Equipment model parameterized configuration system

Abstract

The invention discloses an equipment model parameterized configuration system, and belongs to the technical field of equipment model parameterized configuration. The equipment model parameterization configuration system comprises a data processing module, a model building module and a parameterization configuration module. According to the method, the problem that in the prior art, parameters of the equipment model are not optimally configured in the actual use process, so that the quality problem easily exists in the production process of the equipment is solved, the equipment model is optimized, the operation efficiency of the model is improved, the requirement for computing resources is reduced, and the cost is reduced. The waiting time and resource waste in production can be reduced, the production efficiency is remarkably improved, parameters are optimized during parameterized configuration of an equipment model, the efficiency and performance of equipment can be improved, waste of energy and raw materials is reduced, the service life of the equipment is prolonged, the quality and efficiency of the production process are improved, and the production cost and the maintenance cost are reduced; the failure rate is reduced, and the stability and continuity of the equipment production process are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment model parameterized configuration, and in particular to an equipment model parameterized configuration system. Background Art

[0002] The intelligent design of equipment is mainly related to the product design process. The focus is on optimizing and analyzing the product through the comprehensive use of 3D modeling and multidisciplinary simulation (structure, fluid, thermal, electromagnetic, etc.) to find the optimal solution for product design.

[0003] A Chinese patent with publication number CN116738759A discloses a design and operation and maintenance method, device, computer equipment and readable storage medium for equipment. The method includes: in the design stage of the equipment, obtaining an optimized simulation model of the equipment through simulation optimization software, referred to as a first simulation model; collecting test data of physical samples of the equipment, calibrating the parameters of the first simulation model according to the test data after conversion, driving the simulation optimization software to optimize the first simulation model to obtain a second simulation model; constructing a reduced-order model according to the parameters of the second simulation model to obtain a digital twin of the equipment; in the process of running the equipment, calibrating the parameters of the second simulation model according to the running data after conversion, driving the simulation optimization software to optimize the second simulation model to obtain a third simulation model; updating the digital twin according to the parameters of the third simulation model; and operating and maintaining the equipment based on the updated digital twin.

[0004] The above patent does not optimize the parameters of the equipment model during actual use, which leads to quality problems in the production process of the equipment. Therefore, it does not meet the existing needs. We have proposed a parameterized configuration system for equipment models. Summary of the invention

[0005] The purpose of the present invention is to provide an equipment model parameter configuration system, which optimizes parameters during the parameter configuration of the equipment model, thereby improving the efficiency and performance of the equipment, reducing the waste of energy and raw materials, extending the service life of the equipment, improving the quality and efficiency of the production process, reducing production costs and maintenance costs, reducing the failure rate, ensuring the stability and continuity of the equipment production process, and solving the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: an equipment model parameterized configuration system, comprising:

[0007] A data processing module is used to obtain characteristic parameter data of equipment, process the obtained characteristic parameter data of equipment, and integrate the processed characteristic parameter data of equipment;

[0008] A model building module is used to input characteristic parameter data into the equipment characterization script library and the equipment characteristic component model library to generate equipment characteristic component models, integrate the equipment characteristic component models to generate equipment whole machine models, and build equipment models that simulate the real behavior of the equipment based on the equipment whole machine models;

[0009] The parameterized configuration module is used to optimize the parameterized configuration data of the equipment model, parameterize the equipment model according to the optimized parameterized configuration data, and generate an abstract evaluation coefficient during equipment operation, extract the difference between the abstract evaluation coefficient within a specified time and its nearest abstract evaluation coefficient reference threshold range boundary value, and compare it with a preset difference threshold to obtain the abstract evaluation coefficient within the target specified time, extract the time interval between each two adjacent abstract evaluation coefficients within the target specified time to obtain a comprehensive evaluation coefficient, compare the comprehensive evaluation coefficient with a preset comprehensive evaluation coefficient threshold, and determine whether the reference threshold range of the abstract evaluation coefficient needs to be adjusted based on the comparison result.

[0010] Preferably, the data processing module includes:

[0011] The data cleaning module is used to collect and clean the equipment characteristic parameter data, check the data consistency of the equipment characteristic parameter data, remove invalid values ​​or missing values ​​contained in the equipment characteristic parameter data, and determine the characteristic parameter data that is valuable for equipment model construction;

[0012] The data integration module is used to integrate the remaining equipment characteristic parameter data valuable for equipment model construction after cleaning, and determine the equipment characteristic parameter data of a unified data view.

