A method, device, equipment and storage medium for optimizing a foaming process

Abstract

The present invention discloses a method, device, equipment and storage medium for optimizing a foaming process, relating to the technology of process optimization. The method includes: after determining the root causes of foaming defects and the action ratios of each root cause, determining the deep factors and the action ratios of each deep factor based on the hidden semi-Markov model; determining the recommended values of the root causes and deep factors, and adjusting the equipment parameters and raw material parameters according to the recommended values to optimize the foaming process. According to the above technical solution, after determining the root causes of foaming defects and the action ratios of each root cause, the deep factors causing the root causes and the action ratios of each deep factor can be determined based on the hidden semi-Markov model, and the recommended values of the root causes and deep factors can also be determined according to historical data. The recommended values are used to adjust the equipment parameters and raw material parameters for the foaming process, so as to optimize the foaming process, solve the problem of high foaming bubble rate, and improve the qualification rate of refrigerator products.

Description

Technical Field

[0001] Embodiments of the present invention relate to process optimization technologies, and particularly to a foaming process optimization method, apparatus, device, and storage medium. Background Art

[0002] The foaming process is a crucial link in the production process of refrigerators. The quality of the foaming process directly determines the quality of the refrigerator, and is also related to the production cost of the production line and the energy-saving performance of the refrigerator, thereby affecting the user experience of using the finished refrigerator. Therefore, the foaming quality is one of the key concerns in the entire refrigerator industry.

[0003] Currently, there are defects such as a high foaming bubble rate in the foaming process of refrigerator factories affected by various factors. The factory can only rely on the subjective experience of process management personnel to judge the factors causing foaming defects, and cannot optimize the foaming process, resulting in a low pass rate and a high repair rate of refrigerator products, causing greater economic losses to the factory. Summary of the Invention

[0004] The present invention provides a foaming process optimization method, apparatus, device, and storage medium to optimize the foaming process, solve the problem of a high foaming bubble rate, and improve the pass rate of refrigerator products.

[0005] In a first aspect, an embodiment of the present invention provides a foaming process optimization method, including:

[0006] After determining the root causes of foaming defects and the action ratio of each of the root causes, determining the deep factors and the action ratio of each of the deep factors based on the hidden semi-Markov model;

[0007] Determining the recommended values of the root causes and the deep factors, and adjusting the equipment parameters and raw material parameters according to the recommended values to optimize the foaming process.

[0008] An embodiment of the present invention provides a foaming process optimization method, including: after determining the root causes of foaming defects and the action ratio of each of the root causes, determining the deep factors and the action ratio of each of the deep factors based on the hidden semi-Markov model; determining the recommended values of the root causes and the deep factors, and adjusting the equipment parameters and raw material parameters according to the recommended values to optimize the foaming process. According to the above technical solutions, based on the data in the foaming process, the root causes of foaming defects and the action ratio of each root cause can be determined. Furthermore, the deep factors causing the root causes and the action ratio of each deep factor can be determined based on the hidden semi-Markov model. Also, the recommended values of the root causes and the deep factors can be determined according to historical data, and these recommended values can be used to adjust the equipment parameters and raw material parameters for the foaming process to optimize the foaming process, solve the problem of a high foaming bubble rate, and improve the pass rate of refrigerator products.

[0009] Further, determining the deep factors and the action ratios of the deep factors based on the hidden semi-Markov model includes:

[0010] Constructing a hidden semi-Markov network based on the hidden semi-Markov model and the auto-encoding neural network of multi-layer neurons;

[0011] Taking the root factors and the action ratios of the root factors as input information and inputting same into the hidden semi-Markov network, and the output information obtained is the deep factors and the action ratios of the deep factors, as well as the root factors and the action ratios of the root factors.

[0012] Further, before taking the root factors and the action ratios of the root factors as input information and inputting same into the hidden semi-Markov network, it further includes:

[0013] Training the hidden semi-Markov network based on the training factors and the action ratios of the training factors, as well as the true deep factors corresponding to the training factors and the action ratios of the true deep factors, and calculating the loss function;

[0014] Performing network optimization based on the backpropagation algorithm until the loss function converges to obtain the hidden semi-Markov network.

[0015] Further, determining the recommended values of the root factors and the deep factors includes:

[0016] Determining the operating range, historical range and recent values of the root factors and the deep factors;

[0017] Performing random dynamic optimization and / or mixed integer optimization on the operating range, the historical range and the recent values to determine the recommended values.

