A method and device for generating a semiconductor secondary piping PID

Abstract

The present invention discloses a method for generating a semiconductor secondary piping PID, which includes: obtaining initial process data for the semiconductor secondary piping operation process; matching corresponding normalization strategies based on the distribution states of various parameters in the initial process data to obtain standard process data; analyzing the standard process data to obtain the information amounts of various parameters in the standard process data, and combining the initial weights of each parameter to give the characteristic weights of various parameters in the standard process data; combining the characteristic weights of various parameters in the standard process data to perform cluster analysis on the standard process data to obtain process component matching data; combining the process component matching data to analyze and adjust each component to generate a semiconductor secondary piping PID. The semiconductor secondary piping PID generation solution provided by the present invention improves the flexibility and accuracy of semiconductor secondary piping PID generation to meet the drawing requirements of complex industrial processes.

Description

Technical Field

[0001] The present invention belongs to the technical field of semiconductor secondary piping, and particularly relates to a method and device for generating a semiconductor secondary piping PID. Background Art

[0002] In the field of semiconductor manufacturing, the secondary piping project is a crucial link, which is a process of distributing various utility engineering systems from the main system to the usage points of each process equipment, involving the configuration and installation of multiple components such as equipment, pipelines, valves, instruments, and control systems. This process not only needs to ensure the stable, safe, and efficient transportation of resources, but also has a direct impact on the stability of the production line, product quality, and production cost.

[0003] PID (piping and instrumentation diagram) is a process piping and instrumentation flow chart, which is a drawing representing all the equipment, instruments, pipelines, valves, and other related utility engineering systems of the system. In the fields of industrial automation and informatization, PID is an important tool for describing industrial processes and control systems. Traditional PID production relies on manual drawing, which is inefficient and error-prone. The current automated drawing tools lack flexibility and accuracy in drawing PID, and cannot meet the drawing requirements of complex industrial processes.

[0004] Currently, the research on semiconductor secondary piping PID is limited to the three-dimensional display of PID. For example, Patent CN119442532A discloses a layout device and method for a semiconductor secondary piping installation project, including: a file upload module that receives the layout file of the semiconductor production line; a data parsing module that parses the layout file, obtains the attribute information and location information of the equipment, and transmits them to the secondary piping database; a data analysis and layout module that gives the secondary piping installation pipeline diagram, and then combines the component matching algorithm to obtain the corresponding pipeline instrument components in the secondary piping database to form a pipeline instrument flow chart; a three-dimensional space management module that combines the three-dimensional model generation algorithm to generate the layout model of the semiconductor secondary piping installation project. Through the linkage between the semiconductor layout information and the secondary piping database, combined with the component matching algorithm, the information of the secondary piping components is obtained, and according to the three-dimensional model generation algorithm, the automatic output of the semiconductor secondary piping layout is realized and visualized in a three-dimensional scene.

[0005] How to improve the flexibility and accuracy of semiconductor secondary piping PID generation to meet the drawing requirements of complex industrial processes is a problem that needs to be solved currently. Summary of the Invention

[0006] In view of the defects existing in the above-mentioned prior art, the present invention provides a method for generating a semiconductor secondary piping PID, including: obtaining initial process data for the semiconductor secondary piping operation process; matching corresponding normalization strategies based on the distribution states of various parameters in the initial process data to obtain standard process data; analyzing the standard process data to obtain the information amounts of various parameters in the standard process data, and combining the initial weights of each parameter to give the characteristic weights of various parameters in the standard process data; clustering and analyzing the standard process data in combination with the characteristic weights of various parameters in the standard process data to obtain process component matching data; and analyzing and adjusting each component in combination with the process component matching data to generate a semiconductor secondary piping PID. The semiconductor secondary piping PID generation solution provided by the present invention improves the flexibility and accuracy of semiconductor secondary piping PID generation to meet the drawing requirements of complex industrial processes.

[0007] In a first aspect, the present invention provides a method for generating a semiconductor secondary piping PID, including:

[0008] Obtaining initial process data for the semiconductor secondary piping operation process;

[0009] Matching corresponding normalization strategies based on the distribution states of various parameters in the initial process data to obtain standard process data;

[0010] Analyzing the standard process data to obtain the information amounts of various parameters in the standard process data, and combining the initial weights of each parameter to give the characteristic weights of various parameters in the standard process data;

[0011] Clustering and analyzing the standard process data in combination with the characteristic weights of various parameters in the standard process data to obtain process component matching data;

[0012] Analyzing and adjusting each component in combination with the process component matching data to generate a semiconductor secondary piping PID.

[0013] Further, obtaining the initial process data for the semiconductor secondary piping operation process specifically includes the following steps:

[0014] Obtaining the original process data for the semiconductor secondary piping operation process;

[0015] Converting the format of the original process data to obtain structured process data;

[0016] Analyzing the data situation of the structured process data and cleaning the structured process data to obtain the initial process data.