[0013] Preferably, the model building module includes:

[0014] A sample acquisition module is used to acquire a plurality of characteristic parameter data training samples of the equipment, and record the acquired plurality of characteristic parameter data training samples as first sample data, wherein the plurality of characteristic parameter data of the equipment includes operation parameter data, structure parameter data, electrical parameter data, chemical parameter data, thermodynamic parameter data and property parameter data;

[0015] A data input module is used to input the processed characteristic parameter data into the equipment characterization script library and the equipment characteristic component model library to generate the equipment characteristic component model;

[0016] The model generation module is used to integrate the equipment characteristic component models to generate the equipment whole machine model, and to build the equipment model that simulates the real behavior of the equipment based on the equipment whole machine model;

[0017] A model optimization module is used to optimize the equipment model by using multiple characteristic parameter data training samples of the equipment to obtain an optimized equipment model;

[0018] The model optimization module comprises:

[0019] Acquire multiple characteristic parameter data training samples of the equipment, and record the acquired multiple characteristic parameter data training samples as first sample data;

[0020] Extract features from the plurality of first sample data respectively to obtain a plurality of feature vectors corresponding to the plurality of first sample data one by one;

[0021] For any one of the multiple eigenvectors, calculate the value of the augmented entropy loss function corresponding to the eigenvector;

[0022] Filtering out a plurality of second sample data from a plurality of first sample data according to a value of the augmented entropy loss function corresponding to each eigenvector;

[0023] Each second sample data is the first sample data corresponding to a feature vector whose value is less than a preset threshold;

[0024] Based on the plurality of second sample data and the corresponding augmented entropy loss function, the equipment model is optimized to obtain an optimized equipment model.

[0025] Preferably, the specific process of the model building module includes:

[0026] Input the processed feature parameter data into the equipment characterization script library and the equipment feature component model library to generate the equipment feature component model;

[0027] Integrate the equipment characteristic component models to generate the equipment whole machine model, and build the equipment model that simulates the real behavior of the equipment based on the equipment whole machine model;

[0028] Acquire multiple characteristic parameter data training samples of the equipment, record the acquired multiple characteristic parameter data training samples as first sample data, and select multiple second sample data from the multiple first sample data;

[0029] Based on the plurality of second sample data and the corresponding augmented entropy loss function, the equipment model is optimized to obtain an optimized equipment model.

[0030] Preferably, the parameterized configuration module includes:

[0031] The template creation module is used to classify the characteristic parameter data of the equipment in detail, define the parameter configuration rules of each characteristic parameter data according to industry standards and specifications, and create a basic model template for each characteristic parameter data for each type of characteristic parameter data;

[0032] A configuration module is used to optimize the parameterized configuration data of the equipment model and perform parameterized configuration of the equipment model according to the optimized parameterized configuration data;

[0033] The early warning module is used to monitor the process of equipment model parameter configuration in real time, ensure that the equipment model parameter configuration is successful within the specified time, and issue early warning prompts in the event of unsuccessful parameter configuration.

[0034] Preferably, the configuration module includes:

[0035] Obtaining an original data set set, the original data set set consisting of standard data of digital configuration of each historical characteristic parameter of equipment and minimum data and maximum data of digital configuration of each historical characteristic parameter of equipment;

[0036] According to the parameterized configuration item list, the lowest data and the highest data item of the digitized configuration of each historical characteristic parameter of the equipment are deleted to determine the target data set of the digitized configuration of each historical characteristic parameter of the equipment;

[0037] Edit the target data set of each historical characteristic parameter data configuration of the equipment in the basic model template of each characteristic parameter data to obtain a preset parameter configuration list;

[0038] Screen the preset parameterized configuration list to determine the target data set for the digital configuration of each characteristic parameter of the equipment;

[0039] According to the target data set of the digital configuration of each characteristic parameter of the equipment, the minimum value and the maximum value of the target data of the parameter configuration of the equipment model are obtained;

[0040] If the value of the equipment model parameterized configuration data is between the lowest value and the highest value of the equipment model parameterized configuration target data, then determining a group of parameterized configuration items corresponding to the value of the equipment model parameterized configuration data as optimized parameterized configuration data;

[0041] The equipment model is parameterized according to the optimized parameterized configuration data.

[0042] Preferably, the early warning module includes:

[0043] When the equipment is started or running, the abstract evaluation coefficient generated in each monitoring cycle is obtained through the data analysis mechanism, and the abstract evaluation coefficient is compared and analyzed with the reference threshold range of the abstract evaluation coefficient;

[0044] If the abstract evaluation coefficient is within the abstract evaluation coefficient reference threshold range within the specified time, a signal of successful parameterized configuration of the equipment model is generated, and efficient adaptation of industrial software compatibility is continued based on the equipment model;

[0045] If the abstract evaluation coefficient is not within the abstract evaluation coefficient reference threshold range within the specified time, an equipment model parameter configuration failure signal is generated, and an early warning prompt is issued for this situation, indicating that the equipment model parameter configuration cannot reach the expected state.

