Process quality detection methods, equipment and storage media based on industrial processes

Abstract

This application provides a method, equipment, and storage medium for process quality inspection based on industrial processes, enabling the detection of process quality. The method includes: determining key process parameters corresponding to process nodes; analyzing the key process parameters corresponding to the process nodes to determine stability results; analyzing the process capability index corresponding to the process nodes based on the stability results; and determining the process inspection result based on the process capability index. For complex processes and procedures, it can identify key process parameters, achieve process capability evaluation, and optimize daily quality control.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a process quality inspection method based on industrial processes, an electronic device, and a storage medium. Background Technology

[0002] A process refers to the methods and procedures used to process or treat various raw materials and semi-finished products using various production tools. In different industrial production processes, processes may have different steps and operating methods. For example, the ceramic making process in ceramic production includes processes such as throwing, sun-drying, glazing, and firing. Similarly, the painting process in automobiles includes processes such as electrophoresis, adhesive application, and topcoat spraying.

[0003] In industrial production, every process step can affect product quality. For example, in the painting process of automobiles, welding slag adheres to the car body and forms particles, and incomplete flow of the electrophoretic coating solution after exiting the tank can form secondary flow marks. Both of these can affect the production quality of the vehicle. If the process is not up to standard, it may be necessary to remake the product, which will affect the production efficiency. Summary of the Invention

[0004] This application provides a method for detecting process quality in industrial processes, enabling the detection of process quality.

[0005] Accordingly, embodiments of this application also provide an electronic device and a storage medium to ensure the implementation and application of the above system.

[0006] To address the aforementioned problems, this application discloses a process quality inspection method based on industrial processes, the method comprising:

[0007] The key process parameters corresponding to the process nodes are determined through identification by the identification model.

[0008] The key process parameters corresponding to the process nodes are analyzed to determine the stability results;

[0009] Based on the stability results, analyze the process capability index corresponding to the process node;

[0010] The process testing results are determined based on the process capability index.

[0011] Optionally, the analysis of key process parameters corresponding to the process node to determine the stability results includes:

[0012] Statistical analysis is performed on the key process parameters corresponding to the process node to determine the controlled state information; stability analysis is performed based on the controlled state information to determine the stability result of the process node.

[0013] Optionally, it also includes: if the stability result is poor stability, then analyze the quality problems corresponding to the process node and determine improvement suggestions.

[0014] Optionally, determining the key process parameters corresponding to the process node includes:

[0015] During the production process, identify multiple process nodes of the target process flow and their production data;

[0016] For each process node, the generated data is input into the identification model to determine the corresponding key process parameters, which include process measurement data and / or statistical data of the process measurement data.

[0017] Optionally, statistical analysis is performed on the key process parameters corresponding to the process nodes to determine the controlled state information, including:

[0018] For metering-type key process parameters, a statistical process control chart is drawn based on the key process parameters, and the controlled state information is determined based on the statistical process control chart.

[0019] For the key process parameters of percentage type, a percentile control chart is drawn based on the key process parameters, and the controlled state information is determined based on the percentile control chart.

[0020] Optionally, the step of drawing statistical process control charts based on key process parameters includes:

[0021] Perform a normality test on the key process parameters corresponding to the process nodes to determine the normal distribution results;

[0022] A statistical process control chart was drawn based on the normal distribution results.

[0023] Optionally, the step of drawing a statistical process control chart based on the normal distribution results includes:

[0024] If the normal distribution result satisfies a normal distribution, then a process control chart is drawn based on the statistical process control method;

[0025] If the normal distribution result does not meet the normal distribution, the key process parameters are transformed to meet the normal distribution, and a process control chart is drawn based on statistical process control method when the normal distribution is met.

[0026] Optionally, the step of analyzing the process capability index corresponding to the process node based on the stability results includes:

[0027] If the stability result is good, then the process capability index corresponding to the process node is determined based on the type of key process parameters.

[0028] Optionally, determining the process capability index corresponding to the process node based on the type of key process parameters includes:

[0029] For metering-type key process parameters, the process capability index corresponding to the process node is determined based on the normal distribution results.

[0030] For key process parameters in percentage form, the process capability index corresponding to the process node is determined based on the percentile method.

[0031] Optionally, determining the process testing results based on the process capability index includes:

[0032] Determine the capability level corresponding to the process capability index, and determine the process testing results based on the capability level.

[0033] Optionally, determining the process testing results based on the capability level includes:

[0034] Determine whether the capability level meets the process production conditions of the process node;

[0035] If the process production conditions are not met, analyze the reasons for the insufficient process capability and generate process inspection results for the process to be improved.

