Process parameter adjustment method and device, equipment, storage medium and program product

Abstract

The embodiment of the present application discloses a process parameter adjustment method and apparatus, equipment, storage medium and program product, including: obtaining detection data for evaluating the quality of a workpiece to be measured, and first identification information of the workpiece to be measured; obtaining deviation data between the detection data and preset reference quality data; when the deviation data meets a preset condition, obtaining multiple process parameters corresponding to the second identification information matched by the first identification information in the historical workpiece processing data; inputting the multiple process parameters into a preset parameter adjustment model to obtain the target process parameters of the target process equipment after processing the workpiece to be measured. The process parameters of the process equipment can be adjusted according to the detection results of the workpiece and the process parameters used in the processing process to improve the qualified rate of subsequent workpieces processed by the process equipment, reduce the cost of manual parameter adjustment, and help to achieve precise control of process parameters, improve production efficiency and workpiece quality.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of production process technology, including but not limited to a process parameter adjustment method and apparatus, equipment, storage medium, and program product. Background Art

[0002] In industrial production, for workpiece processing processes involving multiple parameters and steps, such as photovoltaic phosphorus or boron diffusion processes, process parameters such as the temperature of each step, the type and amount of various gases introduced in each step, and the duration of each step will all affect the final silicon wafer diffusion results. To ensure the quality of the finished product, it is necessary to set inspection indicators to conduct spot checks on processed workpieces. If anomalies are found, process parameters are adjusted to ensure the pass rate of subsequent workpieces.

[0003] In related fields, adjusting process parameters typically relies on engineers with specialized knowledge. This approach is not only labor-intensive but also often results in adjustments that are limited by the engineers' prior experience and lack sufficient theoretical and data support. Furthermore, when multiple parameters need to be adjusted, both manual adjustments and expert systems designed based on human experience can suffer from unsatisfactory results and low efficiency. Summary of the Invention

[0004] In view of this, the process parameter adjustment method, device, equipment, storage medium, and program product provided in the embodiments of the present application can adjust the process parameters of the process equipment based on the inspection results of the workpiece and the process parameters used by the corresponding process equipment during the workpiece processing process, thereby improving the pass rate of subsequent workpieces processed by the process equipment, reducing the cost of manual parameter adjustment, and improving production efficiency and workpiece quality. The process parameter adjustment method, device, equipment, storage medium, and program product provided in the embodiments of the present application are implemented as follows:

[0005] The process parameter adjustment method provided in the embodiment of the present application includes:

[0006] Acquire detection data for evaluating the quality of a workpiece to be measured, and first identification information of the workpiece to be measured, wherein the detection data and the first identification information are collected and obtained by a target detection device;

[0007] Obtaining deviation data between the detection data and preset reference quality data;

[0008] When the deviation data satisfies a preset condition, a plurality of process parameters corresponding to the second identification information matched by the first identification information in the historical workpiece processing data are obtained, where the historical workpiece processing data includes the second identification information of the workpiece to be measured and the plurality of process parameters corresponding to the second identification information, where the plurality of process parameters are process parameters adopted by the target process equipment during the processing of the workpiece to be measured;

[0009] The multiple process parameters are input into a preset parameter adjustment model to obtain the target process parameters of the target process equipment after processing the workpiece to be measured. The preset parameter adjustment model is obtained based on sample detection data of multiple sample workpieces and multiple sample process parameters of each sample workpiece processed by the target process equipment. The multiple sample workpieces are of the same type as the workpiece to be measured.

[0010] In some embodiments, after acquiring the detection data for evaluating the quality of the workpiece to be measured and the first identification information of the workpiece to be measured, the method further includes:

[0011] When the target process equipment does not meet the preset normal operating conditions during the processing of the workpiece to be measured, the current process parameter adjustment process is terminated, and an equipment abnormality alarm is generated and sent.

[0012] In some embodiments, the preset condition includes that the deviation data is within a preset deviation threshold range; the method further includes:

[0013] When the deviation data does not meet the preset conditions, the current process parameter adjustment process is terminated, and an abnormal detection alarm of the workpiece to be tested is generated and sent.

[0014] In some embodiments, the first identification information includes the target process equipment information corresponding to the workpiece to be measured and the target detection time for obtaining the detection data, and the second identification information includes the target process equipment information corresponding to the workpiece to be measured and the target processing time of the workpiece to be measured during the processing process, and the target processing time is a time within a preset time range before the target detection time.

[0015] In some embodiments, the preset parameter adjustment model is pre-set by the following method:

[0016] Acquiring sample detection data and sample identification information of the plurality of sample workpieces;

[0017] Acquiring historical sample workpiece processing data, wherein the historical sample workpiece processing data includes a plurality of sample process parameters used by each sample workpiece during a processing process of a corresponding process device;

[0018] Acquire a plurality of sample process parameters corresponding to each sample workpiece matched by sample identification information of each sample workpiece in the historical sample workpiece processing data;

[0019] Performing feature processing on the sample detection data and multiple sample process parameters corresponding to each sample workpiece to construct a sample data set, wherein the feature processing includes eliminating abnormal data according to preset abnormal conditions;

[0020] The parameter adjustment model is obtained according to the sample data set and a preset parameter adjustment formula, wherein the preset parameter adjustment formula is designed according to a machining process of a workpiece of the same type as the workpiece to be measured.

[0021] In some embodiments, the preset parameter adjustment formula is constructed based on a plurality of process parameters of a workpiece of the same type as the workpiece to be measured during processing as input variables, inspection data of a workpiece of the same type as the workpiece to be measured as output variables, and a plurality of preset parameters;

[0022] The parameter adjustment model is obtained according to the sample data set and a preset parameter adjustment formula, including:

[0023] Substituting the detection data and multiple process parameters of each sample data in the sample data set into the preset parameter adjustment formula to solve the value of each preset parameter in the preset parameter adjustment formula;

[0024] By minimizing the loss value algorithm, the values ​​of each preset parameter are optimized to obtain the optimized values ​​of each preset parameter;

[0025] Substitute the optimized values ​​of each preset parameter into the parameter adjustment formula to obtain the parameter adjustment model.

[0026] In some embodiments, inputting the plurality of process parameters into a preset parameter adjustment model to obtain target process parameters of the target process equipment after processing the workpiece to be tested includes:

[0027] Taking a first process parameter as a solution object, substituting numerical values ​​of process parameters other than the first process parameter among the multiple process parameters into the preset parameter adjustment model for solution processing, wherein the first process parameter is one of the multiple process parameters;

[0028] determining whether the first process parameter has a solution;

[0029] When the first process parameter has a solution, the original value of the first process parameter is updated using the value of the solution corresponding to the first process parameter to obtain the target process parameter of the target process equipment after processing the workpiece to be measured;

[0030] When there is no solution for the first process parameter, taking the first process parameter and the second process parameter as solution objects, substituting the values ​​of the process parameters other than the first process parameter and the second process parameter among the multiple process parameters into the preset parameter adjustment model for solution processing, where the second process parameter is a process parameter other than the first process parameter among the multiple process parameters;

[0031] determining whether the first process parameter and the second process parameter have a solution;

[0032] When there is a solution for the first process parameter and the second process parameter, the original values ​​of the first process parameter and the second process parameter are updated using the values ​​of the solutions corresponding to the first process parameter and the second process parameter to obtain target process parameters of the target process equipment after processing the workpiece to be measured;

[0033] The method further comprises:

[0034] In the case that there is no solution between the first process parameter and the second process parameter, the current process parameter adjustment process is terminated, and an adjustment failure alarm is generated and sent.

[0035] In some embodiments, taking the first process parameter as a solution object and substituting the values ​​of the process parameters other than the first process parameter among the multiple process parameters into the preset parameter adjustment model for solution processing includes:

[0036] According to a preset parameter adjustment requirement, a first value interval for adjusting the first process parameter and a target detection data value interval for processing a workpiece of the same type after the workpiece to be tested are obtained;

[0037] Inputting numerical values ​​of the process parameters other than the first process parameter among the plurality of process parameters into the preset parameter adjustment model to solve the first process parameter;

[0038] The solution processing includes obtaining a numerical value of a solution corresponding to the first process parameter within the first value range, so that the detection data output according to the preset parameter adjustment model is within the target detection data value range.

[0039] In some embodiments, the workpiece to be tested is a photovoltaic cell to be tested, the target process equipment for the workpiece to be tested is a photovoltaic diffusion process equipment, the detection data includes the square resistance value of the photovoltaic cell to be tested, and the multiple process parameters include the temperature, duration and diffusion source input of each step of the photovoltaic cell to be tested during the processing.

[0040] In some embodiments, the parameter adjustment formula is based on the temperature, duration, and diffusion source concentration of the diffusion step of the photovoltaic diffusion process equipment corresponding to the same type or model of photovoltaic cell as the photovoltaic cell to be tested during the processing as input variables, and the square resistance value of the photovoltaic cell of the same type as the photovoltaic cell to be tested as the output variable, and the preset parameters include the diffusion source concentration coefficient, the diffusion constant, the diffusion resistivity, the activation energy of the diffusion source, and the temperature offset of the photovoltaic cell when the square resistance test is performed;

[0041] The parameter adjustment formula is:

[0042]

[0043] Where R is the square resistance of the photovoltaic cell, rou is the diffusion resistivity, Ea is the activation energy of the diffusion source, x_temp is the temperature of the diffusion step, T is the temperature offset when the photovoltaic cell is tested for square resistance, 274.15 is used to represent the Kelvin temperature of 274.15 degrees, D is the diffusion constant, x_T is the duration of the diffusion step, k is the diffusion source concentration coefficient, x_z is the diffusion source concentration, 60 is used to represent 60 seconds, and the diffusion source concentration is obtained by the ratio of the diffusion source input to the sum of the diffusion source input, oxygen input, and nitrogen input;

[0044]

[0045] Among them, T k is the temperature offset at the square resistance detection position k, M is the total number of temperature zones in the diffusion step, temp i is the temperature of temperature zone i, a is the temperature influence coefficient of the temperature in temperature zone i on the resistance detection position k; k is the temperature attenuation coefficient of the square resistance detection position k.

