A multi-parameter joint optimization method for sprinkler mold

Abstract

The present invention discloses a multi-parameter joint optimization method for an emitter mold, which relates to the technical field related to the emitter mold. The method comprises: obtaining an emitter mold production instruction; making a multi-node mold production control joint decision according to the emitter mold design plan, and establishing a first space of the mold production control strategy; obtaining a second space of the mold production control strategy; performing variation expansion on the second space of the mold production control strategy, and establishing a third space of the mold production control strategy; introducing a mold production fitness evaluation module to maximize the mold production fitness and generate a mold production control optimization result; and performing emitter mold production control according to the mold production control optimization result. The method solves the technical problems of insufficient parameter optimization, unstable production process, and difficult-to-predict losses in the production process of the emitter mold in the prior art, and achieves the technical effects of improving production stability, reducing losses, and improving production efficiency and mold quality.

Description

Technical Field

[0001] The present application relates to the technical field related to emitter moulds, and in particular to a multi-parameter joint optimization method for emitter moulds. Background Art

[0002] Irrigation mold refers to the mold required for the production of irrigation devices (such as components used to control water flow in automatic irrigation systems). With the popularization of intelligent irrigation systems, the demand for irrigation molds has gradually increased, especially in the fields of gardening, agriculture and family planting. Irrigation molds need to have the characteristics of high precision, strong durability and easy mass production. Irrigation molds not only occupy an important position in the manufacturing industry, but also their design and production process play a key role in improving production efficiency, reducing costs, and improving product quality. Therefore, how to effectively optimize the production process of irrigation molds has become a key issue. However, in the traditional production process of irrigation molds, mold adjustment and production control mainly rely on manual experience and previous design schemes. It is difficult to optimize the various parameters in the production process in real time and accurately, which not only easily leads to instability in the production process, but also difficult to quickly adapt to changing needs when facing complex production tasks, thus affecting the stability of irrigation mold production, product quality and production efficiency.

[0003] At present, relevant technologies still have technical problems such as insufficient parameter optimization during the production of sprinkler molds, unstable production process and unpredictable losses. Summary of the invention

[0004] The present application solves the technical problems of insufficient parameter optimization, unstable production process and unpredictable losses in the production process of the sprinkler mold in the prior art by providing a multi-parameter joint optimization method for the sprinkler mold, thereby achieving the technical effect of improving production stability, reducing losses, and enhancing production efficiency and mold quality.

[0005] The present application provides a multi-parameter joint optimization method for an emitter mold, comprising: obtaining an emitter mold production instruction, wherein the emitter mold production instruction includes an emitter mold design scheme; performing multi-node mold production control joint decision-making according to the emitter mold design scheme to establish a first space of mold production control strategy; performing initial optimization on the first space of mold production control strategy according to an emitter mold loss prediction channel to obtain a second space of mold production control strategy; based on the emitter mold loss prediction channel and according to mold production variation constraint rules, performing variation expansion on the second space of mold production control strategy to establish a third space of mold production control strategy; introducing a mold production fitness evaluation module to perform mold production fitness maximization optimization on the third space of mold production control strategy to generate a mold production control optimization result; based on the emitter mold design scheme, performing emitter mold production control according to the mold production control optimization result.

[0006] In a possible implementation, the multi-parameter joint optimization method for an emitter mold further performs the following processing: disassembling the emitter mold design scheme to obtain Q node mold design information, where Q is a positive integer greater than 1; making production control decisions based on the Q node mold design information to obtain Q node mold production control decision domains; and combining multi-node mold production control decisions based on the Q node mold production control decision domains to obtain the first space of the mold production control strategy.

[0007] In a possible implementation, the multi-parameter joint optimization method for an emitter mold further performs the following processing: extracting the qth node mold design information based on the Q node mold design information, wherein q is a positive integer, 1≤q≤Q; retrieving the emitter mold production control plan based on the qth node mold design information to obtain the qth node mold production plan retrieval set; performing trigger feature analysis based on the qth node mold production plan retrieval set to establish the qth node mold production trigger domain; based on the qth node mold design information, making a production control decision according to the qth node mold production trigger domain to generate the qth node mold production control decision domain; adding the qth node mold production control decision domain to the Q node mold production control decision domains.

[0008] In a possible implementation, the multi-parameter joint optimization method for an emitter mold further performs the following processing: extracting the qth node mold design information based on the Q node mold design information, wherein q is a positive integer, 1≤q≤Q; retrieving the emitter mold production control plan based on the qth node mold design information to obtain the qth node mold production plan retrieval set; performing trigger feature analysis based on the qth node mold production plan retrieval set to establish the qth node mold production trigger domain; based on the qth node mold design information, making a production control decision according to the qth node mold production trigger domain to generate the qth node mold production control decision domain; adding the qth node mold production control decision domain to the Q node mold production control decision domains.

