Foaming process parameter optimization system and method, storage medium and equipment

Abstract

The invention discloses a foaming process parameter optimization system and method, a storage medium and equipment, and relates to the technical field of refrigeration and freezing, the system comprises a data acquisition module used for acquiring foaming process parameters corresponding to each procedure in a foaming process, and the foaming process parameters comprise bubble structure data of a refrigerator body; the foaming defect diagnosis module is used for determining main influence parameters causing bubble defects based on the foaming process parameters and providing early warning information; the foaming quality prediction module is used for predicting the foaming quality of the refrigerator body based on the foaming process parameters; and the foaming process optimization module is used for generating a process parameter adjustment strategy based on the foaming process parameters, the main influence parameters and the foaming quality so as to improve the foaming quality. By adopting the system provided by the invention, the corresponding process parameter adjustment strategy can be carried out according to the predicted foaming quality and foaming defect diagnosis in the foaming process of the refrigerator body, so that the automatic foaming quality improvement is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of refrigeration and freezing, and particularly relates to a foaming process parameter optimization system, method, storage medium and device. Background Art

[0002] The process of foaming the refrigerator cabinet is a chemical change process affected by various factors. Any change in factors will affect the foaming quality and cause problems such as bubble voids. Therefore, it is of great significance to detect the foaming quality.

[0003] Nowadays, usually based on manual experience, multiple tests are carried out according to the season or the change of the cabinet model to adjust the injection volume during the foaming process. And when checking the foaming quality of the refrigerator, the method of manual sampling and disassembly is usually adopted. Determining the injection volume based on manual experience and manual sampling inspection are difficult to ensure the overall quality of the refrigerator in large-scale production, and the manual inspection is relatively cumbersome and costly. Therefore, there is an urgent need for an automated foaming quality prediction scheme that can realize the intelligent prediction of the foaming quality of the refrigerator based on the factors in each link of the refrigerator foaming and propose an accurate and reliable parameter optimization strategy. Summary of the Invention

[0004] The purpose of the present invention is to provide a foaming process parameter optimization system, method, storage medium and device, aiming to solve the problems that in the existing foaming process of the refrigerator cabinet, defect analysis and parameter adjustment overly rely on manual experience and it is difficult to realize automatic optimization of process parameters.

[0005] To achieve the above invention purpose, on the one hand, the present application provides a foaming process parameter optimization system, and the system includes:

[0006] A data acquisition module, configured to obtain the foaming process parameters corresponding to each process in the foaming process, and the foaming process parameters include the bubble structure data of the refrigerator cabinet;

[0007] A foaming defect diagnosis module, configured to determine the main influencing parameters causing bubble defects based on the foaming process parameters and provide a warning message;

[0008] A foaming quality prediction module, configured to predict the foaming quality of the refrigerator cabinet based on the foaming process parameters;

[0009] A foaming process optimization module, configured to generate a process parameter adjustment strategy based on the foaming process parameters, the main influencing parameters and the foaming quality.

[0010] As a further improvement of the present application, the data acquisition module includes:

[0011] A preheating parameter acquisition unit, configured to obtain the cabinet identifier, the back panel temperature, the inner liner temperature and the air temperature;

[0012] A fixture parameter reading unit for obtaining fixture identification, curing time, and temperature parameters;

[0013] A foaming parameter reading unit for obtaining injection flow rate, injection time, injection ratio, and pressure parameters;

[0014] A premixer parameter reading unit for collecting blowing agent content and mixing time data;

[0015] An infrared detection unit for obtaining bubble size information and position information.

[0016] As a further improvement of the present application, the foaming defect diagnosis module is used for:

[0017] Using a causal inference model to quantify the influence ratio of each foaming process parameter on bubble defects;

[0018] Determining the foaming process parameters with an influence ratio exceeding a preset ratio threshold as the main influence parameters.