[0046] The process parameter adjustment device provided in the embodiment of the present application includes:

[0047] a test data management module, configured to obtain test data for evaluating the quality of a workpiece to be tested, and first identification information of the workpiece to be tested, wherein the test data and the first identification information are acquired by a target test device; and obtain deviation data between the test data and preset reference quality data;

[0048] a process parameter acquisition module, which, when the deviation data satisfies a preset condition, acquires, from historical workpiece processing data, a plurality of process parameters corresponding to the second identification information matched by the first identification information, the historical workpiece processing data including the second identification information of the workpiece to be measured and the plurality of process parameters corresponding to the second identification information, the plurality of process parameters being process parameters used by a target process equipment during processing of the workpiece to be measured;

[0049] A process parameter adjustment module inputs the multiple process parameters into a preset parameter adjustment model to obtain the target process parameters of the target process equipment after processing the workpiece to be measured. The preset parameter adjustment model is obtained based on sample detection data of multiple sample workpieces and multiple sample process parameters of each sample workpiece processed by the target process equipment. The multiple sample workpieces are of the same type as the workpiece to be measured.

[0050] The computer device provided in an embodiment of the present application includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, the method described in the embodiment of the present application is implemented.

[0051] The computer-readable storage medium provided in the embodiment of the present application stores a computer program thereon, and when the computer program is executed by a processor, the method provided in the embodiment of the present application is implemented.

[0052] The computer program product provided in the embodiments of the present application includes a computer program, which implements the method provided in the embodiments of the present application when executed.

[0053] The process parameter adjustment method, device, equipment, storage medium, and program product provided in this application have at least the following beneficial effects:

[0054] In the related technical field, because the workpiece inspection data and the process parameters used in the machining process are collected on different devices, manual matching is usually required, which is both time-consuming and error-prone. The method provided in this application automatically matches the first identification information of the workpiece to be inspected obtained by the target inspection device with the second identification information in the historical workpiece machining data, thereby achieving automatic matching of the inspection data and multiple process parameters in the machining process, thereby improving the matching efficiency and accuracy.

[0055] In addition, the method provided by this application obtains a parameter adjustment model through the inspection data of historical sample workpieces and the process parameters used in processing. Compared with manual experience, it has theoretical and data basis and is more accurate in controlling process parameters.

[0056] In this way, in industrial production involving multiple parameters and multiple steps, the process parameters that affect the quality of the workpiece can be adjusted to reduce the cost of manual parameter adjustment, which will help to achieve precise control of process parameters and improve production efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and, together with the specification, are used to illustrate the technical solutions of the present application.

[0058] Figure 1 A schematic diagram of a process flow of a method for adjusting process parameters provided in an embodiment of the present application;

[0059] Figure 2 Another schematic flow chart of the process parameter adjustment method provided in an embodiment of the present application;

[0060] Figure 3 A schematic diagram of a process flow for presetting a parameter adjustment model in the process parameter adjustment method provided in an embodiment of the present application;

[0061] Figure 4 A schematic diagram of a process flow for presetting a parameter adjustment model in a photovoltaic diffusion process scenario in the process parameter adjustment method provided in an embodiment of the present application;

[0062] Figure 5 This is a schematic diagram of the relationship between the temperature zones and the temperatures at each resistance inspection location in the photovoltaic diffusion process scenario;

[0063] Figure 6 This is the fitting curve of different process parameters and square resistance in the photovoltaic diffusion process scenario;

[0064] Figure 7 A schematic diagram of a process flow for adjusting process parameters in the process parameter adjustment method provided in an embodiment of the present application;

[0065] Figure 8 A schematic diagram of the structure of a process parameter adjustment device provided in an embodiment of the present application;

[0066] Figure 9 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0067] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the specific technical solutions of the present application will be further described in detail below in conjunction with the drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application but are not intended to limit the scope of the present application.

[0068] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0069] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0070] It should be pointed out that the terms "first\second\third" involved in the embodiments of the present application are used to distinguish similar or different objects, and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0071] In the industrial production field, when it comes to the production process of a certain workpiece, it usually requires a series of carefully designed steps to obtain the corresponding workpiece. In this process, the process parameters of each step are particularly important.

[0072] Process parameters refer to the various conditions and values ​​set during the production process to control workpiece quality and improve production efficiency. Process parameters permeate the entire production process, from raw material selection to processing and inspection. For example, in the machining of metal workpieces, the selection of process parameters such as cutting speed, feed rate, and depth of cut directly impacts the workpiece's surface roughness, dimensional accuracy, and machining efficiency.

[0073] For some multi-step, multi-parameter production processes, the adjustment of process parameters is particularly important. The process parameters of each step, such as raw material ratio, processing time, etc., will affect product quality and production efficiency.

[0074] Therefore, in complex production processes involving numerous steps and process parameters, the adjustment of process parameters often relies on experienced engineers. This approach not only leads to high labor costs, but also the adjustment results are often limited by the engineer's personal experience and intuition, lacking effective support from scientific theory and data. In addition, process parameters often influence each other, and even a small change in one parameter can cause fluctuations in the entire production process, thereby affecting the final quality of the workpiece. Simultaneously adjusting multiple process parameters based on manual experience is difficult, which not only reduces the efficiency of process parameter adjustment but also may lead to situations where effective adjustment cannot be made.

[0075] Furthermore, during the production process, workpiece processing and quality inspection are often performed by different devices. This means that in order to adjust process parameters based on the inspection results, the workpiece inspection results and process parameters obtained by different devices must be manually matched. This process is not only cumbersome but also prone to errors. Especially when processing large amounts of data, manual matching is inefficient and cannot guarantee accuracy.

[0076] See also Figure 1 , Figure 1 A flow chart of the process parameter adjustment method provided in the embodiment of the present application. Figure 1 As shown, the method may include the following steps 101 to 104.

[0077] Step 101: Acquire detection data for evaluating the quality of a workpiece to be measured and first identification information of the workpiece to be measured.

[0078] In an embodiment of the present application, detection data for evaluating the quality of a workpiece to be detected and first identification information of the workpiece to be detected are obtained, and the detection data and the first identification information are collected by a target detection device.

[0079] It should be noted that the workpiece to be measured is obtained by processing the target process equipment. After the workpiece to be measured is processed, it needs to be inspected by the target inspection equipment to obtain the inspection data of the workpiece to be measured.

[0080] Understandably, in industrial production, the processing and inspection of workpieces requires highly specialized equipment. These devices often have specific functions, with each device typically dedicated to a single function. For example, some equipment is dedicated to cutting, while others are specialized for polishing or inspection. This specialized division of labor allows each device to perform optimally within its specific area. However, this also presents challenges in communicating and integrating data from these devices. In related technical fields, data collected from different devices requires manual matching.

[0081] Therefore, in the present application, while obtaining the inspection data for evaluating the quality of the workpiece to be measured, the first identification information of the workpiece to be measured will also be obtained through the target inspection device corresponding to the workpiece to be measured, which will be used for subsequent matching of the data of the process equipment and the inspection equipment. Through the form of machine matching, the matching efficiency is improved, thereby improving the efficiency of adjusting the process parameters, and improving production efficiency and workpiece quality.

[0082] In some embodiments, the workpiece to be tested is a photovoltaic cell (silicon wafer). After the photovoltaic diffusion process, the photovoltaic cell is passed through a square resistance detection device to obtain the square resistance value of the photovoltaic cell. The square resistance value is used to evaluate the quality of the photovoltaic cell. A smaller square resistance value indicates that the photovoltaic cell has better conductivity and high current transmission efficiency.

[0083] It should be noted that photovoltaic diffusion processes, such as phosphorus diffusion or boron diffusion, are key steps in the manufacturing of photovoltaic cells and play a vital role in improving their performance. Taking the boron diffusion process as an example, boron is diffused into silicon crystals to form p-type doped regions, thereby changing the silicon crystal's conductive properties and promoting photoelectric conversion. By precisely controlling the diffusion depth and concentration of boron, the electric field distribution in the silicon wafer can be adjusted, reducing electric field non-uniformity and improving the output power and conversion efficiency of the photovoltaic cell. Sheet resistance, also known as square resistance, refers to the edge-to-edge resistance of a square thin-film conductive material, measured in ohms per square. A smaller sheet resistance indicates better conductivity; conversely, a larger sheet resistance indicates poorer conductivity. In practical applications, measuring sheet resistance is crucial for evaluating a material's conductive properties and optimizing process parameters.

[0084] In the photovoltaic diffusion process scenario, the workpieces to be tested and the sample workpieces are photovoltaic cells (silicon wafers), and the process equipment is photovoltaic diffusion process equipment. In photovoltaic diffusion process equipment, the furnace tube is a key heating unit used to heat treat photovoltaic cells. Each furnace tube in the photovoltaic diffusion process equipment has its own specific heating area and temperature control range. The boat is the container that carries the photovoltaic cells for diffusion processing, and each boat can hold a certain number of photovoltaic cells.

[0085] Step 102: Obtain deviation data between the detection data and preset reference quality data.

[0086] In an embodiment of the present application, deviation data between the detection data and preset reference quality data is obtained.