[0009] In a possible implementation, the multi-parameter joint optimization method for an emitter mold further performs the following processing: the emitter mold loss prediction channel includes a mold size loss prediction model, a mold surface defect loss prediction model and a mold performance loss prediction model; the emitter mold design scheme and the first mold production control strategy are input into the mold size loss prediction model to obtain a first mold size loss prediction coefficient; the first mold production control strategy is input into the mold surface defect loss prediction model to obtain a first mold surface defect loss prediction coefficient; the first mold production control strategy is input into the mold performance loss prediction model to obtain a first mold performance loss prediction coefficient; the first mold size loss prediction coefficient, the first mold surface defect loss prediction coefficient and the first mold performance loss prediction coefficient are output as the first mold production loss prediction result.

[0010] In a possible implementation, the multi-parameter joint optimization method for the sprinkler mold further performs the following processing: configuring the variation quantity of the second space of the mold production control strategy according to the mold production variation constraint rule to establish the mold production variation quantity distribution; mutating the second space of the mold production control strategy based on the mold production variation quantity distribution to obtain the mold production strategy variation space; performing optimization analysis on the mold production strategy variation space according to the sprinkler mold loss prediction channel to obtain the mold production strategy variation optimization domain; expanding the second space of the mold production control strategy according to the mold production strategy variation optimization domain to obtain the mold production control strategy third space.

[0011] In a possible implementation, the multi-parameter joint optimization method for the sprinkler mold also performs the following processing: the mold production variation constraint rule includes the basic quantity of mold production strategy variation; extracting the sth mold production control strategy in the second space of the mold production control strategy, where s is a positive integer; loading the sth mold production loss prediction result corresponding to the sth mold production control strategy; performing variation value evaluation on the sth mold production control strategy according to the sth mold production loss prediction result to obtain the sth strategy variation value coefficient; performing incentive adjustment on the basic quantity of mold production strategy variation according to the sth strategy variation value coefficient to generate the sth strategy variation quantity, and adding the sth strategy variation quantity to the mold production variation quantity distribution.

[0012] In a possible implementation, the multi-parameter joint optimization method for an emitter mold further performs the following processing: the mold production fitness evaluation module includes a mold production fitness evaluation function, and the mold production fitness evaluation function is: ;

[0013] Among them, MPF represents the mold production fitness, j represents the predetermined factor for fitness evaluation, 0<j<1, G(DL) represents the normalized mold size loss prediction coefficient, DLW represents the mold size loss predetermined weight, G(QL) represents the normalized mold surface defect loss prediction coefficient, QLW represents the mold surface defect loss predetermined weight, G(KL) represents the normalized mold performance loss prediction coefficient, and KLW represents the mold performance loss predetermined weight.

[0014] Through the multi-parameter joint optimization method for sprinkler mold proposed in this application, the sprinkler mold production instructions are obtained; according to the sprinkler mold design plan, multi-node mold production control joint decision-making is carried out to establish the first space of mold production control strategy; the second space of mold production control strategy is obtained; the second space of mold production control strategy is mutated and expanded to establish the third space of mold production control strategy; the mold production fitness evaluation module is introduced to maximize the mold production fitness and generate the mold production control optimization result; the sprinkler mold production control is carried out according to the mold production control optimization result. The technical problems of insufficient parameter optimization, unstable production process and unpredictable losses in the production process of sprinkler molds in the prior art are solved, and the technical effects of improving production stability, reducing losses, improving production efficiency and mold quality are achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0016] Figure 1 A schematic flow chart of a multi-parameter joint optimization method for an emitter mold provided in an embodiment of the present application;

[0017] Figure 2 A schematic diagram of a flow chart of obtaining a second space of a mold production control strategy in a multi-parameter joint optimization method for an emitter mold provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0019] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0020] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of the objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, product, or server comprising a series of steps is not necessarily limited to those steps clearly listed, but may include other steps that are not clearly listed or inherent to these processes, methods, products, or devices, and unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0021] The present application embodiment provides a multi-parameter joint optimization method for an emitter mold, such as Figure 1As shown, the method includes:

[0022] Step S100, obtaining an emitter mold production instruction, wherein the emitter mold production instruction includes an emitter mold design scheme.

[0023] Preferably, obtaining the production instructions for the sprinkler mold, that is, obtaining the sprinkler mold design plan, includes all the necessary parameters and requirements for producing the sprinkler mold to ensure that the sprinkler mold is produced in accordance with the established design and production specifications. Specifically, the sprinkler mold design plan refers to a complete design plan, including detailed information such as the size, shape, structure, etc. of each component of the mold; selection of manufacturing materials for the mold; process requirements (such as injection molding process, pressure control, temperature control and other technical parameters in the production process); efficiency requirements, production cycle, mold life and other parameters in the production process; quality standards and testing requirements for the final product; optimization strategies or control plans for the production process to ensure the optimization of various parameters (such as pressure, temperature, time, etc.) in the mold production process to achieve the best production effect.

