Process parameter recommendation method and device based on industrial big data, equipment and medium
Through the process parameter recommendation method based on industrial big data, combined with injection molding machines, molds and environmental information, the prediction model and particle swarm optimization algorithm are used to determine the optimal process parameters for injection molding products, and the energy consumption waste caused by unreasonable parameters is solved. Quality issues have achieved reduced energy consumption and improved production efficiency.
Patent Information
- Application Number
- CN202411388417.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-08
- Publication Date
- 2024-11-05
AI Technical Summary
In the production process of injection molded products, unreasonable process parameter settings lead to waste of energy consumption and product quality problems, reducing production efficiency.
The process parameter recommendation method based on industrial big data, by generating preset process parameter groups, combining injection molding machines, molds and environmental information, using quality models, cycle models and energy consumption models for prediction, and using particle swarm optimization algorithm to determine the optimal process parameters , to reduce energy consumption and improve product quality.
Significantly reduce energy consumption in the production process of injection molded products, improve production efficiency and product quality, optimize production cycle and energy consumption management, is suitable for a variety of production environments and needs, and reduce production costs.
Smart Images

Figure CN118893799A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of injection molding technology, and in particular to a method, device, equipment and medium for recommending process parameters based on industrial big data. Background Art
[0002] Injection molding machines are important equipment in the plastic processing industry. They inject molten plastic into molds under high pressure and form the desired products after cooling. In the production process of injection molded products, the energy consumption of injection molding machines is mainly concentrated in power drive, heating system and cooling system.
[0003] Since the injection molding process is complex and the production process of the product involves multiple stages and the control of different process parameters, and the process parameters directly affect energy consumption, energy utilization efficiency, product quality and production efficiency during the injection molding process, unreasonable process parameter settings often lead to energy waste and may cause product quality problems such as flash, burning, etc., and reduce production efficiency. Summary of the invention
[0004] The present application provides a process parameter recommendation method, device, equipment and medium based on industrial big data, which is used to solve the technical problem that in the production process of injection molding products, unreasonable process parameter settings often lead to energy waste and may cause product quality problems, thereby reducing production efficiency.
[0005] In a first aspect, the present application provides a process parameter recommendation method based on industrial big data, comprising: Based on the injection molding machine information and the mold information, generating a preset number of groups of first process parameters for production using the injection molding machine and the mold; For each group of the first process parameters, determining a quality prediction result corresponding to the first process parameters based on the first process parameters, the injection molding machine information, the mold information, and the environmental information, wherein the quality prediction result includes a qualified or unqualified result; For each set of second process parameters whose quality prediction result is qualified among the preset number of sets of first process parameters, determine the production cycle prediction value and production energy consumption prediction value of a single product based on the second process parameters, the injection molding machine information, the mold information and the environmental information; Based on the production cycle prediction value and production energy consumption prediction value of a single product corresponding to each group of the second process parameters, the second process parameters that minimize the production cycle and production energy consumption of the target number of products are determined as recommended process parameters.
[0006] Optionally, determining the quality prediction result corresponding to the first process parameter based on the first process parameter, the injection molding machine information, the mold information, and the environmental information includes: The first process parameter, the injection molding machine information, the mold information and the environmental information are input into a pre-trained quality model to obtain a quality prediction result corresponding to the first process parameter, wherein the quality model is trained based on historical process parameters, historical quality results and historical environmental information of the injection molding machine and the mold in historical production processes.
[0007] Optionally, determining a production cycle prediction value and a production energy consumption prediction value of a single product based on the second process parameter, the injection molding machine information, the mold information, and the environmental information includes: Inputting the second process parameter, the injection molding machine information, the mold information and the environmental information into a pre-trained cycle model to obtain a production cycle prediction value of a single product corresponding to the second process parameter, wherein the cycle model is trained based on historical process parameters, historical production cycles and historical environmental information of the injection molding machine and the mold in historical production processes; The second process parameters, the injection molding machine information, the mold information and the environmental information are input into a pre-trained energy consumption model to obtain a production energy consumption prediction value of a single product corresponding to the second process parameters, wherein the energy consumption model is trained based on historical process parameters, historical energy consumption and historical environmental information of the injection molding machine and the mold in historical production processes.
[0008] Optionally, the determining, based on the production cycle prediction value and the production energy consumption prediction value of the single product corresponding to each group of the second process parameters, the second process parameters that minimize the production cycle and the production energy consumption of the target number of products as the recommended process parameters includes: Determine a fitness function based on the predicted value of the production cycle and the predicted value of the production energy consumption of the target number of products, and use a particle swarm optimization algorithm to determine, based on the fitness function value corresponding to each group of the second process parameters, the second process parameters that minimize the production cycle and production energy consumption of generating the target number of products as recommended process parameters.
[0009] Optionally, the generating, based on the injection molding machine information and the mold information, a preset number of groups of first process parameters for production using the injection molding machine and the mold includes: Based on the injection molding machine information and the mold information, historical process parameters of the injection molding machine and the mold in a historical production process are acquired, and based on the historical process parameters, a numerical range of the process parameters is determined; Based on the value range of the process parameter, a preset number of groups of the first process parameter are randomly generated.
[0010] Optionally, the generating, based on the injection molding machine information and the mold information, a preset number of groups of first process parameters for production using the injection molding machine and the mold includes: In response to the injection molding machine information, the mold information and the environment information received by the application interface, a preset number of groups of first process parameters for production using the injection molding machine and the mold are generated.
[0011] Optionally, before responding to the injection molding machine information, mold information, and environment information received by the application interface, the method further includes: A process parameter recommendation request input by a user is obtained, the injection molding machine information, mold information and environment information in the process parameter recommendation request are determined using a large language model, and the application interface is called through the large language model.
[0012] In a second aspect, the present application provides a process parameter recommendation device based on industrial big data, comprising: The processing module is used to generate a preset number of groups of first process parameters for production using the injection molding machine and the mold based on the injection molding machine information and the mold information.
[0013] A determination module is used to determine, for each group of the first process parameters, a quality prediction result corresponding to the first process parameters based on the first process parameters, the injection molding machine information, the mold information and the environmental information, wherein the quality prediction result includes qualified or unqualified.
[0014] The determination module is also used to determine the production cycle prediction value and production energy consumption prediction value of a single product based on the second process parameters, the injection molding machine information, the mold information and the environmental information for each group of second process parameters whose quality prediction results are qualified in a preset number of groups of first process parameters.
[0015] The determination module is also used to determine as the recommended process parameters the second process parameters that minimize the production cycle and production energy consumption of the target number of products based on the production cycle prediction value and production energy consumption prediction value of the single product corresponding to each group of the second process parameters.
[0016] Optionally, the processing module is also used to input the first process parameter, the injection molding machine information, the mold information and the environmental information into a pre-trained quality model to obtain a quality prediction result corresponding to the first process parameter, wherein the quality model is trained based on historical process parameters, historical quality results and historical environmental information of the injection molding machine and the mold in the historical production process.