[0087] It should be noted that in this application, the preset reference quality data and the test data of the workpiece to be measured are of the same type. For example, when the test data of the workpiece to be measured is the value of the square resistance obtained by detection, the preset reference quality data is the value of the square resistance that meets the quality expectations. When the test data of the workpiece to be measured is the weight of the workpiece to be measured, the preset reference quality data is the weight of the standard workpiece. This is determined based on the actual scenario and is not limited here.

[0088] In some embodiments, the preset reference mass data includes a plurality of reference mass sub-data, and the detection data of the workpiece to be measured includes a plurality of detection sub-data. Obtaining deviation data between the detection data and the preset reference mass data includes:

[0089] A plurality of deviation sub-data between the plurality of reference quality sub-data and the corresponding detection sub-data are acquired.

[0090] It is understandable that in industrial production, the quality review standards for corresponding workpieces are not unique, and the quality of workpieces is usually evaluated through multiple dimensions. For example, when testing the processed photovoltaic cells to be tested, it is necessary to detect the values ​​of the square resistance at multiple positions on the photovoltaic cells to be tested to ensure that the conductivity and efficiency of the photovoltaic cells meet the established requirements. The detection data of the photovoltaic cells to be tested may include the square resistance value, the mean square resistance and the standard deviation of the square resistance at each detection position, and the preset reference quality data include the reference square resistance value, the mean reference square resistance and the expected standard deviation at each detection position. In actual applications, the data types of each reference quality sub-data and each detection sub-data are selected according to the type of actual workpiece and are not limited here.

[0091] Step 103 : When the deviation data satisfies a preset condition, a plurality of process parameters corresponding to the second identification information matched with the first identification information in the historical workpiece processing data are obtained.

[0092] In an embodiment of the present application, when the deviation data meets the preset conditions, multiple process parameters corresponding to the second identification information matched by the first identification information are obtained in the historical workpiece processing data. The historical workpiece processing data includes the second identification information of the workpiece to be measured, and the multiple process parameters corresponding to the second identification information. The multiple process parameters are the process parameters adopted by the target process equipment for the workpiece to be measured during the processing process.

[0093] It's important to note that deviation data reflects the difference between the workpiece's inspection data and the preset reference quality data. Smaller deviations indicate that the workpiece's quality more closely meets expectations. Larger deviations indicate a significant deviation from the preset standard, potentially indicating quality issues or instability in the production process.

[0094] In the embodiments of the present application, the preset condition may be a preset deviation data threshold, or a dynamic threshold obtained based on statistical analysis of historical data, which sets an acceptable range for the deviation data.

[0095] In some embodiments, when the deviation data meets a preset condition, multiple process parameters in the historical workpiece processing data are obtained and subsequent process parameter adjustments are performed; otherwise, the current process parameter adjustment process is terminated.

[0096] It should be noted that the historical workpiece processing data may be data of workpieces processed by multiple process equipment including the target process equipment, or data of workpieces processed by the target process equipment processing the workpiece to be tested, which is not limited here.

[0097] In the embodiment of the present application, the test data of the workpiece to be tested and the process parameters used by the target process equipment to process the workpiece to be tested are stored in different locations and need to be matched to adjust the process parameters. Therefore, the first identification information is matched with the second identification information in the historical workpiece processing data to obtain the process parameters used during the processing of the workpiece to be tested.

[0098] It should be noted that both the first identification information and the second identification information are identification information of the workpiece to be tested. The difference is that the first identification information is acquired by the target detection equipment and stored together with the test data of the workpiece to be tested, while the second identification information is acquired by the target process equipment and stored together with the processing parameters of the workpiece to be tested. By matching the first identification information with the second identification information in the historical workpiece processing data, it is possible to match the test data of the workpiece to be tested with the process parameters used during the processing.

[0099] In some embodiments, unique identification information, such as a unique code, serial number, etc., can be set for each workpiece, and the code or serial number corresponding to the workpiece to be measured can be used as the first identification information and the second identification information. During the matching process, only the identification information with the same code or serial number needs to be obtained to achieve matching of the detection data of the workpiece to be measured and the process parameters used in the processing process.

[0100] In some embodiments, the first identification information includes the target process equipment information corresponding to the workpiece to be measured and the target detection time for obtaining the detection data, and the second identification information includes the target process equipment information corresponding to the workpiece to be measured and the target processing time of the workpiece to be measured during the processing process, and the target processing time is a time within a preset time range before the target detection time.

[0101] It is understandable that both the first identification information and the second identification information include target process equipment information. In addition, the first identification information also includes the target detection time, and the second identification information also includes the target processing time. Since the workpiece is processed before being inspected in industrial production, it can be determined that the target process equipment information is the same, and the first identification information and the second identification information whose target detection time is within a preset time range after the target processing time correspond to the same workpiece to be measured, thereby achieving the matching of the detection data of the workpiece to be measured and the process parameters used in the processing process. Through this method, only time information needs to be recorded, which improves the efficiency of data processing. Among them, the preset time range is determined according to the type of workpiece, production scale or process requirements, and is not limited here.

[0102] Step 104 : Input multiple process parameters into a preset parameter adjustment model to obtain target process parameters of the target process equipment after processing the workpiece to be tested.

[0103] In an embodiment of the present application, the multiple process parameters are input into a preset parameter adjustment model to obtain the target process parameters of the target process equipment after processing the workpiece to be measured. The preset parameter adjustment model is obtained based on sample detection data of multiple sample workpieces and multiple sample process parameters of each sample workpiece processed by the target process equipment. The multiple sample workpieces are of the same type as the workpiece to be measured.

[0104] Through the above-mentioned technical solution, the method provided in this application can adjust the process parameters of the process equipment according to the inspection results of the workpiece and the process parameters adopted in the processing process, so as to improve the qualified rate of subsequent workpieces processed by the process equipment, reduce the cost of manual adjustment of parameters, and help to achieve precise control of process parameters and improve production efficiency and workpiece quality.

[0105] See also Figure 2 Another flow chart of the process parameter adjustment method provided in the embodiment of the present application. Figure 2 As shown, the method may include the following steps 201 to 208.

[0106] Step 201: Acquire detection data for evaluating the quality of a workpiece to be measured and first identification information of the workpiece to be measured.

[0107] Step 202 : determining whether the target process equipment meets preset normal operating conditions during the processing of the workpiece to be tested.

[0108] In some embodiments, it is determined whether the target process equipment meets preset normal operating conditions during the processing of the workpiece to be tested.

[0109] It should be noted that the preset normal operating conditions are related to the type and function of the process equipment. Different types of process equipment, such as cutting equipment, grinding equipment, and welding equipment, may have different preset normal operating conditions. For example, cutting equipment may require a stable cutting speed; grinding equipment may require maintaining the rotation temperature of the grinding wheel and the uniformity of the grinding force; and welding equipment may focus on the stability of the welding current, etc.

[0110] In some embodiments, various equipment parameter information of the target process equipment during the processing of the workpiece to be tested, such as temperature, pressure, speed, current, etc., is obtained and compared with the preset normal operating range. If these parameters are outside the normal range, the method provided by this application will determine that the target process equipment does not meet the preset normal operating conditions.

[0111] If the target process equipment meets the preset normal operating conditions during the processing of the workpiece to be tested, step 203 is performed; otherwise, step 204 is performed.

[0112] Step 203: Obtain deviation data between the detection data and preset reference quality data.

[0113] Step 204: End the current process parameter adjustment process, generate and send an equipment abnormality alarm.

[0114] In some embodiments, after acquiring the detection data for evaluating the quality of the workpiece to be measured and the first identification information of the workpiece to be measured, the method further includes:

[0115] When the target process equipment does not meet the preset normal operating conditions during the processing of the workpiece to be measured, the current process parameter adjustment process is terminated, and an equipment abnormality alarm is generated and sent.

[0116] It is understood that if the target process equipment does not meet the preset normal operating conditions during the processing of the workpiece to be tested, it indicates that some problems or abnormal conditions may exist in the target process equipment, which may affect the processing quality of subsequent workpieces and may also have a negative impact on the stability and efficiency of the entire production line. Therefore, the current process parameter adjustment process is terminated, and an equipment abnormality alarm is generated and sent for technical personnel to verify and avoid invalid process parameter adjustments due to process equipment problems.

[0117] In some embodiments, a process parameter adjustment method is applied to parameter adjustment of a photovoltaic diffusion process. When the target process equipment does not meet preset normal operating conditions during the processing of the workpiece to be measured, the current process parameter adjustment process is terminated, and an equipment abnormality alarm is generated and sent, including:

[0118] Perform leak detection on the furnace tubes of target photovoltaic diffusion process equipment and obtain leak detection data;

[0119] Determining whether the furnace tube is leaking based on the leak detection data;

[0120] In the event of gas leakage in the furnace tube of the target photovoltaic diffusion process equipment, the current process parameter adjustment process is terminated, and an equipment abnormality alarm is generated and sent.

[0121] Step 205: Determine whether the deviation data meets a preset condition.

[0122] In some embodiments, if the deviation data satisfies a preset condition, step 206 is performed; otherwise, step 207 is performed.

[0123] Step 206 : When the deviation data satisfies a preset condition, a plurality of process parameters corresponding to the second identification information matched with the first identification information in the historical workpiece processing data are obtained.

[0124] Step 207: End the current process parameter adjustment process, generate and send an abnormality alarm for the workpiece to be tested.

[0125] In some embodiments, the preset condition includes that the deviation data is within a preset deviation threshold range; the method further includes:

[0126] When the deviation data does not meet the preset conditions, the current process parameter adjustment process is terminated, and an abnormal detection alarm of the workpiece to be tested is generated and sent.