[0018] Further, determining the root factors causing the foaming defects and the action ratios of the root factors includes:

[0019] Obtaining the foaming data, gun head data and production data of the foaming process;

[0020] Taking the foaming data, the gun head data and the production data as input data and inputting same into a pre-trained foaming defect diagnosis model, so that the foaming defect diagnosis model combines the influencing factors affecting the foaming effect, determines the root factors causing the foaming defects based on the convolutional neural network, and determines the action ratios corresponding to the root factors based on the Bayesian causal network.

[0021] Further, the foaming data includes environmental data and material data during the foaming process. The material data includes material status data and material barcode data. Accordingly, obtaining the foaming data, gun head data, and production data during the foaming process includes:

[0022] Determining the data collected by environmental sensors at each link of the foaming process as environmental data; determining the data collected by material sensors at each link of the foaming process as material status data; determining the data scanned by the mobile material barcode gun as material barcode data;

[0023] Acquiring a gun head monitoring video based on an image acquisition device, and determining the gun head data according to the gun head monitoring video;

[0024] Obtaining the production data during the foaming process based on a programmable logic controller (PLC).

[0025] Further, before determining the root causes of foaming defects and the action ratios of each of the root causes, it further includes:

[0026] Determining the original defective product ratio of the original foaming process, and determining the original defective product rate according to the defective product ratio;

[0027] After optimizing the foaming process, it further includes:

[0028] Determining the optimized defective product ratio of the foaming process of the optimized foaming process, and determining the optimized defective product rate according to the optimized defective product ratio;

[0029] Determining the optimization efficiency according to the original defective product rate and the optimized defective product rate.

[0030] In a second aspect, an embodiment of the present invention further provides a foaming process optimization device, including:

[0031] A determination module, configured to determine deep factors and the action ratios of each of the deep factors based on a hidden semi-Markov model after determining the root causes of foaming defects and the action ratios of each of the root causes;

[0032] An adjustment module, configured to determine the recommended values of the root causes and the deep factors, and adjust the equipment parameters and raw material parameters according to the recommended values to optimize the foaming process.

[0033] In a third aspect, an embodiment of the present invention further provides a computer device, the device including:

[0034] One or more processors;

[0035] A storage device, configured to store one or more programs,

[0036] When the one or more programs are executed by the one or more processors, the one or more processors implement the foaming process optimization method according to any one of the first aspect.

[0037] In a fourth aspect, an embodiment of the present invention further provides a storage medium including computer-executable instructions, and the computer-executable instructions are used to execute the foaming process optimization method according to any one of the first aspect when executed by a computer processor.

[0038] In a fifth aspect, the present application provides a computer program product, and the computer program product includes computer instructions. When the computer instructions run on a computer, the computer executes the foaming process optimization method provided in the first aspect.

[0039] It should be noted that the above computer instructions can be stored on a computer-readable storage medium in whole or in part. Among them, the computer-readable storage medium can be packaged together with the processor of the foaming process optimization device, or can be separately packaged from the processor of the foaming process optimization device. The present application does not make any limitation in this regard.

[0040] For the descriptions of the second aspect, the third aspect, the fourth aspect, and the fifth aspect in the present application, reference can be made to the detailed description of the first aspect; and for the beneficial effects of the descriptions of the second aspect, the third aspect, the fourth aspect, and the fifth aspect, reference can be made to the analysis of the beneficial effects of the first aspect, which will not be elaborated here.

[0041] In the present application, the names of the above-mentioned foaming process optimization devices do not limit the devices or functional modules themselves. In actual implementation, these devices or functional modules may appear under other names. As long as the functions of each device or functional module are similar to those of the present application and fall within the scope of the claims of the present application and their equivalent technologies.

[0042] These aspects or other aspects of the present application will be more clearly understood in the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flowchart of a foaming process optimization method provided in Embodiment 1 of the present invention;

[0044] Figure 2 It is a flowchart of a foaming process optimization method provided in Embodiment 2 of the present invention;

[0045] Figure 3 It is a fishbone diagram for determining the defective rate and the defective proportion in a foaming process optimization method provided in Embodiment 2 of the present invention;

[0046] Figure 4 It is a structural schematic diagram of a foaming process optimization device provided in Embodiment 3 of the present invention;

[0047] Figure 5 A schematic structural diagram of a computer device provided in the fourth embodiment of the present invention. Specific embodiments

[0048] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present invention, rather than limiting the present invention. In addition, it should be noted that for the sake of description, only parts related to the present invention are shown in the drawings, rather than all the structures.

[0049] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone.

[0050] The terms "first" and "second" in the specification and drawings of this application are used to distinguish different objects, or to distinguish different processes for the same object, rather than to describe the specific order of the objects.

[0051] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally further include other unlisted steps or units, or may optionally further include other steps or units inherent to these processes, methods, products or devices.