[0019] As a further improvement of the present application, the foaming process optimization module is used for determining a target parameter combination through a large-scale random optimization algorithm based on the foaming process parameters, the main influence parameters, and the foaming quality; generating a process parameter adjustment strategy based on the target parameter combination;

[0020] The foaming quality prediction module is further used for, when obtaining the process parameter adjustment strategy, predicting the foaming quality after parameter adjustment through a foaming quality prediction model based on a mapping relationship model and the process parameter adjustment strategy, where the mapping relationship model is used to represent the mapping relationship between each process parameter and the foaming quality.

[0021] As a further improvement of the present application, the data acquisition module is further used for obtaining sample foaming process parameters corresponding to each process in the foaming process of refrigerator cabinets of different models;

[0022] The system further includes:

[0023] A data fusion module for associatively fusing the cabinet identification of the refrigerator cabinet with the sample foaming process parameters to obtain sample data;

[0024] A model library construction module for constructing a mapping relationship model based on the sample data, where the mapping relationship model is used to represent the mapping relationship between each process parameter and the foaming quality.

[0025] As a further improvement of the present application, the data fusion module includes:

[0026] A data alignment unit for performing time series alignment on the sample foaming process parameters corresponding to each process;

[0027] A data parsing unit, configured to convert the sample foaming process parameters corresponding to each process into a unified format.

[0028] As a further improvement of the present application, the model library construction module is further configured to:

[0029] Train a foaming quality prediction model based on the sample data.

[0030] As a further improvement of the present application, the system further includes:

[0031] A foaming data statistics module, configured to monitor the foaming process parameters in real time and identify abnormal points;

[0032] A visualization module, configured to display the change trend of the foaming process parameters and the abnormal points in real time.

[0033] On the other hand, the present application provides a method for optimizing foaming process parameters, the method including:

[0034] Obtain the foaming process parameters corresponding to each process in the foaming process, where the foaming process parameters include the bubble structure data of the refrigerator cabinet;

[0035] Based on the foaming process parameters, determine the main influencing parameters causing bubble defects and provide a warning message;

[0036] Based on the foaming process parameters, predict the foaming quality of the refrigerator cabinet;

[0037] Generate a process parameter adjustment strategy based on the foaming process parameters, the main influencing parameters, and the foaming quality.

[0038] On the other hand, the present application provides a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it executes the method for optimizing foaming process parameters as described in the above aspect.

[0039] On the other hand, the present application provides a computer device, including a memory and a processor, where the processor is configured to execute the computer program stored in the memory to implement the method for optimizing foaming process parameters as described in the above aspect.

[0040] Compared with the related art, the beneficial effects of the present invention are as follows:

[0041] In the embodiments of the present application, the foaming parameter optimization system acquires the foaming process parameters corresponding to each process through the data acquisition module, automatically identifies the main influencing parameters causing bubble defects through the foaming defect diagnosis module, accurately predicts the foaming quality of the refrigerator cabinet through the foaming quality prediction module, and finally automatically generates a process parameter adjustment strategy in a data-driven manner to improve the foaming quality, reduce the dependence on manual experience, improve the scientific nature and efficiency of foaming quality optimization, and at the same time improve the accuracy of parameter adjustment to ensure the bubble quality after parameter adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 shows an architecture diagram of a foaming process optimization system provided by an exemplary embodiment of the present application;

[0043] Figure 2 shows a schematic diagram of an infrared detection unit provided by an exemplary embodiment of the present application;

[0044] Figure 3 shows a schematic diagram of a foaming process parameter optimization system provided by an exemplary embodiment of the present application;

[0045] Figure 4 shows a flowchart of a foaming parameter optimization method provided by an exemplary embodiment of the present application;

[0046] Figure 5 shows a schematic structural diagram of a computer device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] The present invention will be described in detail below with reference to the specific embodiments shown in the drawings. However, these embodiments do not limit the present invention, and any structural, method, or functional transformation made by those of ordinary skill in the art based on these embodiments is included in the protection scope of the present invention.

[0048] It should be noted that the term "comprising" or any other variant thereof is intended to cover a non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or device. In addition, the terms "first", "second", etc. are used for descriptive purposes only and cannot be construed as indicating or implying relative importance.

[0049] Please refer to Figure 1 , which shows an architecture diagram of a foaming process optimization system provided by an exemplary embodiment of the present application. The system includes a data acquisition module 110, a foaming defect diagnosis module 120, a foaming quality prediction module 130, and a foaming process optimization module 140.