[0127] It should be noted that when the deviation data is small, less than the lower limit of the preset deviation threshold interval, it is determined that the most recently processed workpiece to be tested meets the quality requirements, and there is no need to adjust the process parameters to ensure the quality of subsequent workpieces. When the deviation data is large, greater than the upper limit of the preset deviation threshold interval, it is determined that the quality of the most recently processed workpiece to be tested is poor and the quality of subsequent workpieces cannot be guaranteed by adjusting the process parameters. At this time, the current process parameter adjustment process is terminated, and the workpiece detection form to be tested issues a corresponding alarm, prompting technicians to check whether it is an abnormality of a single workpiece or whether there is an abnormality in the process equipment, thereby improving the efficiency of process adjustment and ensuring normal production.

[0128] In some embodiments, before obtaining the deviation data between the detection data and the preset reference quality data, it is determined whether the detection data meets the preset abnormality condition; if so, the current process parameter adjustment process is terminated, and an abnormality alarm for the detection of the workpiece to be tested is generated and sent.

[0129] It should be noted that in some embodiments, it is possible to determine whether the detection data is abnormal before obtaining the deviation data, including whether the detection data is too large, so as to end the current process parameter adjustment process as soon as possible and generate and send an abnormal detection alarm for the workpiece to be tested.

[0130] Step 208 : When the deviation data satisfies a preset condition, a plurality of process parameters corresponding to the second identification information matched with the first identification information in the historical workpiece processing data are obtained.

[0131] By implementing the above technical solution, it is possible to further obtain deviation data between the test data and the preset reference quality data, provided that the target process equipment meets the preset normal operating conditions during the machining of the workpiece to be tested. By comparing the deviation data with the preset conditions, it is determined whether to continue matching and obtaining corresponding process parameters from the historical workpiece machining data to support the subsequent process parameter adjustment process. This not only improves the accuracy and efficiency of process adjustment, but also helps to ensure production stability and product quality reliability.

[0132] In some embodiments, the preset parameter adjustment model is pre-set by the following method:

[0133] Acquiring sample detection data and sample identification information of the plurality of sample workpieces;

[0134] Acquiring historical sample workpiece processing data, wherein the historical sample workpiece processing data includes a plurality of sample process parameters used by each sample workpiece during a processing process of a corresponding process device;

[0135] Acquire a plurality of sample process parameters corresponding to each sample workpiece matched by sample identification information of each sample workpiece in the historical sample workpiece processing data;

[0136] Performing feature processing on the sample detection data and multiple sample process parameters corresponding to each sample workpiece to construct a sample data set, wherein the feature processing includes eliminating abnormal data according to preset abnormal conditions;

[0137] The parameter adjustment model is obtained according to the sample data set and a preset parameter adjustment formula, wherein the preset parameter adjustment formula is designed according to a machining process of a workpiece of the same type as the workpiece to be measured.

[0138] The following describes a method for presetting the preset parameter adjustment model.

[0139] See also Figure 3 , Figure 3 A flow chart of presetting the parameter adjustment model in the process parameter adjustment method provided in the embodiment of the present application. Figure 3 As shown, the method may include the following steps 301 to 305:

[0140] Step 301: Acquire sample detection data and sample identification information of a plurality of sample workpieces.

[0141] It should be noted that the sample workpiece and the workpiece to be tested are of the same type. The sample workpiece can be processed using the same target process equipment as the workpiece to be tested, or it can be processed using the same model of process equipment as the target process equipment used to process the workpiece to be tested. Furthermore, the sample workpiece and the workpiece to be tested have the same function, design, and model. In this way, a parameter adjustment model trained based on the inspection data of multiple sample workpieces and the process parameters used during processing can be used to adjust the process parameters used by the target process equipment after processing the workpiece to be tested.

[0142] Step 302 : Acquire historical sample workpiece processing data, where the historical sample workpiece processing data includes a plurality of sample process parameters used during the processing of each sample workpiece by a corresponding process device.

[0143] Step 303 : Acquire multiple sample process parameters corresponding to each sample workpiece matched with the sample identification information of each sample workpiece in the historical sample workpiece processing data.

[0144] By implementing the above steps 301 to 303 , the sample detection data of each sample workpiece can be matched with a plurality of sample process parameters used in the processing of each sample workpiece by a corresponding process equipment, providing data support for the subsequent construction of a parameter adjustment model.

[0145] The following describes, in some embodiments, the process of matching photovoltaic cell test data with process parameters in a photovoltaic diffusion process. The workpieces to be tested and the sample workpieces are photovoltaic cells (silicon wafers), and the process equipment is photovoltaic diffusion equipment. The process equipment information for the photovoltaic diffusion equipment includes the equipment number, furnace number, and boat number.

[0146] In some embodiments, to improve the efficiency of detection and parameter adjustment, the workpiece to be detected and the sample workpiece are set as multiple photovoltaic cells in the same boat, and the boat is used as a basic unit for data matching.

[0147] First, traverse the square resistance test result text file in the folder of the square resistance test equipment and extract the device number of the process equipment in the path.

[0148] Then, read the square resistance test result text file line by line, and extract the device number, furnace tube number, boat number, piece position, test time and test result from each line. It should be noted that a plurality of photovoltaic cells are placed on a boat, and only the square resistance values ​​of the photovoltaic cells at the specified position will be sampled during the inspection. The device number needs to match the device number in the path, otherwise the device number is left blank, and the keywords are composed of device number-furnace tube number-boat number. Different rows with the same keywords and within a preset time interval (test data of photovoltaic cells at different positions) are spliced ​​together as the square resistance test data of the same boat. The boat detection time is obtained by taking the maximum value or average value through the detection time of photovoltaic cells at different positions on the same boat. And the first identification information is composed of device number-furnace tube number-boat number-boat detection time.

[0149] Next, the system traverses the folder containing the diffusion process data, which stores historical workpiece processing data (a complete photovoltaic diffusion process is represented by a single file, stored in a multi-level directory structured in the order of device number, production date, and furnace tube number. Each file is identified by device number, furnace tube number, boat number, and boat processing time). The system then retrieves files in the folder where the second identification information for device number, furnace tube number, and boat number matches the first identification information. This means the device information is the same, but the boat inspection time and boat processing time differ by a preset time range (which can be one day, but is not limited here). If such a file is found, the match is successful.

[0150] It should be noted that if the quality requirements are high or according to actual requirements, the detection data and process parameters of a single photovoltaic cell can also be matched to construct a data set for training the parameter adjustment model, which is not limited here.

[0151] Step 304 : performing feature processing on the sample inspection data and multiple sample process parameters corresponding to each sample workpiece to construct a sample data set.

[0152] In some embodiments, feature processing is performed on sample detection data and multiple sample process parameters corresponding to each sample workpiece to construct a sample data set. The feature processing includes eliminating abnormal data according to preset abnormal conditions.

[0153] It should be noted that in order to effectively adjust process parameters, sample workpieces whose inspection data meets pre-set qualification standards should be screened and their process parameters used during processing should be collected. Subsequently, the parameter adjustment model is trained using the inspection data and process parameters of these screened sample workpieces to ensure its accuracy and effectiveness.

[0154] Therefore, in some embodiments, feature processing is performed on the sample detection data and multiple sample process parameters corresponding to each sample workpiece, and the sample detection data and multiple sample process parameters corresponding to each sample workpiece obtained according to preset abnormal conditions are eliminated.

[0155] In some embodiments, the process equipment uses a variety of process parameters when processing the sample workpiece. Some process parameters have little effect on the detection results of the sample workpiece or do not change during the processing, so such process parameters are screened.

[0156] In some embodiments, feature processing of process parameters and test results also includes calculating the mean, variance, etc., so as to obtain data that better reflects the processing process and provide more accurate and valuable information for subsequent parameter adjustment model construction.

[0157] In some embodiments, the process parameter adjustment method is applied to a photovoltaic diffusion process. Feature processing is performed on sample detection data and multiple sample process parameters corresponding to each sample workpiece to construct a sample data set, including:

[0158] First, extract the leak detection features and traverse the diffusion process data file including the process parameters of the processing process to determine whether there is a leak from the diffusion source in the step and obtain the leak rate. Then, process the square resistance detection data, extract the data set label, and traverse all the square resistance detection data files. If there is a square resistance value lower than the first threshold or the standard deviation of multiple square resistance values ​​is greater than the second threshold, the square resistance detection data is determined to be abnormal and needs to be eliminated. If not, the multiple square resistance values ​​of each detection position are averaged to obtain the average square resistance value of each detection position.

[0159] Next, other features are extracted from the diffusion process data (including a plurality of sample process parameters).

[0160] 1) Traverse each step and extract the temperature setting value of each temperature zone (6).

[0161] 2) Traverse each step and calculate the mean, variance, 1 / 4 and 3 / 4 digits of the air pressure and the temperature of each temperature zone (6 zones).

[0162] 3) Traverse each step and extract the amount of each gas introduced, that is, the gas formula.

[0163] 4) Traverse each step and calculate the duration.

[0164] Finally, the leakage rate, pumping time, temperature setting values ​​of each step and temperature zone, mean, variance, 1 / 4 and 3 / 4 digits of each step air pressure and temperature of each temperature zone, gas formula of each step, duration of each step, and average square resistance value of each detection position of the same sample master key are spliced ​​into complete sample data. The sample data corresponding to all sample photovoltaic cells constitute the sample data set.

[0165] Step 305: Obtain a parameter adjustment model based on the sample data set and a preset parameter adjustment formula.

[0166] In some embodiments, the parameter adjustment model is obtained based on the sample data set and a preset parameter adjustment formula, and the preset parameter adjustment formula is designed based on a machining process of a workpiece of the same type as the workpiece to be measured.

