Ideal process parameter range acquisition method, parameter adjustment method and related equipment

Abstract

The invention discloses a method for acquiring an ideal technological parameter range of anodic oxidation dyeing, a method for adjusting technological parameters of anodic oxidation dyeing and related equipment, and the method for acquiring the ideal technological parameter range of anodic oxidation dyeing comprises the steps: determining a positive sample in historical processing data according to the historical processing data of an anodic oxidation process, constructing a positive sample processing data set; according to the positive sample processing data set and a yield prediction model, constructing a set process parameter-yield path set corresponding to the positive sample set; counting the occurrence frequency of the path type of the process parameter-yield path set, and obtaining a target process parameter set of the positive sample according to the occurrence frequency of the path type; and obtaining an ideal process parameter range corresponding to the target process according to the target process parameter set. By utilizing the method and the device, the timeliness and the accuracy of monitoring and adjusting the process parameters can be improved.

Description

Technical Field

[0001] The present application belongs to the technical field of anodizing dyeing, and in particular relates to a method for obtaining an ideal process parameter range, a parameter adjustment method and related equipment. Background Art

[0002] Anodizing is an important process for coloring metal surfaces. In the specific process, various process parameters may vary or differ from the predetermined values, and these changes or differences may affect the final coloring effect, resulting in a certain color difference from the expected color. Therefore, it is necessary to monitor and adjust the process parameters to ensure sample quality.

[0003] However, in the process of monitoring and adjusting process parameters, it is difficult to monitor and accurately adjust the process parameters in a timely manner because there are many process parameters that affect the coloring effect, there may be multiple types of color differences, and various independent variables and dependent variables are intertwined. Summary of the invention

[0004] The embodiments of the present application provide a method for obtaining an ideal process parameter range, a parameter adjustment method, and related equipment to solve the problem of low timeliness and accuracy in process parameter monitoring and adjustment.

[0005] In a first aspect, an embodiment of the present application provides a method for obtaining an ideal process parameter range for anodizing dyeing, the method comprising: determining positive samples in the historical processing data based on historical processing data of the anodizing process, and constructing a positive sample processing data set; wherein the positive sample is a processing data combination that meets the set requirements for a single processing; constructing a set of set process parameter-yield paths corresponding to the positive sample set based on the positive sample processing data set and a yield prediction model; wherein the set process parameter-yield path in the set process parameter-yield path set is a correlation between the set process parameter combination of the positive sample and the yield corresponding to the set process parameter combination; counting the frequency of occurrence of the path type of the process parameter-yield path set, and obtaining a target process parameter set for the positive sample based on the frequency of occurrence of the path type; and obtaining an ideal process parameter range corresponding to the target process based on the target process parameter set.

[0006] In some embodiments, the step of determining positive samples in the historical processing data based on the historical processing data of the anodizing process and constructing a positive sample processing data set includes: screening and determining the positive samples based on the yield of each sample in the historical processing data, and constructing a positive sample set; wherein the yield corresponding to the positive sample is greater than a set yield threshold; and obtaining the positive sample processing data set by screening based on the historical processing data.

[0007] In some embodiments, the step of constructing a set of set process parameter-yield paths corresponding to the positive sample set based on the positive sample processing data set and the yield prediction model includes: obtaining the complete process parameter-yield path corresponding to the positive sample, and constructing a complete process parameter-yield path set; wherein the complete process parameter-yield path is the association between the complete process parameter combination of the positive sample and the yield corresponding to the complete process parameter combination; using a frequent item set algorithm to obtain the path association rule of the complete process parameter-yield path set; determining the set process parameter combination based on the path association rule; obtaining the yield corresponding to the set process parameter combination based on the yield prediction model, and constructing the set process parameter-yield path set.

[0008] In some embodiments, the step of counting the occurrence frequencies of the path types of the process parameter-yield path set and obtaining the target process parameter set of the positive sample based on the occurrence frequencies of the path types includes: classifying all the set process parameter combinations according to whether the set process parameter combinations in the process parameter-yield path set are the same or not, to obtain a path type set; obtaining the statistical quantity of each path type in the path type set; and constructing the target process parameter set based on the process parameters corresponding to the path types whose statistical quantities are greater than a set quantity threshold.

[0009] In some embodiments, the step of obtaining an ideal process parameter range corresponding to the target process based on the target process parameter set includes: obtaining a maximum process parameter value and a minimum process parameter value corresponding to the target process based on the target process parameter set; and obtaining an ideal process parameter range corresponding to the target process based on the maximum process parameter value and the minimum process parameter value.

[0010] In some embodiments, after the step of obtaining the ideal process parameter range corresponding to the target process according to the target process parameter set, the method further includes: obtaining a negative sample process parameter set corresponding to the negative sample set according to the historical processing data; wherein the negative samples in the negative sample set are processing data combinations of a single processing that does not meet the set requirements; by removing and adding set processes from the negative sample process parameter set, the degree of influence of the set process on the negative sample set is obtained, and an NG key process set is constructed; according to the degree of influence of each type of NG key process in the NG key process set on the probability of meeting the set requirements, the qualified process parameter range of each type of the NG key process is obtained, and an NG key process parameter set is constructed; when the target process belongs to the NG key process set, the ideal process parameter range of the target process is corrected and optimized according to each type of the NG key process parameter set.

[0011] In some embodiments, the step of obtaining the degree of influence of the set process on the negative sample set by eliminating and adding the set process from the negative sample process parameter set includes: step 11, taking any type of process in the negative sample process parameter set as the set process; step 12, obtaining the yield corresponding to the negative sample set including the set process and the yield corresponding to the negative sample set not including the set process according to the yield prediction model, and determining the predicted difference value corresponding to the set process; step 13, changing the process parameter value of the set process in the negative sample set, and obtaining the influence factor value of the set process on the negative sample set according to the predicted difference value corresponding to the set process; step 14, updating the type of the set process, repeating steps 12 to 13 until all processes in the negative sample process parameter set are traversed, and obtaining the influence factor values ​​of all processes in the negative sample process parameter set on the negative sample set.

[0012] In some embodiments, the step of obtaining the qualified process parameter range of each type of NG key process in the NG key process set according to the degree of influence of each type of NG key process in the NG key process set on the probability of meeting the set requirements includes: obtaining the qualified process parameter range of each type of NG key process according to the yield prediction model using the partial dependency graph algorithm; wherein the total number of process types in the NG key process set is 2.

[0013] In some embodiments, when the target process belongs to the NG key process set, the step of correcting and optimizing the ideal process parameter range of the target process according to each type of the NG key process parameter set includes: determining whether the upper and lower limits of the ideal process parameter range of the target process are complete; if incomplete, completing the ideal process parameter range of the target process according to the qualified process parameter range corresponding to the target process in the NG key process set, and completing the correction and optimization of the ideal process parameter range of the target process; if complete, determining whether the ideal process parameter range corresponding to the target process and the qualified process parameter range corresponding to the target process have an intersection; if there is no intersection, determining the corrected process parameter range corresponding to the target process according to the positive sample processing data set, and taking the intersection of the corrected process parameter range corresponding to the target process and the qualified process parameter range corresponding to the target process as the ideal process parameter range of the target process; if there is an intersection, taking the intersection of the ideal process parameter range corresponding to the target process and the qualified process parameter range corresponding to the target process as the ideal process parameter range of the target process.