[0046] Preferably, the early warning module further includes:

[0047] A difference data extraction module is used to extract the difference between the abstract evaluation coefficient within the abstract evaluation coefficient reference threshold range and its nearest abstract evaluation coefficient reference threshold range boundary value within a specified time;

[0048] A difference comparison module, used for comparing the difference with a preset difference threshold;

[0049] The target specified time abstract evaluation coefficient acquisition module is used to retrieve the abstract evaluation coefficient within the specified time corresponding to the difference value being lower than the preset difference threshold value when the difference value is lower than the preset difference threshold value as the abstract evaluation coefficient within the target specified time;

[0050] A time interval extraction module is used to extract the time interval between the abstract evaluation coefficients of each two adjacent targets within a specified time;

[0051] A comprehensive evaluation coefficient acquisition module, used to obtain a comprehensive evaluation coefficient by combining the abstract evaluation coefficient within the target specified time with the time interval between each two adjacent abstract evaluation coefficients within the target specified time;

[0052] The comprehensive evaluation coefficient is obtained by the following formula:

[0053]

[0054] Among them, U represents the comprehensive evaluation coefficient; n represents the number of abstract evaluation coefficients within the target specified time; S i represents the coefficient value corresponding to the abstract evaluation coefficient within the specified time of the i-th target; T b represents the standard deviation corresponding to m time intervals; T p represents the average value corresponding to m time intervals; S b represents the standard deviation of the coefficients corresponding to the abstract evaluation coefficients of n targets within a specified time; S ci represents the difference between the abstract evaluation coefficient of the i-th target within the specified time and the boundary value of the abstract evaluation coefficient reference threshold range most recently; S cbrepresents the standard deviation of the difference between the abstract evaluation coefficients of n targets within a specified time and the boundary value of the reference threshold range of the abstract evaluation coefficients; m represents the total number of time intervals between the abstract evaluation coefficients of each adjacent target within a specified time; T i represents the time length value corresponding to the i-th time interval; S 01i and S 02i They represent the values ​​of the abstract evaluation coefficients of the two adjacent targets within the specified time corresponding to the i-th time interval;

[0055] An evaluation coefficient comparison module, used for comparing the comprehensive evaluation coefficient with a preset comprehensive evaluation coefficient threshold;

[0056] The range adjustment judgment module is used to determine that the abstract evaluation coefficient reference threshold range needs to be adjusted when the comprehensive evaluation coefficient exceeds the preset comprehensive evaluation coefficient threshold.

[0057] Preferably, the range adjustment judgment module includes:

[0058] A first abstract evaluation coefficient retrieval module, configured to extract the abstract evaluation coefficient within a specified time within a reference threshold range of the abstract evaluation coefficient when the comprehensive evaluation coefficient exceeds the preset comprehensive evaluation coefficient threshold;

[0059] A first evaluation coefficient indicator parameter acquisition module, used to acquire a first evaluation coefficient indicator parameter using the abstract evaluation coefficient within a specified time range within the abstract evaluation coefficient reference threshold value;

[0060] The first evaluation coefficient index parameter is obtained by the following formula:

[0061]

[0062] Among them, P 01 represents the first evaluation coefficient indicator parameter; k represents the number of abstract evaluation coefficients within the specified time within the abstract evaluation coefficient reference threshold range; S ki represents the value of the abstract evaluation coefficient within the specified time within the reference threshold range of the abstract evaluation coefficient; S kci represents the difference between the i-th abstract evaluation coefficient within the abstract evaluation coefficient reference threshold range within the specified time and its nearest abstract evaluation coefficient reference threshold range boundary value; S kcbi represents the standard deviation of the difference between the i-th abstract evaluation coefficient within the abstract evaluation coefficient reference threshold range and its nearest abstract evaluation coefficient reference threshold range boundary value within the specified time; S cb It represents the standard deviation of the difference between the abstract evaluation coefficient of n targets within a specified time and the boundary value of the abstract evaluation coefficient reference threshold range; Skcb It represents the standard deviation of the difference between k abstract evaluation coefficients within the abstract evaluation coefficient reference threshold range within a specified time and their nearest abstract evaluation coefficient reference threshold range boundary value;

[0063] a coefficient indicator parameter comparison module, configured to compare the first evaluation coefficient indicator parameter with a preset first coefficient evaluation parameter threshold;