[0052] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operations are completed, but there may also be additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc. In addition, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0053] It should be noted that in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or more advantageous than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0054] In the description of the present application, unless otherwise specified, the meaning of "a plurality of" refers to two or more.

[0055] Embodiment 1

[0056] Figure 1 As shown in the flowchart of a foaming process optimization method provided in Embodiment 1 of the present invention, this embodiment is applicable to situations where foaming defects need to be optimized. This method can be executed by a foaming process optimization device, such as Figure 1 shown, and specifically includes the following steps:

[0057] Step 110: After determining the root causes of the foaming defects and the action ratios of the respective root causes, determine the deep factors and the action ratios of the respective deep factors based on the hidden semi-Markov model.

[0058] Specifically, a foaming defect diagnosis is performed on the foaming process based on the data of the foaming process, and the root causes of the foaming defects and the action ratios of the respective root causes can be determined.

[0059] Among them, the data of the foaming process includes foaming data, gun head data, and production data. The foaming data includes environmental data and material data. The environmental data can include the data obtained by environmental sensors located in each link of the foaming process, specifically including: environmental temperature, environmental humidity, environmental air pressure, and product coding, etc. The material data can include the material sensing data obtained by material sensors located in each link of the foaming process, specifically including preheating time, predicted temperature, material environmental temperature, and foaming time, etc.; the material data can also include the material barcode data scanned by a mobile material barcode gun, specifically including material type and material number. The gun head data can be the gun head operation status data determined according to the gun head monitoring video collected by the image acquisition device located in each link of the foaming process. The gun head operation status data can be used to determine whether the foaming gun head is clean, so as to regularly remind the user to clean the foaming gun head. The production data can be the data generated by the production equipment during the foaming process of the refrigerator, and the production data can be obtained through a Programmable Logic Controller (PLC). The production data can include the parameter data of key links related to the foaming process, such as foaming preparation, premixing, box preheating, and foaming agent injection, specifically including preheating process parameters, dry part (fixture) parameters, wet part (foaming machine) parameters, premixer parameters, and infrared quality inspection parameters.

[0060] Furthermore, based on the foaming data, gun head data, and production data, the root causes of the foaming defects and the action ratios of the respective root causes can be determined.

[0061] In practical applications, the root factors and the action ratios of each root factor can be used as the input information of the hidden semi-Markov model. After the hidden semi-Markov model processes the root factors and each root factor, the obtained output results include: the deep factors causing the root factors and the action ratios of each deep factor, as well as the root factors and the action ratios of each root factor.

[0062] In the embodiment of the present invention, based on the hidden semi-Markov model, the deep factors causing the foaming defects and the action ratios of each deep factor can be determined, so as to realize the excavation of the deep influencing factors of the foaming defects.

[0063] Step 120: Determine the recommended values of the root factors and the deep factors, and adjust the equipment parameters and raw material parameters according to the recommended values to optimize the foaming process.

[0064] Specifically, according to the data of the historical foaming process, the historical ranges and recent values of the root factors and the deep factors can be obtained. Of course, the allowable operation ranges of the root factors and the deep factors can also be obtained. Furthermore, according to the allowable operation range, historical range and recent value of the root factor, the recommended value of the root factor can be determined, and according to the allowable operation range, historical range and recent value of the deep factor, the recommended value of the deep factor can be determined. Of course, based on the recommended values of the root factors and the deep factors, the equipment parameters and raw material parameters of the foaming process can be adjusted to optimize the process, so as to reduce the bubble rate of the foam and improve the qualification rate of the refrigerator products.

[0065] In the embodiment of the present invention, by optimizing the values of the root factors and the deep factors, the recommended values of the root factors and the deep factors can be determined. The recommended values can be used to adjust the equipment parameters and raw material parameters of the foaming process. Based on the adjustment of the equipment parameters and raw material parameters, the optimization of the foaming process can be realized.

[0066] A foaming process optimization method provided in Embodiment 1 of the present invention includes: after determining the root factors causing the foaming defects and the action ratios of each root factor, determining the deep factors and the action ratios of each deep factor based on the hidden semi-Markov model; determining the recommended values of the root factors and the deep factors, and adjusting the equipment parameters and raw material parameters according to the recommended values to optimize the foaming process. According to the above technical solution, the root factors causing the foaming defects and the action ratios of each root factor can be determined according to the data in the foaming process. Furthermore, the deep factors causing the root factors and the action ratios of each deep factor can be determined based on the hidden semi-Markov model. The recommended values of the root factors and the deep factors can also be determined according to the historical data. The recommended values can be used to adjust the equipment parameters and raw material parameters of the foaming process to realize the optimization of the foaming process, solve the problem of high foam bubble rate, and improve the qualification rate of the refrigerator products.