[0017] Further, matching corresponding normalization strategies based on the distribution states of various parameters in the initial process data to obtain standard process data specifically includes:

[0018] Screen multiple groups of core parameters in the initial process data, and construct corresponding to-be-partitioned datasets according to the values of each group of core parameters;

[0019] Determine the basic parameters in each group of core parameters, and sort each to-be-partitioned dataset according to the basic parameters;

[0020] Partition each to-be-partitioned dataset according to the partitioning granularity, and screen the values of the core parameters of each partition to form intermediate process data, where the partitioning granularity is obtained by analyzing the basic parameters, the operation process coefficient, and other core parameters;

[0021] Divide the first parameter and the second parameter according to the value conditions of each parameter in the intermediate process data, where the value condition of the first parameter is a finite number or a finite range, and the value condition of the second parameter is without a fixed range;

[0022] Based on the analysis of the values of the first parameter, match the corresponding normalization strategy to obtain the corresponding standard process data;

[0023] Conduct a normality test on the second parameter to obtain the test result;

[0024] According to the test result, match the corresponding normalization strategy for the second parameter to obtain the corresponding standard process data.

[0025] Further, according to the test result, match the corresponding normalization strategy for the second parameter to obtain the corresponding standard process data, specifically including:

[0026] If the test result is a normal distribution, combine the preset normal distribution range to screen the second parameter to obtain the standard second parameter, and perform normalization processing on the standard second parameter using the Z-score normalization strategy to obtain the corresponding standard process data;

[0027] If the test result is a non-normal distribution, combine the preset non-normal distribution range to screen the second parameter to obtain the standard second parameter, match the corresponding normalization strategy for the standard second parameter and perform normalization processing to obtain the corresponding standard process data.

[0028] Further, according to the analysis of the standard process data, obtain the information content of each parameter in the standard process data, and combine the initial weight of each parameter to give the characteristic weight of each parameter in the standard process data, specifically including:

[0029] Based on the preset process standard, sort each parameter in the standard process data and give the initial weight of each parameter;

[0030] Calibrate the initial weights by combining the information content of each parameter in the standard process data to obtain the feature weights.

[0031] Furthermore, perform cluster analysis on the standard process data by combining the feature weights of each parameter in the standard process data to obtain process component matching data, specifically including:

[0032] Determine the initial cluster centers from the standard process data based on preset physical constraints;

[0033] According to the initial cluster centers, perform cluster analysis on the standard process data by combining the feature weights of each parameter in the standard process data, and update and iterate the cluster centers until convergence to obtain the clustering result;

[0034] Judge the clustering result to obtain the constraint verification result;

[0035] According to the constraint verification result, adjust the clustering result and the feature weights of each parameter in the standard process data to give the process component matching data.

[0036] Furthermore, according to the initial cluster centers, perform cluster analysis on the standard process data by combining the feature weights of each parameter in the standard process data, and update and iterate the cluster centers until convergence to obtain the clustering result, specifically including:

[0037] According to the initial cluster centers, combine each parameter and the feature weights of each parameter in the standard process data to give the distances between the initial cluster centers and each standard process data;

[0038] Analyze the distances between the initial cluster centers and each standard process data, update and iterate the cluster centers, and give the distances between the new cluster centers and each standard process data, where the new cluster centers satisfy the physical constraints;

[0039] Based on the distances between the new cluster centers and each standard process data, analyze the average distance between the standard process data in each cluster and the cluster centers to give the clustering result.

[0040] Furthermore, combine the process component matching data to analyze and adjust each component to generate the semiconductor secondary piping PID, specifically including:

[0041] Based on the process component matching data, draw each component corresponding to each standard process data to generate the initial PID;

[0042] Construct a reward function according to the component relationships of each component in the initial PID;

[0043] Combine the reward function to adjust the component relationships of each component in the initial PID to give the standard PID;

[0044] Render the standard PID to generate the semiconductor secondary piping PID.

[0045] Further, according to the component relationships of each component in the initial PID, construct a reward function, specifically including:

[0046] According to the connection relationships between each component in the initial PID, analyze the gaps in the corresponding connection metrics of each component, and give the sorting of the connection metric differences.

[0047] Based on the sorting of the connection metric differences, assign corresponding weights to each connection metric, and give the reward weight matrix.

[0048] Combine the reward weight matrix to construct the reward function.

[0049] In a second aspect, the present invention also provides a device for generating a semiconductor secondary piping PID, which adopts the method for generating a semiconductor secondary piping PID as described in any one of the above, including:

[0050] A data acquisition module, configured to acquire initial process data for the semiconductor secondary piping operation process.

[0051] A data processing module, configured to match the corresponding normalization strategy based on the distribution status of each parameter in the initial process data to obtain the standard process data.

[0052] A weight determination module, configured to obtain the information content of each parameter in the standard process data according to the analysis of the standard process data, and combine the initial weight of each parameter to give the characteristic weights of each parameter in the standard process data.

[0053] A component matching module, configured to perform clustering analysis on the standard process data in combination with the characteristic weights of each parameter in the standard process data to obtain the process component matching data.

[0054] A PID generation module, configured to analyze and adjust each component in combination with the process component matching data to generate the semiconductor secondary piping PID.

[0055] The method and device for generating a semiconductor secondary piping PID provided by the present invention have at least the following beneficial effects:

[0056] (1) By obtaining and analyzing the distribution status of each parameter in the initial process data, matching the corresponding normalization strategy to obtain the standard process data, combining the information content of each parameter in the standard process data, assigning feature weights to each parameter in the standard process data, and based on the feature weights, performing clustering analysis on the standard process data to obtain process component matching data; combining the process component matching data, analyzing and adjusting each component to generate a semiconductor secondary piping PID, which improves the flexibility and accuracy of semiconductor secondary piping PID generation and meets the drawing requirements of complex industrial processes.