[0167] The sample dataset contains the inspection data and corresponding process parameters for multiple sample workpieces. This data has undergone preliminary processing and screening to ensure high representativeness and usability. The preset parameter adjustment formula is designed based on the machining process of workpieces of the same type as the workpiece being tested. It fully considers the characteristics and requirements of this type of workpiece during machining, thus ensuring the effectiveness and accuracy of the parameter adjustment model.

[0168] The design of parameter adjustment formulas requires consideration of multiple factors, such as the workpiece's material, size, and shape, as well as parameters such as temperature, pressure, time, and raw materials used during the machining process. A comprehensive analysis of these factors yields a mathematical model that reflects the essence of the machining process. The parameter adjustment formulas are then trained and validated using sample datasets to produce a parameter adjustment model.

[0169] In some embodiments, the preset parameter adjustment formula is constructed based on a plurality of process parameters of a workpiece of the same type as the workpiece to be measured during processing as input variables, inspection data of a workpiece of the same type as the workpiece to be measured as output variables, and a plurality of preset parameters;

[0170] The parameter adjustment model is obtained according to the sample data set and a preset parameter adjustment formula, including:

[0171] Substituting the detection data and multiple process parameters of each sample data in the sample data set into the preset parameter adjustment formula to solve the value of each preset parameter in the preset parameter adjustment formula;

[0172] By minimizing the loss value algorithm, the values ​​of each preset parameter are optimized to obtain the optimized values ​​of each preset parameter;

[0173] Substitute the optimized values ​​of each preset parameter into the parameter adjustment formula to obtain the parameter adjustment model.

[0174] It should be noted that the input variables of the parameter adjustment formula are the adjustable process parameters of the process equipment; the input variables are the inspection data of the workpiece; the preset parameters are the parameters that will affect the processing of the workpiece but cannot be directly controlled, such as the degree of equipment aging. Such parameters cannot be directly controlled, but their impact on the processing process cannot be ignored.

[0175] The loss minimization algorithm is an optimization algorithm whose core goal is to minimize the difference between predicted and actual results, i.e., the loss value, by adjusting the model's parameters. The algorithm iteratively adjusts the model's parameters, gradually reducing the loss function until it reaches a relatively small value or meets a preset stopping condition. This allows the model to better fit the training data and improve prediction accuracy.

[0176] In some embodiments, the values ​​of each preset parameter are optimized using a loss minimization algorithm until the values ​​of each preset parameter tend to stabilize. The optimized values ​​of each preset parameter are then substituted into the parameter adjustment formula to generate a parameter adjustment model. This parameter adjustment model can be used to obtain recommended values ​​for the target process parameters that require adjustment, providing a theoretical basis for process parameter adjustment and improving the efficiency of parameter adjustment compared to manual adjustment methods, thereby ensuring the stability and consistency of workpiece quality.

[0177] By implementing the above technical solution, the parameter adjustment model can be pre-set, which provides sufficient theoretical and data support for process parameter adjustment, helps to achieve precise control of process parameters, and improve production efficiency and workpiece quality.

[0178] See also Figure 4 , Figure 4 A schematic flow chart of presetting the parameter adjustment model in the photovoltaic diffusion process scenario in the process parameter adjustment method provided in the embodiment of the present application. Figure 4 As shown, the method may include the following steps 401 to 404.

[0179] Step 401 : Acquire a sample data set including detection data of a plurality of photovoltaic cells and process parameters used in a diffusion process.

[0180] In the photovoltaic diffusion process scenario, how to obtain a sample data set containing the inspection data of multiple photovoltaic cells and the process parameters used in the diffusion process is described in the attached Figure 3 This is explained in detail in the description and will not be repeated here.

[0181] Step 402: Obtain parameter adjustment formulas in a photovoltaic diffusion process scenario.

[0182] In some embodiments, the workpiece to be tested is a photovoltaic cell to be tested, the target process equipment for the workpiece to be tested is a photovoltaic diffusion process equipment, the detection data includes the square resistance value of the photovoltaic cell to be tested, and the multiple process parameters include the temperature, duration and diffusion source input of each step of the photovoltaic cell to be tested during the processing.

[0183] It should be noted that the photovoltaic diffusion process is a multi-step, multi-parameter process that requires precise control of multiple process parameters, such as step temperature, diffusion source concentration, and purity. The selection and optimization of these process parameters directly impact the diffusion effect and the performance of the photovoltaic cell.

[0184] In some embodiments, the parameter adjustment formula is based on the temperature, duration, and diffusion source concentration of the diffusion step of the photovoltaic diffusion process equipment corresponding to the same type or model of photovoltaic cell as the photovoltaic cell to be tested during the processing as input variables, and the square resistance value of the photovoltaic cell of the same type as the photovoltaic cell to be tested as the output variable.

[0185] The preset parameters include the diffusion source concentration coefficient, diffusion constant, diffusion resistivity, activation energy of the diffusion source, and temperature offset during the square resistance test of the photovoltaic cell;

[0186] The parameter adjustment formula is:

[0187]

[0188] Where R is the square resistance of the photovoltaic cell, rou is the diffusion resistivity, Ea is the activation energy of the diffusion source, x_temp is the temperature of the diffusion step, T is the temperature offset when the photovoltaic cell is tested for square resistance, 274.15 is used to represent the Kelvin temperature of 274.15 degrees, D is the diffusion constant, x_T is the duration of the diffusion step, k is the diffusion source concentration coefficient, x_z is the diffusion source concentration, 60 is used to represent 60 seconds, and the diffusion source concentration is obtained by the ratio of the diffusion source input to the sum of the diffusion source input, oxygen input, and nitrogen input;

[0189]

[0190] Among them, T k is the temperature offset at the square resistance detection position k, M is the total number of temperature zones in the diffusion step, temp i is the temperature of temperature zone i, a is the temperature influence coefficient of the temperature in temperature zone i on the resistance detection position k; k is the temperature attenuation coefficient of the square resistance detection position k.

[0191] Based on the Arrhenius characteristic between emitter sheet resistance and diffusion temperature (the property of boron and phosphorus atoms diffusing at different redistribution temperatures under low pressure: as temperature increases, 1 / (x_temp – T) decreases, while R times the square of x_temp decreases), we can derive the parameter adjustment formula for the above-mentioned photovoltaic diffusion process scenario. Here, 1 / (k*x_Z) is a relationship between sheet resistance and diffusion source concentration established with reference to the commonly used Schockley-Read-Hall model.

[0192] It should be noted that Arrhenius behavior is often used to describe the relationship between rate and temperature in physical or chemical processes. Emitter square resistance is a parameter of the resistive characteristics of the emitter region of a semiconductor, which is usually related to the concentration of the diffusion source, the geometry, and the material properties of the emitter. The diffusion temperature is the temperature at which impurity atoms (such as boron or phosphorus) are introduced into the semiconductor material. The Schockley-Read-Hall model is a theoretical model used to describe the carrier recombination process in semiconductor materials and is widely used in the design and performance evaluation of semiconductor devices.

[0193] In some embodiments, the above formula is abbreviated as (the specific data formula is abbreviated as base_func), and the above parameter adjustment formula can be abbreviated as:

[0194] R=base_func(x_temp,x_T,x_z,T,k,D,rou,Ea),

[0195] Where, R is the square resistance of the photovoltaic cell, rou is the diffusion resistivity, Ea is the activation energy of the diffusion source, x_temp is the temperature of the diffusion step, T is the temperature offset when the photovoltaic cell is subjected to square resistance detection, D is the diffusion constant, x_T is the duration of the diffusion step, k is the diffusion source concentration coefficient, and x_z is the diffusion source concentration.

[0196] Furthermore, in some embodiments, a boat in the photovoltaic diffusion process equipment can carry multiple photovoltaic cells. When performing square resistance testing, the photovoltaic cells at fixed positions are randomly inspected. For the photovoltaic cell at position k, the following formula can be obtained:

[0197] R k =base_func(T k ,x_T,x_z,k,D,rou,Ea),

[0198] Among them, R k is the square resistance of the photovoltaic cell at position k, rou is the diffusion resistivity, Ea is the activation energy of the diffusion source, x_temp is the temperature of the diffusion step, T kis the temperature offset of the photovoltaic cell during the square resistance test, D is the diffusion constant, x_T is the duration of the diffusion step, k is the diffusion source concentration coefficient, and x_z is the diffusion source concentration.

[0199] It should be noted that the temperature zones and the square resistance detection positions during the diffusion process are not in a one-to-one correspondence, but a many-to-many relationship. Figure 5 This diagram illustrates the relationship between temperature zones and the temperatures at various resistance inspection locations in a photovoltaic diffusion process scenario. Atop a furnace tube used to process photovoltaic cells in the photovoltaic diffusion process, multiple temperature sensors (referred to as temperature zones) are located. Below is a boat carrying multiple photovoltaic cells. Because photovoltaic cells are sampled at fixed locations for inspection, there is a many-to-many relationship between the photovoltaic cells under test and the temperature sensors (temperature zones).

[0200] In some embodiments, the logical formula for the relationship between the temperature at each resistance detection position and the temperature in each temperature zone is designed as follows:

[0201]

[0202] Among them, T k is the temperature offset at the square resistance detection position k, M is the total number of temperature zones in the diffusion step, temp i is the temperature of temperature zone i, is the temperature influence coefficient of temperature zone i on the resistance detection position k; k is the temperature attenuation coefficient of the square resistance detection position k.

[0203] It should be noted that T k is the temperature offset at the square resistance detection position k, which reflects the deviation between the temperature of each temperature zone and the temperature at the square resistance detection position k.