[0067] Embodiment 2

[0068] Figure 2 The flowchart of an optimized foaming process method provided in the second embodiment of the present invention. This embodiment is a specific implementation based on the above embodiment. As Figure 2 shown, in this embodiment, the method may further include:

[0069] Step 210: Determine the root causes of foaming defects and the proportion of the effects of each of the root causes.

[0070] In one implementation, step 210 may specifically include:

[0071] Obtain foaming data, gun head data, and production data during the foaming process; input the foaming data, the gun head data, and the production data as input data into a pre-trained foaming defect diagnosis model, so that the foaming defect diagnosis model combines the influencing factors affecting the foaming effect, determines the root causes of foaming defects based on a convolutional neural network, and determines the proportion of the effects corresponding to each of the root causes based on a Bayesian causal network.

[0072] Among them, the foaming defect diagnosis model includes a convolutional neural network and a Bayesian causal network, and is used to determine the root causes of foaming defects. Its input information can be data related to the foaming process, and the output information can be the root causes of foaming defects and the proportion of the effects of each root cause on foaming defects.

[0073] The influencing factors include wet end factors, dry end factors, premixing factors, raw material factors, preheating factors, and environmental factors. The wet end factors include gun head data and foaming gun data. The gun head data includes gun head pressure, gun head temperature, gun head cleaning status, and gun head replacement frequency. The foaming gun data includes foaming gun temperature, foaming gun pressure, and foaming gun flow rate. The dry end factors include fixture data, mandrel data, and curing time. The fixture data includes fixture top plate temperature and fixture side plate temperature. The mandrel data includes mandrel temperature. The premixing factors include premixing ratio. The raw material factors include free bubble density, water content, and viscosity. The prediction factors include oven temperature, waiting time, and cabinet temperature. The environmental factors include atmospheric pressure, humidity, and temperature.

[0074] Specifically, environmental sensors set at each link of the foaming process can obtain environmental data; material sensors set at each link of the foaming process can obtain material state data; a mobile material barcode gun can obtain material barcode data; an image acquisition device set around the gun head can obtain image data of the foaming gun head, and the running state data of the gun head can be determined according to the gun head monitoring video, so as to determine whether the foaming gun head is clean; the PLC can be connected to multiple production devices in the production process to obtain production data generated by each production device during the foaming process.

[0075] After inputting the foaming process data as input data into the foaming defect diagnosis model, the foaming defect diagnosis module can analyze and process the foaming process data in combination with the influencing factors affecting the foaming effect. First, the foaming process data can be input into a convolutional neural network to determine the root causes of the foaming defects. Then, the foaming process data and the root causes are input into a Bayesian causal network to determine the corresponding action ratios of each root cause based on Bayesian probability analysis. Finally, the root causes and the corresponding action ratios of each root cause are used as output data to output from the foaming defect diagnosis model.

[0076] In practical applications, the foaming process data can be input into the foaming defect diagnosis model as input data according to the date or batch to determine the root causes of the foaming defects corresponding to the corresponding date or batch.

[0077] It should be noted that within a preset time or preset batch, the defective product ratio can be determined based on the numbers of grade A, grade B, and grade C bubbles. Based on the defective product ratio, it can be determined whether there are foaming defects in the refrigerator. If there are foaming defects, the root causes of the foaming defects and the corresponding action ratios of each root cause are determined based on the foregoing steps; if there are no foaming defects, the refrigerator foaming process continues.

[0078] Furthermore, the foaming data includes the environmental data and material data of the foaming process. The material data includes the material state data and the material barcode data. Correspondingly, obtaining the foaming data, gun head data, and production data of the foaming process includes:

[0079] Determining the data collected by the environmental sensors at each link of the foaming process as the environmental data; determining the data collected by the material sensors at each link of the foaming process as the material state data; determining the data scanned by the mobile material barcode gun as the material barcode data; acquiring the gun head monitoring video based on the image acquisition device, and determining the gun head data according to the gun head monitoring video; acquiring the production data of the foaming process based on the programmable logic controller PLC.

[0080] In the embodiments of the present invention, the foaming process-related data can be obtained based on sensors, image acquisition devices, mobile material barcode guns, and PLCs. The obtained foaming process-related data can be used to analyze the root causes of foaming defects when there are foaming defects, providing a data basis for foaming defect diagnosis. The pre-trained foaming defect diagnosis model can be used to analyze and trace the foaming defects to determine the root causes of the foaming defects and the action ratios of each root cause on the foaming defects.