[0024] Step S200: performing a multi-node mold production control joint decision according to the emitter mold design solution to establish a first mold production control strategy space.

[0025] Preferably, in the production process of the sprinkler mold, according to the design scheme and the needs of each production node, the first space of the mold production control strategy is formed through comprehensive analysis and multi-node mold production control joint decision-making. Specifically, various parameters (such as temperature, pressure, time, injection speed, etc.) of multiple links of mold production (such as design, manufacturing, testing, debugging, etc.) are controlled, and coordination and integration decisions are made between various production nodes to ensure the optimal configuration of various process parameters in the mold production process. For example, it is necessary to make joint optimization decisions on multiple process parameters at different production stages to ensure that all links in the production process work together to achieve overall optimization; then the first space of the mold production control strategy is established, that is, all possible combinations of production parameters of various production control strategies set according to the design scheme of the sprinkler mold, including a series of operating parameters such as temperature control, injection speed, pressure, etc., to ensure the stability of the production process and reduce production defects. In this space, the effect and scope of the production control strategy have not been fully optimized, but are only a preliminary feasible range, such as temperature, pressure, injection time, material fluidity, etc. Through the analysis of the design of the sprinkler mold, collaborative decision-making is carried out in multiple production links (nodes) to determine the initial scope of the production control strategy (the first space), which provides a framework for subsequent production optimization and ensures the coordination of each production node.

[0026] Further, step S200 also includes step S210, disassembling the sprinkler mold design scheme to obtain Q node mold design information, where Q is a positive integer greater than 1; step S220, making a production control decision based on the Q node mold design information to obtain Q node mold production control decision domains; step S230, making a multi-node mold production control decision combination based on the Q node mold production control decision domains to obtain the first space of the mold production control strategy.

[0027] Preferably, the complete sprinkler mold design is divided into Q independent design nodes, each node represents an independent part or step in the production process, such as pouring system design, mold cavity design, mold cooling system design, etc. Q is a positive integer greater than 1. By splitting the complex mold design into smaller nodes, it is convenient to analyze and optimize the design of each node independently, and then formulate a production control strategy based on the information of each design node. For example, for the mold cavity design node, the decision content may include the control of injection pressure, and for the cooling system design node, the decision content may involve the optimization of cooling time or temperature distribution, so that Q node mold production control decision is obtained. Domain, that is, determine the feasible range of production control parameters of each node, and finally perform multi-node mold production control decision combination according to Q-node mold production control decision domains, that is, use mathematical modeling or algorithms (such as linear programming, genetic algorithm) to analyze and combine the control decision domains of different nodes, and conduct comprehensive analysis and integration of the production control decision domain of each node, considering the correlation and mutual influence between them, forming multiple production control strategies, and then establishing a preliminary mold production control strategy space, which includes all feasible production control strategy combinations. Each dimension corresponds to a production control parameter (such as pressure, temperature, time, etc.), and each point in the space represents a specific control strategy combination.

[0028] Further, step S220 also includes step S221, extracting the qth node mold design information according to the Q node mold design information, wherein q is a positive integer, 1≤q≤Q; step S222, retrieving the sprinkler mold production control plan according to the qth node mold design information, and obtaining the qth node mold production plan retrieval set; step S223, performing trigger feature analysis according to the qth node mold production plan retrieval set, and establishing the qth node mold production trigger domain; step S224, based on the qth node mold design information, making a production control decision according to the qth node mold production trigger domain, and generating the qth node mold production control decision domain; step S225, adding the qth node mold production control decision domain to the Q node mold production control decision domains.

[0029] Preferably, the specific design information of the qth node is selected and extracted from the complete mold design scheme (including Q nodes of mold design information), wherein q is a positive integer, indicating the node to be processed currently, 1≤q≤Q. For example, the design of the sprinkler mold includes multiple nodes (such as cavity design, runner design, cooling design, etc.), and the qth node may be the "cooling system design", and its specific information may include the location, diameter, fluid flow rate, etc. of the cooling channel; according to the mold design information of the qth node, the key parameters (such as geometric shape, material properties, production goals, etc.) of the qth node design information are matched in the database (historical production data, standard solution library of the mold manufacturing industry, optimization cases of similar designs, etc.), and the production control solutions related thereto are retrieved to generate a solution set (mold production solution retrieval set) , providing a variety of reference production control schemes for the qth node; then the trigger feature analysis of the qth node mold production scheme retrieval set is performed, the core features or key parameters of each scheme in the qth node production scheme retrieval set are analyzed, and the trigger features (i.e., decisive factors) that can affect the production effect are extracted, thereby forming the qth node mold production trigger domain, which is a set of parameter ranges or feature combinations used to guide subsequent production control decisions; then, combined with the design information and trigger domain of the qth node, the core control parameters are optimized and decided, and the qth node production control decision domain is generated, including the range of each production parameter; finally, the separately generated qth node production control decision domain is added to the global production control decision domain set of the entire mold design (Q node mold production control decision domains), thereby realizing the coordinated optimization of the overall mold production control.