[0017] Optionally, the processing module is also used to input the second process parameters, the injection molding machine information, the mold information and the environmental information into a pre-trained cycle model to obtain a production cycle prediction value of a single product corresponding to the second process parameters, wherein the cycle model is trained based on historical process parameters, historical production cycles and historical environmental information of the injection molding machine and the mold in historical production processes.
[0018] The processing module is also used to input the second process parameters, the injection molding machine information, the mold information and the environmental information into a pre-trained energy consumption model to obtain a production energy consumption forecast value of a single product corresponding to the second process parameters, wherein the energy consumption model is trained based on historical process parameters, historical energy consumption and historical environmental information of the injection molding machine and the mold in historical production processes.
[0019] Optionally, the determination module is also used to determine a fitness function based on the predicted value of the production cycle and the predicted value of the production energy consumption of a target number of products, and to use a particle swarm optimization algorithm to determine, based on the fitness function values corresponding to each group of the second process parameters, the second process parameters that minimize the production cycle and production energy consumption for generating the target number of products as recommended process parameters.
[0020] Optionally, the process parameter recommendation device also includes: an acquisition module.
[0021] The acquisition module is used to acquire historical process parameters of the injection molding machine and the mold in the historical production process based on the injection molding machine information and the mold information.
[0022] The determination module is further used to determine the value range of the process parameter based on the historical process parameter.
[0023] The processing module is further configured to randomly generate a preset number of groups of the first process parameters based on a numerical range of the process parameters.
[0024] Optionally, the processing module is further used to generate a preset number of groups of first process parameters for production using the injection molding machine and the mold in response to the injection molding machine information, mold information and environmental information received by the application interface.
[0025] Optionally, the acquisition module is also used to obtain a process parameter recommendation request input by a user.
[0026] The determination module is also used to use a large language model to determine the injection molding machine information, mold information and environment information in the process parameter recommendation request.
[0027] The processing module is further used to call the application interface through the large language model.
[0028] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the process parameter recommendation method based on industrial big data as described in the above-mentioned first aspect and various possible implementation methods of the first aspect.
[0029] In a fourth aspect, the present application provides a computer-readable storage medium having computer execution instructions stored thereon, which, when executed by a processor, are used to implement a process parameter recommendation method based on industrial big data as described in the above-mentioned first aspect and various possible implementation methods of the first aspect.
[0030] In a fifth aspect, the present application provides a program product, including a computer program, which, when executed by a processor, implements the process parameter recommendation method based on industrial big data as described above.
[0031] The process parameter recommendation method, device, equipment and medium based on industrial big data provided in the present application generate a preset number of groups of first process parameters when the injection molding machine and the mold are used for production by determining the injection molding machine information and the mold information used at the time; for each group of first process parameters, the first process parameters, the injection molding machine information, the mold information and the environmental information are input into a pre-trained quality model to obtain the corresponding quality prediction result, and the first process parameter with a qualified quality prediction result is determined as the second process parameter; then multiple second process parameters, the injection molding machine information, the mold information and the environmental information are input into a pre-trained cycle model to obtain the production cycle prediction value of a single product corresponding to each second process parameter; determine the fitness function based on the production cycle prediction value and the production energy consumption prediction value of a target number of products, and use a particle swarm optimization algorithm to determine the second process parameters that minimize the production cycle and production energy consumption of the target number of products based on the fitness function value corresponding to each group of second process parameters as the recommended process parameters. This method significantly reduces energy consumption in the production process of injection molding products, improves product production efficiency and quality, optimizes the production cycle and energy consumption management of injection molding products, dynamically generates process parameters based on the production conditions of different injection molding products, is suitable for a variety of production environments and needs, and reduces production costs. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0033] Figure 1Schematic diagram of the process parameter recommendation method based on industrial big data provided for this application Figure 1 ; Figure 2 Schematic diagram of the process parameter recommendation method based on industrial big data provided for this application Figure 2 ; Figure 3 A schematic diagram of the structure of a process parameter recommendation device based on industrial big data provided in this application; Figure 4 A schematic diagram of the structure of the process parameter recommendation equipment based on industrial big data provided in this application.
[0034] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0035] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0036] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein, for example.
[0037] In the embodiments of the present application, the words "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.
[0038] Therefore, the present application proposes a big data cloud platform provided with a process parameter recommendation module, which can automatically recommend process parameters that can be used in the production process of different injection molding products for users. For example, a big data cloud platform provided with a process parameter recommendation module can obtain industrial big data related to injection molding products in real time, including the operation data of multiple injection molding machines, and analyze and process the operation data to determine the type of injection molding machine and mold type used in the current injection molding process; the quality model, cycle model and energy consumption model in the process parameter recommendation module are used to simulate the product quality and energy consumption under different process parameter operation conditions, and then combined with the production quantity of the current product, the process parameters with the best energy consumption are selected from the simulation results, so as to reduce the energy waste in the current production process and improve the production efficiency of injection molding products; wherein, the big data cloud platform is composed of a data lake, data processing, data services, and data governance, so as to realize unified data management and calculation, open up data supply channels, and ensure data security and controllability.
[0039] It can be understood that industrial big data refers to a large, high-speed, and diverse data set generated during the industrial production process. In other words, various data information during the production process of injection molding products can be obtained through the big data cloud platform, that is, the corresponding industrial big data can be obtained. The following embodiment takes the industrial big data including injection molding machine information, mold information, and environmental information as an example for specific explanation. This application does not impose any special restrictions on the data types contained in industrial big data.
[0040] The present application provides a method for recommending process parameters based on industrial big data, based on a big data cloud platform, by collecting industrial big data of energy consumption, cycle, process parameters, temperature, and humidity during the generation process of an injection molding machine, and combining a variety of arbitrary combinations of injection molding machines and molds corresponding to industrial big data, training a quality model that can predict product quality, a cycle model that predicts the product production cycle, and an energy consumption model that predicts the energy consumption of product production; real-time acquisition of the type of injection molding machine and mold type used before product production, using the quality model, cycle model, and energy consumption model to predict product quality, production cycle, and production energy consumption, and obtain multiple process parameters; combined with the production quantity of the current product, a particle swarm optimization algorithm is used to determine the optimal process parameters. This method significantly reduces the energy consumption in the production process of injection molding products, improves the production efficiency and quality of products, optimizes the production cycle and energy consumption management of injection molding products, dynamically generates process parameters based on the production conditions of different injection molding products, is suitable for a variety of production environments and needs, and reduces production costs.
[0041] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.
[0042] Figure 1 Schematic diagram of the process parameter recommendation method based on industrial big data provided in the embodiment of the present application Figure 1 The execution subject of this embodiment may be, for example, a big data cloud platform provided with a process parameter recommendation module. Figure 1 As shown, the process parameter recommendation method based on industrial big data provided in this embodiment includes: S101: Based on the injection molding machine information and the mold information, generate a preset number of groups of first process parameters for production using the injection molding machine and the mold.
