Workshop layout optimization method and device based on vertical model, equipment and medium

Abstract

The embodiment of the application provides a workshop layout optimization method and device, equipment and medium based on a vertical model, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring a basic mathematical model of a target workshop, and acquiring layout optimization demand information of the target workshop; based on a preset workshop numerical simulation driving model, performing information analysis on the layout optimization demand information to obtain structured layout constraint information; supplementing the structured layout constraint information to obtain layout constraint set information; based on the workshop numerical simulation driving model, performing function conversion on the layout constraint set information to obtain a workshop layout expansion constraint function; based on the workshop layout expansion constraint function and the target workshop, performing model optimization on the basic mathematical model to obtain a dynamic workshop simulation model; and performing cyclic iteration optimization on the dynamic workshop simulation model to obtain workshop optimization layout information. The embodiment of the application can improve the accuracy of workshop layout optimization.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a workshop layout optimization method and device based on a vertical model, equipment and medium. BACKGROUND

[0002] Workshop layout optimization refers to adjusting the positions and layout structures of various workshop components in a workshop to achieve optimization actions to improve the performance of the workshop. For example, in the field of electronic product production, through workshop layout optimization of an electronic product production workshop, the production efficiency of electronic products can be improved, or the operating cost of the electronic product production workshop can be reduced.

[0003] At present, a common workshop layout optimization method based on a vertical model is that a professional constructs a workshop simulation model according to the current layout of the workshop and the target of workshop optimization. However, the workshop simulation model constructed by humans is prone to constraint omissions, which leads to the fact that the final workshop layout optimization scheme is not accurate. Therefore, how to improve the accuracy of workshop layout optimization has become a technical problem to be solved. SUMMARY

[0004] The main purpose of the embodiments of the present application is to propose a workshop layout optimization method and device based on a vertical model, equipment and medium, which aims to improve the accuracy of workshop layout optimization.

[0005] To achieve the above-mentioned purpose, the first aspect of the embodiments of the present application proposes a workshop layout optimization method based on a vertical model, which comprises:

[0006] Obtaining a basic mathematical model of a target workshop and obtaining layout optimization requirement information of the target workshop;

[0007] Based on a preset workshop numerical simulation driving model, information analysis is performed on the layout optimization requirement information to obtain structured layout constraint information;

[0008] Constraint supplement is performed on the structured layout constraint information to obtain layout constraint set information;

[0009] Based on the workshop numerical simulation driving model, function conversion is performed on the layout constraint set information to obtain a workshop layout expansion constraint function;

[0010] Based on the workshop layout expansion constraint function and the target workshop, model optimization is performed on the basic mathematical model to obtain a dynamic workshop simulation model;

[0011] Loop iteration optimization is performed on the dynamic workshop simulation model to obtain workshop optimization layout information.

[0012] In some embodiments, the dynamic workshop simulation model comprises a workshop layout optimization objective function and a workshop layout optimization constraint function; the cyclic iteration optimization of the dynamic workshop simulation model comprises:

[0013] Based on the workshop layout optimization constraint function, the feasible solution calculation of the workshop layout optimization objective function is performed to obtain a candidate feasible solution set, wherein the candidate feasible solution set comprises a plurality of candidate feasible solutions;

[0014] Based on the dynamic workshop simulation model, the simulation processing of the candidate feasible solution is performed to obtain a candidate solution fitness;

[0015] Based on the candidate solution fitness, the iteration update of the candidate feasible solution set is performed to obtain an updated candidate solution set;

[0016] The fitness comparison of the updated candidate solution set is performed to obtain an optimal solution of the objective function;

[0017] The workshop layout mapping of the optimal solution of the objective function is performed to obtain the workshop optimization layout information.

[0018] In some embodiments, the simulation processing of the candidate feasible solution based on the dynamic workshop simulation model to obtain a candidate solution fitness comprises:

[0019] The model replication of the dynamic workshop simulation model is performed to obtain a replicated discrete event simulation model;

[0020] Based on the candidate feasible solution, the model running processing of the replicated discrete event simulation model is performed to obtain model performance data;

[0021] The model performance data is quantitatively processed to obtain the candidate solution fitness.

[0022] In some embodiments, the iteration update of the candidate feasible solution set based on the candidate solution fitness to obtain an updated candidate solution set comprises:

[0023] Based on the candidate solution fitness, the candidate solution adjustment direction is determined;

[0024] Based on the preset iteration number and the candidate solution adjustment direction, the candidate solution adjustment of the candidate feasible solution set is performed to obtain the updated candidate solution set.

[0025] In some embodiments, the basic mathematical model comprises a target workshop optimization function and a workshop layout basic constraint function; the target workshop comprises a workshop component; and the model optimization of the basic mathematical model based on the workshop layout expansion constraint function and the target workshop to obtain a dynamic workshop simulation model comprises:

[0026] Constraining and updating the workshop layout basic constraint function based on the workshop layout expansion constraint function, to obtain a workshop layout target constraint function;

[0027] Component modeling is performed on the workshop components to obtain a component simulation model;

[0028] Model splicing is performed on the component simulation model to obtain a static workshop simulation model;

[0029] Based on the workshop layout target constraint function and the target workshop optimization function, function embedding is performed on the static workshop simulation model to obtain the dynamic workshop simulation model.

[0030] In some embodiments, the constraint supplementing of the structured layout constraint information to obtain layout constraint set information comprises:

[0031] Based on a preset multi-level index knowledge base, keyword matching is performed on the structured layout constraint information to obtain first constraint expansion information;

[0032] Based on the multi-level index knowledge base, semantic matching is performed on the structured layout constraint information to obtain second constraint expansion information;

[0033] Information merging is performed on the first constraint expansion information and the second constraint expansion information to obtain the layout constraint set information.

[0034] In some embodiments, the information parsing of the layout optimization demand information based on the preset workshop numerical simulation driving model to obtain structured layout constraint information comprises:

[0035] Based on the workshop numerical simulation driving model, key information extraction is performed on the layout optimization demand information to obtain constraint objects and quantization parameters;

[0036] Based on a preset demand classification dimension, information classification is performed on the layout optimization demand information to obtain workshop layout multi-dimensional constraint information;

[0037] Based on the constraint objects and the quantization parameters, structured processing is performed on the workshop layout multi-dimensional constraint information to obtain the structured layout constraint information.

[0038] To achieve the above object, a second aspect of the embodiment of the present application proposes a workshop layout optimization device based on a vertical model, the device comprising:

[0039] A basic information acquisition module is configured to acquire a basic mathematical model of a target workshop and acquire layout optimization demand information of the target workshop;

[0040] The demand information analysis module is configured to analyze the layout optimization demand information based on a preset workshop numerical simulation driving model to obtain structured layout constraint information.

[0041] The constraint condition supplementing module is configured to supplement the structured layout constraint information to obtain layout constraint set information.

[0042] The constraint information converting module is configured to convert the layout constraint set information into a function based on the workshop numerical simulation driving model to obtain a workshop layout extended constraint function.