[0014] In a second aspect, an embodiment of the present application provides a method for adjusting the process parameters of anodizing dyeing, comprising: obtaining a current set of process parameters that do not meet the set requirements for this processing; adjusting the process parameters in the current set of process parameters according to an ideal process parameter range; wherein the ideal process parameter range is obtained by any of the above-mentioned acquisition methods.

[0015] In a third aspect, an embodiment of the present application provides an electronic device, comprising a controller and a memory, wherein the controller is used to implement the acquisition method and / or adjustment method as described in any one of the above when executing a computer program stored in the memory.

[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a controller, the acquisition method and / or adjustment method described in any one of the above items is implemented.

[0017] In the method for obtaining the ideal process parameter range for anodizing dyeing provided in the embodiment of the present application, the correlation between the set process parameter combination and the yield is determined based on the positive sample processing data set and the yield prediction model. According to the frequency of occurrence of the path type in the set process parameter-yield path set, the target process parameter set with a high yield occurrence frequency is determined, and then the ideal process parameter range corresponding to the target process is determined, which can improve the accuracy of determining the ideal process parameter range; and the present application can timely monitor and accurately adjust the parameter value of the target process according to the ideal process parameter range corresponding to the target process, so that the adjusted target process parameters can meet the requirements of the anode process and improve the sample dyeing quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is an application scenario diagram of the method for obtaining the ideal process parameter range for anodizing dyeing provided in an embodiment of the present application.

[0019] Figure 2 It is a flow chart of a method for obtaining an ideal process parameter range for anodizing dyeing provided in an embodiment of the present application.

[0020] Figure 3 It is a structural diagram of setting the process parameter-yield path provided in the first embodiment of the present application.

[0021] Figure 4 It is a structural diagram of setting the process parameter-yield path provided in the second embodiment of the present application.

[0022] Figure 5 It is a flow chart of a method for determining a process parameter-yield path set provided in an embodiment of the present application.

[0023] Figure 6It is a flow chart of the parameter correction method provided in the embodiment of the present application.

[0024] Figure 7 It is a flowchart of the method for determining the degree of influence provided in an embodiment of the present application.

[0025] Figure 8 It is a schematic diagram of the structure of a device for acquiring an ideal process parameter range for anodizing dyeing provided in an embodiment of the present application.

[0026] Fig. 9 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limiting the present application.

[0028] In the description of the present application, it should be understood that the terms indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first" and "second" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present application, it should be noted that the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0029] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, or mutual communication, it can be a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0030] Some embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0031] Anodizing dyeing is an important process for coloring metal surfaces. It uses electrochemical methods to color the oxide film on the surface of metals or metals with coatings. It is widely used in the automotive, electronics, construction and other industries. The anodizing dyeing process can include chemical polishing, oxidation, washing before dyeing, dyeing, sealing, pickling after sealing and other steps. These steps constitute the overall process of anodizing dyeing. Among them, chemical polishing refers to chemical polishing, the purpose of which is to remove the oxide layer and impurities on the metal surface, improve the smoothness of the metal surface, and prepare for anodizing; oxidation refers to the anodizing process, in which the metal is used as the anode and a uniform and dense oxide film is formed on its surface through electrolysis. The oxide film has high hardness and corrosion resistance and can be dyed; water washing before dyeing refers to the need to remove the residues and possible pollutants generated in the oxidation process by water washing before dyeing to ensure the uniformity and adhesion of dyeing; dyeing refers to immersing the anodized workpiece in a bath containing dye. Due to the porosity of the oxide film, the dye molecules can be adsorbed in the pores of the oxide film, thereby showing the desired color; sealing refers to sealing the workpiece after dyeing to close the pores of the oxide film, prevent the dye from falling off and the intrusion of foreign substances, and improve the corrosion resistance and wear resistance of the coloring layer; pickling after sealing is used to remove residues on the surface of the workpiece to ensure the integrity and smoothness of the workpiece.

[0032] In the above-mentioned process, a variety of process parameters are involved. For example, in the chemical polishing stage, chemical polishing parameters are involved, including chemical polishing residence time, chemical polishing temperature, chemical polishing specific gravity, concentration of chemical polishing liquid and other process parameters; in the oxidation stage, oxidation parameters are involved, including oxidation residence time, oxidation temperature, sulfuric acid concentration, oxalic acid concentration and other process parameters; in the dyeing stage, dyeing parameters are involved, including dyeing liquid concentration and other process parameters; in the sealing stage, sealing parameters are involved, including sealing residence time, sealing temperature, sealing liquid concentration and other process parameters. There will be some changes or differences between the above-mentioned process parameters and the preset values, so that the final sample coloring has a certain color difference from the expected color, affecting the coloring effect. Therefore, it is necessary to monitor and adjust the process parameters to ensure the sample quality.

[0033] However, in the process of monitoring and adjusting process parameters, it is difficult to monitor and accurately adjust the process parameters in a timely manner because there are many process parameters that affect the coloring effect, there may be multiple types of color differences, and various independent variables and dependent variables are intertwined.

[0034] In view of the above problems, in order to solve the technical problems of low accuracy and timeliness of process parameter monitoring and adjustment in the anodizing dyeing process, the embodiments of the present application provide a method for obtaining an ideal process parameter range for anodizing dyeing and a method for adjusting the process parameters of anodizing dyeing. By performing correlation analysis on multiple process parameters and sample yields, target process parameters that affect the sample yield are obtained, and by monitoring the target process parameters, the timeliness and accuracy of process parameter monitoring can be improved. The present application can monitor and adjust the parameter values ​​of the target process according to the ideal process parameter range corresponding to the target process, so that the adjusted process parameters can meet the requirements of the anodizing process and improve the sample dyeing quality.

[0035] See also Figure 1 , Figure 1 : This is an application scenario diagram of the method for obtaining the ideal process parameter range of anodizing dyeing provided in an embodiment of the present application. The application scenario includes an electronic device 10 and anodizing dyeing equipment 20, and the electronic device 10 and the anodizing dyeing equipment 20 are connected via a network. Among them, the network is used to provide a medium for a communication link between the electronic device 10 and the anodizing dyeing equipment 20. The network can include various connection types, for example, a wired communication link, a wireless communication link, etc., which is not limited in the embodiment of the present application.

[0036] In some embodiments, the electronic device 10 represents a device with data processing function, for example, the electronic device may include but is not limited to a mobile phone, a tablet, a desktop computer, and a laptop computer. The anodizing dyeing device 20 is used to perform coloring on the sample surface, collect historical processing data of the anodizing process, and transmit the historical processing parameters to the electronic device 10. By analyzing the historical processing parameters, the electronic device 10 can determine the ideal range of each process parameter in the anodizing dyeing process (for ease of description, this application is referred to as "ideal process parameter range").