[0057] (2) By assigning feature weights to each parameter in the standard process data and performing clustering analysis on the standard process data based on the feature weights, the process component matching data obtained by clustering is closer to the project requirements of semiconductor secondary piping, improving the accuracy of semiconductor secondary piping PID. Description of the Drawings

[0058] Figure 1 It is a flowchart of the method for generating a semiconductor secondary piping PID provided by an embodiment of the present invention;

[0059] Figure 2 It is a flowchart of determining the initial process data provided by an embodiment of the present invention;

[0060] Figure 3 It is a flowchart of obtaining the standard process data provided by an embodiment of the present invention;

[0061] Figure 4 It is a flowchart of obtaining the process component matching data provided by an embodiment of the present invention;

[0062] Figure 5 It is a flowchart of obtaining the clustering result provided by an embodiment of the present invention;

[0063] Figure 6 It is a flowchart of generating a semiconductor secondary piping PID provided by an embodiment of the present invention;

[0064] Figure 7 It is a flowchart of constructing a reward function provided by an embodiment of the present invention;

[0065] Figure 8 It is an example diagram of adjusting component connections through a reward function provided by an embodiment of the present invention;

[0066] Figure 9 It is a structural block diagram of the device for generating a semiconductor secondary piping PID provided by an embodiment of the present invention.

[0067] Among them, 201, data acquisition module; 202, data processing module; 203, weight determination module; 204, component matching module; 205, PID generation module. Detailed implementation manners

[0068] In order to better understand the above technical solutions, the above technical solutions will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present invention.

[0069] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "the" and "said" used in the embodiments of the present invention and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. "Plural" generally includes at least two.

[0070] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a commodity or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such commodity or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the commodity or device including said element.

[0071] PID represents the Process and Instrumentation Diagram, which refers to a drawing that details all the equipment, instruments, pipelines, valves and other relevant utility engineering systems of the system according to the requirements of the Process Flow Diagram (PFD). The focus of the PID expression is on the pipeline flow and how the process technology is controlled, and it can show how the pipeline system connects industrial processing equipment together. The PID also shows the instruments and valves used to monitor the flow of materials in the pipeline.

[0072] Secondary piping is a re-matching or upgrading project carried out on the basis of existing equipment, systems or buildings, aiming to improve performance or expand functions, and involves multiple fields such as electricity, communication, and low voltage. The core of secondary piping is to meet new requirements or solve existing deficiencies by optimizing the existing infrastructure.

[0073] In the semiconductor field, the secondary piping project includes the configuration and installation of multiple components such as pipeline systems, valves and instruments, and control systems. These components need to be reasonably configured according to the nature of the transported medium and process requirements to ensure the stable operation of process equipment. For example, the pipeline system needs to use materials with corrosion resistance, low pollution, and high cleanliness, while the control system needs to have high reliability, easy operation, and scalability. The design and installation requirements of the secondary piping project are strict. Safety, cleanliness, and flexibility are the three core requirements in the design and installation process. The safety requirement is that the system design and installation follow relevant safety codes and standards. The cleanliness requirement is that the system maintains high cleanliness to avoid environmental pollution during production. Flexibility requires the system to be able to adapt to possible future changes and expansion needs.

[0074] With the rapid development of semiconductor technology, the technical requirements for the secondary piping project are also constantly increasing. The traditional drawing method relies on manual work, with low efficiency, easy to make mistakes, and unable to quickly respond to design changes. With the development of technology, some automated drawing tools have emerged, but these tools often lack flexibility and are difficult to adapt to the changing industrial needs. Moreover, the current automated drawing tools have insufficient intelligence level, unable to effectively process complex process flows and equipment interfaces, resulting in unreasonable drawing layouts, resource waste, and lack of targeted optimal drawing selection and layout schemes, unable to accurately identify and process complex process flows, with poor drawing accuracy, which may lead to errors and delays in the production process.

[0075] In view of these shortcomings of the existing technology, the present invention proposes a method for generating a semiconductor secondary piping PID, which optimizes the drawing process, improves the drawing efficiency through automated and intelligent means, reduces human errors, and quickly responds to design changes. It enhances the level of automation and intelligence, enables the automatic drawing system to more effectively process complex process flows and equipment interfaces, optimizes the drawing layout, and saves resources. It develops targeted drawing selection and layout schemes to ensure that the drawings are clear and accurate, meeting the requirements of production safety, maintenance convenience, and cost-effectiveness. It enhances the recognition and processing capabilities of the automatic drawing system, reduces errors and delays in the production process, and improves the overall production efficiency.

[0076] As Figure 1 shown, the embodiment of the present invention provides a method for generating a semiconductor secondary piping PID, and the specific steps are as follows:

[0077] S101: Obtain the initial process data for the semiconductor secondary piping operation process. Among them, the initial process data is obtained after the original process data is format-converted and data-cleaned.