[0081] Step 220: Determine the deep factors and the action ratios of each of the deep factors based on the hidden semi-Markov model.

[0082] In one implementation, step 220 may specifically include:

[0083] Construct a hidden semi-Markov network based on the hidden semi-Markov model and the self-encoding neural network of multi-layer neurons; perform network training on the hidden semi-Markov network based on the training factors and the action ratios of the training factors, as well as the true deep factors corresponding to the training factors and the action ratios of the true deep factors, and calculate the loss function; perform network optimization based on the backpropagation algorithm until the loss function converges to obtain the hidden semi-Markov network; input the root factors and the action ratios of each root factor as input information into the hidden semi-Markov network, and the output information obtained is the deep factors and the action ratios of each deep factor, as well as the root factors and the action ratios of each root factor.

[0084] Specifically, the hidden semi-Markov model and the self-encoding neural network of multi-layer neurons can form a hidden semi-Markov network. In practical applications, the hidden semi-Markov network can be trained in the form of a self-encoding neural network of multi-layer neurons. Specifically, the hidden semi-Markov network can be trained based on the root factors and the action ratios of the root factors that cause foaming defects in the historical foaming process, as well as the deep factors that cause the root factors and the action ratios of the deep factors. The root factors are used as training factors, and the deep factors that cause the root factors are used as true deep factors. Input the training factors and the action ratios of the training factors as input information into the hidden semi-Markov network, and the output information obtained is the training deep factors and the action ratios of the training deep factors. Based on the training deep factors and the action ratios of the training deep factors, as well as the true deep factors and the action ratios of the true deep factors, the loss function can be determined. Furthermore, the hidden semi-Markov network can be optimized based on the backpropagation algorithm. When the loss function converges, the network hyperparameters can be determined, and then the hidden semi-Markov network can be obtained. The hidden semi-Markov network can be used to determine the root factors and the action ratios of the root factors that cause foaming defects, as well as the deep factors that cause the root factors and the action ratios of the deep factors.

[0085] In the embodiment of the present invention, the exploration and excavation of the deep factors that cause foaming defects are realized, providing data support for process optimization.

[0086] Step 230, determine the recommended values of the root factors and the deep factors.

[0087] Among them, the storage device may store the allowable operation ranges, historical ranges, and recent values of the foaming data, gun head data, and production data involved in the foaming process.

[0088] In one implementation, step 230 may specifically include:

[0089] Determine the operating range, historical range, and recent value of the root factors and the deep factors; perform stochastic dynamic optimization and / or mixed integer optimization on the operating range, the historical range, and the recent value to determine the recommended value.

[0090] In an embodiment of the present invention, according to the allowable operating range, historical range, and recent value of the root factors, the recommended value of the root factors can be determined, and according to the allowable operating range, historical range, and recent value of the deep factors, the recommended value of the deep factors can be determined.

[0091] Step 240: Determine the original defective product ratio of the original foaming process, and determine the original defective product rate according to the defective product ratio.

[0092] Specifically, after determining the action ratio corresponding to each root factor, a fishbone diagram can be determined according to the influencing factors and the influencing factors included in each influencing factor. Figure 3 A fishbone diagram for determining the defective product rate and defective product ratio in a foaming process optimization method provided in the second embodiment of the present invention is as Figure 3 shown. The defective product ratio caused by the foaming defect is deployed at the end of the fishbone diagram, which may specifically include the average number of Class A bubbles, the number of Class B bubbles, and the number of Class C bubbles. Furthermore, the defective product rate can be determined according to the number of Class A bubbles, the number of Class B bubbles, and the number of Class C bubbles.

[0093] In practical applications, the original defective product ratio of the original foaming process can be determined before optimizing the foaming process, and the original defective product rate can be determined according to the defective product ratio, that is, the original defective product ratio of the original foaming process is determined before step 260, and the original defective product rate is determined according to the defective product ratio, and the specific execution order of step 240 is not limited.

[0094] Step 250: Adjust the equipment parameters and raw material parameters according to the recommended value to optimize the foaming process.

[0095] Step 260: Determine the optimized defective product ratio of the foaming process for optimizing the foaming process, and determine the optimized defective product rate according to the optimized defective product ratio.

[0096] Specifically, after optimizing the foaming process, it is also possible to determine the optimized defective product ratio and the optimized defective product rate of the foaming process based on Figure 3 the fishbone diagram shown.

[0097] Step 270: Determine the optimization efficiency according to the original defective product rate and the optimized defective product rate.

[0098] Specifically, first, the difference between the original defective product rate and the optimized defective product rate can be determined, and the ratio of the difference to the original defective product rate is determined as the optimization efficiency.