[0037] In the above-mentioned application scenario provided in the embodiment of the present application, the historical processing data in the anodizing process is collected by the anodizing dyeing equipment 20, and the ideal range of each process parameter in the anodizing dyeing process is determined by the electronic device 10 based on the historical processing parameters, so as to facilitate the subsequent monitoring and adjustment of the process parameters according to the ideal process parameter range, thereby improving the accuracy and timeliness of the process parameter monitoring and adjustment, and then improving the coloring effect of the sample.

[0038] The present application will describe the technical solution of the present application in detail through specific embodiments below. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0039] Figure 2is a flow chart of a method for obtaining an ideal process parameter range for anodizing dyeing provided in an embodiment of the present application. The method for obtaining an ideal process parameter range for anodizing dyeing is applied to electronic devices (for example, Figure 1 The electronic device 10 in FIG. Figure 2 As shown, the following steps are included: S11, according to the historical processing data of the anodizing process, determining positive samples in the historical processing data, and constructing a positive sample processing data set.

[0040] In at least one embodiment of the present application, the historical processing data may represent relevant data when each sample is processed using an anodizing dyeing device within a period of time, and the historical processing data includes multiple process parameters involved in the anodizing dyeing process for each sample and the yield of each sample. By collecting data for multiple anodizing processes, collecting parameter values ​​of multiple processing parameters, and calculating the yield of the sample after the anodizing is completed, historical processing data including the processing parameters and yield of multiple samples can be obtained.

[0041] In some embodiments, the process parameters may represent parameters that affect the dyeing effect of the sample during the anodizing dyeing process. Exemplarily, in the anodizing dyeing process, a variety of process parameters are involved, for example, in the chemical polishing stage, chemical polishing parameters are involved, and the chemical polishing parameters include chemical polishing residence time, chemical polishing temperature, chemical polishing specific gravity, concentration of chemical polishing liquid and other process parameters; in the oxidation stage, oxidation parameters are involved, and oxidation parameters include oxidation residence time, oxidation temperature, sulfuric acid concentration, oxalic acid concentration and other process parameters; in the dyeing stage, dyeing parameters are involved, and dyeing parameters include dyeing liquid concentration and other process parameters; in the sealing stage, sealing parameters are involved, and sealing parameters include sealing residence time, sealing temperature, sealing liquid concentration and other process parameters.

[0042] In some embodiments, the yield of a sample can represent the probability that the sample reaches the quality standard after the anodizing dyeing process. In some embodiments, the process of implementing an anodizing dyeing process can be performed on multiple samples at the same time to obtain multiple anodizing dyed samples. Exemplarily, a hanger for anodizing dyeing can hold multiple samples at the same time. In one process, all samples on the same hanger will be subjected to chemical polishing, oxidation, dyeing and sealing processes at the same time, that is, the processing parameters of each process experienced by all samples on the same hanger are the same. Specifically, it is assumed that the multiple processing parameters include at least two of dyeing parameters, oxidation parameters, sealing parameters and chemical polishing parameters, and each processing parameter has a specific parameter value in the actual process. After the multiple samples on the same hanger are subjected to the anodizing dyeing process, multiple dyed samples are obtained, and the probability of each dyed sample reaching the dyeing quality standard is calculated, that is, the yield of the sample.

[0043] In some embodiments, a positive sample may represent a sample that meets the set requirements in a single process. The set requirements may be set according to actual needs. For example, requirements may be set based on functionality, reliability, safety, and environmental adaptability. A positive sample set may represent a set of multiple positive samples, where the positive samples in the positive sample set are a combination of processing data that meet the set requirements in a single process. In some embodiments, based on the historical processing data of the anodizing process, a positive sample set that meets the set requirements may be screened, and then the historical processing data of multiple positive samples may be obtained to obtain a set of historical processing data of the positive samples (for ease of description, this application is referred to as a "positive sample processing data set").

[0044] S12, constructing a set of set process parameters-yield paths corresponding to the positive sample set according to the positive sample processing data set and the yield prediction model.

[0045] In at least one embodiment of the present application, the yield prediction model is used to predict the yield of each sample in the anodizing process, and the yield prediction model may include an XGBoost model. The training data of the yield prediction model is historical processing data, and multiple process parameters involved in the anodizing dyeing process of each sample in the historical processing data are used as input data, and the yield of each sample is used as output data to train the initialized XGBoost model to obtain the yield prediction model. The training process of the XGBoost model can refer to the relevant technology and will not be repeated here.

[0046] In some embodiments, the positive sample processing data set includes historical processing data of multiple positive samples, and each positive sample is anodized and dyed according to the complete process parameters involved in the anodizing and dyeing process, that is, each positive sample has corresponding complete process parameters, wherein the complete process parameters may include multiple of polishing parameters, oxidation parameters, dyeing parameters, and sealing parameters. In some embodiments, each positive sample has a corresponding yield, and the complete process parameters of each positive sample are associated with the yield to obtain a complete process parameter-yield path. The complete process parameter-yield paths of multiple positive samples can obtain a complete process parameter-yield path set.

[0047] In some embodiments, according to a preset association rule mining algorithm, it is possible to mine the correlation between multiple process parameters from a complete process parameter-yield path set, combine multiple process parameters with high correlation, and obtain a set process parameter combination. Among them, the set process parameter combination can be represented in the form of a structure tree, and each structure tree includes multiple process parameters with high correlation. In some embodiments, the set process parameter combination is input into a yield prediction model to obtain the yield corresponding to the set process parameter combination. Construct an association relationship between the set process parameter combination and the yield, and use the association relationship between the set process parameter combination and the yield, as well as the set process parameter combination of the positive sample, as the set process parameter-yield path set.

[0048] S13, counting the occurrence frequencies of the path types of the set process parameter-yield path set, and acquiring the target process parameter set of the positive sample according to the occurrence frequencies of the path types.