[0078] Referring to Figure 2 , S101 specifically includes:

[0079] Obtain the original process data for the semiconductor secondary piping operation process;

[0080] Convert the format of the original process data to obtain structured process data;

[0081] Analyze the data situation of the structured process data, clean the structured process data, and obtain the initial process data.

[0082] The above original process data can be obtained by user upload or input of the data required for the semiconductor factory secondary piping operation process. The original process data includes the parameters of the secondary piping components. The parameters include node information, pipeline attribute information, and interface information. Among them, the node information can be node labels, equipment dimensions, valve positions, component positions, component angles, etc. The pipeline attribute information can be pipeline labels, diameters, paths, orientations, connection points, pressure ranges, etc. The interface information can be interface types (such as flanges, clamps), etc. Of course, the structured process data and initial process data after format conversion and data cleaning also include the parameters of the secondary piping components. The form of the original process data can be an Excel data form or other forms that are convenient for users to upload or input, and this is not limited.

[0083] In a specific implementation, convert the format of the original process data to obtain structured process data. By converting the format of the original process data, it is convenient to perform related operations such as storage, query, and processing of the original process data. In this example, the input original process data is converted from an Excel data form to JSON (JavaScript Object Notation) data, and the JSON data is stored in the corresponding database as a business logic information library.

[0084] JSON data is composed of key-value pairs and supports multiple data types, including strings, numbers, booleans, arrays, and objects, etc. This structure makes JSON data have good organization and predictability, which is convenient for program parsing and operation. In addition, the JSON format has good compatibility between different programming languages and is easy to convert and process.

[0085] Structured data refers to data with a clear data model and format, which can be conveniently stored, queried, and processed. Common structured data types include data in relational databases, spreadsheet data, CSV files, XML files, JSON files, fixed-width files, database views, and HTML tables, etc. In other implementations, according to actual needs, the original process data can be converted into other types of structured data, and this is not limited.

[0086] Data cleaning of structured process data includes correcting and marking obvious error values, filling in missing values, and deleting duplicate values. In the embodiments provided by the present invention, the structured process data is traversed to identify obvious error values, missing values, and duplicate data in the data. For example, for the component specification values in the structured process data, if there are abnormal values that are clearly outside the normal range, corrections or markings will be made. For example, the distribution of other values in the component specification is analyzed, and appropriate values are selected for correction according to the distribution. If there are missing values, appropriate methods will be used for filling according to the overall characteristics of the component data and the secondary piping business logic, such as mean filling, interpolation method, etc. Duplicate data will be identified and deleted to ensure the accuracy and consistency of the data.

[0087] S102: Based on the distribution status of each parameter in the initial process data, match the corresponding normalization strategy to obtain the standard process data.

[0088] Specifically, referring to Figure 3 , to obtain the standard process data, specifically including:

[0089] Screen multiple groups of core parameters in the initial process data, and construct corresponding partition datasets to be partitioned according to the values of each group of core parameters;

[0090] Determine the basic parameters in each group of core parameters, and sort each partition dataset to be partitioned according to the basic parameters;

[0091] According to the partition granularity, partition each partition dataset to be partitioned, and screen the values of the core parameters of each partition to form the intermediate process data, where the partition granularity is obtained by analyzing the basic parameters, operation process coefficients, and other core parameters;

[0092] According to the value conditions of each parameter in the intermediate process data, divide the first parameter and the second parameter, where the value condition of the first parameter is a finite number or a finite range, and the value condition of the second parameter is without a fixed range;

[0093] Based on the value analysis of the first parameter, match the corresponding normalization strategy to obtain the corresponding standard process data;

[0094] Perform a normality test on the second parameter to obtain the test result;

[0095] According to the test result, match the corresponding normalization strategy for the second parameter to obtain the corresponding standard process data.

[0096] For the conversion process from the initial process data to the standard process data, first determine the core parameters for screening, then perform a normality test and match the normalization strategy, which can not only improve the data processing efficiency, but also greatly improve the accuracy of the obtained standard process data.

[0097] The screening of the core parameters is carried out from the parameters of the secondary piping assembly, and the core parameters of different scenarios and different secondary piping assemblies can be different. Taking the pipeline for accurately controlling the gas and liquid flow rates in a certain embodiment as an example, the core parameters can be pipeline size, maximum pressure, interface type, installation location, etc. The values corresponding to the above core parameters are collected to construct the dataset to be partitioned, that is, the dataset to be partitioned includes the set of data composed of the values of the core parameters for each item. For example, as shown in Table 1, in the dataset to be partitioned, there is a certain piece of data where the pipeline size is 2 inches, the maximum pressure is 6 kg / cm 2 , the interface type is PCWS-FL (process cooling return water supply pipe), and the installation location is B6, etc.

[0098] Table 1 Dataset A to be partitioned

[0099]

[0100] For the constructed dataset to be partitioned, taking a certain core parameter as the basic parameter, the data of each item in the dataset to be partitioned is sorted based on the reference parameter, as shown in Table 2.

[0101] Table 2 Dataset B to be partitioned

[0102]

[0103] For the partitioning granularity, it is obtained by analyzing the basic parameter, the operation process coefficient, and other core parameters. The operation process coefficient represents the importance degree of this group of core parameters, and the importance degree can be represented by the number of historical failures of the secondary piping assembly under this group of core parameters.