[0043] The mathematical model optimization module is configured to optimize the basic mathematical model based on the workshop layout extended constraint function and the target workshop to obtain a dynamic workshop simulation model.

[0044] The model iterative optimization module is configured to cyclically and iteratively optimize the dynamic workshop simulation model to obtain workshop optimization layout information.

[0045] To achieve the above object, a third aspect of the embodiment of the present application provides an electronic device, which comprises a memory and a processor, the memory stores a computer program, and the processor implements the method of the first aspect when executing the computer program.

[0046] To achieve the above object, a fourth aspect of the embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method of the first aspect.

[0047] The workshop layout optimization method and device based on a vertical model, the electronic device and the storage medium provided by the present application can determine the direction of workshop optimization by obtaining the basic mathematical model of a target workshop and layout optimization demand information, then analyze the layout optimization demand information into structured layout constraint information by using a pre-constructed workshop numerical simulation driving model, supplement the structured layout constraint information to obtain layout constraint set information, so that the layout constraint set information can cover the explicit demand of users and the implicit index of the industry, thereby ensuring the feasibility of the generated workshop layout scheme, then convert the layout constraint set information into a function based on the workshop numerical simulation driving model to obtain a workshop layout extended constraint function, and optimize the basic mathematical model based on the workshop layout extended constraint function and the target workshop to obtain a dynamic workshop simulation model that can simulate multiple scene conditions in actual production, thereby reducing the dependence on manual work in the modeling process and improving the construction efficiency of the workshop model, finally, cyclically and iteratively optimize the dynamic workshop simulation model to obtain the optimal workshop layout scheme in multiple rounds of verification, thereby improving the accuracy of workshop layout optimization. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 is a flowchart of the workshop layout optimization method based on the vertical model provided by the embodiments of the present application;

[0049] Figure 2 is Figure 1 is a flowchart of step S102 in

[0050] Figure 3 is Figure 1 is a flowchart of step S103 in

[0051] Figure 4 is Figure 1 is a flowchart of step S105 in

[0052] Figure 5 is Figure 1 is a flowchart of step S106 in

[0053] Figure 6 is Figure 5 is a flowchart of step S502 in

[0054] Figure 7 is Figure 5 is a flowchart of step S503 in

[0055] Figure 8 is a structural schematic diagram of the workshop layout optimization device based on the vertical model provided by the embodiments of the present application;

[0056] Figure 9 is a hardware structural schematic diagram of the electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0057] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0058] It should be noted that although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a manner different from the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification and claims and the above-described drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application, and are not intended to limit the present application.

[0060] Firstly, the meanings of several terms involved in the present application are explained:

[0061] Workshop layout optimization system: The workshop layout optimization system is a comprehensive decision support system integrating data collection, digital modeling, constraint management, intelligent optimization and simulation verification. The core function is to realize the scientific planning and optimization of workshop layout schemes. The system first collects workshop basic data and optimization objectives, relies on the modeling module to convert production equipment, auxiliary facilities, functional areas and other workshop components into digital models, and integrates basic constraints and extended constraints to build a complete constraint system. Then, intelligent optimization algorithms such as genetic algorithm and particle swarm algorithm are used to generate multiple candidate feasible solutions. The dynamic simulation module simulates the actual production scene of each candidate scheme and calculates the fitness of the scheme. Then, the optimal solution is selected through iterative updating, and the optimized scheme including intuitive layout drawings, performance evaluation reports and constraint satisfaction proofs is finally output. The system also supports real-time adjustment of scheme parameters and secondary simulation, which can replace the subjective bias of traditional empirical layout, avoid layout conflicts and production risks in advance, and significantly improve the efficiency, compliance and feasibility of workshop layout.

[0062] Artificial intelligence (AI): Artificial intelligence is a new technical science that studies, develops, and applies systems to simulate, extend, and expand human intelligence. Artificial intelligence is a branch of computer science that aims to understand the essence of intelligence and produce new intelligent machines that can react in a similar way to human intelligence. The field of research includes robots, language recognition, image recognition, natural language processing, and expert systems. Artificial intelligence can simulate the information process of human consciousness and thinking. Artificial intelligence is also the theory, method, technology and application system of using digital computers or digital computer controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0063] Workshop layout optimization refers to adjusting the positions and layout structures of various workshop components in a workshop to achieve optimization of improving the performance of the workshop. For example, in the field of electronic product production, by optimizing the layout of the electronic product production workshop, the production efficiency of the electronic product can be improved, or the operating cost of the electronic product production workshop can be reduced.

[0064] Currently, the common workshop layout optimization method based on the vertical model is for professionals to construct a workshop simulation model according to the current layout of the workshop and the optimization target of the workshop. However, the workshop simulation model constructed by humans is prone to constraint omissions, which leads to the inaccuracy of the final workshop layout optimization scheme. Therefore, how to improve the accuracy of workshop layout optimization has become a technical problem to be solved.

[0065] Based on this, the embodiment of the application provides a workshop layout optimization method and device based on a vertical model, an electronic device and a storage medium, aiming to improve the accuracy of workshop layout optimization.

[0066] The embodiment of the application provides a workshop layout optimization method and device based on a vertical model, an electronic device and a storage medium, and is specifically described through the following embodiments. First, the embodiment of the application describes a workshop layout optimization method based on a vertical model.

[0067] The embodiment of the application can acquire and process related data based on artificial intelligence technology. Among them, artificial intelligence (Artificial Intelligence, AI) is to use digital computers or digital computer controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. Theory, method, technology and application system.

[0068] The basic technology of artificial intelligence generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. Artificial intelligence software technology mainly includes computer vision technology, robot technology, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning, etc. Several major directions.

[0069] The embodiment of the application provides a workshop layout optimization method based on a vertical model, which relates to the field of artificial intelligence technology. The embodiment of the application provides a workshop layout optimization method based on a vertical model, which can be applied to a terminal, can also be applied to a server end, and can also be software running in a terminal or a server end. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc.; the server end can be configured as an independent physical server, can also be configured as a server cluster or a distributed system composed of multiple physical servers, can also be configured as a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN and basic cloud computing services such as big data and artificial intelligence platforms; the software can be an application that implements the workshop layout optimization method based on a vertical model, but is not limited to the above forms.

[0070] The application is operable in a multitude of generic or specific computer system environments or configurations. Examples include personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application can be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like, that perform particular tasks or implement particular abstract data types. The application can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules can be located in local and remote computer storage media including memory storage devices.

[0071] Figure 1 is an optional flowchart of a vertical model-based workshop layout optimization method provided by an embodiment of the application. The vertical model-based workshop layout optimization method can be applied to a workshop layout optimization system, Figure 1 The method in the vertical model-based workshop layout optimization system can include, but is not limited to, steps S101 to S106.

[0072] In step S101, a basic mathematical model of a target workshop is acquired, and layout optimization requirement information of the target workshop is acquired.

[0073] In step S102, based on a preset workshop numerical simulation driving model, information analysis is performed on the layout optimization requirement information to obtain structured layout constraint information.