[0043] Among them, the injection molding machine information is used to indicate the data set related to the injection molding machine equipment itself and its operating status. The mold information includes: the structure, size, and type and model of the mold; the process parameters are used to indicate the specific operating conditions and control standards of the injection molding machine during the production process of injection molded products; the first process parameter is used to indicate multiple specific process parameter values corresponding to any process parameter combination, and the preset number of groups can be 500 groups, for example.
[0044] It can be understood that the executor of this step is the big data cloud platform, and the big data cloud platform can obtain the operating data of different injection molding machine and mold combinations in the injection molding product production process, that is, obtain industrial big data related to injection molding products, and the industrial big data includes injection molding machine information and mold information; because different injection molding machine and mold combinations can produce various types of injection molding products, and the same mold uses different injection molding machines to produce corresponding injection molding products. When the process parameters used will be different, therefore, according to the injection molding machine model and mold model used at the time, the type of process parameters used in the production process of the injection molding product can be determined.
[0045] The first process parameter is a preset number of groups of specific and operational process parameter values generated based on a specific injection molding machine model and mold model, combined with the corresponding process parameter type and value range; that is, the first process parameter is a plurality of groups of process parameter combinations with certain values generated on the basis of determining the process parameter type required for the production of the injection molding product at that time, combined with the value range of the corresponding process parameter, thereby obtaining a plurality of groups of first process parameters; the obtained preset number of groups of process parameter values are used to guide how the injection molding machine and the mold are specifically operated and controlled during the production process, so as to ensure the production of injection molding products that meet the requirements.
[0046] According to the injection molding machine model and mold model corresponding to the injection molding machine information and mold information obtained this time, determine the type and quantity of process parameters used, as well as the possible value range of the corresponding process parameters; within the value range corresponding to different process parameters, generate a preset number of groups of first process parameters when using the injection molding machine and mold for production.
[0047] For example, if the injection molding machine model used this time is the No. 39 injection molding machine of the third phase of the Hefei Refrigerator Factory, the mold model is the 9142 mold, and the corresponding process parameter types include: cooling time, pressure holding position, pressure holding stage, temperature zone 1 setting value, temperature zone 3 setting value, among which, the cooling time value range can be 1s to 60s, the pressure holding position value range can be 95% to 99% of the screw stroke, the pressure holding stage value range can be 50bar to 200bar, the temperature zone 1 setting value range can be 180℃ to 250℃, and the temperature zone 3 setting value range can be 150℃ to 200℃. The value range of the zone setting value can be 160°C to 230°C; based on the value range of the obtained process parameters, any numerical combination is performed, and the number of corresponding arbitrary combinations can be 500 groups, and 500 groups of first process parameters are obtained, wherein a group of first process parameters can specifically be: the value range of the cooling time can be 11s, the value range of the pressure holding position can be 96% of the screw stroke, the value range of the pressure holding stage can be 58bar, the value range of the temperature zone 1 setting value can be 235°C, and the value range of the temperature zone 3 setting value can be 215°C.
[0048] S102: For each group of first process parameters, determine a quality prediction result corresponding to the first process parameters based on the first process parameters, injection molding machine information, mold information, and environmental information.
[0049] The environmental information is used to indicate the environmental status of the injection molding machine, and the quality prediction results include: qualified or unqualified.
[0050] It is understandable that during the production process of injection molded products, the environmental conditions of the injection molding machine will affect the quality of the generated products; for example, changes in ambient temperature will affect the fluidity and cooling rate of the plastic material, thereby affecting the quality of the finished product; the humidity in the air will also affect the water absorption of the plastic material, especially for highly hygroscopic plastics (such as nylon), high humidity may cause the material to swell or form bubbles.
[0051] The process parameter recommendation module is called. For each set of first process parameters determined this time, the process parameter recommendation module combines the injection molding machine information, mold information and environmental information to simulate the process of producing injection molded products using different first process parameters, so as to determine the quality prediction results corresponding to each set of first process parameters, that is, to obtain the quality prediction results of injection molded products when different first process parameters are used to produce injection molded products.
[0052] For example, if the model of the injection molding machine used this time is the No. 39 injection molding machine of the third phase of the Hefei Refrigerator Factory, the mold model is the 9142 mold, and the environmental information of the injection molding machine is: temperature 20°C and humidity 50%; the first process parameter A and the first process parameter B in the 500 sets of first process parameters generated this time are used to simulate the injection molding product production process, wherein the first process parameter A can specifically be: the value range of the cooling time can be 11s, the value range of the pressure holding position can be 96% of the screw stroke, the value range of the pressure holding stage can be 58bar, the value range of the temperature zone 1 setting value can be 235°C, and the value range of the temperature zone 3 setting value can be 215°C; the first process parameter B ... The range of the holding pressure position can be 12s, the range of the holding pressure position can be 95% of the screw stroke, the range of the holding pressure can be 60bar, the range of the temperature zone 1 setting value can be 230℃, and the range of the temperature zone 3 setting value can be 210℃; the process parameter recommendation module in the big data platform is used to simulate the environmental conditions of temperature 20℃ and humidity 50%, the No. 39 injection molding machine in the third phase of Hefei Refrigerator Factory uses 9142 mold, and the first process parameter A and the first process parameter B are used for injection molding product production, and the quality simulation results can be: "The first process parameter A is used for production, and the quality of the obtained product is qualified" and "The first process parameter B is used for production, and the quality of the obtained product is qualified".
[0053] S103: For each set of second process parameters with qualified quality prediction results among the preset number of sets of first process parameters, determine the production cycle prediction value and production energy consumption prediction value of a single product based on the second process parameters, injection molding machine information, mold information and environmental information.
[0054] Among them, the second process parameter is used to indicate the first process parameter corresponding to the qualified quality prediction result, the production cycle prediction value is used to indicate the length of time required for producing a single injection molding product using any set of second process parameters, and the production energy consumption prediction value is used to indicate the total amount of energy consumed for producing a single injection molding product using any set of second process parameters.
[0055] It can be understood that in order to ensure the accuracy and reliability of the production cycle prediction and the production energy consumption prediction, the process parameters with qualified quality prediction results among the first process parameters are selected as the second process parameters for cycle and energy consumption simulation, thereby ensuring that the selected process parameters can not only meet the product quality requirements, but also provide a stable and controllable production environment; by excluding process parameters with unqualified quality prediction results, the uncertainty and error in the cycle prediction and energy consumption prediction are reduced, thereby improving the effectiveness and practicality of the corresponding prediction results.