[0036] If the production conditions are met, a qualified process inspection result will be generated.

[0037] This embodiment also provides a process quality testing device for industrial processes, which is applied in server-side electronic equipment.

[0038] The parameter determination module is used to determine the key process parameters corresponding to the process nodes. The key process parameters corresponding to the process nodes are determined by the identification model.

[0039] The stability analysis module is used to analyze the key process parameters corresponding to the process nodes and determine the stability results.

[0040] The capability index determination module is used to analyze the process capability index corresponding to the process node based on the stability results.

[0041] The detection module is used to determine the process detection results based on the process capability index.

[0042] This application also discloses an electronic device, including: a processor; and a memory storing executable code thereon, wherein when the executable code is executed by the processor, the method described in this application is performed.

[0043] This application also discloses one or more machine-readable media storing executable code thereon, which, when executed by a processor, performs the method described in this application.

[0044] Compared with the prior art, the embodiments of this application have the following advantages:

[0045] In this embodiment, process nodes are determined for different processes, key process parameters are analyzed based on the process nodes, and the stability results of the process nodes are analyzed based on the key process parameters to determine whether the process is stable. Then, the process capability index corresponding to the process node is analyzed based on the stability results, and the process detection results are determined based on the process capability index. For complex procedures and processes, key process parameters can be identified, process capability evaluation can be achieved, and the daily quality control level can be optimized. Attached Figure Description

[0046] Figure 1 This is a flowchart illustrating the steps of an embodiment of a process quality testing method for an industrial process according to this application.

[0047] Figure 2 This is a schematic diagram of an example of a coating process according to an embodiment of this application;

[0048] Figure 3 This is a flowchart illustrating the steps of another embodiment of a process quality inspection method for an industrial process according to this application.

[0049] Figure 4 This is a schematic diagram of the structure of an exemplary device provided in one embodiment of this application. Detailed Implementation

[0050] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0051] This application's embodiments can be applied to scenarios such as process detection, evaluation, and improvement in industrial production. The process can be various industrial production processes, specifically set based on requirements. A process node can be understood as a node corresponding to a process method in a process flow. Therefore, process nodes are determined according to the process flow for different processes, and can be determined according to the process methods within the process flow. Specifically, the process methods can be determined based on the process flow and process methods, including process manufacturing methods and process inspection methods. For example, in the vehicle painting process, process nodes may include electrophoresis process nodes, topcoat process nodes, etc. Electrophoresis and topcoat processes can also be combined with their specific process methods to determine sub-nodes. After determining the process nodes, key process parameters can be analyzed based on the process nodes, and the stability results of the process node can be analyzed based on the key process parameters. If the stability is good, production continues; if the stability is poor, the quality problems corresponding to the process node are analyzed, and improvement suggestions are determined. This application's embodiments, for complex processes and procedures, can identify key process parameters, achieve process capability evaluation, and optimize daily quality control levels.

[0052] Reference Figure 1 The diagram shows a flowchart of an embodiment of a process quality testing method for an industrial process according to this application.

[0053] Step 102: Determine the key process parameters corresponding to the process nodes. The key process parameters corresponding to the process nodes are determined by the identification model.

[0054] This application embodiment can pre-train a recognition model, which is then used for identification processing to determine the key process parameters corresponding to process nodes. Specifically, various production data can be collected during the production process as historical data. A training sample set is constructed based on this historical data, and the recognition model is trained using this training sample set. The recognition model can be based on classification models such as logistic regression, extreme gradient boosting (XGboost), gradient boosting decision tree (GBDT), and random forest. The recognition model is constructed using classification models and trained using supervised machine learning algorithms, thereby enabling the identification of important features based on classification problems, which serve as the key process parameters for that process node. Production data collected during the production process is processed by the recognition model to obtain the corresponding key process parameters.

[0055] Taking vehicle painting processes as an example, the painting process mainly includes: pretreatment electrophoresis, sanding line, topcoat line, inspection and finishing line, etc. Figure 2In one example of a painting process flow, the electrophoresis process nodes include: pretreatment electrophoresis sub-node, underbody adhesive application sub-node, weld adhesive application sub-node, and electrophoresis inspection sub-node. The topcoat process nodes include: topcoat spraying sub-node, topcoat inspection sub-node, and topcoat repair sub-node.