[0074] In step S103, constraint supplement is performed on the structured layout constraint information to obtain layout constraint set information.

[0075] In step S104, based on the workshop numerical simulation driving model, function conversion is performed on the layout constraint set information to obtain a workshop layout expansion constraint function.

[0076] In step S105, based on the workshop layout expansion constraint function and the target workshop, model optimization is performed on the basic mathematical model to obtain a dynamic workshop simulation model.

[0077] In step S106, loop iteration optimization is performed on the dynamic workshop simulation model to obtain workshop optimization layout information.

[0078] The steps S101 to S106 shown in the embodiments of the present application can determine the direction of the workshop optimization by obtaining the basic mathematical model of the target workshop and the layout optimization demand information. Then, the layout optimization demand information is parsed into structured layout constraint information by using the pre-constructed workshop numerical simulation driving model, and the structured layout constraint information is supplemented to obtain layout constraint set information, so that the layout constraint set information can cover the explicit requirements of the user and the implicit indicators of the industry, thereby ensuring the feasibility of the generated workshop layout scheme. Subsequently, based on the workshop numerical simulation driving model, the layout constraint set information is functionally converted to obtain the workshop layout expansion constraint function, and based on the workshop layout expansion constraint function and the target workshop, the model optimization of the basic mathematical model is performed to obtain a dynamic workshop simulation model that can simulate multiple scene conditions in actual production, thereby reducing the dependence on manual modeling in the modeling process and improving the construction efficiency of the workshop model. Finally, the dynamic workshop simulation model is iteratively optimized, and the obtained workshop optimization layout information is the optimal workshop layout scheme obtained through multiple rounds of verification, thereby improving the accuracy of the workshop layout optimization.

[0079] In step S101 of some embodiments, the target workshop refers to a production workshop that needs to be optimized in layout, for example, in the automobile manufacturing scene, the target workshop can be an automobile assembly workshop.

[0080] The basic mathematical model refers to a mathematical model constructed according to the physical parameters, equipment basic data, etc. of the target workshop, which contains information such as the spatial boundary of the target workshop, the equipment attribute, and the workshop optimization target, for example, in the mechanical processing scene, the basic mathematical model can be a model containing information such as the length and width dimensions of the workshop, the machine tool coordinates and dimensions, etc.

[0081] The layout optimization demand information refers to various requirements proposed by the user regarding the layout optimization of the target workshop, for example, in the electronic product workshop production scene, the layout optimization demand information can be the requirements such as "the production capacity needs to reach 5000 pieces per day, the equipment utilization rate needs to be maintained at 80%-90%, and the width of the fire-fighting passage needs to be ≥1.5 meters" proposed by the director of the electronic product workshop, and it needs to be known that the layout optimization demand information can be voice data or text data.

[0082] The embodiment of the application can obtain physical parameters, equipment basic data, etc. of the target workshop through on-site measurement and data collection of the target workshop. Secondly, according to the physical parameters, equipment basic data, etc., professional personnel can generate function expressions of the spatial boundary, equipment attribute, etc. of the target workshop. In addition, the optimization target of the target workshop proposed by the user is converted into a function, and the workshop optimization function can be obtained. Finally, the function expressions of the spatial boundary, equipment attribute, etc. of the target workshop and the workshop optimization function are functionally integrated, and the basic mathematical model of the target workshop can be obtained. In detail, the method of on-site measurement and data collection of the target workshop can be that an engineering team uses a laser range finder, a CAD drawing tool, etc. to collect the length, width, height, ground bearing grade, door and window position and size, etc. of the target workshop, and at the same time, collect the equipment model, length, width, height, size, energy consumption parameter, operation space requirement, minimum safety distance between equipment, etc. of each equipment in the target workshop.

[0083] Further, the embodiment of the application can obtain the demand information required for optimization of the layout of the target workshop, i.e. the layout optimization demand information, through interviewing workshop personnel, questionnaire survey or on-site investigation.

[0084] In step S102 of some embodiments, the preset workshop numerical simulation driving model refers to a model that is constructed in advance and used to drive the digitalization and simulation processing of the workshop. The simulation processing can be demand analysis, function conversion, etc. It should also be known that the workshop numerical simulation driving model is usually a vertical model that is fine-tuned or specially trained, for example, a large language model suitable for the field of workshop production and manufacturing. The structured layout constraint information refers to layout constraint information with a clear structure. For example, in the food processing workshop scenario, when the structure of the layout constraint information is "constraint object, type, parameter, priority", the structured layout constraint information can be represented as "constraint object: sterilization equipment, type: safety class, parameter: distance ≥ 2 meters from other equipment, priority: mandatory".

[0085] The embodiment of the application can extract key information in the layout optimization demand information according to the pre-constructed workshop numerical simulation driving model. Secondly, the layout optimization demand information is classified according to the preset dimension to obtain multi-dimensional constraint information. Finally, according to the extracted key information, the multi-dimensional constraint information is converted into structured layout constraint information.

[0086] In detail, please refer to Figure 2 In some embodiments, step S102 can include but is not limited to steps S201 to S203:

[0087] Step S201, based on the workshop numerical simulation driving model, key information extraction is performed on the layout optimization demand information to obtain constraint objects and quantitative parameters;

[0088] In step S202, information classification is performed on the layout optimization demand information based on a preset demand classification dimension, to obtain multi-dimensional constraint information of the workshop layout.

[0089] In step S203, structured processing is performed on the multi-dimensional constraint information of the workshop layout based on the constraint object and the quantitative parameter, to obtain structured layout constraint information.

[0090] In step S201 of some embodiments, the constraint object refers to a specific object that is limited or required in the layout optimization demand information. It needs to be known that the constraint object is the subject of the constraint rule, and therefore, the constraint object is usually equipment, area, performance index, etc. in the workshop, for example, in the automobile assembly workshop scenario, the constraint object is usually the assembly line, the part storage area, the production efficiency, etc.

[0091] The quantitative parameter refers to a specific numerical requirement for the constraint object in the layout optimization demand information, for example, in the logistics and storage workshop scenario, the quantitative parameter can be 1.8 meters in the 1.8-meter shelf spacing, 5 times in the daily 5-time goods turnover rate.

[0092] Embodiments of the present application can input the layout optimization demand information provided by the user (such as “the daily production capacity of the electronic workshop is greater than 8000 pieces, and the distance between the SMT equipment and the detection equipment is greater than 3 meters”) into the preset workshop simulation driving model, and then the workshop simulation driving model can locate the core nouns such as equipment, area, and performance index in the layout optimization demand information as the constraint object through the semantic recognition algorithm and the built-in industrial knowledge graph, and recognize the numerical expression in the layout optimization demand information as the quantitative parameter.

[0093] In step S202 of some embodiments, the preset demand classification dimension refers to a standard that is preset and used for classifying the layout optimization demand information, for example, the dimensions of constraint nature, urgency, and scope of action.

[0094] The multi-dimensional constraint information of the workshop layout refers to the layout constraint content presented from different demand classification dimensions. It needs to be known that each information in the layout optimization demand information should have a clear classification attribute in any dimension.