[0049] In at least one embodiment of the present application, the set process parameter-yield path in the set process parameter-yield path set is a correlation relationship between the set process parameter combination of the positive sample and the yield corresponding to the set process parameter combination. Figure 3 and Figure 4 The schematic diagram of the structure of setting the process parameter-yield rate path provided in the embodiment of the present application is described. Figure 3 and Figure 4 As shown, the process parameter-yield path can be represented in the form of a structure tree. Each process parameter-yield path corresponds to a structure tree. The number of structure trees can be set according to actual needs. For example, the number of structure trees can be 100. This embodiment of the application takes two structure trees as an example for explanation. Figure 3 The structure tree in is denoted as tree 1, and Figure 4The structure tree in is recorded as tree 2. Tree 1 and tree 2 include multiple paths, each path including set process parameters and associated yields. The set process parameters in tree 1 include dyeing time less than 500, dyeing time greater than or equal to 500, oxidation current less than 300, dyeing time greater than or equal to 300, dyeing time less than 700, and dyeing time greater than or equal to 700. Among them, when the set process parameter combination is dyeing time less than 500 and oxidation current less than 300, the yield of the sample is low, and the path is recorded as 1-1. When the set process parameter combination is dyeing time less than 500 and oxidation current greater than or equal to 300, the yield of the sample is high, and the path is recorded as 1-2. When the set process parameter combination is dyeing time greater than or equal to 500 and dyeing time less than 700, the yield of the sample is high, and the path is recorded as 1-3. When the set process parameter combination is dyeing time greater than or equal to 500 and dyeing time greater than or equal to 700, the yield of the sample is low, and the path is recorded as 1-4. The set process parameters in Tree 2 include sealing concentration less than 50, sealing concentration greater than or equal to 50, sealing concentration less than 30, sealing concentration greater than or equal to 30, dyeing time less than 600, and dyeing time greater than or equal to 600. Among them, when the process parameter combination is set to sealing concentration less than 50 and sealing concentration less than 30, the yield of the sample is higher, and this path is recorded as 2-1. When the process parameter combination is set to sealing concentration less than 50 and sealing concentration greater than or equal to 30, the yield of the sample is higher, and this path is recorded as 2-2. When the process parameter combination is set to sealing concentration greater than or equal to 50 and dyeing time less than 600, the yield of the sample is higher, and this path is recorded as 2-3. When the process parameter combination is set to sealing concentration greater than or equal to 50 and dyeing time greater than or equal to 600, the yield of the sample is lower, and this path is recorded as 2-4. Among them, the paths in tree 1 and tree 2 can be combined. For example, path 1-1 can be combined with path 2-1, path 2-2, path 2-3, and path 2-4 respectively, path 1-2 can be combined with path 2-1, path 2-2, path 2-3, and path 2-4 respectively, path 1-3 can be combined with path 2-1, path 2-2, path 2-3, and path 2-4 respectively, and path 1-4 can be combined with path 2-1, path 2-2, path 2-3, and path 2-4 respectively.

[0050] In some embodiments, the step of counting the occurrence frequencies of the path types of the set process parameter-yield path set and obtaining the target process parameter set of the positive sample based on the occurrence frequencies of the path types includes: classifying all the set process parameter combinations based on whether the set process parameter combinations in the process parameter-yield path set are the same or not, to obtain a path type set; obtaining the statistical quantity of each path type in the path type set; and constructing the target process parameter set based on the process parameters corresponding to the path types whose statistical quantities are greater than a set quantity threshold.

[0051] In some embodiments, each set process parameter combination has a corresponding path type, and the path type can represent the combination information of each process parameter in the set process parameter combination and its yield. The same set process parameter combination is divided into one category, based on which, multiple path types can be obtained. For example, path 1-1 is combined with path 2-1 as path type A, path 1-1 is combined with path 2-2 as path type B, and path 1-1 and path 2-3 are combined as path type C. And so on, no further description is given here.

[0052] In some embodiments, in the positive sample processing data set, the number of occurrences of each path type is different, and the yield corresponding to the path type is not necessarily the same each time it appears. For example, path type A appears 10 times, 9 times are judged to have a high yield, and 1 time is judged to have a low yield; path type B appears 6 times, 3 times are judged to have a high yield, and 3 times are judged to have a low yield; path type C appears 3 times, 2 times are judged to have a high yield, and 1 time is judged to have a low yield. The statistical quantity may include the number of times the path type is judged to have a high yield and the ratio of the number of times the path type is judged to have a high yield to the total number of times the path type appears. Taking path type A as an example, the statistical quantity of path type A includes 9 and 0.9 (9 / 10). Based on this, the statistical quantity corresponding to each path type can be determined, and the process parameters corresponding to the path type whose statistical quantity is greater than the set quantity threshold are selected to form a target process parameter set. Path types whose statistical quantity is less than or equal to the set quantity threshold can be temporarily ignored. Among them, the set quantity threshold can be set according to actual needs. For example, the set quantity threshold can include 5 and 0.9, that is, the number of times the path type is judged to have a high yield is greater than 5 times, and the ratio of the number of times the path type is judged to have a high yield to the total number of times the path type appears is greater than 0.9, and the process parameters corresponding to the path type are used as the target process parameters.

[0053] S14, acquiring an ideal process parameter range corresponding to the target process according to the target process parameter set.

[0054] In at least one embodiment of the present application, the target process parameter set includes multiple target process parameters, and the target process parameters may represent a combination of multiple process parameters that results in a higher frequency of high yield of samples.

[0055] In some embodiments, the step of obtaining an ideal process parameter range corresponding to the target process based on the target process parameter set includes: obtaining a maximum process parameter value and a minimum process parameter value corresponding to the target process based on the target process parameter set; and obtaining an ideal process parameter range corresponding to the target process based on the maximum process parameter value and the minimum process parameter value.

[0056] In some embodiments, the target process parameters include process parameters corresponding to multiple target processes and parameter ranges of the process parameters, and the parameter ranges may include a maximum value of the process parameters and a minimum value of the process parameters. According to the target process parameters, the maximum value of the process parameters and the minimum value of the process parameters corresponding to the target process can be obtained, and the maximum value of the process parameters and the minimum value of the process parameters are used as the ideal process parameter range of the target process. Continuing from the above embodiment, if the target process parameters are a combination of path 1-2 and path 2-1, the target process parameters include dyeing time, oxidation current and sealing concentration, wherein the dyeing time is less than 500, the oxidation current is greater than or equal to 300, and the sealing concentration is less than 30. If the target process parameters are a combination of path 1-3 and path 2-2, the target process parameters include dyeing time and sealing concentration, wherein the dyeing time is greater than or equal to 500 and less than 700, and the sealing concentration is greater than or equal to 30 and less than 50.

[0057] The acquisition method provided in the embodiment of the present application determines the correlation between the set process parameter combination and the yield rate according to the positive sample processing data set and the yield prediction model. According to the occurrence frequency of the path type in the set process parameter-yield path set, the target process parameter set with high yield occurrence frequency is determined, and then the ideal process parameter range corresponding to the target process is determined, which can improve the accuracy of determining the ideal process parameter range; and the present application can timely monitor and accurately adjust the parameter value of the target process according to the ideal process parameter range corresponding to the target process, so that the adjusted target process parameters can meet the requirements of the anode process and improve the sample dyeing quality.

[0058] In at least one embodiment of the present application, a positive sample may represent a sample that meets the set requirements in a single process. The set requirements may be set according to actual needs. For example, the requirements may be set based on functionality, reliability, safety, and environmental adaptability. The present application embodiment is described by taking the setting requirement that the yield of the sample is greater than the set yield threshold as an example. In some embodiments, the step of determining the positive samples in the historical processing data based on the historical processing data of the anodizing process and constructing a positive sample processing data set may include: Step 1: According to the yield of each sample in the historical processing data, the positive sample is screened and determined to construct a positive sample set; wherein the yield corresponding to the positive sample is greater than a set yield threshold.

[0059] In some embodiments, the historical processing data includes multiple process parameters involved in the anodizing dyeing process for each sample and the yield of each sample. By comparing the yield of each sample with a set yield threshold, a positive sample set can be screened out. The set yield threshold can be set according to actual needs, for example, the set yield threshold is 99.5%. Samples with a yield greater than 99.5% are taken as positive samples.

[0060] Step 2: Screen and obtain the positive sample processing data set based on the historical processing data.