[0030] Step S300 , performing initial optimization on the first space of the mold production control strategy according to the emitter mold loss prediction channel to obtain a second space of the mold production control strategy.

[0031] Preferably, in the mold production process, by predicting potential production losses, the initially set production control strategy space (first space) is optimized and adjusted to obtain an optimized control strategy range (second space). Specifically, the sprinkler mold loss prediction channel is used to predict the losses or defects that may occur in the mold production process. The loss prediction channel uses historical data, simulation models, etc. to predict the losses or deviations that may occur under a specific production control strategy, and helps determine the production links that need to be optimized. The sprinkler mold loss may include but is not limited to material waste (excessive use or waste of raw materials in the production process), low production efficiency (too long production cycle, the efficiency of machines or personnel is not optimal), quality problems (products do not meet the predetermined quality standards, resulting in waste or defective products), equipment failure or maintenance problems (production During the production process, equipment aging or failure causes downtime, resulting in production losses); then, based on the first space, by analyzing the results of the loss prediction channel, we begin to look for the optimal control strategy combination, that is, based on the feedback of loss prediction, use some optimization algorithms (such as genetic algorithms, particle swarm optimization, simulated annealing, etc.) to adjust various production parameters, and preliminarily evaluate which parameter combinations may lead to lower production losses, which parameter combinations may improve production efficiency or reduce scrap rates, and then obtain the second space of mold production control strategy. The new control strategy range obtained after preliminary optimization represents the optimized production control strategy under the guidance of the feedback of the loss prediction channel, which may have better production efficiency, lower material waste and higher quality control level, thereby maximizing production efficiency, reducing losses, and ensuring that production quality reaches the expected goals.

[0032] Further, such as Figure 2 As shown, step S300 also includes step S310, extracting the first mold production control strategy according to the first space of the mold production control strategy; step S320, performing mold production loss prediction on the first mold production control strategy based on the sprinkler mold loss prediction channel to obtain a first mold production loss prediction result; step S330, judging whether the first mold production loss prediction result satisfies the mold production loss constraint; step S340, if the first mold production loss prediction result satisfies the mold production loss constraint, adding the first mold production control strategy to the second space of the mold production control strategy; step S350, if the first mold production loss prediction result does not satisfy the mold production loss constraint, eliminating the first mold production control strategy; step S360, taking the mold production loss constraint as the initial optimization target, combining the sprinkler mold loss prediction channel to continue to perform optimization analysis on the first space of the mold production control strategy to generate the second space of the mold production control strategy.

[0033] Preferably, a specific control parameter combination (i.e., the first mold production control strategy) is selected or extracted from the first space of the mold production control strategy for loss prediction and verification, and then the loss prediction channel is used to simulate and evaluate the possible losses in the production process, such as mold size loss (whether the produced mold meets the predetermined size accuracy), mold surface defect loss (whether there are surface defects such as bubbles, cracks, dents, etc.) and mold performance loss (whether the produced mold meets the strength, wear resistance and other performance requirements during use). Through the loss prediction channel, the amount of loss that may be caused by the current first strategy in actual production is evaluated, and a prediction result is generated. The first mold production loss prediction result is compared with the preset mold production loss constraints (including size loss constraints, surface defect loss constraints and performance loss constraints). If the loss prediction result of the current first strategy meets all loss constraints, the current strategy is considered acceptable and included in the second space of mold production control strategy; if the loss prediction result of the current first strategy exceeds any loss constraint, the current strategy is considered unacceptable and is directly eliminated and no longer included in the second space; finally, the mold production loss constraint is used as the optimization target, and the remaining strategies in the first space are further optimized and screened. Combined with the loss prediction channel, the optimization algorithm is used to improve the remaining strategies in the first space to generate a better control strategy. All the screened control strategies that meet the loss constraints are included in the second space to form an optimized control strategy set, and the second space of mold production control strategy is established, thereby improving the efficiency, quality and stability of mold production, while reducing waste and defects in production.

[0034] Further, step S320 also includes step S321, wherein the sprinkler mold loss prediction channel includes a mold size loss prediction model, a mold surface defect loss prediction model and a mold performance loss prediction model; step S322, inputting the sprinkler mold design scheme and the first mold production control strategy into the mold size loss prediction model to obtain a first mold size loss prediction coefficient; step S323, inputting the first mold production control strategy into the mold surface defect loss prediction model to obtain a first mold surface defect loss prediction coefficient; step S324, inputting the first mold production control strategy into the mold performance loss prediction model to obtain a first mold performance loss prediction coefficient; step S325, outputting the first mold size loss prediction coefficient, the first mold surface defect loss prediction coefficient and the first mold performance loss prediction coefficient as the first mold production loss prediction result.