[0056] The control process parameter recommendation module screens out the first process parameters with qualified quality prediction results from a preset number of groups of first process parameters, and determines the screened out first process parameters as second process parameters; for each group of second process parameters, combined with the injection molding machine information, mold information and environmental information, the process of producing injection molded products using different second process parameters is simulated, so as to determine the production cycle prediction value and production energy consumption prediction value of a single product corresponding to each group of second process parameters.
[0057] For example, if the injection molding machine model used this time is the No. 39 injection molding machine of the third phase of Hefei Refrigerator Factory, the mold model is the 9142 mold, and the environmental information of the injection molding machine is: temperature 20°C and humidity 50%; for the first process parameters A and the first process parameters B with qualified quality prediction results among the 500 groups of first process parameters generated this time, the injection molding product production process is simulated, that is, the process parameter recommendation module in the big data platform is used to simulate the environmental conditions of temperature 20°C and humidity 50%, the No. 39 injection molding machine of the third phase of Hefei Refrigerator Factory uses the 9142 mold, and uses the first process parameters A and the first process parameters B respectively to produce injection molding products, the length of time for producing a single product and the total amount of energy consumed, so as to obtain the production cycle prediction value and production energy consumption prediction value of the corresponding single product, specifically: "The production cycle prediction value of the first process parameter A is 15min, and the production energy consumption prediction value is 4.5kW•h" and "The production cycle prediction value of the first process parameter B parameter group C is 14min, and the production energy consumption prediction value is 4.2kW•h".
[0058] S104: Based on the production cycle prediction value and production energy consumption prediction value of a single product corresponding to each set of second process parameters, determine the second process parameters that minimize the production cycle and production energy consumption of the target number of products as recommended process parameters.
[0059] It can be understood that the recommended process parameters are the parameters with the minimum production cycle and production energy consumption selected from multiple groups of second process parameters after determining the injection molding machine model and mold model used at the time, combined with the environmental information of the injection molding machine and the target number of injection molded products produced at the time; wherein, the parameters with the minimum production cycle and production energy consumption have a unique corresponding injection molding machine model and mold model. In the parameter screening process, for multiple groups of second process parameters, multiple groups of process parameters corresponding to the minimum production cycle can be first screened out, and then multiple groups of process parameters with the minimum energy consumption can be screened out from the multiple groups of process parameters corresponding to the minimum cycle; multiple second process parameters corresponding to the minimum production energy consumption can also be first screened out from multiple groups of second process parameters, and then the process parameters with the minimum cycle can be screened out from multiple process parameters corresponding to the minimum energy consumption. After two screening processes, the number of second process parameters obtained is at least one group; in addition, the production cycle and production energy consumption can be normalized respectively so that they have the same scale, and a comprehensive indicator is determined based on the normalized production cycle and production energy consumption, and the comprehensive indicator is used to determine the parameters with the minimum production cycle and production energy consumption.
[0060] Determine the target number of injection molded products to be produced at the time, and based on the production cycle prediction value and production energy consumption prediction value of a single product corresponding to each set of second process parameters, respectively calculate the total time length for producing the target number of injection molded products and the total energy consumption for producing the target number of injection molded products under different second process parameters, so as to obtain the total production cycle and total production energy consumption corresponding to different second process parameters; control the process parameter recommendation module to screen among multiple total production cycles and total production energy consumption, and determine the second process parameter that minimizes the total production cycle and total production energy consumption, that is, obtain the second process parameter with the smallest production cycle and production energy consumption for producing the target number of products, and determine the second process parameter as the recommended process parameter.
[0061] Specifically, the second process parameters that minimize the total production cycle and total production energy consumption include: normalizing the total production cycle and total production energy consumption of each group of second process parameters, comprehensively calculating the normalized total production cycle and total production energy consumption to obtain a comprehensive index, and comparing the comprehensive indexes of all second process parameters, and selecting the parameter with the smallest comprehensive index as the recommended process parameter.
[0062] For example, if the target number of injection molded products produced at a time is 60 pieces, the total production cycle corresponding to the first process parameter A is 900 minutes and the total production energy consumption is 270 kW•h, the total production cycle corresponding to the first process parameter B is 840 minutes and the total production energy consumption is 252 kW•h, and the total production cycle corresponding to the first process parameter C is 800 minutes and the total production energy consumption is 240 kW•h; the first process parameter A, the first process parameter B and the first process parameter C are normalized respectively, and the results are: "First process parameter A: the normalized total production cycle is 1, the normalized total The normalized total production cycle and total production energy consumption are 1", "The first process parameter B: the normalized total production cycle is 0.4, and the normalized total production energy consumption is 0.4", "The normalized total production cycle of the first process parameter C is 0, and the normalized total production energy consumption is 0", and the comprehensive indicators corresponding to different process parameters are calculated respectively. The comprehensive indicator corresponding to the first process parameter A is 2, the comprehensive indicator corresponding to the first process parameter B is 0.8, and the comprehensive indicator corresponding to the first process parameter C is 1. Therefore, the parameter that minimizes the total production cycle and the total production energy consumption is the second process parameter C. The second process parameter C is determined as the recommended process parameter.
[0063] The process parameter recommendation method based on industrial big data provided in this embodiment generates a preset number of groups of first process parameters when using the injection molding machine and the mold for production by determining the injection molding machine information and mold information used at the time; for each group of first process parameters, the quality prediction result corresponding to the first process parameter is determined based on the first process parameter, the injection molding machine information, the mold information and the environmental information; for the preset number of groups of first process parameters, the first process parameter with a qualified quality prediction result is determined as the second process parameter, and the production cycle prediction value and production energy consumption prediction value of a single product are determined based on the second process parameter, the injection molding machine information, the mold information and the environmental information; based on the production cycle prediction value and production energy consumption prediction value of a single product corresponding to each group of second process parameters, the second process parameter that minimizes the production cycle and production energy consumption of the target number of products is determined as the recommended process parameter. This method significantly reduces the energy consumption in the production process of injection molding products, improves the production efficiency and quality of products, dynamically generates process parameters based on the production conditions of different injection molding products, is suitable for a variety of production environments and needs, and reduces production costs.
[0064] Figure 2 Schematic diagram of the process parameter recommendation method based on industrial big data provided in the embodiment of the present application Figure 2 .like Figure 2 As shown, in this embodiment Figure 1 Based on the embodiment, a method for recommending process parameters based on industrial big data is described in detail. The method for recommending process parameters based on industrial big data shown in this embodiment includes: S201: Based on the injection molding machine information and the mold information, generate a preset number of groups of first process parameters for production using the injection molding machine and the mold.
[0065] According to the injection molding machine model and mold model corresponding to the injection molding machine information and mold information obtained this time, determine the type and quantity of process parameters used, as well as the possible value range of the corresponding process parameters; within the value range corresponding to different process parameters, generate a preset number of groups of first process parameters when using the injection molding machine and mold for production.