[0061] In some embodiments, based on the historical processing data of the anodizing process, a set of positive samples that meet the set requirements can be screened, and then the historical processing data of multiple positive samples are obtained to obtain a set of historical processing data of the positive samples, that is, a positive sample processing data set.

[0062] In the acquisition method provided in the embodiment of the present application, based on the yield of each sample, a positive sample processing data set can be quickly and accurately screened from historical processing data, and then the positive sample processing data set is used to analyze and determine the ideal process parameter range of the target process, and anodizing dyeing is performed based on the ideal process parameter range, which can improve the effect of anodizing dyeing.

[0063] In at least one embodiment of the present application, according to a preset association rule mining algorithm, it is possible to mine the correlation between multiple process parameters from a complete process parameter-yield path set, combine multiple process parameters with high correlation, and obtain a set process parameter combination. The present application embodiment takes the association rule mining algorithm as a frequent item set algorithm as an example for explanation. Figure 5 1 is a flow chart of a method for determining a set of process parameters-yield paths provided in an embodiment of the present application, and the method for determining a set of process parameters-yield paths is applied to electronic devices. Figure 5 As shown, the following steps are included: S21, obtaining the complete process parameter-yield path corresponding to the positive sample, and constructing a complete process parameter-yield path set.

[0064] In at least one embodiment of the present application, the positive sample processing data set includes historical processing data of multiple positive samples, and each positive sample is anodized and dyed according to the complete process parameters involved in the anodizing and dyeing process, that is, each positive sample has corresponding complete process parameters. Among them, the complete process parameters may include multiple of polishing parameters, oxidation parameters, dyeing parameters and sealing parameters. In some embodiments, each positive sample has a corresponding yield, and the complete process parameters of each positive sample are associated with the yield to obtain a complete process parameter-yield path. The complete process parameter-yield path of multiple positive samples can obtain a complete process parameter-yield path set. Among them, the complete process parameter-yield path is the association relationship between the complete process parameter combination of the positive sample and the yield corresponding to the complete process parameter combination.

[0065] S22, using a frequent item set algorithm to obtain path association rules of the complete process parameter-yield path set.

[0066] In at least one embodiment of the present application, the frequent item set algorithm may include an Apriori algorithm, which can be used to mine the correlation between various process parameters based on the complete process parameter-yield path set to obtain path association rules. The method for determining the path association rules can refer to related technologies and will not be described in detail here.

[0067] S23, determining the set process parameter combination according to the path association rule.

[0068] In at least one embodiment of the present application, the process parameters with association are combined according to the path association rule to obtain a set process parameter combination. Continuing from the above embodiment, the multiple process parameters after the combination of path 1-1 and path 2-1, and the multiple process parameters after the combination of path 1-1 and path 2-2 are all set process parameter combinations. S24, obtaining the yield corresponding to the set process parameter combination according to the yield prediction model, and constructing the set process parameter-yield path set.

[0069] In at least one embodiment of the present application, a set process parameter combination is used as input data and input into a yield prediction model to obtain the yield of the set process parameter combination. An association between the set process parameter combination and the yield is established to obtain a set process parameter-yield path, and multiple set process parameter-yield paths are used as a set process parameter-yield path set.

[0070] In the acquisition method provided in the embodiment of the present application, a frequent item set algorithm is used to obtain the path association rules of the complete process parameter-yield path set, and the set process parameter combination is determined according to the path association rules. According to the yield prediction model, the yield corresponding to the set process parameter combination is obtained, and the set process parameter-yield path set is constructed, so that the ideal process parameter range can be determined subsequently according to the set process parameter-yield path set, thereby improving the accuracy of parameter range acquisition.

[0071] In at least one embodiment of the present application, after the step of obtaining the ideal process parameter range corresponding to the target process based on the target process parameter set, the ideal process parameter range of the target process can be corrected and optimized in combination with the negative sample set in the historical processing data, so as to improve the accuracy of determining the ideal process parameter range and thereby improve the effect of anodizing dyeing. Figure 6 is a flow chart of a parameter correction method provided in an embodiment of the present application, and the parameter correction method is applied to an electronic device. Figure 6 As shown, the following steps are included: S31, acquiring a negative sample process parameter set corresponding to a negative sample set according to the historical processing data.

[0072] In at least one embodiment of the present application, the historical processing data includes a plurality of process parameters involved in the anodizing dyeing process for each sample and the yield of each sample. A negative sample may represent a sample whose single processing does not meet the set requirements. The set requirements may be set according to actual needs. For example, a sample whose yield is less than or equal to a set yield threshold is a negative sample. A negative sample set may represent a set of multiple negative samples, wherein the negative samples in the negative sample set are a combination of processing data whose single processing does not meet the set requirements. In some embodiments, based on the historical processing data of the anodizing process, a set of negative samples that do not meet the set requirements may be screened, and then the process parameters in the historical processing data corresponding to the multiple negative samples are obtained to obtain a set of negative sample process parameters.

[0073] S32, by removing and adding set processes from the negative sample process parameter set, the influence of the set process on the negative sample set is obtained, and an NG key process set is constructed.

[0074] In at least one embodiment of the present application, the Shapley Additive Explanations (SHAP) algorithm can be used to determine the set process (for ease of description, referred to as "NG key process" in this application) that has a greater impact on whether the yield of the sample meets the standard. Exemplarily, the degree of influence of the set process on the negative sample set can be obtained by removing or adding the set process from the negative sample process parameter set, and the set process with a large degree of influence is used as the NG key process. The ideal process parameter range of the set process with a small degree of influence may not be corrected and optimized. Among them, the negative sample process parameter set contains process parameters in the historical processing data corresponding to multiple negative samples, and the process parameters are complete process parameters involved in the anodizing dyeing process. For example, the complete process parameters can include polishing parameters, oxidation parameters, dyeing parameters, and sealing parameters. Each process parameter corresponds to a process flow. Based on this, the negative sample process parameter set contains multiple process flows, and any one of the process flows is selected as the set process to determine the degree of influence of the set process on the negative sample set.

[0075] S33, according to the influence degree of each type of NG key process in the NG key process set on the achievement probability of meeting the set requirements, obtain the qualified process parameter range of each type of the NG key process, and construct the NG key process parameter set.

[0076] In at least one embodiment of the present application, the NG key process set includes multiple types of NG key processes. The step of obtaining the qualified process parameter range of each type of NG key process in the NG key process set according to the degree of influence of each type of NG key process in the NG key process set on the probability of meeting the set requirements comprises: obtaining the qualified process parameter range of each type of NG key process according to the yield prediction model using the partial dependency graph algorithm; wherein the total number of process types in the NG key process set is 2. The partial dependency plot (PDP) algorithm is a visualization tool for explaining the relationship between features and prediction results in machine learning models. It shows the impact of these features on the prediction results by fixing all other features and focusing only on the changes in one or more features.

