scheme of the pipeline.
3. The secondary optimization design method for production lines according to claim 1, characterized in that, In a genetic algorithm, for any individual X, individual X is a set containing n-1 elements, and each element is a natural number with a value in the range of 1 to n-1. If the value of any a-th element in individual X is equal to that of the b-th element, it means that in the design method corresponding to individual X, the a-th original process and the b-th original process are included in the same new process in a serial manner.
4. A secondary optimization design system for a production line, characterized in that, The pipeline secondary optimization design method according to any one of claims 1-3 is adopted, and includes: The data collection module is used to collect the area required for each parallel process in the production line and the process time, and to number all parallel processes in ascending order of process time. The optimization design module is used to perform secondary optimization design of the pipeline based on the data collected by the data collection module and a genetic algorithm.
5. An electronic terminal, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it causes the electronic terminal to perform the pipeline secondary optimization design method according to any one of claims 1 to 3.
6. A computer-readable storage medium having a computer program stored thereon, wherein when executed by a processor, the computer program causes the processor to perform the pipeline secondary optimization design method according to any one of claims 1 to 3.