[0050] The data acquisition module 110 is used to obtain the foaming process parameters corresponding to each process in the foaming process. The foaming process parameters include the bubble structure data of the refrigerator cabinet.

[0051] Optionally, the data acquisition module 110 accesses the sensor data of each process in the foaming process from multiple on-site PLCs (Programmable Logic Controllers). The data of different sensors are parsed and converted, sorted into a unified format, and the relevant data of the same device are integrated. For the data collected by multiple PLCs, the data acquisition module 110 needs to perform data alignment and data integration to solve possible problems in the data acquisition process such as out-of-order, packet loss, retransmission, and peak floods.

[0052] The foaming defect diagnosis module 120 is used to determine the main influencing parameters that cause bubble defects based on the foaming process parameters and provide early warning information.

[0053] Optionally, the foaming defect diagnosis module 120 analyzes the big data related to the foaming process through artificial intelligence. For the direct and indirect factors affecting the foaming quality, a quantitative proportion of the effects is given through a causal inference model to guide the process management personnel to supervise the production operation of the foaming production line.

[0054] Optionally, Bayesian probability analysis, as a way of causal reasoning, can perform quantitative analysis on each influencing factor. The foaming defect diagnosis module 120 uses Bayesian probability analysis (i.e., the causal inference model) to quantify the influence proportion of each foaming process parameter on the bubble defect, and determines the foaming process parameter with an influence proportion greater than the preset proportion threshold as the main influencing parameter.

[0055] Among them, the causal inference model can analyze the complex causal relationship between the foaming bubbles and the process factors, establish an independent action model including various types, environments, equipment, and bubble quality inspection results, break through the dependence of traditional predictive models on the correlation relationship, and explain the possible potential effects of process improvement measures through counterfactual effects.

[0056] The foaming quality prediction module 130 is used to predict the foaming quality of the refrigerator cabinet based on the foaming process parameters.

[0057] The foaming quality prediction module 130 combines the correlation relationship between the foaming production process data and the product quality inspection data, and constructs a foaming quality prediction model based on machine learning technology to achieve intelligent foaming quality prediction. Optionally, the constructed foaming quality prediction model can not only verify the effectiveness of the foaming defect diagnosis module 120, but also be extended to other production line scenarios lacking foaming defect detection.

[0058] The foaming process optimization module 140 is used to generate a process parameter adjustment strategy based on foaming process parameters, main influencing parameters, and foaming quality, so as to improve the foaming quality.

[0059] The foaming process optimization module 140 meets the requirements of intelligent manufacturing and realizes the improvement and optimization of the foaming process through large-scale random optimization technology. The foaming process optimization module 140 intelligently puts forward improvement suggestions and solutions for manipulable foaming process parameters, assisting production line personnel to reduce foaming defects and improve product quality levels.

[0060] Optionally, the foaming process optimization module 140 determines the target parameter combination based on foaming process parameters, main influencing parameters, and foaming quality through a large-scale random optimization algorithm, and then generates a process parameter adjustment strategy based on the target parameter combination. The large-scale random optimization algorithm can efficiently search for the optimal parameter combination in a complex multi-parameter space, and has higher efficiency and accuracy compared with traditional parameter adjustment methods.

[0061] In summary, in the embodiments of the present application, the foaming parameter optimization system obtains the foaming process parameters corresponding to each process through the data acquisition module 110, automatically identifies the main influencing parameters causing bubble defects through the foaming defect diagnosis module 120, accurately predicts the foaming quality of the refrigerator box body through the foaming quality prediction module 130, and finally automatically generates a process parameter adjustment strategy in a data-driven manner to improve the foaming quality, reduce the dependence on manual experience, improve the scientificity and efficiency of foaming quality optimization, and at the same time improve the accuracy of parameter adjustment to ensure the bubble quality after parameter adjustment.