[0035] Preferably, the sprinkler mold loss prediction channel includes multiple prediction models for evaluating various losses that may occur in the mold during the production process, including a mold size loss prediction model, a mold surface defect loss prediction model, and a mold performance loss prediction model, wherein the mold size loss prediction model is used to predict the degree of mold size error or deviation, the mold surface defect loss prediction model is used to predict defects that may appear on the mold surface (such as cracks, bubbles, dents, etc.), and the mold performance loss prediction model is used to predict the performance loss of the mold during use (such as insufficient strength, decreased wear resistance, etc.); then the sprinkler mold design scheme and the first mold production control strategy are input into the mold size loss prediction model, and the first mold size loss prediction coefficient is predicted and output, and the mold performance loss prediction model is used to predict the performance loss of the mold during use. The method is used to measure the possibility and degree of mold size error; the first mold production control strategy is input into the mold surface defect loss prediction model, and the first mold surface defect loss prediction coefficient is predicted and output, which is used to measure the probability or severity of defects that may occur on the mold surface; the first mold production control strategy is then input into the mold performance loss prediction model, and the first mold performance loss prediction coefficient is predicted and output, which is used to evaluate the degree of performance degradation that may occur during the use of the mold; finally, the first mold size loss prediction coefficient, the first mold surface defect loss prediction coefficient and the first mold performance loss prediction coefficient are integrated and output as the first mold production loss prediction result, which is used to judge the overall applicability of the current production control strategy, thereby realizing an efficient and low-loss mold production process.

[0036] Step S400 , based on the emitter mold loss prediction channel and according to mold production variation constraint rules, the second space of the mold production control strategy is mutated and expanded to establish a third space of the mold production control strategy.

[0037] Preferably, on the basis of the production control strategy after preliminary optimization, taking into account the variations (i.e., uncertainties and deviations) that may occur in the production process, the scope of the control strategy is further expanded and optimized to enhance its adaptability and robustness, thereby obtaining a more comprehensive and robust control strategy space, i.e., the third space of mold production control strategy. Specifically, variation constraint rules refer to rules for constraining and controlling variations that may occur in the production process (such as equipment deviations, material non-uniformity, changes in environmental factors, etc.). Variation is an inevitable phenomenon in the production process, which may lead to unstable quality of mold products or reduced production efficiency. For example, variation constraint rules may include the allowable range of equipment operation errors, the allowable range of temperature and pressure fluctuations, and the allowable deviations of material properties. Through these variation constraint rules, it is ensured that even if variations occur in the actual production process, their impact on the production results can be controlled.

[0038] Preferably, the second space of the mold production control strategy is expanded with variations, that is, on the basis of the existing production control strategy space, the possible variations and uncertainties in the production process are further considered, and these variation factors are incorporated into the optimization process, so that the space of the mold production control strategy becomes more extensive and flexible to adapt to various changes and uncertainties in the production process, so that the optimization strategy can not only be effective under ideal conditions, but also maintain good production effects and stability under the influence of variations or uncertainties, such as adjusting the range of control parameters and adding some redundant adjustment space to cope with possible production variations; introducing more robust designs in the strategy space so that even when production conditions change, the optimization strategy can be effectively controlled. When there are changes in the production process, the control strategy can still ensure product quality; enhance tolerance for abnormal situations, take extreme situations into consideration when designing the control strategy, and ensure that even if there are large fluctuations or errors in the production process, they can be adjusted within a controllable range to avoid affecting production quality; finally, the third space of mold production control strategy is obtained. The control strategy in the third space takes into account the uncertainty and variation factors in the production process, so it can maintain high efficiency and stability under different production conditions. It is more flexible than the previous space and can effectively respond to external changes to ensure the smooth progress of the production process, thereby ensuring that in the actual production When faced with uncertainty and variation, it can still maintain high production efficiency and quality.

[0039] Furthermore, step S400 also includes step S410, configuring the variation quantity of the second space of the mold production control strategy according to the mold production variation constraint rule, and establishing the mold production variation quantity distribution; step S420, mutating the second space of the mold production control strategy based on the mold production variation quantity distribution, and obtaining the mold production strategy variation space; step S430, performing optimization analysis on the mold production strategy variation space according to the sprinkler mold loss prediction channel, and obtaining the mold production strategy variation optimization domain; step S440, expanding the second space of the mold production control strategy according to the mold production strategy variation optimization domain, and obtaining the third space of the mold production control strategy.