[0104] The partitioning granularity is specifically expressed as:

[0105]

[0106] Among them, G is the partitioning granularity, P0 is the basic parameter, N is the operation process coefficient, is the weight coefficient of the first core parameter, is the first core parameter, is the weight coefficient of the nth core parameter, is the nth core parameter. Among them, the basic parameter and the n core parameters constitute all the core parameters of this dataset to be partitioned.

[0107] The partitioning of each dataset to be partitioned is carried out according to the partitioning granularity, and the values of the core parameters for each partition are screened to eliminate the unreasonable data in the initial process data, forming the intermediate process data.

[0108] It is understandable that since the data of different parameters (i.e., nodes, pipeline attributes, and / or interfaces) in the intermediate process data may have different dimensions and value ranges, it will affect the accuracy of the analysis of the intermediate process data and subsequent plotting. Therefore, it is necessary to standardize the intermediate process data. However, considering that there are significant differences in the value ranges, distribution conditions, etc. of each parameter in the intermediate process data, if the same normalization strategy is adopted, it may reduce the effect of data standardization and thus affect the accuracy of plotting.

[0109] In a specific implementation, according to the value-taking situations of different parameters in the intermediate process data, they are divided into the first parameter and the second parameter. The value-taking situation of the first parameter is finite or within a finite range, and the value-taking situation of the second parameter has no fixed range. For example, the pipeline diameter in the pipeline attributes belongs to the second parameter because the value range of the pipeline diameter is not fixed, and the size of the pipeline diameter is related to the actual required scenario. In different requirements, the pipeline diameter may be large or small. Another example is that the interface type in the interface is the first parameter because the values of the interface type are finite and can be types such as flange and clamp. If the value-taking situation of the first parameter is finite, one-hot encoding is used to normalize the first parameter to obtain the corresponding standard process data. For example, the code for the value of flange in the interface type is defined as 001, and the code for clamp is defined as 100. If the value-taking situation of the first parameter is within a finite range, the min-max normalization method is used to process the first parameter to obtain the corresponding standard process data. All other parameters except the first parameter are the second parameter. It is necessary to perform a normality test on the second parameter. When the test result conforms to the normal distribution, the Z-score normalization method is used to process the second parameter to obtain the corresponding standard process data. When the test result does not conform to the normal distribution, according to the distribution difference from the normal distribution, the corresponding normalization strategy is matched to obtain the corresponding standard process data. In a specific example, if the test result is a right-skewed distribution, the Log transformation is used to normalize the second parameter. In other examples, the Box-Cox transformation, quantile normalization, Robust normalization, etc. can also be used to process the second parameter, and no limitation is made in this regard.

[0110] In a specific example, the multi-dimensional data matrix corresponding to different parameters in the input intermediate process data includes pipeline attributes (such as pipeline diameter, pressure), interfaces (flanges / clamps), etc. Then, normality tests are performed on different parameters in the intermediate process data respectively. The Shapiro-Wilk test is used to determine whether the features conform to the normal distribution, which is used to screen the features within the normal value range. First, it is judged whether each parameter in the intermediate process data is within the corresponding fixed range. For example, the fixed range corresponding to the pressure data is 0 - 10 MPa, and the fixed range corresponding to the pipeline diameter is 0.5 mm - 10 mm. The data that is not within the corresponding fixed range is removed, and normality verification is performed on each parameter after the removal. For example, the p-value of the pressure data is calculated, and the p-value = 0.03, indicating that the pressure data is non-normally distributed and belongs to a right-skewed distribution. The p-value of the pipeline diameter is calculated, and the p-value = 0.45, indicating that the pipeline diameter is approximately normal. For the second parameter, although there is no fixed range, corresponding fixed ranges are preset for judgment based on different process data. For the first parameter, a corresponding finite range is used for range analysis. For example, it is judged whether the valve opening is within the range of 0% - 100%. According to the test results, the corresponding normalization strategy is matched to obtain the standard process data.

[0111] Further, the corresponding standard process data is obtained, specifically including:

[0112] If the test result is a normal distribution, combined with the preset normal distribution range, the second parameter is screened to obtain the standard second parameter;

[0113] The Z-score normalization strategy is used to normalize the standard second parameter to obtain the corresponding standard process data.

[0114] If the test result is a non-normal distribution, combined with the preset non-normal distribution range, the second parameter is screened to obtain the standard second parameter;

[0115] Match the corresponding normalization strategy for the standard second parameter and perform normalization processing to obtain the corresponding standard process data.

[0116] In a specific embodiment, after performing a normality test on the second parameter, a corresponding test result will be obtained. The test result may be a normal distribution or a non-normal distribution, such as a left-skewed distribution or a right-skewed distribution. Regardless of the distribution state, there are regions in the data set. According to different data requirements, the second parameter is screened. In a specific example, the preset normal distribution range is one standard deviation range (μ±σ), and the data within one standard deviation range in the second parameter is screened out to obtain the standard second parameter. For a right-skewed distribution, the preset non-normal distribution range is the range between the median and the first quartile, and the data within the range between the median and the first quartile in the second parameter is screened out to obtain the standard second parameter. For a left-skewed distribution, the preset non-normal distribution range is the range between the median and the third quartile, and the data within the range between the median and the third quartile in the second parameter is screened out to obtain the standard second parameter.