[0062] In a possible implementation manner, the process flow of refrigerator box body foaming includes box body pre-installation, preheating, foaming, cleaning and repair, and offline. Correspondingly, foaming process parameters can be obtained from five links corresponding to each box body: premixing, preheating, fixture, foaming machine, and environment. The data acquisition module 110 includes a preheating parameter acquisition unit, a fixture parameter reading unit, a foaming parameter reading unit, a premixing machine parameter reading unit, and an infrared detection unit.

[0063] Among them, the preheating parameter acquisition unit is used to obtain parameters such as box body identification and temperature, which have an important impact on foaming quality in the preheating process.

[0064] The fixture parameter reading unit is used to obtain fixture identification, curing time, temperature parameters, and so on.

[0065] The foaming parameter reading unit is used to obtain parameters such as injection flow rate, injection time, injection ratio, and pressure.

[0066] The premixing machine parameter reading unit is used to collect data such as blowing agent content and mixing time.

[0067] An infrared detection unit, which is used to obtain bubble size information, position information, and so on.

[0068] Optionally, during operation, each of the above parameter reading units reads corresponding parameter information based on the PLC (Programmable Logic Controller) of the corresponding component, the structure premixer.

[0069] Please refer to Figure 2 , which shows a schematic diagram of the infrared detection unit provided by an exemplary embodiment of the present application. After the box body comes out of the mold, infrared detection technology is used to obtain the infrared image data of the box body. According to the different characteristics of the bubbles and the box body temperature, combined with the artificial intelligence algorithm, the size and position of the bubbles are accurately and quickly determined. Moreover, the box body identification and the line position information are synchronously obtained, and the detected infrared image data, position information, and box body identification are transmitted to the camera control unit, and can be displayed to the staff through a display.

[0070] In a possible implementation manner, in order to verify the process parameter adjustment strategy generated by the foaming process optimization module 140, the foaming quality prediction module 130 can be used to predict the foaming quality after parameter adjustment based on the mapping relationship model and the process parameter adjustment strategy. The mapping relationship model is used to represent the mapping relationship between each process parameter and the foaming quality.

[0071] Among them, the foaming quality prediction model is a neural network pre-trained based on sample data. Based on this prediction mechanism, the adjustment effect can be evaluated before actually adjusting the process parameters, reducing the trial-and-error cost.

[0072] Then, in order to pre-construct the foaming quality prediction model, the mapping relationship model, etc., the foaming process parameter optimization system provided by the present application also provides a data fusion module and a model library construction module, which is beneficial to realizing the fusion of multi-source heterogeneous data and the construction of the mapping relationship model and the foaming quality prediction model.

[0073] Optionally, the above data acquisition module 110 is further used to obtain the sample foaming process parameters corresponding to each process in the foaming process of refrigerator box bodies of different models.

[0074] Since there are many refrigerator product models, and the box bodies of different models have different structural characteristics and foaming process requirements, the data acquisition module 110 needs to collect the sample foaming process parameters corresponding to the box bodies of various refrigerator models, providing a data basis for establishing a model library applicable to different products later.

[0075] The data fusion module is used to associate and fuse the box body identification of the refrigerator box body with the sample foaming process parameters to obtain sample data.

[0076] In the foaming process of the refrigerator cabinet, due to diverse data sources and inconsistent formats, the various foaming process parameters corresponding to the same cabinet may be scattered in different systems and devices. It is crucial to associate this data through the cabinet identification (such as barcodes) to form complete sample data.

[0077] Optionally, the data fusion module includes a data alignment unit and a data parsing unit. The data alignment unit is used to perform time series alignment on the sample foaming process parameters corresponding to each process, solving the problem of inconsistency of multi-source heterogeneous data in the time dimension. Since the foaming process includes multiple consecutive processes and the data acquisition time points of different processes are different, time series alignment is required to ensure the consistency and integrity of the data. The data parsing unit is used to convert the sample foaming process parameters corresponding to each process into a unified format, solving the problem of inconsistent data formats generated by different devices and different systems, and providing a dataset with a unified format for subsequent data analysis and model construction.

[0078] The foaming process parameter optimization system provided by this application further includes a model library construction module. The model library construction module is used to construct a mapping relationship model based on the sample data.