[0077] In some embodiments, using the PDP algorithm, any NG key process can be selected from the NG key process set, and the parameter values ​​of the process parameters of the selected NG key process can be adjusted according to the negative sample process parameter set, and the parameter values ​​of the process parameters of the remaining NG key processes are kept unchanged to obtain the adjusted negative sample process parameter set. The adjusted negative sample process parameter set is processed according to the yield prediction model to obtain the yield of the adjusted negative sample. When the yield of the negative sample is increased to a specified range (for example, a yield threshold is set, or other values), the parameter range of the process parameters of the selected NG key process is determined as the qualified process parameter range of the NG key process. Based on this, the qualified process parameter range of each type of NG key process can be determined. The embodiment of the present application takes the total number of process types in the NG key process set as 2 as an example to illustrate, by fixing the parameter value of one of the NG key processes unchanged and changing the parameter value of another NG key process, the degree of influence of the changed NG key process on the achievement probability is determined, and the qualified process parameter range of the changed NG key process is determined.

[0078] The embodiment of the present application combines the partial dependency graph with the yield prediction model to obtain the qualified process parameter range for each type of NG key process, and adjusts the ideal process parameter range corresponding to the target process according to the qualified process parameter range, thereby improving the accuracy of parameter range acquisition.

[0079] S34, when the target process belongs to the NG key process set, correct and optimize the ideal process parameter range of the target process according to each type of the NG key process parameter set.

[0080] In at least one embodiment of the present application, when the target process is any NG key process in the NG key process set, the NG key process parameters of the NG key process may be used to correct and optimize the ideal process parameter range of the target process. In some embodiments, when the target process belongs to the NG key process set, the step of correcting and optimizing the ideal process parameter range of the target process according to each type of the NG key process parameter set includes: determining whether the upper and lower limits of the ideal process parameter range of the target process are complete; if incomplete, completing the ideal process parameter range of the target process according to the qualified process parameter range corresponding to the target process in the NG key process set, and completing the correction and optimization of the ideal process parameter range of the target process; if complete, determining whether the ideal process parameter range corresponding to the target process and the qualified process parameter range corresponding to the target process have an intersection; if there is no intersection, determining the corrected process parameter range corresponding to the target process according to the positive sample processing data set, and taking the intersection of the corrected process parameter range corresponding to the target process and the qualified process parameter range corresponding to the target process as the ideal process parameter range of the target process; if there is an intersection, taking the intersection of the ideal process parameter range corresponding to the target process and the qualified process parameter range corresponding to the target process as the ideal process parameter range of the target process.

[0081] In some embodiments, the ideal process parameter range of the target process may lack an upper limit or a lower limit. It is possible to determine whether the upper and lower limits of the ideal process parameter range of the target process are complete, and when the upper and lower limits of the ideal process parameter range of the target process are incomplete, the upper and lower limits are promptly completed. In some embodiments, if the result of the determination is that the upper and lower limits of the ideal process parameter range of the target process are incomplete, the ideal process parameter range of the target process corresponding to the target process in the NG key process set can be used to complete the ideal process parameter range of the target process. For example, if the ideal process parameter range of the target process lacks an upper limit, the upper limit in the standard process parameter range is obtained, and the upper limit is used as the upper limit of the ideal process parameter range of the target process. If the ideal process parameter range of the target process lacks a lower limit, the lower limit in the standard process parameter range is obtained, and the upper limit is used as the lower limit of the ideal process parameter range of the target process. In other embodiments, if the result of the determination is that the upper and lower limits of the ideal process parameter range of the target process are incomplete, it is determined whether the ideal process parameter range corresponding to the target process and the standard process parameter range corresponding to the target process have an intersection, so as to determine whether the ideal process parameter range corresponding to the target process and the standard process parameter range corresponding to the target process are mutually exclusive.

[0082] In some embodiments, if the judgment result is that there is no intersection between the ideal process parameter range corresponding to the target process and the standard process parameter range corresponding to the target process, it indicates whether there is a mutual exclusion between the ideal process parameter range corresponding to the target process and the standard process parameter range corresponding to the target process. In this case, considering that the accuracy of the standard process parameter range is higher, the corrected process parameter range corresponding to the target process can be determined according to the positive sample processing data set, and the standard process parameter range can be corrected in combination with the corrected process parameters to obtain the ideal process parameter range of the target process. Among them, the positive sample processing data set contains various process parameters of multiple positive samples, and the corrected process parameter range can be obtained by performing data processing on the parameter values ​​of multiple process parameters corresponding to the target process. Among them, data processing can include mean processing and other methods, which are not limited here. In other embodiments, if the judgment result is that there is an intersection between the ideal process parameter range corresponding to the target process and the standard process parameter range corresponding to the target process, the intersection of the ideal process parameter range corresponding to the target process and the standard process parameter range corresponding to the target process is taken.

[0083] In the above-mentioned acquisition method provided in the embodiment of the present application, the ideal process parameter range of the target process is determined based on multiple working conditions such as whether the ideal process parameter range of the target process is complete and whether the ideal process parameter range corresponding to the target process and the qualified process parameter range corresponding to the target process have an intersection, thereby improving the accuracy of determining the ideal process parameter range.

[0084] In at least one embodiment of the present application, the influence of the set process on the negative sample set is obtained by removing and adding set processes from the negative sample process parameter set. Figure 7 1 is a flow chart of a method for determining the degree of influence provided in an embodiment of the present application, and the method for determining the degree of influence is applied to electronic equipment. Figure 7 As shown, the following steps are included: S41, taking any type of process in the negative sample process parameter set as the set process.

[0085] In at least one embodiment of the present application, based on the historical processing data of the anodizing process, a negative sample set that does not meet the set requirements can be screened, and then the process parameters in the historical processing data corresponding to the multiple negative samples are obtained to obtain a negative sample process parameter set. In the negative sample process parameter set, each process parameter corresponds to a type of process, and any type of process in the negative sample process parameter set is used as the set process.

[0086] S42, according to the yield prediction model, obtaining the yield corresponding to the set process included in the negative sample set and the yield corresponding to the set process not included in the negative sample set, and determining the predicted difference value corresponding to the set process.

[0087] In at least one embodiment of the present application, the negative sample set includes negative sample process parameters of the set process as input data, which are input into the yield prediction model to obtain the yield corresponding to the negative sample including the set process, which is recorded as the first yield. The negative sample set does not include negative sample process parameters of the set process as input data, which are input into the yield prediction model to obtain the yield corresponding to the negative sample not including the set process, which is recorded as the second yield. The difference between the first yield and the second yield is calculated as the predicted difference value.

[0088] S43, changing the process parameter value of the set process in the negative sample set, and obtaining the influence factor value of the set process on the negative sample set according to the predicted difference value corresponding to the set process.

[0089] In at least one embodiment of the present application, the process parameter value of the set process in the negative sample set is changed to obtain the changed negative sample process parameter, and the changed negative sample process parameter including the set process is used as input data and input into the yield prediction model to obtain the yield corresponding to the negative sample including the set process, which is recorded as the third yield; the changed negative sample process parameter not including the set process is used as input data and input into the yield prediction model to obtain the yield corresponding to the negative sample not including the set process, which is recorded as the fourth yield. The difference between the third yield and the fourth yield is calculated as the predicted difference value. According to the predicted difference value under different conditions, the influence factor value of the set process on the negative sample set is determined. Among them, the larger the influence factor value, the greater the influence of the set process on the yield of the sample; the smaller the influence factor, the smaller the influence of the set process on the yield of the sample.