[0066] Specifically, based on the injection molding machine information and the mold information, the historical process parameters of the injection molding machine and the mold in the historical production process are obtained, and based on the historical process parameters, the numerical range of the process parameters is determined; based on the numerical range of the process parameters, a preset number of groups of first process parameters are randomly generated.
[0067] It is understandable that different injection molding machines are equipped with corresponding ranges of process parameter values. When different molds are used to produce injection molded products, not all parameter values of the injection molding machine will be used. Therefore, the parameter values in actual production can be determined more accurately by combining the historical process parameter values of the injection molding machine.
[0068] Based on the injection molding machine information and the mold information, the historical process parameters of the injection molding machine and the mold in the historical production process are obtained, and based on the historical process parameters, the historical value range of each process parameter is analyzed, and the historical value range is determined as the numerical range of the corresponding process parameter; based on the numerical ranges of different process parameters, the first process parameter of a preset number of groups is randomly generated.
[0069] For example, historical process parameters include: injection speed, mold temperature, cooling time. Based on the production combination of any injection molding machine and mold, the historical process parameters in the historical production process determine the historical value range of the corresponding parameters, including: the historical value range of injection speed: 80-120mm / s; the historical value range of mold temperature: 40-60℃; the historical value range of cooling time: 15-25s; that is, the numerical range of the corresponding process parameters is obtained, and based on the numerical range, 10 groups of first process parameters are generated, and each group of parameters includes injection speed, mold temperature and cooling time. This application does not impose any special restrictions on the number of randomly generated first process parameters.
[0070] Optionally, before generating the first process parameters, the big data cloud platform responds to the injection molding machine information, mold information and environmental information received by the application interface to generate a preset number of groups of first process parameters for production using the injection molding machine and the mold.
[0071] It can be understood that the user can use the process parameter recommendation service through the application interface to obtain the most suitable parameter values recommended by the process parameter recommendation module for the injection molding machine, mold, and surrounding environment used at the time of injection molding product production.
[0072] For example, a big data cloud platform equipped with a process parameter recommendation module provides external services in the form of an API interface, so that it can query the process parameters recommended by the process parameter recommendation module based on the current environmental information when using different injection molding machines and mold combinations; the front end calls this interface so that the factory can view the new recommended process parameters in real time.
[0073] Specifically, before responding to the injection molding machine information, mold information, and environmental information received by the application interface, the process parameter recommendation method based on industrial big data further includes: The process parameter recommendation request input by the user is obtained, the injection molding machine information, mold information and environmental information in the process parameter recommendation request are determined using a large language model, and an application interface is called through the large language model.
[0074] For example, based on the basic model ChatGLM3-6B, a question-answering system is implemented. The user inputs natural language, and the system uses the large language model LLM to convert the user's input questions into calls to the API tool, including the API name and extracted parameters. Specifically, the input natural language includes: "No. 39 injection molding machine in the third phase of Hefei Refrigerator Factory, to use 9142 mold for production, temperature 20°C, humidity 50%, please recommend the optimal parameters", extract the injection molding machine number, mold number, temperature, and humidity information in the language, and call the corresponding API recommendation interface to obtain the optimal recommended value of the process parameters.
[0075] S202: For each set of first process parameters, the first process parameters, injection molding machine information, mold information, and environmental information are input into a pre-trained quality model to obtain a quality prediction result corresponding to the first process parameters.
[0076] Among them, the quality model is trained based on the historical process parameters, historical quality results and historical environmental information of the injection molding machine and mold in the historical production process.
[0077] It can be understood that a quality model is provided in the process parameter recommendation module, and the quality model can predict the quality of products produced under different production conditions, and different production conditions refer to any combination of different injection molding machine models, different mold types and different environmental conditions.
[0078] For each set of first process parameters, multiple sets of first process parameters, injection molding machine information, mold information and environmental information are input into a pre-trained quality model, and the quality model predicts the quality of injection molded products produced using different first process parameters to obtain multiple quality prediction results.
[0079] For example, if the first process parameter determined this time includes: the first process parameter A and the first process parameter B, the injection molding machine model used this time is the injection molding machine No. 39 of the third phase of the Hefei Refrigerator Factory, the mold model is the 9142 mold, and the environmental information of the injection molding machine is: temperature 20°C and humidity 50%; the first process parameter A, the first process parameter B, the injection molding machine model, the mold model and the environmental information of the injection molding machine determined this time are input into the quality model, and the quality model predicts the quality of the injection molded products produced by using the first process parameter A and the first process parameter B respectively, and the obtained quality prediction results can be: "The quality of the product obtained by using the first process parameter A for production is qualified" and "The quality of the product obtained by using the first process parameter B for production is qualified".
[0080] S203: For each group of second process parameters with qualified quality prediction results in a preset number of groups of first process parameters, the second process parameters, injection molding machine information, mold information and environmental information are input into a pre-trained cycle model to obtain a production cycle prediction value of a single product corresponding to the second process parameters.
[0081] S204: For each group of second process parameters with qualified quality prediction results in a preset number of groups of first process parameters, the second process parameters, injection molding machine information, mold information and environmental information are input into a pre-trained energy consumption model to obtain a production energy consumption prediction value of a single product corresponding to the second process parameters.
[0082] Among them, the cycle model is trained based on the historical process parameters, historical production cycle and historical environmental information of the injection molding machine and mold in the historical production process; the energy consumption model is trained based on the historical process parameters, historical energy consumption and historical environmental information of the injection molding machine and mold in the historical production process.
[0083] For a preset number of groups of first process parameters, the first process parameters with qualified quality prediction results are screened out, and the screened out first process parameters are determined as second process parameters; the second process parameters, injection molding machine information, mold information and environmental information determined this time are input into a pre-trained cycle model, and the cycle model is used to predict the cycle of single injection molding product production using different second process parameters to obtain production cycle prediction values of multiple single products; the second process parameters, injection molding machine information, mold information and environmental information are then input into a pre-trained energy consumption model, and the energy consumption model is used to predict the energy consumption of single injection molding product production using different second process parameters to obtain production energy consumption prediction values of multiple single products.
[0084] For example, if the qualified first process parameters include: the first process parameter A and the first process parameter B, the injection molding machine model used this time is the injection molding machine No. 39 of the third phase of the Hefei Refrigerator Factory, the mold model is the 9142 mold, and the environmental information of the injection molding machine is: temperature 20°C and humidity 50%, then the qualified first process parameter A, the first process parameter B, the injection molding machine model, the mold model and the environmental information of the injection molding machine are respectively input into the cycle model and the energy consumption model, and the cycle model and the energy consumption model respectively predict the production cycle and energy consumption of a single injection molded product produced by using the first process parameter A and the first process parameter B. The obtained production cycle prediction values and production energy consumption prediction values of the corresponding single products are: "The production cycle prediction value of the first process parameter A is 15min, and the production energy consumption prediction value is 4.5kW•h" and "The production cycle prediction value of the first process parameter B parameter group C is 14min, and the production energy consumption prediction value is 4.2kW•h".