[0095] Before performing information classification on the layout optimization demand information, embodiments of the present application need to determine the demand classification dimension and set the classification attribute of each demand classification dimension, for example, the classification attribute of the constraint nature is safety class, efficiency class, and space class, and the classification attribute of the urgency is divided into mandatory, important, and suggestion.

[0096] After obtaining the demand classification dimensions and the classification attributes of each demand classification dimension, the embodiment of the present application can match each constraint information in the layout optimization demand information with the classification attributes of the demand classification dimensions according to the semantic information of the layout optimization demand information. For example, in the demand classification dimension of constraint property, the layout optimization demand information "fire passage width ≥ 1.2 meters" can be explicitly related to production safety through semantic understanding, so the layout optimization demand information "fire passage width ≥ 1.2 meters" is matched with the safety class classification attribute in the constraint property, so that the layout optimization demand information "fire passage width ≥ 1.2 meters" can be classified as a safety class constraint. The above classification process is repeated until each constraint information in the layout optimization demand information is classified, and the workshop layout multidimensional constraint information is obtained.

[0097] In step S203 of some embodiments, the constraint object, the quantitative parameter and the workshop layout multidimensional constraint information can be adjusted as core elements according to the pre-set structured format. For example, when the pre-set structured format is the field splicing of constraint object, constraint type, emergency degree, action range and quantitative parameter, the layout optimization demand information can be arranged as constraint object: fire passage width, constraint type: safety class, emergency degree: mandatory, action range: global, and quantitative parameter: ≥ 1.2 meters.

[0098] The steps S201 to S203 shown in the embodiment of the present application can extract key information from the layout optimization demand information based on the workshop numerical simulation driving model to obtain the constraint object and the quantitative parameter, which can avoid the information ambiguity or omission of the constraint information in the layout optimization demand information. Secondly, the information classification of the layout optimization demand information is performed based on the pre-set demand classification dimensions to obtain the workshop layout multidimensional constraint information, which can avoid the problem of disorder of the layout optimization demand information. Finally, the structured layout constraint information is obtained by structuring the workshop layout multidimensional constraint information based on the constraint object and the quantitative parameter, which improves the standardization degree of the constraint information, thereby reducing the distortion and loss of the constraint information in the transmission process, and ensuring the accuracy of the generated constraint function.

[0099] In step S103 of some embodiments, the layout constraint set information refers to the constraint set covering the requirements proposed by the user and the requirements of the industry. For example, in the scene of a chemical production workshop, the layout constraint set information can be a set of various constraints including equipment explosion-proof distance, personnel passage width, production efficiency indicators, etc.

[0100] The embodiment of the application can first perform keyword matching on the structured layout constraint information to obtain first constraint extension information, then perform semantic matching to obtain second constraint extension information, and finally combine the first and second constraint extension information to obtain layout constraint set information based on a preset multi-level index knowledge base.

[0101] In detail, refer to Figure 3 In some embodiments, step S103 can include but is not limited to steps S301 to S303:

[0102] In step S301, first constraint extension information is obtained by performing keyword matching on the structured layout constraint information based on a preset multi-level index knowledge base.

[0103] In step S302, second constraint extension information is obtained by performing semantic matching on the structured layout constraint information based on the multi-level index knowledge base.

[0104] In step S303, layout constraint set information is obtained by combining the first constraint extension information and the second constraint extension information.

[0105] In step S301 of some embodiments, the preset multi-level index knowledge base refers to a database that is pre-constructed, divided by levels, and contains various types of layout constraint related indexes. It is to be known that the levels in the multi-level index knowledge base include general industrial standard level, industry specification level, enterprise process level, etc. For example, in the scenario of an automobile parts production workshop, the multi-level index knowledge base can be a database containing national fire safety standards, automobile industry equipment spacing specifications, and enterprise internal logistics path requirements.

[0106] The first constraint extension information refers to constraint extension content directly corresponding to the keywords of the structured layout constraint information obtained from the multi-level index knowledge base. For example, in the scenario of a mechanical processing workshop, if the keyword of the structured layout constraint information is equipment utilization rate, the first constraint extension information can be direct association information such as CNC machine tool utilization rate ≥ 85% and milling machine maintenance interval ≤ 7 days in the multi-level index knowledge base.

[0107] The embodiment of the application can establish a mapping rule between the keyword and the pre-constructed multi-level index knowledge base, for example, directly associating the keyword fire passage with the index of the fire related level in the multi-level index knowledge base, and associating the equipment utilization rate with the production efficiency related level index in the multi-level index knowledge base. Further, the structured layout constraint information is extracted to obtain constraint core keywords, then the constraint core keywords are queried for corresponding constraint information in the multi-level index knowledge base according to the above mapping rule, and the first constraint extension information is formed.

[0108] In step S302 of some embodiments, the second constraint extension information refers to constraint extension content related to the semantics of the structured layout constraint information obtained from the multi-level index knowledge base. For example, in the medical device production workshop scenario, if the semantics of the structured layout constraint information is to ensure sterile production, the second constraint extension information can be hidden information such as the isolation belt between the sterile area and the non-sterile area in the multi-level index knowledge base being greater than or equal to 3 meters, and the ventilation system air exchange frequency being greater than or equal to 15 times per hour. It should be noted that the second constraint extension information is supplementary information of the first constraint extension information.

[0109] The embodiments of the present application can first perform semantic word segmentation and intent recognition on each piece of structured layout constraint information to obtain the information intent of each piece of structured layout constraint information, and then perform theme similarity matching and scene association matching on each index in the multi-level index knowledge base according to the information intent, so as to find the constraint information in the multi-level index knowledge base that is semantically associated with the structured layout constraint information, i.e., the second constraint extension information.

[0110] In step S303 of some embodiments, by comparing the first constraint extension information and the second constraint extension information, the repeated constraint information is deleted, for example, the first constraint extension information and the second constraint extension information both contain the constraint information that the width of the fire exit is greater than or equal to 1.2 meters, and any one of the constraint information that the width of the fire exit is greater than or equal to 1.2 meters is deleted, and the constraint information that the width of the fire exit is greater than or equal to 1.2 meters is retained. Further, by performing structured processing on the first constraint extension information and the second constraint extension information from which the repeated constraint information is deleted, the structured layout constraint information can be obtained.

[0111] The steps S301 to S303 shown in the embodiments of the present application perform keyword matching on the structured layout constraint information based on the preset multi-level index knowledge base to obtain the first constraint extension information, and perform semantic matching on the structured layout constraint information based on the multi-level index knowledge base to obtain the second constraint extension information, and then perform information merging on the first constraint extension information and the second constraint extension information, which can ensure that the obtained layout constraint set information covers the easy-to-find specification requirements in the multi-level index knowledge base and also covers the difficult-to-find specification requirements in the multi-level index knowledge base, thereby improving the comprehensiveness of the layout constraint set information.

[0112] In step S104 of some embodiments, the workshop layout extension constraint function refers to constraint information represented in the form of a function, for example, in the chemical production workshop scenario, the workshop layout extension constraint function can be a function representation of various constraints such as equipment explosion-proof distance, personnel passage width, and production efficiency index.