[0056] Taking the electrophoresis process node as an example, feature engineering is constructed by collecting historical data of key indicators from pretreatment and electrophoresis, and supervised machine learning algorithms are built based on offline vehicle body indicators during the electrophoresis inspection process to analyze key process parameters. This allows key process parameters to be determined during production based on the indicators of each sub-node. Similarly, taking the topcoat process node as an example, key process parameters can be determined by analyzing key offline factors of the vehicle body.

[0057] In this embodiment, the key process parameter can be a monitored value or a statistical indicator of the monitored value, such as a summation, average, or other aggregated value, or a value obtained after satisfying a certain affine transformation. In an optional embodiment, determining the key process parameter corresponding to the process node includes: determining multiple process nodes and their production data in the target process flow during production; for each process node, inputting the generated data into the recognition model to determine the corresponding key process parameter, wherein the process parameter includes process measurement data and / or statistical data of the process measurement data.

[0058] Step 104: Analyze the key process parameters corresponding to the process node and determine the stability results.

[0059] Statistical analysis can be performed on key process parameters corresponding to process nodes to determine the stability results of those nodes. This stability result characterizes the stability of the process during production, and includes stable (or good stability) and unstable (or poor stability) results. In some examples, the stability result of a process node can be determined by analyzing the controlled state information of that node, which is information about the process control state generated by the process. During production, maintaining the process under a certain controlled state achieves the goal of quality control. Therefore, process control during production can promptly detect signs of systematic factors and take measures to eliminate their impact, maintaining the process under controlled conditions despite random factors, thus achieving the goal of quality control. This application embodiment can analyze the controlled state information of the process method corresponding to the process node based on key process parameters, and then analyze the stability results of the process. The controlled state information includes controlled state and / or uncontrolled state. A controlled state can be understood as being in a statistically controlled state, such as conforming to a normal distribution or other stable random distribution, where the process is only affected by random factors, and fluctuations have statistical regularity. An out-of-control state can be understood as a state of statistical out-of-control, where the process may be affected by other system factors leading to loss of control. This application embodiment can analyze and control the process based on the statistical regularity of fluctuations during production, determine controlled state information, and analyze process stability. The step of analyzing the key process parameters corresponding to the process node to determine the stability result includes: analyzing the key process parameters corresponding to the process node to determine controlled state information; and performing stability analysis based on the controlled state information to determine the stability result of the process node.

[0060] In this embodiment, the key process parameters include both quantitative and percentage types. Different methods can be used to analyze the controlled state information for different types of key process parameters. The key process parameters are analyzed according to their type to determine the controlled state information. Analysis can be based on some or all of the key process parameters. For example, key process parameters can be sampled, and corresponding control charts can be drawn according to their type. The controlled state information is then determined based on the control charts. A control chart is a graph with control limits used to analyze and determine whether a process is in a stable state. Specifically, for quantitative key process parameters, a statistical process control chart is drawn based on the key process parameters, and the controlled state information is determined based on the statistical process control chart; for percentage-type key process parameters, a percentile control chart is drawn based on the key process parameters, and the controlled state information is determined based on the percentile control chart.

[0061] For key process parameters that are quantifiable, an SPC (Statistical Process Control) chart can be drawn, and then the controlled state information can be analyzed based on the SPC control chart. In one optional embodiment, drawing a statistical process control chart based on key process parameters includes: performing a normality test on the key process parameters corresponding to the process nodes to determine the normal distribution result; and drawing a control chart based on the normal distribution result. Performing a normality test on the key process parameters corresponding to the process nodes allows analysis of the distribution information of the key process parameters corresponding to the process nodes, comparing the distribution information with a set significance level to determine whether it conforms to a normal distribution. In actual industrial production processes, data is difficult to conform to a standard normal distribution. Therefore, a significance level can be pre-set, and a normality inference can be given based on the significance level information to obtain a normal distribution result. The significance level information is information that characterizes the significance level. The significance level is the probability of error that might occur if the population parameter falls within a certain interval. Significance refers to the degree of difference. When performing hypothesis testing, an acceptable low-probability standard as a judgment boundary is determined in advance. Then, a control chart can be drawn based on the normal distribution result. The process of drawing a statistical process control chart based on the normal distribution result includes: if the normal distribution result satisfies the normal distribution, then a process control chart is drawn based on the statistical process control method; if the normal distribution result does not satisfy the normal distribution, then the key process parameters are transformed to satisfy the normal distribution, and a process control chart is drawn based on the statistical process control method when the normal distribution is satisfied.