[0085] It can be understood that in the process of training the quality model, cycle model and energy consumption model, the training data of the corresponding model is generated based on the historical data in the historical production process of the injection molding products, and the historical data includes: historical process parameters, historical injection molding machine information, historical mold information, historical production cycle, historical energy consumption, historical environmental information and historical quality results; in order to ensure the effectiveness of the training data, when generating the training data, all the historical data that can be obtained at that time can be filtered according to the preset filtering conditions, and the filtering conditions can be, for example: the output of each batch of injection molding products is greater than 50, and the number of records of changes in process parameters during the production process is greater than 7 times.
[0086] For example, the data of injection molding machine code, mold code, process parameters, temperature, humidity, single-piece power consumption, and single-piece cycle in the data information corresponding to the historical production process of injection molding products are obtained, and according to the preset screening conditions, the data information corresponding to the production process of multiple different batches of injection molding products with an output greater than 50 and a number of changes in process parameters greater than 7 is screened from the historical data, and the data information is the combined data of injection molding machine, mold, and parameter records; then, the combined data of injection molding machine, mold, and parameter records and the time grouping corresponding to different combined data are used to determine the single-piece cycle and single-piece energy consumption of the injection molding products produced on the same day in the combined data under different time groups, and the product quality data stored in the process parameter recommendation module is called, and the quality of different batches of injection molding products is stored in the product quality data; then, according to the temperature and humidity information in the historical data, different time groups are added to the obtained multiple combined data, so as to obtain training data that can be used for model training. This application does not impose special restrictions on the acquisition of product quality data.
[0087] Optionally, during the training of the quality model, cycle model and energy consumption model, it is necessary to classify and integrate the obtained training data according to the training requirements of different models; based on the classified and integrated training data, model training is performed separately to obtain the corresponding quality model, cycle model and energy consumption model; in addition, during the recommendation of process parameters, new operating data is continuously generated as time changes, that is, the data information of the injection molding product production process using the recommended process parameters is combined with the new operating data to dynamically update the quality model, cycle model and energy consumption model, thereby realizing continuous optimization of the model and improving the accuracy of the model prediction results.
[0088] For example, when training a quality model, the training data is classified and integrated according to historical process parameters, historical injection molding machine information, historical mold information, historical environmental information, and whether the corresponding product quality is qualified, and the corresponding model training data is obtained. The quality model is trained using the Support Vector Machine (SVC) model. The process is as follows: The training sample set is defined as ,in Represents input data, namely historical process parameters, historical injection molding machine information, historical mold information, and historical environment information. , To indicate whether the quality is qualified or not, +1 indicates good quality. A value of -1 indicates that the quality is unsatisfactory.
[0089] The decision hyperplane can be defined , where W is the normal vector of the hyperplane, x is the input data, and b is the intercept. In the feature space where the input data is located, there is a hyperplane as the decision boundary, namely the decision hyperplane, which separates the training samples into positive samples and negative samples, and makes the distance from any training sample to the decision hyperplane greater than or equal to 1. By constructing two parallel hyperplanes and , as the interval boundary to distinguish the classification of training samples.
[0090] and The distances between them are as follows:
[0091] The purpose of model training is to maximize , which is equivalent to maximizing The square of is also equivalent to minimizing The reciprocal of the square of , that is:
[0092] The minimum value of the above formula is the optimal solution of SVC, thus ensuring the best prediction effect of SVC quality model. In addition, since all training samples are distributed outside the interval of the hyperplane, the training samples also meet the following constraints:
[0093] By jointly solving the above formulas, w and b corresponding to the decision hyperplane that maximizes the distance between the two interval boundaries can be calculated, thereby obtaining a quality model.
[0094] When training the cycle model, the obtained training data is classified and integrated according to the historical process parameters, historical injection molding machine information, historical mold information, historical environmental information, and the production cycle of the corresponding single injection molding product to obtain the corresponding model training data, and the SVR regression model is used to train the cycle model. The process is as follows: The training sample set is defined as ,in Represents input data, namely historical process parameters, historical injection molding machine information, historical mold information, and historical environment information. Indicates the production cycle.
[0095] The function of the SVR regression model is: , creating a "gap" on both sides of the function, , , no loss is calculated for all samples falling into the interval band, and finally the optimized model is obtained by minimizing the total loss and maximizing the interval. The loss function , the optimization objective is equivalent to:
[0096] Among them, C is the regularization parameter.
[0097] Based on the above optimization objectives and combined with the training samples, w and b in the function of the SVR regression model are determined to obtain a periodic model.
[0098] First, divide the training set and the test set, then build the SVR model, use the SVR model in the sklearn.svm library, and set different parameters. Finally, evaluate the effect of the model and select the best model.
[0099] In actual prediction, the injection molding machine code, mold information, injection molding machine process parameter information, and environmental temperature and humidity information are used as input data, and the above three trained models are applied to predict the time, energy consumption, and quality of producing a single product.
[0100] When training the energy consumption model, the training data is classified and integrated according to the combined data recorded by the process parameters, corresponding to the length, width, height of the mold, as well as the mold ID, injection molding machine ID, and single-piece energy consumption, to obtain the corresponding model training data, and the SVR regression model in sklearn is used to train the energy consumption model.
[0101] Since the SVC classification model and the SVR regression model can set different model parameters, we add a model evaluator and a model selector to obtain the optimal model, as follows: For the SVC classification model, that is, the quality model, two different quality models are obtained by setting two different sets of model parameters, and the quality prediction is performed using the two quality models with different model parameters respectively; using the model evaluator, the accuracy (ACCURACY) of the evaluation index of the quality model with different model parameters is given respectively, and the model with the largest ACCURACY value is selected as the optimal model through the model selector, so as to obtain the quality model under the current training data; for the SVR regression model, that is, the energy consumption model, two different energy consumption models are obtained by setting two different sets of model parameters, and the energy consumption prediction is performed using the two energy consumption models with different model parameters respectively; using the model evaluator, the evaluation index Mean Absolute Percentage Error (MAPE) of the energy consumption model with different model parameters is given respectively, and when selecting the model, the model with the smallest MAPE value is selected as the optimal model, so as to obtain the energy consumption model under the current training data.
[0102] S205: Determine a fitness function based on the predicted value of the production cycle and the predicted value of the production energy consumption of the target number of products, and use a particle swarm optimization algorithm to determine, based on the fitness function value corresponding to each group of second process parameters, the second process parameters that minimize the production cycle and production energy consumption of generating the target number of products as recommended process parameters.
[0103] The fitness function is used to determine the quality of each set of second process parameters.