[0113] According to the function conversion function of the workshop numerical simulation driving model, the constraint information can be converted according to the classification attribute of each constraint information in the layout constraint set information. For example, for the space constraint device distance >= 2 meters, the workshop numerical simulation driving model can convert it into a geometric distance function ||x1-x2|| >= 2, where x1 and x2 are the horizontal coordinates of the center points of the devices with device labels 1 and 2 in the target workshop, respectively.

[0114] In step S105 of some embodiments, the dynamic workshop simulation model refers to a model that contains constraint rules and optimization objective functions and can simulate multiple scene conditions in actual production, such as device failure and demand fluctuation, and can be directly used for simulation running.

[0115] According to the embodiment of the application, the constraint function of the workshop layout can be extended to update the constraint function contained in the basic mathematical model to obtain a target constraint function, and then the workshop components in the target workshop are modeled and spliced into a static workshop simulation model. Finally, the target constraint function and the target workshop optimization function are embedded in the static workshop simulation model to obtain a dynamic workshop simulation model.

[0116] In detail, please refer to Figure 4 In some embodiments, the basic mathematical model includes a target workshop optimization function and a workshop layout basic constraint function, the target workshop includes workshop components, and step S105 can include but is not limited to steps S401 to S404:

[0117] Step S401, based on the workshop layout extension constraint function, the constraint function of the workshop layout basic constraint function is updated to obtain the target constraint function of the workshop layout;

[0118] Step S402, component modeling is performed on the workshop components to obtain a component simulation model;

[0119] Step S403, model splicing is performed on the component simulation model to obtain a static workshop simulation model;

[0120] Step S404, based on the target constraint function of the workshop layout and the target workshop optimization function, the function embedding is performed on the static workshop simulation model to obtain a dynamic workshop simulation model.

[0121] In step S401 of some embodiments, the target workshop optimization function refers to the function representation of the optimization target of the target workshop.

[0122] The workshop layout basic constraint function refers to a mathematical function that only contains device size, workshop basic space requirements, and other core explicit needs of the workshop layout.

[0123] The workshop components refer to various functional units that constitute the target workshop, such as production equipment, auxiliary facilities, functional areas, etc.

[0124] The workshop layout target constraint function refers to a mathematical function integrating the basic constraint conditions expressed by the workshop layout basic constraint function and the extended constraint conditions expressed by the workshop layout extended constraint function.

[0125] In the embodiment of the present application, by comparing the constraint information represented by the workshop layout basic constraint function and the workshop layout extended constraint function, the constraint function of the constraint information not covered by the workshop layout basic constraint function in the workshop layout extended constraint function is retained, and the retained constraint function is added to the workshop layout basic constraint function, so as to obtain the workshop layout target constraint function.

[0126] In step S402 of some embodiments, the component simulation model refers to a digital model capable of simulating the function and state of the workshop component.

[0127] In the embodiment of the present application, the large language model can be used to convert the mathematical scheme represented by the workshop layout target constraint function into detailed information of each workshop component, such as size, weight, running power, operation space requirement, position information, etc. It needs to be known that the detailed information of the above-mentioned workshop component can be described in a structured JSON format to ensure that the information of the workshop component is organized clearly and orderly, so as to quickly and accurately extract the required information. In addition, using the structured JSON format to describe the detailed information of the workshop component can also ensure the information integrity of the workshop component, thereby improving the accuracy of workshop modeling. Further, after obtaining the JSON format workshop component detailed information, the component simulation model can be obtained by calling the pre-constructed model component library. Specifically, according to the JSON format workshop component detailed information, the component model corresponding to the workshop component, i.e. the component simulation model, can be accurately selected from the model component library.

[0128] In step S403 of some embodiments, the static workshop simulation model refers to a simulation model containing only the spatial layout and basic physical properties of the workshop component, and unable to simulate the dynamic running state of the workshop component. For example, in the textile workshop scenario, the static workshop simulation model can be a digital model that only presents the spatial positions of the loom, the bobbin winder and the finished product stacking area, and is unable to simulate the production flow.

[0129] In the embodiment of the present application, the component simulation models of various workshop components can be connected according to the spatial position relationship and production process logical relationship between the various workshop components in the target workshop, so as to obtain the static workshop simulation model.

[0130] In step S404 of some embodiments, by converting the workshop layout target constraint function into a rule module, and then embedding the rule module into the static workshop simulation model, a workshop simulation constraint model can be obtained. Further, by associating the target workshop optimization function with the evaluation module built in the workshop simulation constraint model, a dynamic workshop simulation model can be obtained.

[0131] The steps S401 to S404 shown in the embodiments of the present application, based on the workshop layout extension constraint function, constrain and update the workshop layout basic constraint function to obtain the workshop layout target constraint function, which not only retains the constraint information represented by the workshop layout basic constraint function, but also supplements the constraint information represented by the workshop layout extension constraint function, solving the problem of incomplete coverage of the workshop layout basic constraint function. On this basis, the component modeling is performed on the workshop components to obtain the component simulation model, and the model splicing is performed on the component simulation model to obtain the static workshop simulation model, avoiding the layout deviation caused by the disconnection between the model and the target workshop. Finally, based on the workshop layout target constraint function and the target workshop optimization function, the function embedding is performed on the static workshop simulation model to obtain the dynamic workshop simulation model, so that the model can be converted from static to dynamic, thereby realizing the real-time calculation of the production efficiency, cost and other optimization indicators of the model, and providing observable numerical indicators for the workshop layout optimization.

[0132] In step S106 of some embodiments, the workshop optimization layout information refers to the scheme information containing the optimal layout of the workshop, wherein the optimal layout of the workshop can include optimal coordinates of equipment, logistics path planning, performance verification report, etc.

[0133] The embodiments of the present application can calculate the candidate feasible solution set of the dynamic workshop simulation model by using an optimization algorithm, and then determine the optimal solution by calculating the performance data of the dynamic workshop simulation model under each candidate feasible solution in the candidate feasible solution set. Finally, according to the optimal solution, the layout information of the target workshop, i.e. the workshop optimization layout information, is determined, wherein the optimization algorithm can be a genetic algorithm, a particle swarm algorithm or an ant colony algorithm, etc.

[0134] In detail, please refer to Figure 5 In some embodiments, the dynamic workshop simulation model includes a workshop layout optimization target function and a workshop layout optimization constraint function, and step S106 can include but is not limited to steps S501 to S505:

[0135] In step S501, based on the workshop layout optimization constraint function, the feasible solution calculation is performed on the workshop layout optimization target function to obtain a candidate feasible solution set, wherein the candidate feasible solution set includes a plurality of candidate feasible solutions.

[0136] In step S502, based on the dynamic workshop simulation model, the simulation processing is performed on the candidate feasible solution to obtain a candidate solution fitness.

[0137] In step S503, the candidate feasible solution set is iteratively updated based on the candidate solution fitness to obtain an updated candidate solution set.

[0138] In step S504, the updated candidate solution set is compared in terms of fitness to obtain an optimal solution of the target function.