[0117] In other embodiments, a Dynamic and Adaptive Clustering Algorithm model can be built into the data processing layer, which can automatically detect the distribution patterns (such as normal distribution, long-tail distribution) of multi-dimensional parameters such as nodes, pipeline attributes, and interfaces in the initial process data of the semiconductor secondary piping operation process, and dynamically match the corresponding normalization strategies (such as Min-Max, Log transformation, Z-score) according to the distribution type. Optimize the clustering results in combination with physical constraints (such as pipeline connection rules, safety distances), extract feature vectors that can reflect the overall structure, screen out more representative and relevant high-value features, and improve the layout rationality.

[0118] S103: Based on the analysis of the standard process data, obtain the information content of each parameter in the standard process data, and combine the initial weight of each parameter to give the characteristic weight of each parameter in the standard process data.

[0119] Furthermore, giving the characteristic weight of each parameter in the standard process data specifically includes:

[0120] Sort each parameter in the standard process data based on the preset process standard, and give the initial weight of each parameter;

[0121] Combine the information content of each parameter in the standard process data to correct the initial weight to obtain the characteristic weight.

[0122] In a specific embodiment, the preset process standard is the installation requirement and / or configuration requirement of the secondary piping assembly. It can be understood that for different secondary piping assemblies, the importance of corresponding parameters is different. For example, for a pipeline, the importance ranking of parameters is interface model, internal pipe pressure, pipeline diameter, and coordinate position in sequence. The process standard is preset by experienced experts. After obtaining the ranking of different parameters in the standard process data, corresponding initial weights are configured for each parameter. For example, the initial weight corresponding to the interface model is 0.4, the initial weight corresponding to the internal pipe pressure is 0.3, the initial weight corresponding to the pipeline diameter is 0.2, and the initial weight corresponding to the coordinate position is 0.1.

[0123] The information quantity is a measure of the degree of dispersion and can be characterized by standard deviation, variance, etc. In a certain embodiment provided by the present invention, the variance corresponding to each parameter in the standard process data is used as the information quantity of each parameter. For example, the variance of the pipeline diameter is 0.8, and the variance of the internal pipe pressure is 0.5. According to the preset corresponding relationship between variance and weight, the weight corresponding to the variance of the pipeline diameter is adjusted to +0.1, and the weight corresponding to the variance of the internal pipe pressure is adjusted to -0.1. Then the final feature weights are obtained, that is, the feature weight corresponding to the interface model is 0.4, the feature weight corresponding to the internal pipe pressure is 0.3 - 0.1 = 0.2, the feature weight corresponding to the pipeline diameter is 0.2 + 0.1 = 0.3, and the feature weight corresponding to the coordinate position is 0.1. The sum of the feature weights corresponding to each parameter in the standard process data is 1.

[0124] S104: Combine the feature weights of each parameter in the standard process data, and perform clustering analysis on the standard process data to obtain process component matching data.

[0125] Specifically, referring to Figure 4 , the process component matching data is obtained, which specifically includes:

[0126] Determine the initial cluster center from the standard process data based on the preset physical constraints;

[0127] According to the initial cluster center, combine the feature weights of each parameter in the standard process data, perform clustering analysis on the standard process data, and update and iterate the cluster center until convergence to obtain the clustering result;

[0128] Judge the clustering result to obtain the constraint verification result;

[0129] According to the constraint verification result, adjust the clustering result and the feature weights of each parameter in the standard process data, and give the process component matching data.

[0130] Further, referring to Figure 5 , the clustering result is obtained, which specifically includes:

[0131] According to the initial cluster centers, combined with each parameter in the standard process data and the characteristic weights of each parameter, the distances between the initial cluster centers and each standard process data are given;

[0132] Analyze the distances between the initial cluster centers and each standard process data, update and iterate the cluster centers, and give the distances between the new cluster centers and each standard process data, where the new cluster centers satisfy physical constraints;

[0133] Based on the distances between the new cluster centers and each standard process data, analyze the average distance between the standard process data in each cluster and the cluster centers, and give the clustering results.

[0134] In a specific implementation manner, the above-mentioned preset physical constraint is the connection relationship between each component in the standard process data. The connection relationship includes multiple connection metrics, and each connection metric includes the safety distance between each component, whether there is an intersection between each component, whether the interfaces of each component match, etc. The determination criterion of the initial cluster centers takes the preset physical constraint as a reference. When there are multiple initial cluster centers, the initial cluster centers can be screened according to the actual situation. For example, select the standard process data corresponding to the component with the largest number of connected components as the initial cluster center. In other implementation manners, other rules can be used to screen the initial cluster centers, which are not limited herein.

[0135] Cluster each component in combination with the characteristic weights obtained in the foregoing process, specifically expressed as:

[0136]

[0137] Among them, is the distance between the i-th initial cluster center and the j-th component, is the characteristic weight corresponding to the k-th parameter in the standard process data, m is the number of parameters in the standard process data, is the parameter value of the k-th parameter in the i-th initial cluster center, is the parameter value of the k-th parameter in the standard process data corresponding to the j-th component.