[0062] If the normal distribution result satisfies a normal distribution, a process control chart can be drawn based on statistical process control methods. Then, control judgment rules can be obtained, and control status information can be determined based on these rules. If the normal distribution result does not satisfy a normal distribution, the key process parameters are transformed to convert non-normally distributed data into normally distributed data, for example, through Box-Cox transformation and Johnson transformation. Then, control status information is determined based on the control judgment rules.

[0063] In process control analysis, every method exhibits variation and is influenced by time and space. Even under ideal conditions, a set of analytical results will contain a certain degree of random error. However, when a result exceeds the allowable range of random error, statistical methods can be used to determine that the result is abnormal and unreliable. Therefore, controlled judgment rules can be set to assess variation in process control; for example, the controlled judgment rule can be set to ensure that the error does not exceed the acceptable range. The resulting controlled state information includes: controlled state and / or uncontrolled state.

[0064] For the key process parameters of percentage type, a percentile control chart is drawn based on the key process parameters, and the controlled judgment rule is used to analyze the percentile control chart to determine the controlled state information.

[0065] In this embodiment, stability analysis can also be performed based on the controlled state information to determine the stability result of the process node. It can be determined whether the controlled state information is stable. If it is in a controlled state, the stability result of the process node is determined to be stable or good; if it is in an uncontrolled state, the stability result of the process node is determined to be unstable or poor. If the stability result is poor, the quality problems corresponding to the process node are analyzed and improvement suggestions are determined. Uncontrolled process parameters can be identified and indicator diagnosis performed to determine the corresponding quality problems, investigate the causes of uncontrolled behavior, and analyze modification suggestions. If the stability is good, subsequent processing steps can continue.

[0066] Step 106: Analyze the process capability index corresponding to the process node based on the controlled state information.

[0067] For key process parameters with good stability, the process capability index corresponding to the process node can be analyzed based on the key process parameters. The process capability index (CPK) represents the degree to which process capability meets technical standards (e.g., specifications, tolerances). It refers to the degree to which process capability meets product quality standard requirements (specification range, etc.), also known as the operation capability index. It refers to the actual processing capacity of an operation under controlled conditions within a certain time. It is the inherent capability of the operation, or in other words, the operation's ability to guarantee quality. The operation referred to here is the process resulting from the combined effects of five basic quality factors: operator, machine, raw materials, process method, and production environment.

[0068] When analyzing process capability indices, the process capability index corresponding to a process node can be determined based on the type of key process parameters. Specifically, determining the process capability index based on the type of key process parameters includes: for metered key process parameters, determining the process capability index based on normal distribution results; and for percentage-based key process parameters, determining the process capability index based on percentiles.

[0069] For metered critical process parameters, the process capability index is determined by combining the normal distribution results from the previous step. If the critical process parameters satisfy the normal distribution, taking a two-sided specification as an example, the index can be calculated using the following formula:

[0070] Cp=T / (6*σ)=(Tu-Tl) / (6*σ)

[0071] Where TU and Tl are the upper and lower tolerance limits, respectively, T = maximum allowable value (TU) - minimum allowable value (Tl), and σ is the population standard deviation of the process statistic, which can be obtained when the process is in steady state. Therefore, the smaller σ is, the larger its Cp value, and the better the process technical capability.

[0072] It can also be calculated using the following formula:

[0073] Cpk=MIN(Tu-μ,μ-Tl) / (3*σ)

[0074] Where Cpk refers to the magnitude of the deviation (ε) between the process average and the product standard specification, ε = |M - μ|, where μ is the population mean of the distribution and M is the tolerance center. ε is the deviation of the population mean μ of the distribution from the tolerance center M.

[0075] If the critical process parameters do not conform to a normal distribution, a transformation algorithm is used to convert these non-normally distributed critical process parameters into normally distributed critical process parameters for calculation. Transformation algorithms such as Box-Cox transformation and Johnson transformation are examples. Then, the actual distribution of the data can be fitted, and the mean, standard deviation, etc., can be estimated based on this distribution to calculate the process capability index. In this case, CPK is established under controllable SPC conditions, and a corresponding solution scheme is provided based on distribution testing, making it more scientific.

[0076] For percentage-based key process parameters, a process capability index is calculated based on a percentile method using nonparametric statistical methods.

[0077] Therefore, for different types of key process parameters, process capability index analysis can be performed on stable processes to determine whether they meet technical standards and quality requirements.

[0078] Step 108: Determine the process testing results based on the process capability index.