[0064] a first abstract evaluation coefficient reference threshold range adjustment execution module, configured to adjust the abstract evaluation coefficient reference threshold range using the first evaluation coefficient indicator parameter when the first evaluation coefficient indicator parameter does not exceed a preset first coefficient evaluation parameter threshold, and obtain an adjusted abstract evaluation coefficient reference threshold range;

[0065] The upper limit and lower limit corresponding to the adjusted abstract evaluation coefficient reference threshold range are obtained by the following formula:

[0066]

[0067] Among them, X up and X down Indicates the upper and lower limits of the adjusted abstract evaluation coefficient reference threshold range; X up0 and X down0 represents the upper and lower limits of the reference threshold range of the abstract evaluation coefficient before adjustment; P 01 represents the first evaluation coefficient indicator parameter;

[0068] The range adjustment module is used to adjust the abstract evaluation coefficient reference threshold range by using the abstract evaluation coefficient within the specified time that is not within the abstract evaluation coefficient reference threshold range when the first evaluation coefficient indicator parameter exceeds the preset first coefficient evaluation parameter threshold.

[0069] Preferably, the range adjustment module includes:

[0070] A second abstract evaluation coefficient retrieving module, configured to retrieve an abstract evaluation coefficient within a specified time period that is not within a range of an abstract evaluation coefficient reference threshold value when the first evaluation coefficient indicator parameter exceeds a preset first coefficient evaluation parameter threshold value;

[0071] A second evaluation coefficient indicator parameter acquisition module, used to acquire a second evaluation coefficient indicator parameter using the abstract evaluation coefficient within the specified time that is not within the abstract evaluation coefficient reference threshold range;

[0072] The second evaluation coefficient index parameter is obtained by the following formula:

[0073]

[0074] Among them, P 02 represents the second evaluation coefficient indicator parameter; k represents the number of abstract evaluation coefficients within the specified time within the abstract evaluation coefficient reference threshold range; S ki represents the value of the abstract evaluation coefficient within the specified time within the reference threshold range of the abstract evaluation coefficient; S kci represents the difference between the abstract evaluation coefficient within the i-th specified time within the abstract evaluation coefficient reference threshold range and its nearest abstract evaluation coefficient reference threshold range boundary value; r represents the number of abstract evaluation coefficients within the specified time that are not within the abstract evaluation coefficient reference threshold range; S ri represents the value of the abstract evaluation coefficient within the specified time that is not within the reference threshold range of the abstract evaluation coefficient; S rci represents the difference between the i-th abstract evaluation coefficient within the specified time that is not within the abstract evaluation coefficient reference threshold range and its nearest abstract evaluation coefficient reference threshold range boundary value; S kcbi represents the standard deviation of the difference between the i-th abstract evaluation coefficient within the abstract evaluation coefficient reference threshold range and its nearest abstract evaluation coefficient reference threshold range boundary value within the specified time; S cb It represents the standard deviation of the difference between the abstract evaluation coefficient of n targets within a specified time and the boundary value of the abstract evaluation coefficient reference threshold range; S rcb represents the standard deviation of the difference between the abstract evaluation coefficients within a specified time period that are not within the abstract evaluation coefficient reference threshold range and their nearest abstract evaluation coefficient reference threshold range boundary values; S rbi represents the numerical standard deviation of the abstract evaluation coefficient within the specified time when the i-th abstract evaluation coefficient is not within the reference threshold range; S kb represents the standard deviation of the values ​​of the abstract evaluation coefficients within the reference threshold range of the abstract evaluation coefficients within a specified time;

[0075] A first evaluation coefficient indicator parameter retrieving module, used to retrieve the first evaluation coefficient indicator parameter;

[0076] A second abstract evaluation coefficient reference threshold range adjustment execution module is used to adjust the abstract evaluation coefficient reference threshold range by using the first evaluation coefficient indicator parameter and the second evaluation coefficient indicator parameter to obtain an adjusted abstract evaluation coefficient reference threshold range;

[0077] The upper limit and lower limit corresponding to the adjusted abstract evaluation coefficient reference threshold range are obtained by the following formula:

[0078]

[0079] Among them, Xup and X down Indicates the upper and lower limits of the adjusted abstract evaluation coefficient reference threshold range; X up0 and X down0 represents the upper and lower limits of the reference threshold range of the abstract evaluation coefficient before adjustment; P 01 Represents the first evaluation coefficient index parameter; P 02 Represents the second evaluation coefficient indicator parameter.