[0040] Preferably, according to the mold production variation constraint rule, the variation quantity of each control strategy parameter in the second space of the mold production control strategy is allocated to form a variation quantity distribution, that is, the variation range and quantity of each parameter are counted, and then the mold production variation quantity distribution is established, and then according to the mold production variation quantity distribution, the control strategy in the second space of the mold production control strategy is expanded and modified according to the variation constraint rule to generate a space containing new strategies after variation, for example, using random variation to randomly generate parameters within a specified variation range; using rule variation to generate a set of variation parameters according to a fixed step size or ratio; thereby constructing a more flexible and comprehensive strategy set (variation space) to adapt to possible uncertainties in production; and then using the sprinkler mold loss prediction channel pair The optimization analysis of the mold production strategy variation space is carried out, that is, prediction models such as mold size, surface defects, and performance loss are used to evaluate each strategy in the variation space, calculate its loss coefficient, and analyze the loss coefficient through the optimization algorithm to screen out strategies that meet the loss constraints or minimize the loss, thereby screening out a group of best variation strategies to form the mold production strategy variation optimization domain; finally, the preferred strategies in the variation optimization domain are added to the second space of the mold production control strategy to generate the third space of the mold production control strategy, which includes both the strategies that have been initially optimized (the second space) and the preferred strategies after variation optimization. It can effectively deal with the uncertainty in production, ensure the applicability and stability of the production control strategy, and provide solid technical support for the production of high-quality sprinkler molds.

[0041] Further, step S410 also includes step S411, wherein the mold production variation constraint rule includes a basic quantity of mold production strategy variation; step S412, extracting the sth mold production control strategy within the second space of the mold production control strategy, wherein s is a positive integer; step S413, loading the sth mold production loss prediction result corresponding to the sth mold production control strategy; step S414, performing variation value evaluation on the sth mold production control strategy according to the sth mold production loss prediction result to obtain the sth strategy variation value coefficient; step S415, performing incentive adjustment on the basic quantity of mold production strategy variation according to the sth strategy variation value coefficient to generate the sth strategy variation quantity, and adding the sth strategy variation quantity to the mold production variation quantity distribution.

[0042] Preferably, in the process of mold production optimization, based on the variation constraint rules and loss prediction results, the variation value of the specific production control strategy (the sth strategy) is evaluated, and by adjusting the variation base number, its variation range and frequency are dynamically adjusted, and finally the variation number is generated and added to the variation number distribution. Specifically, the mold production variation constraint rules include the variation base number of the mold production strategy, which represents the initial variation number acceptable for each control strategy under the default condition, and then the mold production control sth strategy in the second space of the mold production control strategy is extracted, and then the mold production loss prediction result of the sth mold corresponding to the mold production control sth strategy is loaded through the sprinkler mold loss prediction channel (including size, surface defect, and performance loss model) to reflect the potential loss of the current production strategy, and then the variation value of the sth strategy is evaluated according to the sth mold production loss prediction result, that is, based on the loss prediction result of the sth strategy. , evaluate the value of its variation. If the loss of the current strategy is small, the variation may bring limited optimization space, and the variation value coefficient is low. If the loss of the current strategy is large, it means that there is a large optimization space, and the variation value coefficient is high. According to the loss prediction results, different types of losses are comprehensively evaluated in combination with weights to calculate their variation value coefficients; finally, according to the variation value coefficient of the sth strategy, the basic number of variations of the mold production strategy is incentivized and adjusted, that is, the basic number of variations of the sth strategy is dynamically adjusted according to the variation value coefficient, so as to generate a new number of variations. If the variation value coefficient is high, it means that the current strategy has great optimization potential, and the number of variations is increased to explore more possibilities. If the variation value coefficient is low, the number of variations is reduced to avoid unnecessary exploration, and then the specific number of variations of the sth strategy is obtained, and added to the distribution of the number of mold production variations to ensure efficient and accurate exploration of the optimal production control strategy.

[0043] Step S500, introducing a mold production fitness evaluation module to optimize the mold production fitness maximization of the third space of the mold production control strategy, and generating a mold production control optimization result.

[0044] Preferably, the mold production fitness evaluation module is used to maximize the mold production fitness of the mold production control strategy in the third space, that is, to measure the effects of different production control strategies, so as to find the optimal production plan in the control strategy space as the mold production control optimization result, wherein the mold production fitness evaluation module is used to evaluate the effect of the production control strategy, and usually evaluates the effect of the production process according to some indicators, including but not limited to production efficiency, product quality, production cost, production stability and resource utilization. The mold production fitness evaluation module quantifies these indicators and provides a fitness value for each control strategy to reflect the effect of the strategy in production. Specifically, in the third space, the fitness evaluation module is used to score different production control strategies. And find the optimal control strategy through optimization algorithms (such as genetic algorithms, particle swarm optimization, simulated annealing, etc.). The optimization goal is to maximize the fitness value (among all possible control strategies, find the solution that optimizes various indicators such as production efficiency, product quality, and cost), and consider the balance of multiple goals (such as quality, cost, and efficiency) at the same time to find the best overall production plan, that is, to generate the control strategy that best suits the current production environment and conditions as the mold production control optimization result, such as the optimal control parameters, such as temperature, pressure, injection speed, etc. The optimization plan includes optimization suggestions on process flow adjustment, production equipment configuration, etc., which not only improves production efficiency and quality, but also provides a precise and executable control plan for the production process, ensuring the optimal effect of mold production.