[0079] The process capability index may include capability levels, which can be determined based on the process. Process testing results can be determined based on these capability levels. Determining process testing results based on the process capability index includes: determining the capability level corresponding to the process capability index, and determining the process testing results based on the capability level. Determining process testing results based on the capability level includes: determining whether the capability level meets the process production conditions of the process node; if it does not meet the process production conditions, analyzing the reasons for the insufficient process capability and generating process testing results for improved processes; if it meets the process production conditions, generating process testing results indicating that the process is qualified. Process production conditions can be set based on the process and process nodes. These process production conditions are the technical standards and quality conditions for the testing process. Then, it can be determined whether the capability level meets the process production conditions of the process node. If the process production conditions are not met, the reasons for the insufficient process capability are analyzed. The capability level can correspond to the reasons for the insufficient capability, therefore, the reasons for the insufficient capability can also be determined based on the capability level. Based on the reasons for the insufficient capability, methods for improving the process are analyzed to obtain process testing results for improved processes. If the process production conditions are met, generating process testing results indicating that the process is qualified.

[0080] In one example, corresponding countermeasures are taken based on the calculated process capability index according to the standards of the production process. A common standard is as follows:

[0081] A++ level: Cpk≥2.0, ability level is excellent, description: cost reduction can be considered;

[0082] A+ level: 2.0>Cpk≥1.67, ability level is excellent, description: should be maintained;

[0083] Grade A: 1.67>Cpk≥1.33, ability level is good, description: good ability, stable status, but should strive to improve to Grade A+;

[0084] Grade B: 1.33>Cpk≥1.0, capability level is average, described as: the status is average, there is a risk of adverse effects if the factors in the production process vary slightly, and various resources and methods should be used to upgrade it to Grade A;

[0085] Grade C: 1.0>Cpk≥0.67, capability level is poor, described as: there are many defects in the production process, and its capability must be improved.

[0086] Grade D: 0.67>Cpk, capability level is unacceptable, described as: its capability is too poor and the design process should be redesigned.

[0087] The descriptions corresponding to each capability level above can be obtained from the process testing results.

[0088] This provides an adaptive method for critical process capability in complex multi-process scenarios, improving the rationality of process level evaluation and assisting in the improvement of production processes.

[0089] In summary, for different processes, the process nodes are identified, and key process parameters are analyzed based on these process nodes. The stability of each process node is then analyzed based on these key process parameters to determine whether the process is stable. Furthermore, the process capability index corresponding to each process node is analyzed based on the stability results, and the process inspection results are determined based on the process capability index. For complex procedures and processes, key process parameters can be identified, process capability evaluation can be achieved, and daily quality control can be optimized.

[0090] Based on the above embodiments, this application also discloses a process quality detection method for industrial processes, which can perform SPC control and process capability index calculation for data of different types.

[0091] Reference Figure 3 The diagram illustrates a flowchart of another embodiment of a process quality inspection method for an industrial process according to this application.

[0092] Step 302: Determine multiple process nodes and their production data for the target process flow during the production process.

[0093] Step 304: For each process node, input the generated data into the recognition model to determine the corresponding key process parameters.

[0094] The process parameters include process measurement data and / or statistical data of the process measurement data.

[0095] Step 306: For metering-type key process parameters, draw a statistical process control chart based on the key process parameters, and determine the controlled state information based on the statistical process control chart.

[0096] The step of drawing a statistical process control chart based on key process parameters includes: performing a normality test on the key process parameters corresponding to the process nodes to determine the normal distribution result; and drawing a statistical process control chart based on the normal distribution result. The step of drawing a statistical process control chart based on the normal distribution result includes: if the normal distribution result satisfies a normal distribution, then drawing a process control chart based on statistical process control methods; if the normal distribution result does not satisfy a normal distribution, then transforming the key process parameters to satisfy a normal distribution, and drawing a process control chart based on statistical process control methods when the normal distribution is satisfied.

[0097] Step 308: For the key process parameters of the percentage type, draw a percentile control chart based on the key process parameters, and determine the controlled state information based on the percentile control chart.

[0098] Step 310: Determine if it is stable.

[0099] Based on the controlled state information, a stability analysis is performed to determine the stability result of the process node. If yes, the stability result is stable (good stability), and step 314 is executed; otherwise, the stability result is unstable (poor stability), and step 312 is executed.

[0100] Step 312: If the stability result is poor, analyze the quality problems corresponding to the process node and determine improvement suggestions.

[0101] Step 314: For the metered key process parameters, determine the process capability index corresponding to the process node based on the normal distribution results.

[0102] Step 316: For the percentage-type key process parameters, determine the process capability index corresponding to the process node based on the percentile method.

[0103] Step 318: Determine the capability level corresponding to the process capability index.

[0104] Step 320: Determine whether the capability level meets the process production conditions of the process node.