[0079] Among them, the mapping relationship model is used to characterize the mapping relationship between each process parameter and the foaming quality, and the mapping relationship model can accurately describe the influence mechanism of the change of process parameters on the foaming quality, providing a theoretical basis for process optimization.

[0080] In addition, the model library construction module is also used to construct a foaming quality prediction model.

[0081] Optionally, the model library construction module is also used to train the foaming quality prediction model based on the sample data.

[0082] By using a large number of sample data for model training, the system can continuously improve the prediction accuracy and optimization effect. For different models of cabinets and different molds, the system jointly constructs a model library, mapping out the complex relationship between different parameters and the bubble structure, and realizing a large model for process monitoring of the cross-influence of multiple process parameters.

[0083] In the embodiments of this application, through the above extended function modules, the foaming process parameter optimization system realizes the adaptive expansion for different models of refrigerator cabinets, improves the accuracy and efficiency of data processing, and enhances the prediction ability and optimization effect of the model.

[0084] In a possible implementation manner, in addition to the above basic modules for meeting the optimization of foaming process parameters, the foaming process parameter optimization system further includes some extended function modules for supporting the usability and practical value of the system.

[0085] Optionally, the system further includes a foaming data statistics module for real-time monitoring of foaming process parameters and identifying abnormal points. The data statistics module forms a statistical analysis report of the foaming process data by statistically analyzing the changes, trends, and abnormal points of the foaming process data, providing data support for the continuous monitoring and improvement of the foaming process.

[0086] The foaming process parameter optimization system further includes a visualization module for real-time displaying the change trends of foaming process parameters and abnormal points, and presenting the change trends of process parameters and abnormal conditions through an intuitive graphical interface, facilitating the staff to quickly grasp the production status and promptly discover and handle abnormal situations.

[0087] In addition, the foaming process parameter optimization system of the embodiment of the present application further includes a foaming test data management module and a foaming gun head status management module.

[0088] The foaming test data management module enables technicians to input foaming test data through a computer via the established information input sub-unit, realizing paperless input and management of test data, facilitating the subsequent traceability of foaming raw material quality data.

[0089] The foaming process parameter optimization system further includes a foaming gun head status management module for monitoring whether the foaming gun head is clean through a camera and regularly reminding to clean the gun head to ensure the normal operation state of the foaming equipment and reduce the impact of equipment problems on foaming quality.

[0090] In the embodiment of the present application, through the real-time monitoring and visualization display functions, the usability and practical value of the system are improved. These extended functions enable the system to more comprehensively and accurately optimize the foaming process, greatly improving the foaming quality and production efficiency of the refrigerator cabinet, and enhancing the applicability of the foaming process parameter optimization system.

[0091] Please refer to Figure 3 , which shows a schematic diagram of the foaming process parameter optimization system provided by an exemplary embodiment of the present application. The data acquisition module 110, the foaming defect diagnosis module 120, the foaming quality prediction module 130, the foaming process optimization module 140, the foaming data storage module 150, the test data management module 160, the data statistics module 170, and the foaming gun head status management module 180.

[0092] During the process of optimizing the foaming process parameters, first, the data acquisition module 110 acquires the foaming process parameters corresponding to each process, including but not limited to preheating process parameters, fixture parameters, foaming agent parameters, premixer parameters, infrared non-destructive testing parameters, environmental parameters, and camera parameters, etc. The foaming process parameters of each link are multi-source heterogeneous parameters, which are acquired into the database through various transmission protocols.

[0093] The data acquisition module 110 also performs time alignment and structural integration on the data collected from different PLCs. Moreover, the data acquisition module 110 uses a robust fusion algorithm to fuse the cabinet representation with multi-source heterogeneous parameters to form effective sample data. Through the model library construction module (not shown in the figure), a model library is established for different models of cabinets and different molds, mapping the complex relationship between different parameters and the bubble structure, and then realizing the process monitoring large model for the cross-influence of multiple process parameters.

[0094] The foaming defect diagnosis module 120 uses a causal inference framework to give the quantitative relationship between the foaming process parameters and the bubble quality, and the foaming quality prediction module 130 gives the bubble prediction result through the method of "simulation". Through the coupling method of the causal judgment architecture and machine learning technology, based on the main influencing parameters and the bubble prediction result, a process parameter optimization strategy is formed, thus realizing the automatic optimization of process parameters and overcoming the limitation of over-reliance on manual experience in the traditional foaming process.