[0138] In a specific example, the standard process data includes four parameters, namely interface model, internal pipe pressure, pipe diameter, and coordinate position, and the corresponding characteristic weights are 0.4, 0.2, 0.3, and 0.1 in sequence. Calculate the distances between the initial cluster centers and each standard process data, and obtain:

[0139]

[0140] is the pipe diameter corresponding to the initial cluster center, is the internal pipe pressure corresponding to the initial cluster center, is the interface type corresponding to the initial cluster center, is the coordinate position corresponding to the initial cluster center, is the pipe diameter corresponding to the j-th standard process data, is the internal pipe pressure corresponding to the j-th standard process data, is the interface type corresponding to the j-th standard process data, is the coordinate position corresponding to the j-th standard process data.

[0141] After calculating the distances between the initial cluster center and each standard process data, update and iterate the cluster center, recalculate the distances between the new cluster center and each standard process data until the clustering result is obtained. The update process of the cluster center can be carried out in a random adjustment manner, or can be selected and determined according to the distance from the previous cluster center, or can also be determined through various types of optimization algorithms, which is not limited here. After obtaining the distances between the new cluster center and each standard process data each time, analyze the average distance between the standard process data in each cluster and the cluster center. When the average distances corresponding to all clusters are less than the distance threshold, it indicates that the clustering reaches the convergence stage and the clustering result is given.

[0142] After obtaining the clustering result, it is also necessary to further judge the clustering result according to the preset physical constraints to obtain the constraint verification result. According to the specific situation of the constraint verification result, adjust the clustering result to give the process component matching data. In a specific example, in a certain category, if pipe A and pipe B cross, it means that there is a large deviation in the coordinate positions of pipe A and pipe B, then increase the feature weight corresponding to the coordinate position and adjust the coordinate position of pipe A and / or pipe B.

[0143] S105: Analyze and adjust each component in combination with the process component matching data to generate the semiconductor secondary piping PID.

[0144] Furthermore, referring to Figure 6 , generate the semiconductor secondary piping PID, specifically including:

[0145] Based on the process component matching data, draw each component corresponding to each standard process data to generate the initial PID;

[0146] According to the connection relationship between each component in the initial PID, construct the reward function;

[0147] In combination with the reward function, adjust each component in the initial PID to give the standard PID;

[0148] Render the standard PID to generate the semiconductor secondary piping PID.

[0149] Furthermore, referring to Figure 7, construct a reward function, specifically including:

[0150] According to the connection relationship between each component in the initial PID, analyze the gap of the corresponding connection indicators in each component, and give the sorting of the connection indicator differences.

[0151] Based on the sorting of the connection indicator differences, assign corresponding weights to each connection indicator, and give the reward weight matrix.

[0152] Combine the reward weight matrix to construct the reward function.

[0153] Although the process component matching data is adjusted according to the constraint verification results, the initial PID still deviates from the physical constraints. In a specific implementation manner, first, according to the process component matching data, draw and connect each component in the standard process data to obtain the initial PID. Then analyze the connection relationship between each component in the initial PID and construct a reward function. For example, as Figure 8 shown, when there is no problem with the connection between component A and component B and it fully conforms to the physical constraints, there is no need to construct a reward function for adjustment. If there is a positional deviation between component A and component B, it is necessary to obtain the gap of each connection indicator in component A and component B, and according to the gap of the connection indicators, correspond to different reward functions.

[0154] In different implementation manners, according to the different requirements of semiconductor secondary piping, the weights corresponding to different drawing indicators are initially set.

[0155] After each round of drawing is completed and the evaluation result is obtained, adjust the reward weight matrix according to the evaluation result. Then, use the reward function corresponding to the adjusted reward weight matrix to adjust the PID, calculate the reward values of each drawing step and result using the new reward function, and continuously optimize the drawing process.

[0156] After completing component matching and attribute adjustment, reasonably layout and connect each component, and finally generate a visually rendered PID diagram of semiconductor secondary piping, that is, the semiconductor secondary piping PID, which can clearly and intuitively display the detailed structure and component relationship of semiconductor secondary piping.

[0157] Refer to Figure 9 , the embodiment of the present invention provides a device for generating a semiconductor secondary piping PID, including:

[0158] A data acquisition module 201, configured to acquire initial process data for a semiconductor secondary piping operation process;

[0159] A data processing module 202, configured to match a corresponding normalization strategy based on the distribution state of each parameter in the initial process data to obtain standard process data;

[0160] A weight determination module 203, configured to obtain the information content of each parameter in the standard process data according to the analysis of the standard process data, and combine the initial weight of each parameter to give the characteristic weight of each parameter in the standard process data;

[0161] A component matching module 204, configured to perform clustering analysis on the standard process data by combining the characteristic weights of each parameter in the standard process data to obtain process component matching data;

[0162] A PID generation module 205, configured to analyze and adjust each component by combining the process component matching data to generate a semiconductor secondary piping PID.