[0105] If yes, proceed to step 324; otherwise, proceed to step 320.

[0106] Step 322: Analyze the reasons for insufficient process capability and generate process inspection results for process improvement.

[0107] If the process production conditions are not met, analyze the reasons for the insufficient process capability and generate process inspection results for process improvement.

[0108] Step 324: Generate process inspection results indicating that the process is qualified.

[0109] If the production conditions are met, a qualified process inspection result will be generated, which can then be used for production.

[0110] This application's embodiments can quickly locate key process parameters based on machine learning algorithms. Taking the painting process as an example, the painting process mainly includes: pretreatment electrophoresis, sanding line, topcoat line, and inspection and finishing line. In the painting process, each step can potentially become a source of painting quality problems, such as: welding slag adhering to the vehicle body to form particles, incomplete dripping of electrophoretic coating forming secondary flow marks, incomplete wiping of sealant resulting in adhesive contamination, unstable flow rate of the spraying robot, etc., involving at least 30 core steps and at least 2000 process indicators. This application's embodiments can design a key factor identification algorithm, solving the problem of process indicator information overload and helping to quickly locate key indicators at process nodes.

[0111] An adaptive algorithm module is provided, which can perform SPC control and process capability index calculation for different data types, such as normal / non-normal data and percentage data. In complex multi-stage process scenarios, an adaptive critical capability calculation method is presented to improve the rationality of process level evaluation and assist in improving production processes.

[0112] In all embodiments of this application, user-related information is collected, used, and stored only after obtaining the user's authorization and permission, and various operations based on user information are also executed only after obtaining the user's authorization and permission.

[0113] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of this application are not limited to the described order of actions, because according to the embodiments of this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of this application.

[0114] Based on the above embodiments, this embodiment also provides a process quality testing device for industrial processes, which is applied in server-side electronic equipment.

[0115] The parameter determination module is used to determine the key process parameters corresponding to the process nodes. The key process parameters corresponding to the process nodes are determined by the identification model.

[0116] The stability analysis module is used to analyze the key process parameters corresponding to the process nodes and determine the stability results.

[0117] The capability index determination module is used to analyze the process capability index corresponding to the process node based on the stability results.

[0118] The detection module is used to determine the process detection results based on the process capability index.

[0119] In summary, for different processes, the process nodes are identified, and key process parameters are analyzed based on these process nodes. The stability of each process node is then analyzed based on these key process parameters to determine its stability. Furthermore, the process capability index corresponding to each process node is analyzed based on the stability results, and the process inspection results are determined based on the process capability index. For complex procedures and processes, key process parameters can be identified, process capability evaluation can be achieved, and daily quality control can be optimized.

[0120] The stability analysis module is used to perform statistical analysis on the key process parameters corresponding to the process node to determine the controlled state information; and to perform stability analysis based on the controlled state information to determine the stability result of the process node. The stability analysis module is also used to analyze the quality problems corresponding to the process node and determine improvement suggestions when the stability result is poor.

[0121] The acquisition module is used to determine multiple process nodes and their production data of the target process flow during the production process; for each process node, the generated data is input into the recognition model to determine the corresponding key process parameters, which include process measurement data and / or statistical data of the process measurement data.

[0122] The controlled analysis module is used to draw statistical process control charts based on the key process parameters for metering-type key process parameters, and to determine the controlled state information based on the statistical process control charts; and to draw percentile control charts based on the key process parameters for percentage-type key process parameters, and to determine the controlled state information based on the percentile control charts.

[0123] The controlled analysis module is used to perform normality tests on the key process parameters corresponding to the process nodes to determine the normal distribution results; and to draw statistical process control charts based on the normal distribution results.

[0124] The controlled analysis module is used to draw a process control chart based on statistical process control if the normal distribution result satisfies the normal distribution; if the normal distribution result does not satisfy the normal distribution, the key process parameters are transformed to satisfy the normal distribution, and a process control chart is drawn based on statistical process control if the normal distribution is satisfied.

[0125] The capability index determination module is used to determine the process capability index corresponding to the process node based on the type of key process parameters when the stability result is good.

[0126] The capability index determination module is used to determine the process capability index corresponding to the process node based on the normal distribution result for metered key process parameters; and to determine the process capability index corresponding to the process node based on the percentile method for percentage-type key process parameters.

[0127] The detection module is used to determine the capability level corresponding to the process capability index, and to determine the process detection result based on the capability level.