[0080] Compared with the prior art, the present invention has the following beneficial effects:

[0081] The present invention optimizes the equipment model, improves the operating efficiency of the model, reduces the demand for computing resources, speeds up the model's operation, improves the overall performance, can reduce waiting time and resource waste in production, and significantly improves production efficiency. By optimizing parameters during parameterized configuration of the equipment model, the efficiency and performance of the equipment can be improved, the waste of energy and raw materials can be reduced, the service life of the equipment can be extended, the quality and efficiency of the production process can be improved, the production cost and maintenance cost can be reduced, the failure rate can be reduced, and the stability and continuity of the equipment production process can be ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 It is a schematic diagram of the equipment model parameter configuration system module of the present invention;

[0083] Figure 2 The figure is a schematic diagram of the working process of the equipment model parameter configuration system of the present invention. DETAILED DESCRIPTION

[0084] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0085] In order to solve the problem that the existing patents do not optimize the parameters of the equipment model in actual use, resulting in quality problems in the production process of the equipment, please refer to Figure 1-Figure 2 , this embodiment provides the following technical solutions:

[0086] Equipment model parameterized configuration system, including:

[0087] A data processing module is used to obtain characteristic parameter data of equipment, process the obtained characteristic parameter data of equipment, and integrate the processed characteristic parameter data of equipment;

[0088] A model building module is used to input characteristic parameter data into the equipment characterization script library and the equipment characteristic component model library to generate equipment characteristic component models, integrate the equipment characteristic component models to generate equipment whole machine models, and build equipment models that simulate the real behavior of the equipment based on the equipment whole machine models;

[0089] The parameterized configuration module is used to optimize the parameterized configuration data of the equipment model, parameterize the equipment model according to the optimized parameterized configuration data, and generate an abstract evaluation coefficient during equipment operation, extract the difference between the abstract evaluation coefficient within a specified time and its nearest abstract evaluation coefficient reference threshold range boundary value, and compare it with a preset difference threshold to obtain the abstract evaluation coefficient within the target specified time, extract the time interval between each two adjacent abstract evaluation coefficients within the target specified time to obtain a comprehensive evaluation coefficient, compare the comprehensive evaluation coefficient with a preset comprehensive evaluation coefficient threshold, and determine whether the reference threshold range of the abstract evaluation coefficient needs to be adjusted based on the comparison result.

[0090] Data processing module, including:

[0091] The data cleaning module is used to collect and clean the equipment characteristic parameter data, check the data consistency of the equipment characteristic parameter data, remove invalid values ​​or missing values ​​contained in the equipment characteristic parameter data, and determine the characteristic parameter data that is valuable for equipment model construction;

[0092] It should be noted that the consistency check is to check whether the data meets the requirements based on the reasonable value range and mutual relationship of each variable, and to find data that exceeds the normal range, is logically unreasonable or contradictory; for example, if a variable measured by a 1-7 scale has a value of 0, or a negative number appears in weight, they should be considered to be beyond the normal range;

[0093] It should be noted that due to survey, coding and input errors, there may be some invalid values ​​and missing values ​​in the characteristic parameter data of the equipment, which need to be properly processed; the commonly used processing methods are: estimation, whole case deletion, variable deletion and pairwise deletion;

[0094] Among them, estimation is to replace invalid and missing values ​​with the sample mean, median or mode of a variable. This method is simple, but it does not fully consider the existing data in the data, and the error may be large;

[0095] Among them, the whole case deletion is to remove samples with missing values. Since many questionnaires may have missing values, this approach may result in a significant reduction in the effective sample size and fail to fully utilize the collected data. Therefore, it is only suitable for situations where key variables are missing or the proportion of samples with invalid or missing values ​​is very small.

[0096] Among them, variable deletion means that if a variable has many invalid values ​​and missing values, and the variable is not particularly important for the research problem, then the variable can be considered to be deleted; this approach reduces the number of variables for analysis, but does not change the sample size;

[0097] Among them, pairwise deletion uses a special code to represent invalid values ​​and missing values, while retaining all variables and samples in the data set;

[0098] The data integration module is used to integrate the remaining equipment characteristic parameter data valuable for equipment model construction after cleaning;

[0099] Obtain the remaining equipment characteristic parameter data that is valuable for equipment model construction after cleaning, integrate the remaining equipment characteristic parameter data after cleaning, collect, organize and convert the equipment characteristic parameter data in different data sources, and determine the equipment characteristic parameter data of a unified data view;

[0100] It should be noted that by pre-processing the collected equipment characteristic parameter data through cleaning, integration and mining, the accuracy and consistency of the equipment characteristic parameter data can be ensured, thereby improving data processing efficiency and realizing the value of data.