[0099] A foam process optimization method provided in the second embodiment of the present invention includes: determining the root causes of foam defects and the action ratios of the root causes; determining the deep factors and the action ratios of the deep factors based on the hidden semi-Markov model; determining the recommended values of the root causes and the deep factors; determining the original defective product ratio of the original foam process and determining the original defective product rate according to the defective product ratio; adjusting the equipment parameters and raw material parameters according to the recommended values to optimize the foam process; determining the optimized defective product ratio of the foam process after optimizing the foam process and determining the optimized defective product rate according to the optimized defective product ratio; and determining the optimization efficiency according to the original defective product rate and the optimized defective product rate. According to the above technical solution, the root causes of foam defects and the action ratios of the root causes can be determined based on the data in the foam process. Furthermore, the deep factors causing the root causes and the action ratios of the deep factors can be determined based on the hidden semi-Markov model. The recommended values of the root causes and the deep factors can also be determined according to historical data. The recommended values can be used to adjust the equipment parameters and raw material parameters for the foam process to optimize the foam process, solve the problem of high foam bubble rate, and improve the qualified rate of refrigerator products.

[0100] In addition, the optimization efficiency is determined according to the original defective product rate before optimizing the foam process and the optimized defective product rate after optimizing the foam process, so that the optimization effect of the foam process is visualized in data.

[0101] Embodiment Three

[0102] Figure 4 The structure diagram of a foam process optimization device provided in the third embodiment of the present invention is applicable to the situation where foam defects need to be optimized. The device can be implemented by software and / or hardware and is generally integrated in a computer device.

[0103] As Figure 4 shown, the device includes:

[0104] A determination module 410, configured to determine the deep factors and the action ratios of the deep factors based on the hidden semi-Markov model after determining the root causes of foam defects and the action ratios of the root causes;

[0105] An adjustment module 420, configured to determine the recommended values of the root causes and the deep factors, and adjust the equipment parameters and raw material parameters according to the recommended values to optimize the foam process.

[0106] The foaming process optimization device provided in this embodiment, after determining the root causes of foaming defects and the action ratios of each of the root causes, determines the deep factors and the action ratios of each of the deep factors based on the hidden semi-Markov model; determines the recommended values of the root causes and the deep factors, and adjusts the equipment parameters and raw material parameters according to the recommended values to optimize the foaming process. According to the above technical solution, the root causes of foaming defects and the action ratios of each root cause can be determined based on the data during the foaming process. Furthermore, the deep factors causing the root causes and the action ratios of each deep factor can be determined based on the hidden semi-Markov model. The recommended values of the root causes and the deep factors can also be determined according to historical data. These recommended values can be used to adjust the equipment parameters and raw material parameters for the foaming process to optimize the foaming process, solve the problem of high foaming bubble rate, and improve the qualification rate of refrigerator products.

[0107] Based on the above embodiment, the determination module 410 is specifically configured to:

[0108] Obtain the foaming data, gun head data, and production data of the foaming process;

[0109] Use the foaming data, the gun head data, and the production data as input data and input them into a pre-trained foaming defect diagnosis model, so that the foaming defect diagnosis model combines the influencing factors affecting the foaming effect, determines the root causes of foaming defects based on a convolutional neural network, and determines the action ratios corresponding to each of the root causes based on a Bayesian causal network;

[0110] Construct a hidden semi-Markov network based on the hidden semi-Markov model and an autoencoder neural network with multiple layers of neurons;

[0111] Based on the training factors and the action ratios of the training factors, as well as the true deep factors corresponding to the training factors and the action ratios of the true deep factors, perform network training on the hidden semi-Markov network and calculate the loss function;

[0112] Perform network optimization based on the backpropagation algorithm until the loss function converges to obtain the hidden semi-Markov network;

[0113] Use the root causes and the action ratios of each of the root causes as input information and input them into the hidden semi-Markov network. The output information obtained is the deep factors and the action ratios of each of the deep factors, as well as the root causes and the action ratios of each of the root causes.

[0114] In one implementation, the foaming data includes the environmental data and material data of the foaming process. The material data includes material state data and material barcode data. Correspondingly, obtaining the foaming data, gun head data, and production data of the foaming process includes:

[0115] Determine the data collected by the environmental sensors at each link of the foaming process as environmental data; determine the data collected by the material sensors at each link of the foaming process as material state data; determine the data scanned by the mobile material barcode gun as material barcode data;

[0116] Based on the image acquisition device, collect the gun head monitoring video, and determine the gun head data according to the gun head monitoring video;

[0117] Based on the programmable logic controller PLC, obtain the production data of the foaming process.