[0045] Furthermore, step S500 further includes that the mold production fitness evaluation module includes a mold production fitness evaluation function, and the mold production fitness evaluation function is: ;

[0046] Among them, MPF represents the mold production fitness, j represents the fitness evaluation predetermined factor, 0<j<1, G(DL) represents the normalized mold size loss prediction coefficient, DLW represents the mold size loss predetermined weight, G(QL) represents the normalized mold surface defect loss prediction coefficient, QLW represents the mold surface defect loss predetermined weight, G(KL) represents the normalized mold performance loss prediction coefficient, KLW represents the mold performance loss predetermined weight. The mold production fitness evaluation function is used to integrate multiple key indicators (dimensional accuracy, surface quality, performance) in mold production into a fitness value (MPF), providing a quantitative evaluation of the comprehensive performance of the production strategy. MPF represents the mold production fitness and represents the comprehensive performance value of the current mold production control strategy in the fitness evaluation. The larger the value, the better the current strategy. Among them, the mold size loss prediction coefficient is used to indicate the influence of mold size deviation on production adaptability. It is calculated through mold historical production data, mold size measurement data and manufacturing tolerance data. If the mold size deviation is small, the mold size loss prediction coefficient is small, indicating that the influence of size loss on fitness is small. On the contrary, when the size deviation is large, the mold size loss prediction coefficient increases, indicating that the influence of size loss on fitness increases. The mold surface defect loss prediction coefficient is used to indicate the production fitness loss caused by mold surface defects (such as scratches, wear, corrosion, etc.). Through the detection, classification and quantification of mold surface defects, combined with the frequency and severity of surface defects, the mold size loss prediction coefficient is used to indicate the production fitness loss caused by mold surface defects (such as scratches, wear, corrosion, etc.). The severity of the defects is obtained by, for example, using image processing technology, surface scanning detection, etc. to evaluate the mold surface, and calculating the mold surface defect loss prediction coefficient based on the size and number of defects detected; the mold performance loss prediction coefficient reflects the loss of the mold caused by performance degradation (such as wear, fatigue, thermal cracking, etc.), and its performance degradation is usually manifested as a decrease in mold hardness, loss of precision, fatigue fracture, etc., and is calculated through the mold's service life, load conditions, physical properties of the mold material (such as hardness, toughness, etc.) and historical usage data. For example, accelerated aging test experiments (such as high temperature, high pressure, etc.) are used to evaluate the long-term changes in mold performance, and then the mold performance loss prediction coefficient is calculated.

[0047] Step S600: Based on the emitter mold design solution, emitter mold production control is performed according to the mold production control optimization result.

[0048] Preferably, in the production process of the sprinkler mold, by combining the design scheme and the optimized production control strategy, the actual production process is accurately guided to achieve high-quality and efficient mold manufacturing. Specifically, the production parameters (such as pressure, temperature, time, etc.) in the optimization results are input into the production equipment, and the specific operating parameters of the injection molding machine, cooling system, etc. are configured. During the mold manufacturing process, the parameters such as pressure fluctuations and temperature distribution are monitored in real time, and the equipment operation is adjusted according to the optimization parameters to ensure that the production process complies with the optimization plan. The quality of the produced molds (such as dimensional accuracy, surface quality, etc.) is inspected. If the actual results deviate from the target, the production control parameters are further adjusted. By combining the mold design scheme and the optimization results, high-quality mold production is achieved, production time and resource consumption are reduced, production efficiency is improved, material waste, defective rate and equipment failure are reduced, and the overall production cost is reduced. It can also cope with uncertainties in production and reduce fluctuations, thereby realizing an efficient and intelligent mold production process.

[0049] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A multi-parameter joint optimization method for an emitter mold, characterized in that: The method comprises: Obtaining an emitter mold production instruction, wherein the emitter mold production instruction includes an emitter mold design scheme; According to the sprinkler mold design scheme, a multi-node mold production control joint decision is made to establish a first mold production control strategy space; Performing initial optimization on the first space of the mold production control strategy according to the prediction channel of the mold loss of the sprinkler to obtain the second space of the mold production control strategy; Based on the emitter mold loss prediction channel and according to the mold production variation constraint rules, the second space of the mold production control strategy is mutated and expanded to establish the third space of the mold production control strategy; Introducing a mold production fitness evaluation module to maximize the mold production fitness of the mold production control strategy in the third space, and generating a mold production control optimization result; Based on the design scheme of the sprinkler mold, the production control of the sprinkler mold is performed according to the optimization result of the mold production control; The injector mold loss prediction channel includes a mold size loss prediction model, a mold surface defect loss prediction model and a mold performance loss prediction model.

2. A multi-parameter joint optimization method for an emitter mold as claimed in claim 1, characterized in that: According to the injector mold design scheme, a multi-node mold production control joint decision is made to establish the first mold production control strategy space, including: Disassemble the emitter mold design scheme to obtain Q node mold design information, where Q is a positive integer greater than 1; Making a production control decision based on the Q node mold design information to obtain the Q node mold production control decision domain; A multi-node mold production control decision combination is performed according to the Q-node mold production control decision domains to obtain the first space of the mold production control strategy.