[0101] Model building modules, including:

[0102] A sample acquisition module is used to acquire a plurality of characteristic parameter data training samples of the equipment, and record the acquired plurality of characteristic parameter data training samples as first sample data, wherein the plurality of characteristic parameter data of the equipment includes operation parameter data, structure parameter data, electrical parameter data, chemical parameter data, thermodynamic parameter data and property parameter data;

[0103] A data input module is used to input the processed characteristic parameter data into the equipment characterization script library and the equipment characteristic component model library to generate the equipment characteristic component model;

[0104] The model generation module is used to integrate the equipment feature component models to generate the equipment whole machine model, and build the equipment model that simulates the real behavior of the equipment according to the whole machine model of the equipment. The equipment feature component model library is the equipment feature component model that has been parameterized in the WebGL software, and the motion pins are configured at each position rotation point, and a data interface is left to accept the feature data in the equipment feature size library corresponding to the equipment model selected by the equipment selection and method module;

[0105] The model optimization module is used to optimize the equipment model by using multiple characteristic parameter data training samples of the equipment to obtain the optimized equipment model.

[0106] Model optimization module, including:

[0107] Acquire multiple characteristic parameter data training samples of the equipment, and record the acquired multiple characteristic parameter data training samples as first sample data;

[0108] Extract features from the plurality of first sample data respectively to obtain a plurality of feature vectors corresponding to the plurality of first sample data one by one;

[0109] For any one of the multiple eigenvectors, calculate the value of the augmented entropy loss function corresponding to the eigenvector;

[0110] Filtering out a plurality of second sample data from a plurality of first sample data according to a value of the augmented entropy loss function corresponding to each eigenvector;

[0111] Each second sample data is the first sample data corresponding to a feature vector whose value is less than a preset threshold;

[0112] Based on the plurality of second sample data and the corresponding augmented entropy loss function, the equipment model is optimized to obtain an optimized equipment model.

[0113] The specific process of the model building module includes:

[0114] Input the processed feature parameter data into the equipment characterization script library and the equipment feature component model library to generate the equipment feature component model;

[0115] Integrate the equipment characteristic component models to generate the equipment whole machine model, and build the equipment model that simulates the real behavior of the equipment based on the equipment whole machine model;

[0116] Acquire multiple characteristic parameter data training samples of the equipment, record the acquired multiple characteristic parameter data training samples as first sample data, and select multiple second sample data from the multiple first sample data;

[0117] Based on the plurality of second sample data and the corresponding augmented entropy loss function, the equipment model is optimized to obtain an optimized equipment model.

[0118] Parameterized configuration module, including:

[0119] The template creation module is used to classify the characteristic parameter data of the equipment in detail, define the parameter configuration rules of each characteristic parameter data according to industry standards and specifications, and create a basic model template for each characteristic parameter data for each type of characteristic parameter data;

[0120] A configuration module is used to optimize the parameterized configuration data of the equipment model and perform parameterized configuration of the equipment model according to the optimized parameterized configuration data;

[0121] The early warning module is used to monitor the process of equipment model parameter configuration in real time, ensure that the equipment model parameter configuration is successful within the specified time, and issue early warning prompts in the event of unsuccessful parameter configuration.

[0122] Configuration modules, including:

[0123] Obtaining an original data set set, the original data set set consisting of standard data of digital configuration of each historical characteristic parameter of equipment and minimum data and maximum data of digital configuration of each historical characteristic parameter of equipment;

[0124] According to the parameterized configuration item list, the lowest data and the highest data item of the digitized configuration of each historical characteristic parameter of the equipment are deleted to determine the target data set of the digitized configuration of each historical characteristic parameter of the equipment;

[0125] Edit the target data set of each historical characteristic parameter data configuration of the equipment in the basic model template of each characteristic parameter data to obtain a preset parameter configuration list;

[0126] Screen the preset parameterized configuration list to determine the target data set for the digital configuration of each characteristic parameter of the equipment;

[0127] According to the target data set of the digital configuration of each characteristic parameter of the equipment, the minimum value and the maximum value of the target data of the parameter configuration of the equipment model are obtained;

[0128] If the value of the equipment model parameterized configuration data is between the lowest value and the highest value of the equipment model parameterized configuration target data, then determining a group of parameterized configuration items corresponding to the value of the equipment model parameterized configuration data as optimized parameterized configuration data;

[0129] The equipment model is parameterized according to the optimized parameterized configuration data.