[0118] On the basis of the above embodiments, the adjustment module 420 is specifically used for:

[0119] Determine the operating range, historical range and recent values of the root cause and the deep cause;

[0120] Perform random dynamic optimization and / or mixed integer optimization on the operating range, the historical range and the recent values to determine the recommended value;

[0121] Adjust the equipment parameters and raw material parameters according to the recommended value to optimize the foaming process.

[0122] On the basis of the above embodiments, the device further includes:

[0123] An efficiency determination module, specifically used for: before optimizing the foaming process, determine the original defective product ratio of the original foaming process, and determine the original defective product rate according to the defective product ratio; after optimizing the foaming process, determine the optimized defective product ratio of the foaming process of the optimized foaming process, and determine the optimized defective product rate according to the optimized defective product ratio; determine the optimization efficiency according to the original defective product rate and the optimized defective product rate.

[0124] The foaming process optimization device provided by the embodiments of the present invention can execute the foaming process optimization method provided by any embodiment of the present invention, and has corresponding function modules and beneficial effects for executing the method.

[0125] It should be noted that in the embodiments of the above foaming process optimization device, the included units and modules are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0126] Embodiment 4

[0127] Figure 5 It is a schematic structural diagram of a computer device provided by Embodiment 4 of the present invention. Figure 5FIG. 0 shows a block diagram of an exemplary computer device 5 suitable for use in implementing embodiments of the present invention. Figure 5 The shown computer device 5 is only an example and should not impose any limitation on the functions and scope of use of the embodiments of the present invention.

[0128] As Figure 5 shown, the computer device 5 is presented in the form of a general-purpose computing computer device. The components of the computer device 5 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0129] The bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus structures. By way of example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0130] The computer device 5 typically includes a variety of computer system-readable media. These media can be any available media that can be accessed by the computer device 5, including volatile and non-volatile media, removable and non-removable media.

[0131] The system memory 28 may include computer system-readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 5 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, a storage system 34 can be used to read and write non-removable, non-volatile magnetic media ( Figure 5 not shown, typically referred to as a "hard disk drive"). Although Figure 5 not shown in FIG., a disk drive for reading and writing removable non-volatile disks (such as "floppy disks") and an optical disk drive for reading and writing removable non-volatile optical disks (such as CD-ROM, DVD-ROM, or other optical media) can be provided. In these cases, each drive can be connected to the bus 18 through one or more data media interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0132] A program / utilities 40 having a set (at least one) of program modules 42 can be stored in, for example, the system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. The program modules 42 generally execute the functions and / or methods in the embodiments described in the present invention.

[0133] The computer device 5 can also communicate with one or more external devices 14 (such as a keyboard, a pointing device, a display 24, etc.), and can also communicate with one or more devices that enable a user to interact with the computer device 5, and / or communicate with any device that enables the computer device 5 to communicate with one or more other computing devices (such as a network card, a modem, etc.). Such communication can be carried out through the input / output (I / O) interface 22. Moreover, the computer device 5 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 20. As Figure 5 shown, the network adapter 20 communicates with other modules of the computer device 5 through the bus 18. It should be understood that although Figure 5 not shown in the figure, other hardware and / or software modules can be used in conjunction with the computer device 5, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0134] The processing unit 16 executes various functional applications and page displays by running the programs stored in the system memory 28, for example, implementing the foam process optimization method provided in the embodiments of the present invention. The method includes:

[0135] After determining the root causes of the foam defects and the proportion of the effects of each of the root causes, determining the deep factors and the proportion of the effects of each of the deep factors based on the hidden semi-Markov model;

[0136] Determining the recommended values of the root causes and the deep factors, and adjusting the device parameters and raw material parameters according to the recommended values to optimize the foam process.

[0137] Of course, those skilled in the art can understand that the processor can also implement the technical solutions of the foam process optimization method provided in any embodiment of the present invention.

[0138] Embodiment Five

[0139] Embodiment Five of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements, for example, the foam process optimization method provided in the embodiments of the present invention. The method includes:

[0140] After determining the root factors causing the foaming defects and the action ratios of the root factors, determine the deep factors and the action ratios of the deep factors based on the hidden semi-Markov model;

[0141] Determine the recommended values of the root factors and the deep factors, and adjust the equipment parameters and raw material parameters according to the recommended values to optimize the foaming process.

[0142] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0143] The computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal may take various forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0144] The program code contained on the computer-readable medium may be transmitted by any suitable medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0145] Computer program code for performing the operations of the present invention may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it may be connected to an external computer (e.g., connected through the Internet using an Internet service provider).