[0095] In addition, the foaming data storage module 150 is used to establish a foaming process parameter file and save the parsed parameter data in the database for the query and long-term preservation of historical foaming process parameters. The foaming test data management module 160 realizes the paperless input and management of experimental data by establishing an information input subsystem, and technicians input the foaming experiment data, which is convenient for the traceability of subsequent foaming raw material quality data. The foaming data statistics module 170 statistics the changes, trends and abnormal points of the foaming process data to form the statistical analysis of the foaming process data. The foaming gun head status management module 180 monitors whether the foaming gun is clean through a camera and regularly reminds to clean the gun head.

[0096] Please refer to Figure 4 , which shows the flowchart of the foaming parameter optimization method provided by an exemplary embodiment of the present application. The method includes the following steps:

[0097] Step 401, obtain the foaming process parameters corresponding to each process in the foaming process, and the foaming process parameters include the bubble structure data of the refrigerator cabinet.

[0098] Step 402, based on the foaming process parameters, determine the main influencing parameters that cause bubble defects and provide early warning information.

[0099] Step 403, based on the foaming process parameters, predict the foaming quality of the refrigerator cabinet.

[0100] Step 404, based on the foaming process parameters, the main influencing parameters and the foaming quality, generate a process parameter adjustment strategy.

[0101] In the embodiments of the present application, collecting foaming parameters can form a complete, time-aligned, and format-consistent dataset of foaming process parameters. By quantifying the influence ratio of each foaming process parameter on bubble defects, the main influencing parameters are determined, breaking through the limitations of traditional influencing factor analysis, and being able to more accurately identify the factors leading to bubble defects. Thus, an optimization strategy is proposed based on the main influencing parameters and the foaming prediction structure. Compared with the traditional methods relying on manual experience and experimental design, the solution provided in this embodiment has higher efficiency and accuracy, can effectively improve the foaming quality, and reduce bubble defects.

[0102] Please refer to Figure 5 , which shows a schematic structural diagram of a computer device 500 provided by an exemplary embodiment of the present application. The computer device in the present application may include one or more of the following components: a processor 510 and a memory 520.

[0103] Optionally, the processor 510 runs or executes instructions, programs, code sets, or instruction sets stored in the memory 520, and calls data stored in the memory 520 to execute the steps in the foaming parameter optimization method provided in any of the above embodiments.

[0104] In addition, the processor can also execute various functions of the device and process data. Optionally, the processor 510 can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 510 can integrate one or a combination of several of a central processing unit (CPU), a graphics processing unit (GPU), a neural-network processing unit (NPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the touch display screen; the NPU is used to implement artificial intelligence (AI) functions; the modem is used to process wireless communications. It can be understood that the above modem may not be integrated into the processor 510 and can be implemented separately by a single chip.

[0105] The memory 520 may include a Random Access Memory (RAM), and may also include a Read-Only Memory (ROM). Optionally, the memory 520 includes a non-transitory computer-readable storage medium. The memory 520 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 520 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing each of the following method embodiments, etc.; the data storage area may store data created according to the use of the device (such as audio data, phone book), etc.

[0106] The device in the embodiments of the present application further includes a communication component 530 and a display component 540. Among them, the communication component 530 may be a Bluetooth component, a WiFi (Wireless-Fidelity) component, an NFC (Near Field Communication) component, etc., and is used to communicate with external devices (servers or other devices) through a wired or wireless network; the display component 540 is used to display a graphical user interface and / or receive user interaction operations.

[0107] In addition, those skilled in the art can understand that the structure of the device shown in the above drawings does not limit the device. The device may include more or fewer components than shown in the drawings, or combine some components, or have different component arrangements. For example, the device further includes components such as a radio frequency circuit, an input unit, a sensor, an audio circuit, a speaker, a power supply, etc., which will not be elaborated here.