[0104] It can be understood that when the particle swarm optimization algorithm is used to screen the optimal process parameters from multiple groups of second process parameters, a group of particles is randomly generated, and each particle contains multiple dimensions, each dimension corresponds to the type of the second process parameter determined this time, and the number of particles generated this time is the same as the number of groups of the second process parameters; when determining the fitness function, the two indicators of production cycle and production energy consumption are combined, and the weighted sum method can be used to combine the two indicators into a fitness function to facilitate the determination of the optimal process parameters. The production cycle and production energy consumption in this application are minimized, corresponding to the minimum value of the fitness function. This application does not impose any special restrictions on the determination of the fitness function.
[0105] Determine the fitness function based on the production cycle prediction value and production energy consumption prediction value of the target number of products and the target number of injection molded products to be produced at the time, and based on the production cycle prediction value and production energy consumption prediction value of the single product corresponding to each set of second process parameters, respectively calculate the total time length of producing the target number of injection molded products and the total energy consumption of producing the target number of injection molded products under different second process parameters, so as to obtain the total production cycle and total production energy consumption corresponding to different second process parameters; based on the total production cycle and total production energy consumption corresponding to the different second process parameters determined at the time, calculate the fitness value corresponding to each set of second process parameters, and use the particle swarm optimization algorithm to search for the obtained multiple second process parameters based on the fitness value corresponding to each set of second process parameters; in the particle swarm optimization algorithm, the position and speed of each particle need to be updated according to the fitness value, therefore, the position and speed of each particle are iteratively updated according to the preset number of iterations, and the global optimal position and global optimal fitness of the random particles are obtained, so as to determine the optimal process parameters among the multiple sets of second process parameters, that is, the recommended process parameters.
[0106] For example, according to the particle swarm search method in the operations planning algorithm, multiple groups of second process parameters determined at the time are searched, and the number of the second process parameters is less than or equal to 500 groups; if the number of the second process parameters at the time is 500 groups, then based on 500 combinations of process parameters, the particle swarm search method is used, the search number is 50 times, and the parameters with qualified quality, lowest production energy consumption and production cycle are obtained as the recommended process parameters for the injection molding machine and mold combination used at the time.
[0107] The process parameter recommendation method based on industrial big data provided in this embodiment generates a preset number of groups of first process parameters when the injection molding machine and the mold are used for production by determining the injection molding machine information and the mold information used at the time; for each group of first process parameters, the first process parameters, the injection molding machine information, the mold information and the environmental information are input into a pre-trained quality model to obtain the corresponding quality prediction result, and the first process parameter with a qualified quality prediction result is determined as the second process parameter; then multiple second process parameters, the injection molding machine information, the mold information and the environmental information are input into a pre-trained cycle model to obtain the production cycle prediction value of a single product corresponding to each second process parameter; determine the fitness function based on the production cycle prediction value and the production energy consumption prediction value of a target number of products, and use a particle swarm optimization algorithm to determine the second process parameters that minimize the production cycle and production energy consumption of the target number of products based on the fitness function value corresponding to each group of second process parameters as the recommended process parameters. By continuously updating and training the model, this method can continuously optimize the process parameter recommendations, thereby reducing unnecessary energy consumption and production cycles, significantly reducing energy consumption in the production process of injection molding products, improving product production efficiency and quality, optimizing the production cycle and energy consumption management of injection molding products, and dynamically generating process parameters based on the production conditions of different injection molding products. It is suitable for a variety of production environments and needs, improves product qualification rates, and reduces production costs.
[0108] Figure 3 This is a schematic diagram of the structure of the process parameter recommendation device provided in this application. Figure 3 As shown, the present application provides a process parameter recommendation device, and the process parameter recommendation device 300 includes: The processing module 301 is used to generate a preset number of groups of first process parameters for production using the injection molding machine and the mold based on the injection molding machine information and the mold information.
[0109] The determination module 302 is used to determine, for each group of the first process parameters, a quality prediction result corresponding to the first process parameters based on the first process parameters, the injection molding machine information, the mold information and the environmental information, wherein the quality prediction result includes qualified or unqualified.
[0110] The determination module 302 is also used to determine the production cycle prediction value and production energy consumption prediction value of a single product based on the second process parameters, the injection molding machine information, the mold information and the environmental information for each group of second process parameters whose quality prediction results are qualified in a preset number of groups of first process parameters.
[0111] The determination module 302 is further used to determine as the recommended process parameters the second process parameters that minimize the production cycle and production energy consumption of the target number of products based on the production cycle prediction value and production energy consumption prediction value of the single product corresponding to each group of the second process parameters.
[0112] Optionally, the processing module 301 is also used to input the first process parameters, the injection molding machine information, the mold information and the environmental information into a pre-trained quality model to obtain a quality prediction result corresponding to the first process parameters, wherein the quality model is trained based on historical process parameters, historical quality results and historical environmental information of the injection molding machine and the mold in the historical production process.
[0113] Optionally, the processing module 301 is also used to input the second process parameters, the injection molding machine information, the mold information and the environmental information into a pre-trained cycle model to obtain a production cycle prediction value of a single product corresponding to the second process parameters, wherein the cycle model is trained based on historical process parameters, historical production cycles and historical environmental information of the injection molding machine and the mold in historical production processes.
[0114] The processing module 301 is also used to input the second process parameters, the injection molding machine information, the mold information and the environmental information into a pre-trained energy consumption model to obtain a production energy consumption prediction value of a single product corresponding to the second process parameters, wherein the energy consumption model is trained based on historical process parameters, historical energy consumption and historical environmental information of the injection molding machine and the mold in historical production processes.
[0115] Optionally, the determination module 302 is also used to determine a fitness function based on the production cycle prediction value and the production energy consumption prediction value of the target number of products, and to determine, using a particle swarm optimization algorithm, the second process parameters that minimize the production cycle and production energy consumption for generating the target number of products based on the fitness function values corresponding to each group of the second process parameters, as recommended process parameters.
[0116] Optionally, the process parameter recommendation device further includes: an acquisition module 303 .
[0117] The acquisition module 303 is used to acquire historical process parameters of the injection molding machine and the mold in the historical production process based on the injection molding machine information and the mold information.
[0118] The determination module 302 is further configured to determine a numerical range of the process parameter based on the historical process parameter.
[0119] The processing module 301 is further configured to randomly generate a preset number of groups of the first process parameters based on the value range of the process parameters.
[0120] Optionally, the processing module 301 is further used to generate a preset number of groups of first process parameters for production using the injection molding machine and the mold in response to the injection molding machine information, mold information and environment information received by the application interface.
[0121] Optionally, the acquisition module 303 is further used to acquire a process parameter recommendation request input by a user.
[0122] The determination module 302 is further configured to use a large language model to determine the injection molding machine information, mold information and environment information in the process parameter recommendation request.
[0123] The processing module 301 is further configured to call the application interface through the large language model.
[0124] Figure 4 This is a schematic diagram of the structure of the equipment recommended for the process parameters provided in this application. Figure 4 As shown, the present application provides a process parameter recommendation device, and the process parameter recommendation device 400 includes: a receiver 401, a transmitter 402, a processor 403 and a memory 404.