3. A multi-parameter joint optimization method for an emitter mold as claimed in claim 2, characterized in that: A production control decision is made according to the Q node mold design information to obtain the Q node mold production control decision domain, including: Extracting the qth node mold design information according to the Q node mold design information, wherein q is a positive integer, 1≤q≤Q; Retrieve the production control plan of the sprinkler mold according to the qth node mold design information to obtain a qth node mold production plan retrieval set; Perform trigger feature analysis according to the qth node mold production plan retrieval set to establish the qth node mold production trigger domain; Based on the qth node mold design information, a production control decision is made according to the qth node mold production trigger domain to generate a qth node mold production control decision domain; The q-th node mold production control decision domain is added to the Q node mold production control decision domains.

4. A multi-parameter joint optimization method for an emitter mold as claimed in claim 1, characterized in that: The first space of the mold production control strategy is initially optimized according to the injection mold loss prediction channel to obtain the second space of the mold production control strategy, including: Extracting a first mold production control strategy according to the first mold production control strategy space; Based on the emitter mold loss prediction channel, the mold production loss prediction is performed on the first mold production control strategy to obtain a first mold production loss prediction result; Determining whether the first mold production loss prediction result meets the mold production loss constraint; If the first mold production loss prediction result satisfies the mold production loss constraint, adding the first mold production control strategy to the second mold production control strategy space; If the first mold production loss prediction result does not meet the mold production loss constraint, eliminating the first mold production control strategy; The mold production loss constraint is used as the initial optimization target, and the first space of the mold production control strategy is continuously optimized and analyzed in combination with the emitter mold loss prediction channel to generate the second space of the mold production control strategy.

5. A multi-parameter joint optimization method for an emitter mold as claimed in claim 4, characterized in that: Based on the emitter mold loss prediction channel, the mold production loss prediction is performed on the first mold production control strategy to obtain a first mold production loss prediction result, including: The injector mold loss prediction channel includes a mold size loss prediction model, a mold surface defect loss prediction model and a mold performance loss prediction model; Inputting the emitter mold design scheme and the first mold production control strategy into the mold size loss prediction model to obtain a first mold size loss prediction coefficient; Inputting the first mold production control strategy into the mold surface defect loss prediction model to obtain a first mold surface defect loss prediction coefficient; Inputting the first mold production control strategy into the mold performance loss prediction model to obtain a first mold performance loss prediction coefficient; The first mold size loss prediction coefficient, the first mold surface defect loss prediction coefficient and the first mold performance loss prediction coefficient are output as the first mold production loss prediction result.

6. A multi-parameter joint optimization method for an emitter mold as claimed in claim 1, characterized in that: Based on the emitter mold loss prediction channel and according to the mold production variation constraint rules, the second space of the mold production control strategy is mutated and expanded to establish the third space of the mold production control strategy, including: According to the mold production variation constraint rule, the second space of the mold production control strategy is configured with variation quantity to establish the mold production variation quantity distribution; Based on the mold production variation quantity distribution, mutate the second space of the mold production control strategy to obtain the mold production strategy variation space; Performing optimization analysis on the mold production strategy variation space according to the emitter mold loss prediction channel to obtain the mold production strategy variation optimization domain; The second space of the mold production control strategy is expanded according to the mold production strategy variation optimization domain to obtain the third space of the mold production control strategy.

7. A multi-parameter joint optimization method for an emitter mold as claimed in claim 6, characterized in that: According to the mold production variation constraint rule, the second space of the mold production control strategy is configured with variation quantity to establish the mold production variation quantity distribution, including: The mold production variation constraint rules include the mold production strategy variation base quantity; Extracting the s-th mold production control strategy in the second space of the mold production control strategy, where s is a positive integer; Loading the s-th mold production loss prediction result corresponding to the s-th mold production control strategy; According to the prediction result of the production loss of the sth mold, the variation value of the sth strategy of the mold production control is evaluated to obtain the variation value coefficient of the sth strategy; The basic quantity of the mold production strategy variation is incentivized and adjusted according to the sth strategy variation value coefficient to generate the sth strategy variation quantity, and the sth strategy variation quantity is added to the mold production variation quantity distribution.

8. The multi-parameter joint optimization method for an emitter mold according to claim 1, characterized in that: The mold production fitness evaluation module includes a mold production fitness evaluation function, and the mold production fitness evaluation function is: ； Among them, MPF represents the mold production fitness, j represents the predetermined factor for fitness evaluation, 0<j<1, G(DL) represents the normalized mold size loss prediction coefficient, DLW represents the mold size loss predetermined weight, G(QL) represents the normalized mold surface defect loss prediction coefficient, QLW represents the mold surface defect loss predetermined weight, G(KL) represents the normalized mold performance loss prediction coefficient, and KLW represents the mold performance loss predetermined weight.

Images