[0204] In some embodiments, when there is only one photovoltaic cell on a boat, the logical formula for the relationship between the temperature at the square resistance detection position and the temperature in each temperature zone is as follows:

[0205]

[0206] Where T is the temperature offset at the resistance detection position, M is the total number of temperature zones in the diffusion step, and temp i is the temperature of temperature zone i, is the temperature influence coefficient of temperature zone i on the square resistance detection position; a is the temperature attenuation coefficient of the square resistance detection position.

[0207] Step 403 : Obtain optimized values ​​of preset parameters in the parameter adjustment formula according to the parameter adjustment formula in the photovoltaic diffusion process scenario and the sample data set.

[0208] In some embodiments, the data in the sample data set are substituted into the parameter adjustment formula in the photovoltaic diffusion process scenario as input variables and the values ​​of the input variables, and the values ​​of each preset parameter are obtained. The numerical optimization is performed through the following steps:

[0209] 1) Design a loss function. Calculate the square resistance of a sample (i.e., a boat) in the sample dataset. Substitute the process parameters into the parameter adjustment formula and subtract the square resistance from the actual inspection value to obtain the square resistance error. Since a sample has square resistances at multiple inspection locations, the squared errors of these multiple square resistances need to be summed and divided by the total number of inspection locations to obtain the average squared error of the sample. Finally, the average squared errors of all samples in the dataset are summed and averaged to obtain the loss value.

[0210] 2) Set the preset parameter value range. Set upper and lower limits for the preset parameters such as k, D, rou, and Ea, and select a set of them as the initialization value for the first round of loss value calculation.

[0211] 3) Iterative solution: Evolutionary learning, reinforcement learning, nonlinear least squares methods, and other methods can be used to iteratively optimize the preset parameters over multiple rounds, with the goal of minimizing the loss.

[0212] After solving the optimal preset parameters, by observing the function fitting effect, draw a fitting curve of an input variable (fix all other input variables) and square resistance to see if it matches the trend of discrete points in the data set, so as to adjust the process parameters later.

[0213] The fitting curve of input variables (fix all other input variables) and square resistance is as follows Figure 6 As shown, Figure 6 is the fitting curve of different process parameters and square resistance in the photovoltaic diffusion process scenario. Figure 6 (a) Fitting curves of boron source concentration and square resistance at different temperatures for a fixed diffusion duration. Figure 6 (b) is the fitting curve of boron source concentration and square resistance at fixed temperature and different durations.

[0214] Figure 6 (a) is the fitting curve of boron source concentration and square resistance at fixed duration and different temperatures. Figure 6 (a) shows the curves from top to bottom: temperature 930℃, duration 2000s; temperature 950℃, duration 2000s; temperature 970℃, duration 2000s.

[0215] Figure 6 (b) is the fitting curve of boron source concentration and square resistance at fixed temperature and different durations. Figure 6(b) shows the curves from top to bottom: duration 1700s, temperature 950℃; duration 1800s, temperature 950℃; duration 2000s, temperature 950℃.

[0216] In addition, fitting curves of process parameters and square resistance can be obtained under conditions of fixed boron source concentration and different durations or fixed boron source concentration and different temperatures, which are not limited here.

[0217] Step 404 , substituting the values ​​of the preset parameters into the parameter adjustment formula in the photovoltaic diffusion process scenario to obtain a parameter adjustment model.

[0218] By implementing the above technical solution, a parameter adjustment model for the photovoltaic diffusion process scenario can be obtained.

[0219] See also Figure 7 , Figure 7 A schematic diagram of a process flow for adjusting process parameters in the process parameter adjustment method provided in an embodiment of the present application; Figure 7 As shown, the method may include the following steps 701 to 707.

[0220] In step 701 , a first process parameter is taken as a solution object, and the values ​​of the process parameters other than the first process parameter among the plurality of process parameters are substituted into a preset parameter adjustment model for solution processing.

[0221] In some embodiments, the first process parameter is taken as the solution object, and the numerical values ​​of the process parameters other than the first process parameter among the multiple process parameters are substituted into the preset parameter adjustment model for solution processing, and the first process parameter is one of the multiple process parameters.

[0222] It should be noted that in order to improve the efficiency of process parameters, a specified process parameter from multiple process parameters adopted by the target process equipment is selected as the first process parameter for adjustment, and the numerical values ​​of the process parameters other than the first process parameter adopted by the target process equipment to process the workpiece to be measured are substituted into the parameter adjustment model, and the first process parameter is set as the solution object. If the first process parameter has a solution within the required range, it means that the target process parameter of the target process equipment after processing the workpiece to be measured can be adjusted by only adjusting the first process parameter to improve the quality of subsequent workpieces.

[0223] In some embodiments, taking the first process parameter as a solution object and substituting the values ​​of the process parameters other than the first process parameter among the multiple process parameters into the preset parameter adjustment model for solution processing includes:

[0224] According to a preset parameter adjustment requirement, a first value interval for adjusting the first process parameter and a target detection data value interval for processing a workpiece of the same type after the workpiece to be tested are obtained;

[0225] Inputting numerical values ​​of the process parameters other than the first process parameter among the plurality of process parameters into the preset parameter adjustment model to solve the first process parameter;

[0226] The solution processing includes obtaining a numerical value of a solution corresponding to the first process parameter within the first value range, so that the detection data output according to the preset parameter adjustment model is within the target detection data value range.

[0227] It should be noted that the first value range is the range of optional values ​​for the first process parameter. This is due to the limitations on adjusting equipment parameters in industrial production. Similarly, the target inspection data value range is the range that the subsequent workpiece's expected inspection data should reach, that is, the quality standard that the subsequent workpiece should meet after processing.

[0228] Step 702: Determine whether the first process parameter has a solution.

[0229] If there is a solution, proceed to step 703; otherwise, proceed to step 704.

[0230] Step 703 : using the value of the solution corresponding to the first process parameter, the original value of the first process parameter is updated to obtain the target process parameter of the target process equipment after processing the workpiece to be measured.

[0231] It should be noted that if the first process parameter has a corresponding solution value, the solution value is used to update the original value to obtain the target process parameter containing multiple process parameters. When processing the workpiece after the workpiece to be tested, the target process parameter is used to improve the quality of subsequent workpieces.

[0232] In step 704 , the first process parameter and the second process parameter are taken as solution objects, and the values ​​of the process parameters other than the first process parameter and the second process parameter among the plurality of process parameters are substituted into a preset parameter adjustment model for solution processing.

[0233] In some embodiments, when there is no solution for the first process parameter, the first process parameter and the second process parameter are used as solution objects, and the numerical values ​​of the process parameters other than the first process parameter and the second process parameter among the multiple process parameters are substituted into the preset parameter adjustment model for solution processing, and the second process parameter is a process parameter among the multiple process parameters other than the first process parameter.

[0234] It should be noted that if the first process parameter in the above steps does not have a solution, it means that it is impossible to achieve the required quality of subsequent workpieces by adjusting the first process parameter alone. In this case, a more complex parameter adjustment strategy is adopted, which combines the first and second process parameters as solution objects and performs joint adjustment. This not only improves the flexibility of parameter adjustment but also enhances the model's adaptability to complex process environments, helping to achieve higher levels of quality control in actual production.

[0235] Step 705 , determining whether the first process parameter and the second process parameter have a solution.

[0236] If there is a solution, proceed to step 706; otherwise, proceed to step 707.

[0237] Step 706 : using the values ​​of the solutions corresponding to the first process parameter and the second process parameter, the original values ​​of the first process parameter and the second process parameter are updated to obtain target process parameters of the target process equipment after processing the workpiece to be measured.

[0238] In some embodiments, when there is a solution for the first process parameter and the second process parameter, the original values ​​of the first process parameter and the second process parameter are updated using the values ​​of the solutions corresponding to the first process parameter and the second process parameter to obtain the target process parameters of the target process equipment after processing the workpiece to be measured.

[0239] Step 707: End the current process parameter adjustment process, and generate and send an adjustment failure alarm.

[0240] In some embodiments, when there is no solution between the first process parameter and the second process parameter, the current process parameter adjustment process is terminated, and an adjustment failure alarm is generated and sent.

[0241] When both the first and second process parameters are unresolved, it means that even by adjusting both parameters simultaneously, the quality of subsequent workpieces cannot meet the expected standards. The current process flow is terminated, and an adjustment failure alarm is generated and sent. This alarm can include a detailed record of the adjustment process, the current process parameter values, and the reason for the adjustment failure. This allows technicians to quickly understand the problem and take appropriate measures to resolve it.

[0242] In some embodiments, depending on the complexity of workpiece processing and the types of controllable process parameters of the process equipment, a third process parameter or more process parameters may be introduced for solution operation, which is not limited here.

[0243] In some embodiments, the process of adjusting process parameters in the photovoltaic diffusion process is as follows:

[0244] 1) Obtain the square resistance data of the most recent boat number of the target furnace tube of the photovoltaic diffusion process equipment, that is, the detection data of the workpiece to be tested;

[0245] 2) Determine whether the furnace tube is leaking based on the leak detection air pressure data. If there is a leak, abandon the parameter adjustment. If there is no leak, further test whether the standard deviation of the square resistance value is too large, or whether the difference between the square resistance value and the target value is too large. In these two cases, abandon the parameter adjustment. In other words, determine whether the target process equipment meets the preset normal operating conditions and whether the test data is abnormal.