[0146] Those of ordinary skill in the art should understand that the above-described modules or steps of the present invention can be implemented using a general-purpose computing device. They can be centralized on a single computing device or distributed across a network composed of multiple computing devices. Optionally, they can be implemented using program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0147] Note that the above is only the preferred embodiment of the present invention and the applied technical principles. Those skilled in the art will understand that the present invention is not limited to the specific embodiments here. Various obvious changes, re-adjustments, and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments. Without departing from the concept of the present invention, more other equivalent embodiments can be included, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for optimizing a foaming process, characterized in that, Including: Obtain foaming data, gun head data, and production data during the foaming process; Input the foaming data, the gun head data, and the production data as input data into a pre-trained foaming defect diagnosis model, so that the foaming defect diagnosis model combines the influencing factors affecting the foaming effect, determines the root causes of the foaming defects based on a convolutional neural network, and determines the action ratios corresponding to each of the root causes based on a Bayesian causal network; Construct a hidden semi-Markov network based on a hidden semi-Markov model and a multi-layer neuron autoencoder neural network; Based on the training factors and the action ratios of the training factors, as well as the corresponding true deep factors and the action ratios of the true deep factors of the training factors, train the hidden semi-Markov network and calculate the loss function; Perform network optimization based on the backpropagation algorithm until the loss function converges to obtain the hidden semi-Markov network; Input the root causes and the action ratios of each of the root causes as input information into the hidden semi-Markov network, and the output information obtained is the deep factors and the action ratios of each of the deep factors, as well as the root causes and the action ratios of each of the root causes; Determine the operating ranges, historical ranges, and recent values of the root causes and the deep factors; Perform random dynamic optimization and / or mixed integer optimization on the operating ranges, the historical ranges, and the recent values to determine the recommended values, and adjust the equipment parameters and raw material parameters according to the recommended values to optimize the foaming process.

2. The foam process optimization method according to claim 1, wherein The foaming data includes environmental data and material data during the foaming process, and the material data includes material status data and material barcode data. Correspondingly, obtaining the foaming data, gun head data, and production data during the foaming process includes: Determine the data collected by the environmental sensors located at each link of the foaming process as environmental data; Determine the data collected by the material sensors located at each link of the foaming process as material status data; Determine the data scanned by the mobile material barcode gun as material barcode data; Collect the gun head monitoring video based on an image acquisition device, and determine the gun head data according to the gun head monitoring video; Obtain the production data during the foaming process based on a programmable logic controller (PLC).

3. The foaming process optimization method according to claim 2, characterized in that, Before optimizing the foaming process, it further includes: Determine the original defective product ratio of the original foaming process, and determine the original defective product rate according to the defective product ratio; After optimizing the foaming process, it further includes: Determine the optimized defective product ratio of the foaming process of the optimized foaming process, and determine the optimized defective product rate according to the optimized defective product ratio; Determine the optimization efficiency according to the original defective product rate and the optimized defective product rate.

4. An apparatus for optimizing a foaming process, characterized in that, Including: A determination module for obtaining foaming data, gun head data, and production data during the foaming process; Input the foaming data, the gun head data, and the production data as input data into a pre-trained foaming defect diagnosis model, so that the foaming defect diagnosis model combines the influencing factors affecting the foaming effect, determines the root causes of the foaming defects based on a convolutional neural network, and determines the corresponding action ratios of each of the root causes based on a Bayesian causal network; construct a hidden semi-Markov network based on a hidden semi-Markov model and an auto-encoder neural network with multiple neurons; Based on the training factors and the action ratios of the training factors, as well as the corresponding true deep factors and the action ratios of the true deep factors of the training factors, train the hidden semi-Markov network and calculate the loss function; perform network optimization based on the backpropagation algorithm until the loss function converges to obtain the hidden semi-Markov network; input the root causes and the action ratios of each of the root causes as input information into the hidden semi-Markov network, and the output information obtained is the deep factors and the action ratios of each of the deep factors, as well as the root causes and the action ratios of each of the root causes; An adjustment module, configured to determine the operating range, historical range, and recent values of the root causes and the deep factors; perform random dynamic optimization and / or mixed integer optimization on the operating range, the historical range, and the recent values to determine a recommended value, and adjust the equipment parameters and raw material parameters according to the recommended value to optimize the foaming process.

5. A computer device, characterized in that, The device includes: One or more processors; A memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the foaming process optimization method according to any one of claims 1-3.

6. A storage medium containing computer-executable instructions, where the computer-executable instructions are used to execute the foaming process optimization method according to any one of claims 1-3 when executed by a computer processor.

Images