[0130] Early warning module, including:

[0131] When the equipment is started or running, the abstract evaluation coefficient generated in each monitoring cycle is obtained through the data analysis mechanism, and the abstract evaluation coefficient is compared and analyzed with the reference threshold range of the abstract evaluation coefficient;

[0132] If the abstract evaluation coefficient is within the abstract evaluation coefficient reference threshold range within the specified time, a signal of successful parameterized configuration of the equipment model is generated, and efficient adaptation of industrial software compatibility is continued based on the equipment model;

[0133] If the abstract evaluation coefficient is not within the abstract evaluation coefficient reference threshold range within the specified time, an equipment model parameter configuration failure signal is generated, and an early warning prompt is issued for this situation, indicating that the equipment model parameter configuration cannot reach the expected state.

[0134] Working principle: When using the equipment model parameter configuration system of the present invention, according to Figure 1 and Figure 2 , including the following steps:

[0135] Step 1: Acquire characteristic parameter data of equipment and multiple characteristic parameter data training samples of equipment, process the acquired characteristic parameter data of equipment, and integrate the processed characteristic parameter data of equipment;

[0136] Step 2: Input the characteristic parameter data into the equipment characterization script library and the equipment characteristic component model library to generate the equipment characteristic component model, integrate the equipment characteristic component model to generate the equipment whole machine model, and build the equipment model that simulates the real behavior of the equipment according to the equipment whole machine model;

[0137] Step 3: Utilize the acquired multiple characteristic parameter data training samples to optimize the equipment model and obtain an optimized equipment model;

[0138] Step 4: Create a basic model template for each characteristic parameter data and optimize the equipment model parameter configuration data, and parameterize the equipment model according to the optimized parameter configuration data;

[0139] Step 5: When the equipment is started or running, the abstract evaluation coefficient generated in each monitoring cycle is obtained through the data analysis mechanism, and the abstract evaluation coefficient is compared and analyzed with the reference threshold range of the abstract evaluation coefficient. If there is a parameterized configuration failure, an early warning prompt is issued for this situation, indicating that the parameterized configuration of the equipment model cannot reach the expected state.

[0140] Specifically, the early warning module further includes:

[0141] A difference data extraction module is used to extract the difference between the abstract evaluation coefficient within the abstract evaluation coefficient reference threshold range and its nearest abstract evaluation coefficient reference threshold range boundary value within a specified time;

[0142] A difference comparison module, used for comparing the difference with a preset difference threshold;

[0143] The target specified time abstract evaluation coefficient acquisition module is used to retrieve the abstract evaluation coefficient within the specified time corresponding to the difference value being lower than the preset difference threshold value when the difference value is lower than the preset difference threshold value as the abstract evaluation coefficient within the target specified time;

[0144] A time interval extraction module is used to extract the time interval between the abstract evaluation coefficients of each two adjacent targets within a specified time;

[0145] A comprehensive evaluation coefficient acquisition module, used to obtain a comprehensive evaluation coefficient by combining the abstract evaluation coefficient within the target specified time with the time interval between each two adjacent abstract evaluation coefficients within the target specified time;

[0146] The comprehensive evaluation coefficient is obtained by the following formula:

[0147]

[0148] Among them, U represents the comprehensive evaluation coefficient; n represents the number of abstract evaluation coefficients within the target specified time; S i represents the coefficient value corresponding to the abstract evaluation coefficient within the specified time of the i-th target; T b represents the standard deviation corresponding to m time intervals; T p represents the average value corresponding to m time intervals; S b represents the standard deviation of the coefficients corresponding to the abstract evaluation coefficients of n targets within a specified time; S ci represents the difference between the abstract evaluation coefficient of the i-th target within the specified time and the boundary value of the abstract evaluation coefficient reference threshold range most recently; S cb represents the standard deviation of the difference between the abstract evaluation coefficients of n targets within a specified time and the boundary value of the reference threshold range of the abstract evaluation coefficients; m represents the total number of time intervals between the abstract evaluation coefficients of each adjacent target within a specified time; T i represents the time length value corresponding to the i-th time interval; S 01i and S 02i They represent the values ​​of the abstract evaluation coefficients of the two adjacent targets within the specified time corresponding to the i-th time interval;

[0149] An evaluation coefficient comparison module, used for comparing the comprehensive evaluation coefficient with a preset comprehensive evaluation coefficient threshold;

[0150] The range adjustment judgment module is used to determine that the abstract evaluation coefficient reference threshold range needs to be adjusted when the comprehensive evaluation coefficient exceeds the preset comprehensive evaluation coefficient threshold.