[0246] 3) Calculate the mean square resistance of each resistance detection area, and calculate the deviation between the mean square resistance of each resistance area and the target value, that is, obtain the deviation data between the detection data and the preset reference quality data;

[0247] 4) Obtain the process parameters of the most recent boat number for the same equipment and the same furnace tube (including the set temperature of each temperature zone, the amount of diffusion source, oxygen, nitrogen and other gases introduced, and the duration of each step);

[0248] 5) Determine whether adjusting the temperature can compensate for the deviation. First, substitute other parameters except temperature (diffusion source, oxygen, nitrogen and other gas flow rates, duration of each step) into the parameter adjustment model, then set the upper and lower limits of the temperature value of each temperature zone, set the optimization goal to minimize the temperature adjustment value, set the upper and lower limits of the square resistance target value, and finally use the sequential least squares method to optimize and solve. If there is a solution, the recommended value of the temperature of each temperature zone is output. If there is no solution, it means that adjusting the temperature alone cannot compensate for the deviation, and go to step 6;

[0249] 6) Determine whether simultaneous adjustment of the diffusion source flow rate and temperature can compensate for the deviation. Substitute all other parameters (the flow rate of gases such as oxygen and nitrogen, and the duration of each step) except for temperature and diffusion source flow rate into the parameter adjustment model. Then set the upper and lower limits of the temperature values ​​for each temperature zone, set the optimization goal to minimize the diffusion source flow rate adjustment value, set the upper and lower limits of the square resistance target value, and finally use the sequential least squares method to optimize and solve. If a solution is found, the recommended values ​​of the diffusion source flow rate and the temperature of each temperature zone are output. If no solution is found, the current process parameter adjustment process is terminated, and an adjustment failure alarm is generated and sent.

[0250] It should be understood that, although the steps in the above-mentioned flowcharts are shown in sequence according to the instructions of the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the above-mentioned flowcharts may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0251] Based on the foregoing embodiments, an embodiment of the present application provides a process parameter adjustment device, which includes the modules included and the units included in each module, and can be implemented by a processor; of course, it can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA), etc.

[0252] Figure 8 A schematic diagram of the structure of the process parameter adjustment device provided in the embodiment of the present application is shown in FIG. Figure 8 As shown, the process parameter adjustment device 800 includes a detection data management module 801, a process parameter acquisition module 802 and a process parameter adjustment module 803, wherein:

[0253] The test data management module 801 is configured to obtain test data for evaluating the quality of a workpiece to be tested, as well as first identification information of the workpiece to be tested, wherein the test data and the first identification information are acquired by a target test device; and obtain deviation data between the test data and preset reference quality data;

[0254] The process parameter acquisition module 802 acquires, when the deviation data satisfies a preset condition, a plurality of process parameters corresponding to the second identification information matched by the first identification information in the historical workpiece processing data, wherein the historical workpiece processing data includes the second identification information of the workpiece to be measured and the plurality of process parameters corresponding to the second identification information, wherein the plurality of process parameters are process parameters used by the target process equipment during the processing of the workpiece to be measured;

[0255] The process parameter adjustment module 803 inputs the multiple process parameters into a preset parameter adjustment model to obtain the target process parameters of the target process equipment after processing the workpiece to be measured. The preset parameter adjustment model is obtained based on sample detection data of multiple sample workpieces and multiple sample process parameters of each sample workpiece processed by the target process equipment. The multiple sample workpieces are of the same type as the workpiece to be measured.

[0256] In some embodiments, the process parameter adjustment module 803 is further configured to terminate the current process parameter adjustment process and generate and send an equipment abnormality alarm when the target process equipment does not meet preset normal operating conditions during the processing of the workpiece to be measured.

[0257] In some embodiments, the process parameter adjustment module 803 is further configured to terminate the current process parameter adjustment process and generate and send an abnormality alarm for the workpiece to be tested when the deviation data does not meet the preset condition.

[0258] In some embodiments, the process parameter adjustment module 803 is also used to pre-set the parameter adjustment model, including: obtaining sample detection data and sample identification information of the multiple sample workpieces; obtaining historical sample workpiece processing data, the historical sample workpiece processing data including multiple sample process parameters adopted by each sample workpiece in the processing process of the corresponding process equipment; obtaining multiple sample process parameters corresponding to each sample workpiece matched by the sample identification information of each sample workpiece in the historical sample workpiece processing data; performing feature processing on the sample detection data and multiple sample process parameters corresponding to each sample workpiece to construct a sample data set, the feature processing including eliminating abnormal data according to preset abnormal conditions; obtaining the parameter adjustment model according to the sample data set and a preset parameter adjustment formula, the preset parameter adjustment formula being designed according to the processing process of the same type of workpiece as the workpiece to be measured.

[0259] In some embodiments, the preset parameter adjustment formula is constructed based on multiple process parameters of a workpiece of the same type as the workpiece to be measured during the processing as input variables, detection data of a workpiece of the same type as the workpiece to be measured as output variables, and multiple preset parameters. The process parameter adjustment module 803 is also used to substitute the detection data and multiple process parameters of each sample data in the sample data set into the preset parameter adjustment formula to solve the values ​​of each preset parameter in the preset parameter adjustment formula; optimize the values ​​of each preset parameter through a loss value minimization algorithm to obtain the optimized values ​​of each preset parameter; substitute the optimized values ​​of each preset parameter into the parameter adjustment formula to obtain the parameter adjustment model.

[0260] In some embodiments, the process parameter adjustment module 803 is further used to take the first process parameter as a solution object, substitute the numerical values ​​of the process parameters other than the first process parameter among the multiple process parameters into the preset parameter adjustment model for solution processing, where the first process parameter is one of the multiple process parameters; determine whether the first process parameter has a solution; if the first process parameter has a solution, use the numerical value of the first process parameter corresponding to the solution to update the original numerical value of the first process parameter so as to obtain the target process parameter of the target process equipment after processing the workpiece to be measured; if the first process parameter has no solution, take the first process parameter and the second process parameter as solution objects, substitute the numerical values ​​of the process parameters other than the first process parameter among the multiple process parameters The numerical values ​​of process parameters other than the first process parameter and the second process parameter are substituted into the preset parameter adjustment model for solution processing, and the second process parameter is a process parameter other than the first process parameter among the multiple process parameters; it is determined whether the first process parameter and the second process parameter have a solution; if the first process parameter and the second process parameter have a solution, the original numerical values ​​of the first process parameter and the second process parameter are updated with the numerical values ​​of the corresponding solutions of the first process parameter and the second process parameter to obtain the target process parameters of the target process equipment after processing the workpiece to be measured; if the first process parameter and the second process parameter have no solution, the current process parameter adjustment process is ended, and an adjustment failure alarm is generated and sent.

[0261] In some embodiments, the process parameter adjustment module 803 is also used to obtain a first value range for adjusting the first process parameter and a target detection data value range for processing the same type of workpiece after the workpiece to be measured according to a preset parameter adjustment requirement; input the numerical values ​​of the process parameters other than the first process parameter among the multiple process parameters into the preset parameter adjustment model, and solve the first process parameter; the solution includes obtaining the numerical value of the solution corresponding to the first process parameter within the first value range, so that the detection data output according to the preset parameter adjustment model is within the target detection data value range.

[0262] The description of the above device embodiment is similar to the description of the above method embodiment and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiment of this application, please refer to the description of the method embodiment of this application for understanding.

[0263] It should be noted that in the embodiments of this application Figure 8The division of modules in the process parameter adjustment device shown is schematic and is only a logical functional division. In actual implementation, there may be other division methods. In addition, the functional units in the various embodiments of the present application can be integrated into a processing unit, or they can exist physically separately, or two or more units can be integrated into a single unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units. It can also be implemented in the form of a combination of software and hardware.

[0264] It should be noted that, in the embodiment of the present application, if the above method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling an electronic device to execute all or part of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific combination of hardware and software.

[0265] The embodiment of the present application provides a computer device, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown. The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0266] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method provided in the above embodiment are implemented.

[0267] An embodiment of the present application provides a computer program product containing instructions, which, when executed on a computer, enables the computer to execute the steps of the method provided in the above method embodiment.

[0268] Those skilled in the art will understand that Figure 9The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0269] In one embodiment, the process parameter adjustment device provided by the present application can be implemented in the form of a computer program. The computer program can be used in Figure 9 The computer device is operated on the computer device shown. The memory of the computer device can store various program modules that constitute the above-mentioned device. The computer program composed of each program module enables the processor to execute the steps of the method of each embodiment of the present application described in this specification.

[0270] It should be noted that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium, storage medium, and device embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0271] It should be understood that "one embodiment" or "an embodiment" or "some embodiments" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" or "in some embodiments" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments. The above description of the various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other. For the sake of brevity, they will not be repeated here.

[0272] The term "and / or" in this article is only a description of the association relationship between associated objects, indicating that there can be three relationships. For example, object A and / or object B can mean: object A exists alone, object A and object B exist at the same time, and object B exists alone.

[0273] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0274] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or modules can be electrical, mechanical or other forms.

[0275] The modules described above as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules; they may be located in one place or distributed across multiple network units; some or all of the modules may be selected according to actual needs to achieve the purpose of this embodiment.

[0276] In addition, all functional modules in the embodiments of the present application can be integrated into one processing unit, or each module can be a separate unit, or two or more modules can be integrated into one unit; the above-mentioned integrated modules can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0277] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, and other media that can store program codes.

[0278] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application, or the part that contributes to the relevant technology, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling an electronic device to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks or optical disks.