[0090] S44, updating the type of the set process, repeating steps 42 to 43 until all processes in the negative sample process parameter set are traversed, and obtaining the influence factor values ​​of all processes in the negative sample process parameter set on the negative sample set.

[0091] In at least one embodiment of the present application, the type of the set process is updated, and steps 42 to 43 are repeated until all processes in the negative sample process parameter set are traversed, and the impact factor value corresponding to each set process can be obtained. In some embodiments, the order of the impact factor values ​​is sorted from large to small, and the set processes with a preset number of the top sorted are selected as NG key processes. Among them, the preset number can be set according to actual needs, for example, the preset number can be 2. In other embodiments, the set process with an impact factor value greater than the preset factor value can be selected as the NG key process.

[0092] In the above-mentioned acquisition method provided in the embodiment of the present application, the Shapley Additive exPlanations (SHAP) algorithm can be used to determine the set process that has a greater impact on whether the sample yield meets the standard as the NG key process, which can improve the accuracy of determining the NG key process and then improve the accuracy of parameter acquisition.

[0093] In at least one embodiment of the present application, after determining the ideal process parameter range corresponding to the target process, the process parameters of anodizing dyeing can be adjusted according to the ideal process parameter range, so that the sample after anodizing dyeing can meet the dyeing requirements. In some embodiments, the method for adjusting the process parameters of anodizing dyeing includes: obtaining a current process parameter set that does not meet the set requirements for this processing; adjusting the process parameters in the current process parameter set according to the ideal process parameter range; wherein the ideal process parameter range is obtained by an acquisition method. In some embodiments, the current process parameter set of this processing is obtained, and the current process parameter set is processed using a yield prediction model to determine the yield of the sample corresponding to the current process parameter set. If the yield of the sample is less than or equal to the set yield threshold, it is necessary to adjust the process parameters in the current process parameter set; if the yield of the sample is greater than the set yield threshold, it is not necessary to adjust the process parameters in the current process parameter set.

[0094] In the method for adjusting the process parameters of anodizing dyeing provided in the embodiment of the present application, an ideal process parameter range is used to guide the anodizing dyeing process, thereby improving the dyeing quality of the sample.

[0095] See also Figure 8 , Figure 81 is a schematic diagram of the structure of the device for obtaining the ideal process parameter range of anodizing dyeing provided in an embodiment of the present application. In some embodiments, the device 20 for obtaining the ideal process parameter range of anodizing dyeing may include a plurality of functional modules composed of computer program segments. The computer program of each program segment in the device 20 for obtaining the ideal process parameter range of anodizing dyeing may be stored in the memory of the electronic device 10 and executed by at least one controller to execute (see Figure 2 Description) The function of obtaining the ideal process parameter range for anodizing dyeing.

[0096] In this embodiment, the acquisition device 20 of the ideal process parameter range of anodizing dyeing can be divided into multiple functional modules according to the functions performed. The functional modules may include: a processing data acquisition module 201, an association determination module 202, an occurrence frequency determination module 203 and a parameter range acquisition module 204. The module referred to in this application refers to a series of computer program segments that can be executed by at least one controller and can complete fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0097] The processing data acquisition module 201 can be used to determine the positive samples in the historical processing data according to the historical processing data of the anodizing process, and construct a positive sample processing data set; wherein the positive samples in the positive sample set are processing data combinations that meet the set requirements for a single processing.

[0098] The association relationship determination module 202 can be used to construct a set of set process parameter-yield paths corresponding to the positive sample set based on the positive sample processing data set and the yield prediction model; wherein the set process parameter-yield path in the set process parameter-yield path set is the association relationship between the set process parameter combination of the positive sample and the yield corresponding to the set process parameter combination.

[0099] The occurrence frequency determination module 203 may be used to count the occurrence frequencies of the path types of the set process parameter-yield path set, and obtain the target process parameter set of the positive sample according to the occurrence frequencies of the path types.

[0100] The parameter range acquisition module 204 may be used to acquire an ideal process parameter range corresponding to the target process according to the target process parameter set.

[0101] It can be understood that the device 20 for acquiring the ideal process parameter range of anodizing dyeing and the method for acquiring the ideal process parameter range of anodizing dyeing in the above-mentioned embodiment belong to the same inventive concept, and the specific implementation method of each module of the device 20 for acquiring the ideal process parameter range of anodizing dyeing corresponds to the steps of the method for acquiring the ideal process parameter range of anodizing dyeing in the above-mentioned embodiment, which will not be repeated in this application.

[0102] The module division described above is a logical function division, and there may be other division methods in actual implementation. In addition, the functional modules in each embodiment of the present application may be integrated in the same processing unit, or each module may exist physically separately, or two or more modules may be integrated in the same unit. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0103] Fig. 9 Schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Fig. 9 As shown, the electronic device 10 includes a memory 11, at least one controller 12 and at least one communication bus 13, wherein the controller 12 is used to implement a method for acquiring and / or adjusting an ideal process parameter range for anodizing dyeing when executing a computer program stored in the memory 11, and the at least one communication bus 13 is configured to implement connection and communication between the memory 11 and at least one controller 12.

[0104] Fig. 9 The structure of the electronic device shown does not constitute a limitation on the embodiments of the present application. The electronic device 10 may also include more or less other hardware or software than shown in the figure, or a different arrangement of components.

[0105] In some embodiments of the present application, the electronic device 10 can also be connected to a client device, which includes but is not limited to any electronic product that can interact with a user through a keyboard, mouse, remote control, touchpad or voice control device, such as a personal computer, a tablet computer, a smart phone, a digital camera, etc.

[0106] It should be noted that the electronic device 10 is only an example, and other existing or future electronic products that are suitable for the present application should also be included in the protection scope of the present application and included here by reference.

[0107] In some embodiments, the electronic device 10 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0108] In some embodiments, a computer program is stored in the memory 11, and when the computer program is executed by at least one controller 12, all or part of the steps in the method for obtaining and / or adjusting the ideal process parameter range of anodizing dyeing are implemented. The memory 11 includes a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0109] In some embodiments, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the electronic device 10, etc.

[0110] In some embodiments, at least one controller 12 is the control core (Control Unit) of the electronic device 10, and uses various interfaces and lines to connect various components of the entire electronic device 10, and executes various functions and processes data of the electronic device 10 by running or executing programs or modules stored in the memory 11, and calling data stored in the memory 11. For example, when at least one controller 12 executes the computer program stored in the memory, it implements all or part of the steps of the method for obtaining and / or adjusting the ideal process parameter range of anodizing dyeing in the embodiment of the present application; or implements all or part of the functions of the device for obtaining and / or adjusting the ideal process parameter range of anodizing dyeing. At least one controller 12 can be composed of an integrated circuit, for example, it can be composed of a single packaged integrated circuit, or it can be composed of multiple integrated circuits with the same function or different functions, including one or more central controllers (Central Processing unit, CPU), microcontrollers, digital processing chips, graphics controllers, and combinations of various control chips.