[0128] The detection module is used to determine whether the capability level meets the process production conditions of the process node; if the process production conditions are not met, the reasons for the insufficient process capability are analyzed and process detection results for improved process are generated; if the process production conditions are met, process detection results for qualified process are generated.

[0129] This application's embodiments enable rapid location of key process parameters based on machine learning algorithms. A key factor identification algorithm is designed to address the problem of information overload in process indicators, helping to quickly locate key indicators for critical processes. Furthermore, an adaptive algorithm module is provided, capable of calculating SPC control and process capability indices for different data types, such as normal / non-normal data and percentage-based data. In complex multi-process scenarios, an adaptive method for calculating critical capability process capacity is presented, improving the rationality of process level evaluation and assisting in the improvement of production processes.

[0130] This application also provides a non-volatile readable storage medium storing one or more modules (programs). When these modules are applied to a device, they enable the device to execute the instructions for the method steps in this application.

[0131] This application provides one or more machine-readable media storing instructions that, when executed by one or more processors, cause an electronic device to perform one or more of the methods described in the above embodiments. In this application, the electronic device includes devices such as servers and terminal devices.

[0132] Embodiments of this disclosure can be implemented as an apparatus with any suitable hardware, firmware, software, or any combination thereof, configured as desired, and the apparatus may include electronic devices such as servers (clusters) and terminals. Figure 4 An exemplary apparatus 400 is schematically shown that can be used to implement the various embodiments described in this application.

[0133] In one embodiment, Figure 4An exemplary device 400 is shown, which includes one or more processors 402, a control module (chipset) 404 coupled to at least one of the processors 402, a memory 406 coupled to the control module 404, a non-volatile memory (NVM) / storage device 408 coupled to the control module 404, one or more input / output devices 410 coupled to the control module 404, and a network interface 412 coupled to the control module 404.

[0134] Processor 402 may include one or more single-core or multi-core processors, and processor 402 may include any combination of general-purpose processors or special-purpose processors (e.g., graphics processors, application processors, baseband processors, etc.). In some embodiments, device 400 can serve as a server, terminal, or other device as described in the embodiments of this application.

[0135] In some embodiments, the apparatus 400 may include one or more computer-readable media (e.g., memory 406 or NVM / storage device 408) having instructions 414 and one or more processors 402 that are combined with the one or more computer-readable media and configured to execute the instructions 414 to implement the module and thus perform the actions described in this disclosure.

[0136] In one embodiment, the control module 404 may include any suitable interface controller to provide any suitable interface to at least one of the processors 402 and / or any suitable device or component communicating with the control module 404.

[0137] The control module 404 may include a memory controller module to provide an interface to the memory 406. The memory controller module may be a hardware module, a software module, and / or a firmware module.

[0138] Memory 406 may be used, for example, to load and store data and / or instructions 414 for device 400. In one embodiment, memory 406 may include any suitable volatile memory, such as suitable DRAM. In some embodiments, memory 406 may include double data rate type quad synchronous dynamic random access memory (DDR4 SDRAM).

[0139] In one embodiment, the control module 404 may include one or more input / output controllers to provide an interface to the NVM / storage device 408 and (one or more) input / output devices 410.

[0140] For example, NVM / storage device 408 may be used to store data and / or instructions 414. NVM / storage device 408 may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable (one or more) non-volatile storage devices (e.g., one or more hard disk drives (HDDs), one or more optical disc drives (CDs), and / or one or more digital universal optical disc (DVD) drives).

[0141] NVM / storage device 408 may include storage resources that are part of a device on which device 400 is mounted, or that are accessible to the device but do not necessarily have to be part of the device. For example, NVM / storage device 408 may be accessed via a network through one or more input / output devices 410.

[0142] One or more input / output devices 410 may provide an interface for device 400 to communicate with any other suitable device. Input / output devices 410 may include communication components, audio components, sensor components, etc. Network interface 412 may provide an interface for device 400 to communicate via one or more networks. Device 400 may wirelessly communicate with one or more components of a wireless network according to any of one or more wireless network standards and / or protocols, such as accessing wireless networks based on communication standards, such as WiFi, 2G, 3G, 4G, 5G, etc., or combinations thereof.

[0143] In one embodiment, at least one of the processors 402 may be logically packaged with one or more controllers (e.g., memory controller modules) of the control module 404. In one embodiment, at least one of the processors 402 may be logically packaged with one or more controllers of the control module 404 to form a system-in-package (SiP). In one embodiment, at least one of the processors 402 may be integrated with the logic of one or more controllers of the control module 404 on the same die. In one embodiment, at least one of the processors 402 may be integrated with the logic of one or more controllers of the control module 404 on the same die to form a system-on-a-chip (SoC).