[0139] In step S505, the optimal solution of the target function is mapped to the workshop layout to obtain workshop optimization layout information.

[0140] In step S501 of some embodiments, the workshop layout optimization target function refers to a quantitative mathematical function for measuring the optimization effect of the workshop layout, for example, in the electronic assembly workshop scenario, the workshop layout optimization target function can be a composite function of maximizing equipment utilization and minimizing material handling cost.

[0141] The workshop layout optimization constraint function refers to a quantitative mathematical function that defines the boundary conditions of the layout of the target workshop, wherein the layout boundary can be in the dimensions of space, safety, compliance, etc.

[0142] The candidate feasible solution set refers to a set containing multiple layout schemes that satisfy the constraint conditions. It should be noted that the candidate feasible solution set is the initial scheme pool for iterative optimization of the dynamic workshop simulation model.

[0143] The candidate feasible solution refers to a single layout scheme in the candidate feasible solution set. It should be noted that each candidate feasible solution corresponds to a specific workshop component position and regional division scheme.

[0144] In the embodiments of the present application, the quantitative boundary can be determined according to the workshop layout optimization constraint function in the dynamic workshop simulation model, and then a plurality of workshop layout parameters that satisfy the quantitative boundary, i.e., candidate feasible solutions, can be randomly generated according to the selected optimization algorithm. Further, the generated candidate feasible solutions can be integrated to obtain the candidate feasible solution set.

[0145] In step S502 of some embodiments, the candidate solution fitness refers to a quantitative index for measuring the pros and cons of the candidate feasible solution. It should be noted that the higher the candidate solution fitness, the closer the target workshop layout scheme represented by the candidate feasible solution to the optimization target.

[0146] In the embodiments of the present application, the replicated discrete event simulation model is obtained by copying the dynamic workshop simulation model, the performance data is obtained by running the model based on the candidate feasible solution, and finally the candidate solution fitness is obtained by combining the quantitative data of the workshop layout optimization target function.

[0147] In detail, please refer to Figure 6 In some embodiments, step S502 can include but is not limited to steps S601 to S603:

[0148] In step S601, a model replication is performed on the dynamic workshop simulation model to obtain a replicated discrete event simulation model.

[0149] In step S602, a model running process is performed on the replicated discrete event simulation model based on the candidate feasible solution to obtain model performance data.

[0150] In step S603, a quantitative process is performed on the model performance data to obtain a candidate solution fitness.

[0151] In step S601 of some embodiments, the replicated discrete event simulation model refers to a simulation model copy that can be independently used for performance testing of the candidate feasible solution.

[0152] In the embodiments of the present application, the replicated discrete event simulation model that is completely consistent with the dynamic workshop simulation model can be obtained through parameter replication and component replication on the dynamic workshop simulation model.

[0153] In step S602 of some embodiments, the model performance data refers to various data reflecting the performance of the workshop production, such as production capacity and equipment utilization, which are output after the replicated discrete event simulation model is run.

[0154] In the embodiments of the present application, after the workshop layout scheme represented by the candidate feasible solution is input to the replicated discrete event simulation model, the replicated discrete event simulation model can be simulated and run according to the input information. Further, by calculating the production capacity, equipment utilization and other indicators of the running replicated discrete event simulation model, the model performance data can be obtained.

[0155] In step S603 of some embodiments, the fitness value represented by each model performance data can be obtained by mapping each model performance data to the fitness space. Further, according to the weight proportion of each model performance data in the workshop layout optimization objective function, a weighted sum of all fitness values is obtained to obtain the candidate solution fitness.

[0156] The steps S601 to S603 shown in the embodiments of the present application can improve the calculation speed of the candidate solution fitness and the speed of the workshop layout optimization by performing model replication on the dynamic workshop simulation model to obtain a replicated discrete event simulation model, performing a model running process on the replicated discrete event simulation model based on the candidate feasible solution to obtain model performance data, and further performing a quantitative process on the model performance data to obtain a candidate solution fitness.

[0157] In step S503 of some embodiments, updating the candidate solution set refers to containing the newly generated and the retained candidate feasible solution set. It is to be known that the updated candidate solution set has a higher overall fitness than the candidate feasible solution set.

[0158] The embodiment of the present application can determine the adjustment direction of the candidate solution according to the candidate solution fitness, and then adjust the candidate feasible solution set in combination with the preset iteration number and the adjustment direction to obtain the updated candidate solution set.

[0159] In detail, please refer to Figure 7 In some embodiments, step S503 can include but is not limited to steps S701-S702:

[0160] In step S701, the adjustment direction of the candidate solution is determined based on the candidate solution fitness.

[0161] In step S702, the candidate solution adjustment is performed on the candidate feasible solution set based on the preset iteration number and the adjustment direction of the candidate solution to obtain the updated candidate solution set.

[0162] In step S701 of some embodiments, the adjustment direction of the candidate solution refers to the specific direction in which the candidate feasible solution needs to be optimized and improved based on the numerical value of the candidate solution fitness and the performance short board corresponding to the candidate solution fitness, such as insufficient capacity or excessive cost, etc. For example, in the scenario of a mechanical processing workshop, if the candidate solution fitness of a certain candidate feasible solution indicates that the cost is high and the fitness is low due to the long material handling distance, the adjustment direction of the candidate solution of this candidate feasible solution can be to reduce the parameter representing the distance between the numerical control machine tool and the material temporary storage area.

[0163] The embodiment of the present application can determine the performance short board of the candidate feasible solution according to the pre-constructed mapping relationship between the fitness and the performance advantage and disadvantage, and the candidate solution fitness of the candidate feasible solution in each dimension, and further inversely deduce the adjustment direction according to the performance short board to obtain the adjustment direction of the candidate solution.

[0164] In step S702 of some embodiments, the preset iteration number refers to the upper limit of the total number of times of adjusting and optimizing the candidate feasible solution set before optimizing the workshop layout.

[0165] After the adjustment direction of the candidate solution is determined, the embodiment of the present application adjusts the candidate feasible solution set according to the adjustment direction of the candidate solution to obtain the adjusted candidate feasible solution set, and further repeats the above steps S601-S603 on the adjusted candidate feasible solution set until the adjustment number of the candidate feasible solution set reaches the upper limit of the iteration number, and then stops adjusting the candidate feasible solution set to obtain the updated candidate solution set.

[0166] The steps S701 to S702 shown in the embodiments of the present application determine the candidate solution adjustment direction based on the candidate solution fitness, avoid the problem of blind trial and error of the simulation model in the optimal solution solving process, improve the efficiency of the workshop layout optimization, and further, based on the preset iteration number and the candidate solution adjustment direction, the candidate feasible solution set is adjusted to obtain an updated candidate solution set, which avoids the resource waste caused by over-optimization.

[0167] In step S504 of some embodiments, the optimal solution of the objective function refers to the function solution that meets the constraint condition represented by the workshop layout optimization constraint function and has the highest candidate solution fitness.