[0111] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling an electronic device (which can be a personal computer, an electronic device, or a network device, etc.) or a controller (processor) to execute parts of the methods of various embodiments of the present application.

[0112] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0113] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0114] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0115] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present application is limited by the attached claims rather than the above description, so it is intended to include all changes that fall within the meaning and scope of the equivalent elements of the claims in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "including" does not exclude other units or, and the singular does not exclude the plural. Multiple units or devices stated in the specification can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical solution of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present application.

Claims

1. A method for obtaining an ideal process parameter range for anodizing dyeing, characterized in that: The method comprises: According to the historical processing data of the anodizing process, positive samples in the historical processing data are determined, and a positive sample processing data set is constructed; wherein the positive sample is a processing data combination that meets the set requirements for a single processing; According to the positive sample processing data set and the yield prediction model, a set of set process parameter-yield paths corresponding to the positive sample set is constructed; wherein the set process parameter-yield paths in the set process parameter-yield path set are the correlation relationships between the set process parameter combinations of the positive sample and the yields corresponding to the set process parameter combinations; Counting the occurrence frequencies of the path types of the set process parameter-yield path set, and acquiring the target process parameter set of the positive sample according to the occurrence frequencies of the path types; According to the target process parameter set, an ideal process parameter range corresponding to the target process is obtained.

2. The acquisition method according to claim 1, characterized in that: The step of determining positive samples in the historical processing data according to the historical processing data of the anodizing process and constructing a positive sample processing data set comprises: According to the yield of each sample in the historical processing data, the positive sample is screened and determined, and a positive sample set is constructed; wherein the yield corresponding to the positive sample is greater than a set yield threshold; The positive sample processed data set is obtained by screening according to the historical processed data.

3. The acquisition method according to claim 1, characterized in that: The step of constructing a set of set process parameters-yield paths corresponding to the positive sample set according to the positive sample processing data set and the yield prediction model comprises: Obtaining a complete process parameter-yield path corresponding to the positive sample, and constructing a complete process parameter-yield path set; wherein the complete process parameter-yield path is an association relationship between a complete process parameter combination of the positive sample and a yield corresponding to the complete process parameter combination; Using a frequent item set algorithm, obtaining a path association rule of the complete process parameter-yield path set; Determining the set process parameter combination according to the path association rule; According to the yield prediction model, the yield corresponding to the set process parameter combination is obtained, and the set process parameter-yield path set is constructed.

4. The acquisition method according to claim 1, characterized in that: The step of counting the occurrence frequencies of the path types of the set process parameter-yield path set and acquiring the target process parameter set of the positive sample according to the occurrence frequencies of the path types comprises: According to whether the combinations of the set process parameters in the set process parameter-yield path set are the same or not, classifying all the combinations of the set process parameters to obtain a path type set; Obtaining a statistical quantity of each path type in the path type set; The target process parameter set is constructed according to the process parameters corresponding to the path type whose statistical quantity is greater than a set quantity threshold.

5. The acquisition method according to claim 1, characterized in that: The step of obtaining an ideal process parameter range corresponding to the target process according to the target process parameter set includes: According to the target process parameter set, obtaining a maximum value and a minimum value of the process parameters corresponding to the target process; According to the maximum value of the process parameter and the minimum value of the process parameter, an ideal process parameter range corresponding to the target process is obtained.

6. The acquisition method according to claim 1, characterized in that: After the step of obtaining an ideal process parameter range corresponding to the target process according to the target process parameter set, the method further includes: According to the historical processing data, a negative sample process parameter set corresponding to the negative sample set is obtained; wherein the negative sample in the negative sample set is a processing data combination of a single processing that does not meet the set requirements; By removing and adding set processes from the negative sample process parameter set, the influence of the set process on the negative sample set is obtained, and an NG key process set is constructed; According to the influence degree of each type of NG key process in the NG key process set on the achievement probability of meeting the set requirements, the qualified process parameter range of each type of the NG key process is obtained to construct the NG key process parameter set; When the target process belongs to the NG key process set, the ideal process parameter range of the target process is corrected and optimized according to each type of the NG key process parameter set.

7. The acquisition method according to claim 6, characterized in that: The step of obtaining the influence of the set process on the negative sample set by removing and adding the set process from the negative sample process parameter set includes: Step 11, using any type of process in the negative sample process parameter set as the set process; Step 12, according to the yield prediction model, obtaining the yield corresponding to the set process included in the negative sample set and the yield corresponding to the set process not included in the negative sample set, and determining the predicted difference value corresponding to the set process; Step 13, changing the process parameter value of the set process in the negative sample set, and obtaining the influence factor value of the set process on the negative sample set according to the predicted difference value corresponding to the set process; Step 14, updating the type of the set process, repeating steps 12 to 13 until all processes in the negative sample process parameter set are traversed, and obtaining the impact factor values ​​of all processes in the negative sample process parameter set on the negative sample set.

8. The acquisition method according to claim 6, characterized in that: The step of obtaining the qualified process parameter range of each type of NG key process in the NG key process set according to the influence degree of each type of NG key process in the NG key process set on the achievement probability of meeting the set requirement comprises: According to the yield prediction model, the qualified process parameter range of each type of the NG key process is obtained using the partial dependence graph algorithm; wherein the total number of process types in the NG key process set is 2.

9. The acquisition method according to claim 6, characterized in that: When the target process belongs to the NG key process set, the step of correcting and optimizing the ideal process parameter range of the target process according to each type of the NG key process parameter set comprises: Determining whether the upper and lower limits of the ideal process parameter range of the target process are complete; If it is incomplete, the ideal process parameter range of the target process is completed according to the qualified process parameter range corresponding to the target process in the NG key process set, so as to complete the correction and optimization of the ideal process parameter range of the target process; If complete, determine whether the ideal process parameter range corresponding to the target process and the qualified process parameter range corresponding to the target process have an intersection; If there is no intersection, determining the corrected process parameter range corresponding to the target process according to the positive sample processing data set, and taking the intersection of the corrected process parameter range corresponding to the target process and the qualified process parameter range corresponding to the target process as the ideal process parameter range of the target process; If there is an intersection, the intersection of the ideal process parameter range corresponding to the target process and the qualified process parameter range corresponding to the target process is taken as the ideal process parameter range of the target process.

10. A method for adjusting process parameters of anodizing dyeing, characterized in that: include: Get the current process parameter set that does not meet the set requirements for this processing; According to the ideal process parameter range, the process parameters in the current process parameter set are adjusted; wherein the ideal process parameter range is obtained by the acquisition method described in any one of claims 1 to 9.

11. An electronic device, characterized in that: It comprises a controller and a memory, wherein the controller is used to implement the acquisition method according to any one of claims 1 to 9 and / or the adjustment method according to claim 10 when executing the computer program stored in the memory.

12. A computer-readable storage medium, characterized in that: A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the controller, the acquisition method according to any one of claims 1 to 8 and / or the adjustment method according to claim 10 are implemented.

Images