[0279] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0280] The features disclosed in the several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0281] The features disclosed in the several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0282] The above is merely an embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A process parameter adjustment method, characterized in that: The method comprises: Acquire detection data for evaluating the quality of a workpiece to be measured, and first identification information of the workpiece to be measured, wherein the detection data and the first identification information are collected and obtained by a target detection device; Obtaining deviation data between the detection data and preset reference quality data; When the deviation data satisfies a preset condition, a plurality of process parameters corresponding to the second identification information matched by the first identification information in the historical workpiece processing data are obtained, where the historical workpiece processing data includes the second identification information of the workpiece to be measured and the plurality of process parameters corresponding to the second identification information, where the plurality of process parameters are process parameters adopted by the target process equipment during the processing of the workpiece to be measured; Inputting the plurality of process parameters into a preset parameter adjustment model to obtain target process parameters of the target process equipment after processing the workpiece to be tested, wherein the preset parameter adjustment model is obtained based on sample detection data of a plurality of sample workpieces and a plurality of sample process parameters of each sample workpiece processed by the target process equipment, wherein the plurality of sample workpieces are of the same type as the workpiece to be tested; The preset parameter adjustment model is pre-set by the following method: obtaining sample detection data and sample identification information of the multiple sample workpieces; obtaining historical sample workpiece processing data, the historical sample workpiece processing data including multiple sample process parameters adopted by each sample workpiece during the processing of the corresponding process equipment; obtaining multiple sample process parameters corresponding to each sample workpiece matched by the sample identification information of each sample workpiece in the historical sample workpiece processing data; performing feature processing on the sample detection data and multiple sample process parameters corresponding to each sample workpiece to construct a sample data set, the feature processing including eliminating abnormal data according to preset abnormal conditions; obtaining the parameter adjustment model according to the sample data set and a preset parameter adjustment formula, the preset parameter adjustment formula being designed according to the processing process of a workpiece of the same type as the workpiece to be measured; The preset parameter adjustment formula is constructed based on multiple process parameters of a workpiece of the same type as the workpiece to be measured during processing as input variables, inspection data of the workpiece of the same type as the workpiece to be measured as output variables, and multiple preset parameters; the parameter adjustment model is obtained based on the sample data set and the preset parameter adjustment formula, including: The detection data and multiple process parameters of each sample data in the sample data set are substituted into the preset parameter adjustment formula to solve the numerical value of each preset parameter in the preset parameter adjustment formula; the numerical value of each preset parameter is optimized by minimizing the loss value algorithm to obtain the optimized numerical value of each preset parameter; the optimized numerical value of each preset parameter is substituted into the parameter adjustment formula to obtain the parameter adjustment model.

2. The method according to claim 1, characterized in that After obtaining the detection data for evaluating the quality of the workpiece to be measured and the first identification information of the workpiece to be measured, the method further includes: When the target process equipment does not meet the preset normal operating conditions during the processing of the workpiece to be measured, the current process parameter adjustment process is terminated, and an equipment abnormality alarm is generated and sent.

3. The method according to claim 1, characterized in that The preset condition includes that the deviation data is within a preset deviation threshold range; the method further includes: When the deviation data does not meet the preset conditions, the current process parameter adjustment process is terminated, and an abnormal detection alarm of the workpiece to be tested is generated and sent.

4. The method according to claim 1, wherein The first identification information includes the target process equipment information corresponding to the workpiece to be measured and the target detection time for obtaining the detection data. The second identification information includes the target process equipment information corresponding to the workpiece to be measured and the target processing time of the workpiece to be measured during the processing. The target processing time is a time within a preset time range before the target detection time.

5. The method according to any one of claims 1 to 4, characterized in that: Inputting the plurality of process parameters into a preset parameter adjustment model to obtain target process parameters of the target process equipment after processing the workpiece to be tested includes: Taking a first process parameter as a solution object, substituting numerical values ​​of process parameters other than the first process parameter among the multiple process parameters into the preset parameter adjustment model for solution processing, wherein the first process parameter is one of the multiple process parameters; determining whether the first process parameter has a solution; When the first process parameter has a solution, the original value of the first process parameter is updated using the value of the solution corresponding to the first process parameter to obtain the target process parameter of the target process equipment after processing the workpiece to be measured; When there is no solution for the first process parameter, taking the first process parameter and the second process parameter as solution objects, substituting the values ​​of the process parameters other than the first process parameter and the second process parameter among the multiple process parameters into the preset parameter adjustment model for solution processing, where the second process parameter is a process parameter other than the first process parameter among the multiple process parameters; determining whether the first process parameter and the second process parameter have a solution; When there is a solution for the first process parameter and the second process parameter, the original values ​​of the first process parameter and the second process parameter are updated using the values ​​of the solutions corresponding to the first process parameter and the second process parameter to obtain target process parameters of the target process equipment after processing the workpiece to be measured; The method further comprises: In the case that there is no solution between the first process parameter and the second process parameter, the current process parameter adjustment process is terminated, and an adjustment failure alarm is generated and sent.

6. The method according to claim 5, characterized in that The first process parameter is taken as a solution object, and the values ​​of the process parameters other than the first process parameter among the multiple process parameters are substituted into the preset parameter adjustment model for solution processing, including: According to a preset parameter adjustment requirement, a first value interval for adjusting the first process parameter and a target detection data value interval for processing a workpiece of the same type after the workpiece to be tested are obtained; Inputting numerical values ​​of the process parameters other than the first process parameter among the plurality of process parameters into the preset parameter adjustment model to solve the first process parameter; The solution processing includes obtaining a numerical value of a solution corresponding to the first process parameter within the first value range, so that the detection data output according to the preset parameter adjustment model is within the target detection data value range.

7. The method according to claim 1, characterized in that The workpiece to be tested is a photovoltaic cell to be tested, and the target process equipment for the workpiece to be tested is a photovoltaic diffusion process equipment. The detection data includes the square resistance value of the photovoltaic cell to be tested, and the multiple process parameters include the temperature, duration and diffusion source input of each step of the photovoltaic cell to be tested during the processing process.

8. The method according to claim 7, characterized in that The parameter adjustment formula is based on the temperature, duration, and diffusion source concentration of the diffusion step of the photovoltaic diffusion process equipment corresponding to the photovoltaic cell of the same type or model as the photovoltaic cell to be tested during the processing as input variables, and the square resistance value of the photovoltaic cell of the same type as the photovoltaic cell to be tested as the output variable, and the preset parameters include the diffusion source concentration coefficient, diffusion constant, diffusion resistivity, activation energy of the diffusion source, and temperature offset of the photovoltaic cell when performing square resistance detection; The parameter adjustment formula is: Where R is the square resistance of the photovoltaic cell, rou is the diffusion resistivity, Ea is the activation energy of the diffusion source, x_temp is the temperature of the diffusion step, T is the temperature offset when the photovoltaic cell is tested for square resistance, 274.15 is used to represent the Kelvin temperature of 274.15 degrees, D is the diffusion constant, x_T is the duration of the diffusion step, k is the diffusion source concentration coefficient, x_z is the diffusion source concentration, 60 is used to represent 60 seconds, and the diffusion source concentration is obtained by the ratio of the diffusion source input to the sum of the diffusion source input, oxygen input, and nitrogen input; Among them, T k is the temperature offset at the square resistance detection position k, M is the total number of temperature zones in the diffusion step, temp i is the temperature of temperature zone i, a is the temperature influence coefficient of the temperature in temperature zone i on the resistance detection position k; k is the temperature attenuation coefficient of the square resistance detection position k.

9. A process parameter adjustment device, characterized in that: The process parameter adjustment device is used to implement the method according to any one of claims 1 to 8, and the process parameter adjustment device includes: a test data management module, configured to obtain test data for evaluating the quality of a workpiece to be tested, and first identification information of the workpiece to be tested, wherein the test data and the first identification information are acquired by a target test device; and obtain deviation data between the test data and preset reference quality data; a process parameter acquisition module, configured to acquire, when the deviation data satisfies a preset condition, a plurality of process parameters corresponding to the second identification information matched by the first identification information in historical workpiece processing data, wherein the historical workpiece processing data includes the second identification information of the workpiece to be measured and the plurality of process parameters corresponding to the second identification information, wherein the plurality of process parameters are process parameters adopted by a target process equipment during the processing of the workpiece to be measured; a process parameter adjustment module, configured to input the plurality of process parameters into a preset parameter adjustment model to obtain target process parameters of the target process equipment after processing the workpiece to be tested, wherein the preset parameter adjustment model is obtained based on sample detection data of a plurality of sample workpieces and a plurality of sample process parameters of each sample workpiece processed by the target process equipment, wherein the plurality of sample workpieces are of the same type as the workpiece to be tested; The process parameter adjustment module is further used to pre-set the preset parameter adjustment model, including: obtaining sample detection data and sample identification information of the multiple sample workpieces; obtaining historical sample workpiece processing data, the historical sample workpiece processing data including multiple sample process parameters adopted by each sample workpiece during the processing of the corresponding process equipment; obtaining multiple sample process parameters corresponding to each sample workpiece matched by the sample identification information of each sample workpiece in the historical sample workpiece processing data; performing feature processing on the sample detection data and multiple sample process parameters corresponding to each sample workpiece to construct a sample data set, the feature processing including eliminating abnormal data according to preset abnormal conditions; obtaining the parameter adjustment model according to the sample data set and a preset parameter adjustment formula, the preset parameter adjustment formula being designed according to the processing process of a workpiece of the same type as the workpiece to be measured; The preset parameter adjustment formula is constructed based on multiple process parameters of the same type of workpiece as the workpiece to be measured during the processing as input variables, detection data of the same type of workpiece as the workpiece to be measured as output variables and multiple preset parameters; the process parameter adjustment module is also used to substitute the detection data and multiple process parameters of each sample data in the sample data set into the preset parameter adjustment formula to solve the numerical value of each preset parameter in the preset parameter adjustment formula; optimize the numerical value of each preset parameter through the loss value minimization algorithm to obtain the optimized numerical value of each preset parameter; substitute the optimized numerical value of each preset parameter into the parameter adjustment formula to obtain the parameter adjustment model.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, wherein: When the processor executes the program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

12. A computer program product comprising a computer program, characterized in that When the computer program is executed, the method according to any one of claims 1 to 8 is implemented.

Images