[0168] The embodiments of the present application can calculate the updated solution fitness by calculating the fitness of all solutions in the updated candidate solution set, further arrange all updated solution fitness in descending order, find the solution with the highest fitness, which is the optimal solution of the objective function. It is known that if there are multiple solutions with the highest and same candidate solution fitness, further compare the performance data of the replicated discrete event simulation model under each solution, and select the solution that is better in the core indicator as the optimal solution of the objective function, wherein the core indicator can be capacity, cost or utilization.

[0169] In step S505 of some embodiments, the running parameters, spatial positions, etc. of each workshop component in the target workshop can be determined according to the optimal solution of the objective function, and then a new workshop layout scheme, i.e. workshop optimization layout information, can be generated according to the running parameters, spatial positions, etc. of each workshop component.

[0170] The steps S501 to S505 shown in the embodiments of the present application calculate the feasible solution of the workshop layout optimization objective function based on the workshop layout optimization constraint function, obtain a candidate feasible solution set, further simulate the candidate feasible solution based on the dynamic workshop simulation model to obtain the candidate solution fitness, solve the problem of subjective ambiguity caused by the traditional workshop modeling process that can only evaluate the workshop performance according to experience, make the optimization of the workshop layout more accurate, and further, based on the candidate solution fitness, the candidate feasible solution set is iteratively updated to obtain an updated candidate solution set, the updated candidate solution set is compared in fitness to obtain the optimal solution of the objective function, and the optimal solution of the objective function is mapped to the workshop layout, so that the obtained workshop optimization layout information is the optimal workshop layout scheme obtained in multiple rounds of verification, and the accuracy of the workshop layout optimization is improved.

[0171] The application can determine the direction of workshop optimization by obtaining the basic mathematical model of the target workshop and the layout optimization demand information. Then, the layout optimization demand information is parsed into structured layout constraint information by using the pre-constructed workshop numerical simulation driving model, and the structured layout constraint information is supplemented to obtain layout constraint set information, so that the layout constraint set information can cover the explicit demand of the user and the implicit index of the industry, thereby ensuring the feasibility of the generated workshop layout scheme. Subsequently, based on the workshop numerical simulation driving model, the layout constraint set information is functionally converted to obtain the workshop layout expansion constraint function, and based on the workshop layout expansion constraint function and the target workshop, the basic mathematical model is optimized to obtain a dynamic workshop simulation model that can simulate multiple scene conditions in actual production, thereby reducing the dependence on manual modeling during the modeling process and improving the efficiency of workshop model construction. Finally, the dynamic workshop simulation model is iteratively optimized to obtain the optimal workshop layout scheme in multiple rounds of verification, thereby improving the accuracy of workshop layout optimization.

[0172] Please refer to Figure 8 The embodiment of the application also provides a workshop layout optimization device based on a vertical model, which can implement the above-mentioned workshop layout optimization method based on a vertical model. The device comprises:

[0173] A basic information acquisition module 801 is configured to acquire a basic mathematical model of a target workshop and acquire layout optimization demand information of the target workshop.

[0174] A demand information analysis module 802 is configured to analyze the layout optimization demand information based on a preset workshop numerical simulation driving model to obtain structured layout constraint information.

[0175] A constraint condition supplementing module 803 is configured to supplement the structured layout constraint information to obtain layout constraint set information.

[0176] A constraint information conversion module 804 is configured to convert the layout constraint set information into a function based on the workshop numerical simulation driving model to obtain a workshop layout expansion constraint function.

[0177] A mathematical model optimization module 805 is configured to optimize the basic mathematical model based on the workshop layout expansion constraint function and the target workshop to obtain a dynamic workshop simulation model.

[0178] A model iterative optimization module 806 is configured to iteratively optimize the dynamic workshop simulation model to obtain workshop optimization layout information.

[0179] The specific embodiments of the workshop layout optimization device based on a vertical model are basically the same as the specific embodiments of the above-mentioned workshop layout optimization method based on a vertical model, and will not be described here again.

[0180] The embodiment of the present application further provides an electronic device, which comprises a memory and a processor, the memory stores a computer program, and the processor executes the computer program to realize the vertical model based workshop layout optimization method. The electronic device can be any intelligent terminal such as a tablet computer or a vehicle-mounted computer.

[0181] Please refer to Figure 9 , Figure 9 The hardware structure of the electronic device of another embodiment is shown, which comprises:

[0182] The processor 901 can be implemented in the form of a general CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, and is used to execute related programs to realize the technical solutions provided by the embodiments of the present application.

[0183] The memory 902 can be implemented in the form of a ROM (ReadOnly Memory), a static storage device, a dynamic storage device, or a RAM (Random Access Memory). The memory 902 can store an operating system and other application programs. When the technical solutions provided by the embodiments of the present application are implemented by software or firmware, the related program codes are stored in the memory 902 and are called and executed by the processor 901 to realize the vertical model based workshop layout optimization method of the embodiments of the present application.

[0184] The input / output interface 903 is used to realize information input and output.

[0185] The communication interface 904 is used to realize the communication interaction between the device and other devices, and can realize communication through a wired manner (for example, a USB, a network cable, etc.) or a wireless manner (for example, a mobile network, WIFI, Bluetooth, etc.).

[0186] The bus 905 is used to transmit information between various components (for example, the processor 901, the memory 902, the input / output interface 903, and the communication interface 904) of the device.

[0187] The processor 901, the memory 902, the input / output interface 903, and the communication interface 904 are connected to each other through the bus 905 to realize communication connection between them in the device.

[0188] The embodiment of the application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the above-mentioned workshop layout optimization method based on a vertical model.

[0189] The memory, as a non-transitory computer readable storage medium, can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory remotely arranged relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0190] The embodiment of the application provides a workshop layout optimization method based on a vertical model, a workshop layout optimization device based on a vertical model, an electronic device and a storage medium. The method comprises the following steps: obtaining a basic mathematical model of a target workshop; obtaining layout optimization demand information of the target workshop; performing information analysis on the layout optimization demand information based on a preset workshop numerical simulation driving model to obtain structured layout constraint information; supplementing constraints on the structured layout constraint information to obtain layout constraint set information; performing function conversion on the layout constraint set information based on the workshop numerical simulation driving model to obtain a workshop layout expansion constraint function; performing model optimization on the basic mathematical model based on the workshop layout expansion constraint function and the target workshop to obtain a dynamic workshop simulation model; and performing cyclic iteration optimization on the dynamic workshop simulation model to obtain workshop optimization layout information.

[0191] The embodiments described in the embodiments of the application are used to more clearly illustrate the technical solutions of the embodiments of the application, and do not constitute a limitation on the technical solutions provided by the embodiments of the application. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the application are also applicable to similar technical problems.

[0192] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the application, and can include more or fewer steps than the figures, or combine certain steps, or different steps.

[0193] The device embodiments described above are only schematic, and the units described as separate components can or can not be physically separate, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments of the application.

[0194] Those skilled in the art can understand that all or some of the steps in the method disclosed above, the function modules / units in the system and the device can be implemented as software, firmware, hardware or appropriate combination thereof.