[0144] In various embodiments, device 400 may be, but is not limited to, a server, desktop computing device, or mobile computing device (e.g., laptop, handheld computing device, tablet, netbook, etc.). In various embodiments, device 400 may have more or fewer components and / or different architectures. For example, in some embodiments, device 400 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including a touchscreen display), a non-volatile memory port, multiple antennas, a graphics chip, an application-specific integrated circuit (ASIC), and a speaker.

[0145] The detection device can use a main control chip as a processor or control module, and sensor data, position information, etc. can be stored in a memory or NVM / storage device. The sensor group can be used as an input / output device, and the communication interface can include a network interface.

[0146] This application also provides an electronic device, including: a processor; and a memory storing executable code thereon. When the executable code is executed, the processor performs one or more methods as described in this application embodiment. In this application embodiment, the memory can store various types of data, such as target files, file-application association data, and user behavior data, thereby providing a data foundation for various processing operations.

[0147] This application also provides one or more machine-readable media having executable code stored thereon, which, when executed, causes a processor to perform one or more of the methods described in this application.

[0148] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0149] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0150] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations. Figure 1One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0151] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0152] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0153] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.

[0154] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0155] The present application provides a detailed description of a process quality inspection method, an electronic device, and a storage medium based on industrial processes. Specific examples have been used to illustrate the principles and implementation methods of the present application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and its core ideas. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of the present application. Therefore, the content of this specification should not be construed as a limitation of the present application.

Claims

1. A method for detecting process quality in an industrial process, characterized in that, The method includes: In the production process, multiple process nodes and their production data of the target process flow are determined. The process nodes in the vehicle painting process flow include electrophoresis process nodes and topcoat process nodes. For each process node, the production data is input into the identification model to determine the corresponding key process parameters, which include process measurement data and / or statistical data of the process measurement data. Statistical analysis is performed on the key process parameters corresponding to the process nodes to determine the controlled state information; Based on the controlled state information, a stability analysis is performed to determine the stability result of the process node; Based on the stability results, analyze the process capability index corresponding to the process node; The process testing results are determined based on the process capability index. It also includes: if the stability result is poor, then analyze the quality problems corresponding to the process node and determine improvement suggestions.

2. The method according to claim 1, characterized in that, Statistical analysis is performed on the key process parameters corresponding to the process nodes to determine the controlled state information, including: For metering-type key process parameters, a statistical process control chart is drawn based on the key process parameters, and the controlled state information is determined based on the statistical process control chart. For the key process parameters of percentage type, a percentile control chart is drawn based on the key process parameters, and the controlled state information is determined based on the percentile control chart.

3. The method according to claim 2, characterized in that, The method of drawing statistical process control charts based on key process parameters includes: Perform a normality test on the key process parameters corresponding to the process nodes to determine the normal distribution results; A statistical process control chart was drawn based on the normal distribution results.

4. The method according to claim 3, characterized in that, The step of drawing a statistical process control chart based on the normal distribution results includes: If the normal distribution result satisfies a normal distribution, then a process control chart is drawn based on the statistical process control method; If the normal distribution result does not meet the normal distribution, the key process parameters are transformed to meet the normal distribution, and a process control chart is drawn based on statistical process control method when the normal distribution is met.

5. The method according to claim 4, characterized in that, The process capability index analysis based on the stability results for the process node includes: If the stability result is good, then the process capability index corresponding to the process node is determined based on the type of key process parameters.

6. The method according to claim 5, characterized in that, The determination of the process capability index corresponding to the process node based on the type of key process parameters includes: For metering-type key process parameters, the process capability index corresponding to the process node is determined based on the normal distribution results. For key process parameters in percentage form, the process capability index corresponding to the process node is determined based on the percentile method.

7. The method according to claim 1, characterized in that, Determining process testing results based on the process capability index includes: Determine the capability level corresponding to the process capability index, and determine the process testing results based on the capability level.

8. The method according to claim 7, characterized in that, The determination of process testing results based on the capability level includes: Determine whether the capability level meets the process production conditions of the process node; If the process production conditions are not met, analyze the reasons for the insufficient process capability and generate process inspection results for the process to be improved. If the production conditions are met, a qualified process inspection result will be generated.

9. An electronic device, comprising: processor; and a memory having executable code stored thereon, which, when executed by a processor, performs the method as described in any one of claims 1-8.

10. One or more machine-readable media having executable code stored thereon, which, when executed by a processor, performs the method as described in any one of claims 1-8.

Images