[0163] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the described modules can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0164] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present invention. Obviously, those skilled in the art can make various changes and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A method for generating a semiconductor secondary piping PID, characterized in that, Including: Obtain the initial process data for the semiconductor secondary piping operation process; Based on the distribution status of each parameter in the initial process data, match the corresponding normalization strategy to obtain the standard process data, where the parameters include node information, pipeline attribute information, and interface information; Based on the preset process standards, sort different parameters in the standard process data and give the initial weight of each parameter, where the preset process standards are the installation requirements and / or configuration requirements of the secondary piping components; Combine the information content of each parameter in the standard process data to correct the initial weight and obtain the feature weight, where the information content is a measure of the degree of dispersion; Based on the preset physical constraints, determine the initial cluster center from the standard process data, where the preset physical constraints are the connection relationships between various components in the standard process data, and the connection relationships include multiple connection indicators, and the connection indicators include the safety distance between various components, whether there is intersection between various components, and whether the interfaces of various components match; According to the initial cluster center, combine each parameter in the standard process data and the feature weight of each parameter to give the distance between the initial cluster center and each standard process data; Analyze the distance between the initial cluster center and each standard process data, update and iterate the cluster center, and give the distance between the new cluster center and each standard process data, where the new cluster center meets the physical constraints; Based on the distance between the new cluster center and each standard process data, analyze the average distance between the standard process data in each cluster and the cluster center to give the clustering result; Based on the physical constraints, judge the clustering result to obtain the constraint verification result; According to the constraint verification result, adjust the clustering result and the feature weight of each parameter in the standard process data to give the process component matching data; Combine the process component matching data, analyze and adjust each component to generate the semiconductor secondary piping PID.

2. The method for generating a semiconductor secondary piping PID according to claim 1, wherein Obtain the initial process data for the semiconductor secondary piping operation process, which specifically includes the following steps: Obtain the original process data for the semiconductor secondary piping operation process; Convert the format of the original process data to obtain the structured process data; Analyze the data situation of the structured process data, clean the data of the structured process data to obtain the initial process data.

3. The method for generating the semiconductor secondary piping PID according to claim 1, wherein Based on the distribution status of each parameter in the initial process data, match the corresponding normalization strategy to obtain the standard process data, specifically including: According to the value situation of each parameter in the initial process data, divide the first parameter and the second parameter, where the value situation of the first parameter is finite or within a finite range, and the value situation of the second parameter has no fixed range; Based on the value analysis of the first parameter, match the corresponding normalization strategy to obtain the corresponding standard process data; Conduct a normality test on the second parameter to obtain the test result; According to the test result, match the corresponding normalization strategy for the second parameter to obtain the corresponding standard process data.

4. The method for generating a semiconductor secondary piping PID according to claim 3, characterized in that According to the test result, match the corresponding normalization strategy for the second parameter to obtain the corresponding standard process data, specifically including: When the test result is a normal distribution, combine the preset normal distribution range to screen the second parameter to obtain the standard second parameter; The standard second parameter is normalized using the Z-score normalization strategy to obtain the corresponding standard process data; When the test result is non-normal distribution, the second parameter is screened in combination with the preset non-normal distribution range to obtain the standard second parameter; Match the corresponding normalization strategy for the standard second parameter and perform normalization processing to obtain the corresponding standard process data.

5. The method for generating the semiconductor secondary piping PID according to claim 1, wherein Combined with the process component matching data, analyze and adjust each component to generate the semiconductor secondary piping PID, specifically including: Based on the process component matching data, draw each component corresponding to each standard process data to generate the initial PID; According to the component relationship of each component in the initial PID, construct a reward function; Combined with the reward function, adjust the component relationship of each component in the initial PID to give the standard PID; Render the standard PID to generate the semiconductor secondary piping PID.

6. The method for generating the semiconductor secondary piping PID according to claim 5, wherein According to the component relationship of each component in the initial PID, construct a reward function, specifically including: According to the component relationship of each component in the initial PID, analyze the gap of the corresponding parameters in each component to give the parameter difference ranking; Based on the parameter difference ranking, assign corresponding weights to each parameter to give the reward parameter weights; Combine the reward parameter weights corresponding to each parameter to construct a reward function.

7. A generating device for a semiconductor secondary piping PID, characterized in that, Adopt the method for generating the semiconductor secondary piping PID as described in any one of claims 1-6, including: A data acquisition module for acquiring the initial process data for the semiconductor secondary piping operation process; A data processing module for matching the corresponding normalization strategy based on the distribution status of each parameter in the initial process data to obtain the standard process data; A weight determination module for sorting different parameters in the standard process data based on the preset process standard to give the initial weight of each parameter; and correcting the initial weight in combination with the information amount of each parameter in the standard process data to obtain the feature weight; A component matching module for determining the initial cluster center from the standard process data based on the preset physical constraints; according to the initial cluster center, combine each parameter in the standard process data and the feature weight of each parameter to give the distance between the initial cluster center and each standard process data; analyze the distance between the initial cluster center and each standard process data, update and iterate the cluster center, and give the distance between the new cluster center and each standard process data, where the new cluster center satisfies the physical constraints; based on the distance between the new cluster center and each standard process data, analyze the average distance between the standard process data in each cluster and the cluster center to give the clustering result; based on the physical constraints, judge the clustering result to obtain the constraint verification result; according to the constraint verification result, adjust the clustering result and the feature weight of each parameter in the standard process data to give the process component matching data; A PID generation module for combining the process component matching data, analyzing and adjusting each component to generate the semiconductor secondary piping PID.

Images