[0195] The terms "first", "second", "third", "fourth" etc. (if any) in the description of the application and in the claims that follow are used for distinguishing between similar elements and not necessarily for describing a sequential or chronological order. It is to be understood that the use of these terms herein is to be construed to cover the embodiments of the application whether or not the embodiments are described using the same term. Furthermore, the terms "comprise", "comprising", "include", "including", and "has", "having" and variants thereof are to be construed in a non-exclusive manner when used in this description and in the claims that follow. For example, when used in the context of a process, method, system, product or apparatus, the term "comprising" means that the process, method, system, product or apparatus includes the recited steps or units, but can also include additional steps or units not specifically recited.

[0196] It should be understood that, in the present application, "at least one" means one or more, and "multiple" means two or more. "And / or" is used to describe the relationship between associated objects, which means that there can be three relationships, for example, "A and / or B" can mean that there are three cases: only A, only B, and A and B at the same time, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c can mean a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be singular or plural.

[0197] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division, and actual implementation can have another division manner. For example, multiple units or components can be combined or integrated into another system, or some features can be omitted or not implemented. The coupling or direct coupling or communication connection between the shown or discussed objects can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0198] The units described as separate components above can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0199] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0200] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application, essentially or the part that contributes to the prior art, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program storage media.

[0201] The preferred embodiments of the embodiments of the present application are described above with reference to the accompanying drawings, and are not limited to the scope of the embodiments of the present application. Any modifications, equivalent replacements and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of the embodiments of the present application.

Claims

1. A method for optimizing a plant layout based on a vertical model, characterized in that, The method comprises: acquiring a basic mathematical model of a target workshop, and acquiring layout optimization demand information of the target workshop; performing information analysis on the layout optimization demand information based on a preset workshop numerical simulation driving model to obtain structured layout constraint information; performing keyword matching on the structured layout constraint information based on a preset multi-level index knowledge base to obtain first constraint expansion information; performing semantic matching on the structured layout constraint information based on the multi-level index knowledge base to obtain second constraint expansion information; performing information merging on the first constraint expansion information and the second constraint expansion information to obtain layout constraint set information; performing function conversion on the layout constraint set information based on the workshop numerical simulation driving model to obtain a workshop layout expansion constraint function; performing model optimization on the basic mathematical model based on the workshop layout expansion constraint function and the target workshop to obtain a dynamic workshop simulation model, wherein the dynamic workshop simulation model comprises a workshop layout optimization objective function and a workshop layout optimization constraint function; performing feasible solution calculation on the workshop layout optimization objective function based on the workshop layout optimization constraint function to obtain a candidate feasible solution set, wherein the candidate feasible solution set comprises a plurality of candidate feasible solutions; performing simulation processing on the candidate feasible solutions based on the dynamic workshop simulation model to obtain candidate solution fitness; performing iterative updating on the candidate feasible solution set based on the candidate solution fitness to obtain an updated candidate solution set; performing fitness comparison on the updated candidate solution set to obtain an optimal solution of the objective function; performing workshop layout mapping on the optimal solution of the objective function to obtain workshop optimization layout information.

2. The method of claim 1, wherein, The simulation processing on the candidate feasible solutions based on the dynamic workshop simulation model to obtain candidate solution fitness comprises: performing model copying on the dynamic workshop simulation model to obtain a copied discrete event simulation model; performing model running processing on the copied discrete event simulation model based on the candidate feasible solutions to obtain model performance data; performing quantitative processing on the model performance data to obtain the candidate solution fitness.

3. The method of claim 1, wherein, The iterative updating on the candidate feasible solution set based on the candidate solution fitness to obtain an updated candidate solution set comprises: determining a candidate solution adjustment direction based on the candidate solution fitness; performing candidate solution adjustment on the candidate feasible solution set based on a preset number of iterations and the candidate solution adjustment direction to obtain the updated candidate solution set.

4. The method of claim 1, wherein, The basic mathematical model comprises a target workshop optimization function and a workshop layout basic constraint function; the target workshop comprises a workshop component; the model optimization on the basic mathematical model based on the workshop layout expansion constraint function and the target workshop to obtain a dynamic workshop simulation model comprises: performing constraint updating on the workshop layout basic constraint function based on the workshop layout expansion constraint function to obtain a workshop layout target constraint function; performing component modeling on the workshop component to obtain a component simulation model; performing model splicing on the component simulation model to obtain a static workshop simulation model; Based on the workshop layout target constraint function and the target workshop optimization function, function embedding is performed on the static workshop simulation model to obtain the dynamic workshop simulation model.

5. The method according to any one of claims 1 to 4, characterized in that, The information analysis is performed on the layout optimization demand information based on the preset workshop simulation driving model to obtain the structured layout constraint information, which includes: Based on the workshop simulation driving model, key information of the layout optimization demand information is extracted to obtain a constraint object and a quantitative parameter; Based on a preset demand classification dimension, the layout optimization demand information is classified to obtain multi-dimensional constraint information of the workshop layout; Based on the constraint object and the quantitative parameter, the multi-dimensional constraint information of the workshop layout is processed in a structured manner to obtain the structured layout constraint information.

6. A plant layout optimization apparatus based on a vertical model, characterized by, The device comprises: a basic information acquisition module configured to acquire a basic mathematical model of a target workshop and acquire layout optimization demand information of the target workshop; a demand information analysis module configured to perform information analysis on the layout optimization demand information based on a preset workshop simulation driving model to obtain structured layout constraint information; a constraint condition supplementing module configured to perform keyword matching on the structured layout constraint information based on a preset multi-level index knowledge base to obtain first constraint extension information, perform semantic matching on the structured layout constraint information based on the multi-level index knowledge base to obtain second constraint extension information, and perform information merging on the first constraint extension information and the second constraint extension information to obtain layout constraint set information; a constraint information conversion module configured to perform function conversion on the layout constraint set information based on the workshop simulation driving model to obtain a workshop layout extension constraint function; a mathematical model optimization module configured to perform model optimization on the basic mathematical model based on the workshop layout extension constraint function and the target workshop to obtain a dynamic workshop simulation model, wherein the dynamic workshop simulation model comprises a workshop layout optimization target function and a workshop layout optimization constraint function; a model iterative optimization module configured to perform feasible solution calculation on the workshop layout optimization target function based on the workshop layout optimization constraint function to obtain a candidate feasible solution set, wherein the candidate feasible solution set comprises a plurality of candidate feasible solutions, perform simulation processing on the candidate feasible solutions based on the dynamic workshop simulation model to obtain candidate solution fitness, perform iterative updating on the candidate feasible solution set based on the candidate solution fitness to obtain an updated candidate solution set, perform fitness comparison on the updated candidate solution set to obtain a target function optimal solution, and perform workshop layout mapping on the target function optimal solution to obtain workshop optimization layout information.

7. An electronic device, comprising: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the vertical model-based workshop layout optimization method in any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium storing a computer program, the computer-readable storage medium comprising: The computer program is executed by the processor to implement the vertical model-based workshop layout optimization method in any one of claims 1 to 5.

Images