[0108] The present invention also provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, it executes the foaming parameter optimization method as described above. The storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, an optical disc, or other media suitable for storing computer programs. The computer program on the storage medium contains all the instruction codes required to implement the foaming parameter optimization method. When the program is executed by the processor of a computer device, it can complete all steps such as obtaining foaming process parameters, determining the main influencing parameters, predicting foaming quality, and generating a process parameter adjustment strategy.

[0109] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims described above.

Claims

1. A foaming process parameter optimization system, characterized in that, The system includes: A data acquisition module, configured to obtain the foaming process parameters corresponding to each process in the foaming process, where the foaming process parameters include the bubble structure data of the refrigerator cabinet; A foaming defect diagnosis module, configured to determine the main influencing parameters causing bubble defects based on the foaming process parameters and provide a warning message; A foaming quality prediction module, configured to predict the foaming quality of the refrigerator cabinet based on the foaming process parameters; A foaming process optimization module, configured to generate a process parameter adjustment strategy based on the foaming process parameters, the main influencing parameters, and the foaming quality.

2. The system according to claim 1, characterized in that, The data acquisition module includes: A preheating parameter acquisition unit, configured to obtain the cabinet identifier, the back panel temperature, the inner liner temperature, and the air temperature; A fixture parameter reading unit, configured to obtain the fixture identifier, the curing time, and the temperature parameter; A foaming parameter reading unit, configured to obtain the injection flow rate, the injection time, the injection ratio, and the pressure parameter; A premixer parameter reading unit, configured to collect the blowing agent content and the mixing time data; An infrared detection unit, configured to obtain the bubble size information and the position information.

3. The system according to claim 1, wherein The foaming defect diagnosis module is configured to: Utilize a causal inference model to quantify the influence ratio of each foaming process parameter on the bubble defect; Determine the foaming process parameters with an influence ratio exceeding a preset ratio threshold as the main influencing parameters.

4. The system according to claim 3, wherein The foaming process optimization module is configured to determine a target parameter combination based on the foaming process parameters, the main influencing parameters, and the foaming quality through a large-scale random optimization algorithm; generate the process parameter adjustment strategy based on the target parameter combination; The foaming quality prediction module is further configured to, when obtaining the process parameter adjustment strategy, predict the foaming quality after parameter adjustment based on the mapping relationship model and the process parameter adjustment strategy through a foaming quality prediction model, where the mapping relationship model is used to characterize the mapping relationship between each process parameter and the foaming quality.

5. The system according to claim 1, wherein The data acquisition module is further configured to obtain the sample foaming process parameters corresponding to each process in the foaming process of different models of refrigerator cabinets; The system further includes: A data fusion module, configured to perform associated fusion on the cabinet identifier of the refrigerator cabinet and the sample foaming process parameters to obtain sample data; A model library construction module, configured to construct a mapping relationship model based on the sample data, where the mapping relationship model is used to characterize the mapping relationship between each process parameter and the foaming quality.

6. The system according to claim 5, wherein The data fusion module includes: A data alignment unit, configured to perform time series alignment on the sample foaming process parameters corresponding to each process; A data parsing unit, configured to convert the sample foaming process parameters corresponding to each process into a unified format.

7. The system according to claim 5, characterized in that The model library construction module is further configured to: Train a foaming quality prediction model based on the sample data.

8. The system according to claim 1, wherein The system further includes: A foaming data statistics module, configured to monitor the foaming process parameters in real time and identify abnormal points; A visualization module, configured to display the change trend of the foaming process parameters and the abnormal points in real time.

9. A method for optimizing foaming process parameters, characterized in that, The method includes: Obtain the foaming process parameters corresponding to each process in the foaming process, where the foaming process parameters include the bubble structure data of the refrigerator cabinet; Based on the foaming process parameters, determine the main influencing parameters that cause bubble defects and provide a warning message; Based on the foaming process parameters, predict the foaming quality of the refrigerator cabinet; Generate a process parameter adjustment strategy based on the foaming process parameters, the main influencing parameters, and the foaming quality.

10. A storage medium, on which a computer program is stored. When the computer program is executed by a processor, it executes the foaming process parameter optimization method according to claim 9.

Images