[0125] Receiver 401, used for receiving instructions and data; A transmitter 402, used for sending instructions and data; Memory 404, for storing computer-executable instructions; The processor 403 is used to execute the computer-executable instructions stored in the memory 404 to implement the various steps performed by the process parameter recommendation method based on industrial big data in the above embodiment. For details, please refer to the relevant description in the above embodiment of the process parameter recommendation method based on industrial big data.
[0126] Optionally, the memory 404 may be independent or integrated with the processor 403 .
[0127] When the memory 404 is independently provided, the electronic device further includes a bus for connecting the memory 404 and the processor 403 .
[0128] The present application also provides a computer-readable storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, a process parameter recommendation method based on industrial big data as performed by the above-mentioned process parameter recommendation device is implemented.
[0129] The present application also provides a program product, including a computer program, which, when executed by a processor, implements the process parameter recommendation method based on industrial big data as described above.
[0130] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.
[0131] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
[0132] It should be understood that the above-mentioned device embodiments are only illustrative, and the device of the present application can also be implemented in other ways. For example, the division of units / modules in the above-mentioned embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.
[0133] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present application may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.
[0134] If the integrated unit / module is implemented in the form of hardware, the hardware may be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. Unless otherwise specified, the processor may be any appropriate hardware processor, such as a CPU, a GPU, an FPGA, a DSP, an ASIC, etc. Unless otherwise specified, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory (RRAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), an enhanced dynamic random access memory (EDRAM), a high-bandwidth memory (HBM), a hybrid memory cube (HMC), etc.
[0135] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.
[0136] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0137] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.
[0138] So far, the technical solution of the present application has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments, and the above embodiments are only used to illustrate the technical solution of the present application rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.
Claims
1. A process parameter recommendation method based on industrial big data, characterized in that: The method comprises: Based on the injection molding machine information and the mold information, generating a preset number of groups of first process parameters for production using the injection molding machine and the mold; For each group of the first process parameters, determining a quality prediction result corresponding to the first process parameters based on the first process parameters, the injection molding machine information, the mold information, and the environmental information, wherein the quality prediction result includes a qualified or unqualified result; For each set of second process parameters whose quality prediction result is qualified among the preset number of sets of first process parameters, determine the production cycle prediction value and production energy consumption prediction value of a single product based on the second process parameters, the injection molding machine information, the mold information and the environmental information; Based on the production cycle prediction value and production energy consumption prediction value of a single product corresponding to each group of the second process parameters, the second process parameters that minimize the production cycle and production energy consumption of the target number of products are determined as recommended process parameters.
2. The method according to claim 1, characterized in that The determining, based on the first process parameter, the injection molding machine information, the mold information, and the environmental information, a quality prediction result corresponding to the first process parameter includes: The first process parameter, the injection molding machine information, the mold information and the environmental information are input into a pre-trained quality model to obtain a quality prediction result corresponding to the first process parameter, wherein the quality model is trained based on historical process parameters, historical quality results and historical environmental information of the injection molding machine and the mold in historical production processes.
3. The method according to claim 1, characterized in that The step of determining a production cycle prediction value and a production energy consumption prediction value of a single product based on the second process parameter, the injection molding machine information, the mold information, and the environmental information includes: Inputting the second process parameter, the injection molding machine information, the mold information and the environmental information into a pre-trained cycle model to obtain a production cycle prediction value of a single product corresponding to the second process parameter, wherein the cycle model is trained based on historical process parameters, historical production cycles and historical environmental information of the injection molding machine and the mold in historical production processes; The second process parameters, the injection molding machine information, the mold information and the environmental information are input into a pre-trained energy consumption model to obtain a production energy consumption prediction value of a single product corresponding to the second process parameters, wherein the energy consumption model is trained based on historical process parameters, historical energy consumption and historical environmental information of the injection molding machine and the mold in historical production processes.
4. The method according to any one of claims 1 to 3, characterized in that The step of determining the second process parameters that minimize the production cycle and production energy consumption of the target number of products based on the production cycle prediction value and production energy consumption prediction value of the single product corresponding to each group of the second process parameters as the recommended process parameters includes: Determine a fitness function based on the predicted value of the production cycle and the predicted value of the production energy consumption of the target number of products, and use a particle swarm optimization algorithm to determine, based on the fitness function value corresponding to each group of the second process parameters, the second process parameters that minimize the production cycle and production energy consumption of generating the target number of products as recommended process parameters.
5. The method according to any one of claims 1 to 3, characterized in that: The step of generating a preset number of groups of first process parameters for production using the injection molding machine and the mold based on the injection molding machine information and the mold information includes: Based on the injection molding machine information and the mold information, historical process parameters of the injection molding machine and the mold in a historical production process are acquired, and based on the historical process parameters, a numerical range of the process parameters is determined; Based on the value range of the process parameter, a preset number of groups of the first process parameter are randomly generated.
6. The method according to any one of claims 1 to 3, characterized in that The step of generating a preset number of groups of first process parameters for production using the injection molding machine and the mold based on the injection molding machine information and the mold information includes: In response to the injection molding machine information, the mold information and the environment information received by the application interface, a preset number of groups of first process parameters for production using the injection molding machine and the mold are generated.
7. The method according to claim 6, characterized in that Before responding to the injection molding machine information, mold information and environment information received by the application interface, the method further includes: A process parameter recommendation request input by a user is obtained, the injection molding machine information, mold information and environment information in the process parameter recommendation request are determined using a large language model, and the application interface is called through the large language model.
8. A process parameter recommendation device based on industrial big data, characterized in that: include: A processing module, for generating a preset number of groups of first process parameters for production using the injection molding machine and the mold based on the injection molding machine information and the mold information; a determination module, configured to determine, for each group of the first process parameters, a quality prediction result corresponding to the first process parameters based on the first process parameters, the injection molding machine information, the mold information, and the environmental information, wherein the quality prediction result includes a qualified or unqualified result; The determination module is further configured to determine, for each set of second process parameters whose quality prediction result is qualified among a preset number of sets of first process parameters, a production cycle prediction value and a production energy consumption prediction value of a single product based on the second process parameters, the injection molding machine information, the mold information, and the environmental information; The determination module is also used to determine as the recommended process parameters the second process parameters that minimize the production cycle and production energy consumption of the target number of products based on the production cycle prediction value and production energy consumption prediction value of the single product corresponding to each group of the second process parameters.
9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.
Citation Information
Patent Citations
System and method for setting process parameters of injection molding machine based on data recording
CN105690694A
Multi-objective optimization method for injection molding parameters
CN110377948A
Process parameter determination method and device, electronic equipment and storage medium
CN114565354A
Intelligent diet recommendation system based on food image segmentation and uric acid index
CN115171848A
Intelligent determination method and system for injection molding process parameters
CN115230067A