[0151] The technical effect of the above technical solution is: through the difference data extraction module and the difference comparison module, the slight changes between the abstract evaluation coefficient and its reference threshold range boundary can be accurately captured. This refined monitoring helps to timely discover potential problems or trends. When the difference is lower than the preset difference threshold, the abstract evaluation coefficient acquisition module within the target specified time can quickly locate and extract relevant data, providing an accurate basis for subsequent comprehensive evaluation. The range adjustment judgment module realizes the dynamic adjustment of the reference threshold range of the abstract evaluation coefficient based on the comparison result between the comprehensive evaluation coefficient and the preset threshold, ensuring the flexibility and adaptability of the evaluation system. The comprehensive evaluation coefficient acquisition module combines the multiple dimensional information of the abstract evaluation coefficient and the time interval within the target specified time, and calculates the comprehensive evaluation coefficient through the above formula, which greatly improves the accuracy and comprehensiveness of the evaluation. The formula takes into account multiple factors such as the coefficient value, the standard deviation and average value of the time interval, the coefficient standard deviation, and the difference standard deviation. The comprehensive consideration of these factors makes the evaluation results more objective and scientific. Through modular design, the technical solution realizes the independent operation and collaborative work of each functional module, which greatly improves the efficiency and accuracy of the evaluation. At the same time, through the preset difference threshold and comprehensive evaluation coefficient threshold, the corresponding operations (such as retrieving data, calculating comprehensive evaluation coefficients, judging whether thresholds need to be adjusted, etc.) can be automatically triggered, reducing manual intervention and improving the automation level of evaluation. The various modules and formula designs in this technical solution have certain flexibility and scalability, and can be customized and adjusted according to the needs of actual application scenarios.

[0152] In summary, the technical effects of the above technical solutions in terms of performance indicators are mainly reflected in accurate early warning and dynamic adjustment, enhanced comprehensive assessment capabilities, improved assessment efficiency and accuracy, and strong adaptability and scalability. These technical effects have jointly improved the scientificity and practicality of the assessment system and provided strong support for decision-making and management in related fields.

[0153] Specifically, the range adjustment judgment module includes:

[0154] A first abstract evaluation coefficient retrieval module, configured to extract the abstract evaluation coefficient within a specified time within a reference threshold range of the abstract evaluation coefficient when the comprehensive evaluation coefficient exceeds the preset comprehensive evaluation coefficient threshold;

[0155] A first evaluation coefficient indicator parameter acquisition module, used to acquire a first evaluation coefficient indicator parameter using the abstract evaluation coefficient within a specified time range within the abstract evaluation coefficient reference threshold value;

[0156] The first evaluation coefficient index parameter is obtained by the following formula:

[0157]

[0158] Among them, P 01 represents the first evaluation coefficient indicator parameter; k represents the number of abstract evaluation coefficients within the specified time within the abstract evaluation coefficient reference threshold range; S ki represents the value of the abstract evaluation coefficient within the specified time within the reference threshold range of the abstract evaluation coefficient; S kci represents the difference between the i-th abstract evaluation coefficient within the abstract evaluation coefficient reference threshold range within the specified time and its nearest abstract evaluation coefficient reference threshold range boundary value; S kcbi represents the standard deviation of the difference between the i-th abstract evaluation coefficient within the abstract evaluation coefficient reference threshold range and its nearest abstract evaluation coefficient reference threshold range boundary value within the specified time; S cb It represents the standard deviation of the difference between the abstract evaluation coefficient of n targets within a specified time and the boundary value of the abstract evaluation coefficient reference threshold range; S kcb It represents the standard deviation of the difference between k abstract evaluation coefficients within the abstract evaluation coefficient reference threshold range within a specified time and their nearest abstract evaluation coefficient reference threshold range boundary value;

[0159] a coefficient indicator parameter comparison module, configured to compare the first evaluation coefficient indicator parameter with a preset first coefficient evaluation parameter threshold;

[0160] a first abstract evaluation coefficient reference threshold range adjustment execution module, configured to adjust the abstract evaluation coefficient reference threshold range using the first evaluation coefficient indicator parameter when the first evaluation coefficient indicator parameter does not exceed a preset first coefficient evaluation parameter threshold, and obtain an adjusted abstract evaluation coefficient reference threshold range;

[0161] The upper limit and lower limit corresponding to the adjusted abstract evaluation coefficient reference threshold range are obtained by the following formula:

[0162]

[0163] Among them, X up and X down Indicates the upper and lower limits of the adjusted abstract evaluation coefficient reference threshold range; X up0 and X down0 represents the upper and lower limits of the reference threshold range of the abstract evaluation coefficient before adjustment; P 01 represents the first evaluation coefficient indicator parameter;

[0164] The range adjustment module is used to adjust the abstract evaluation coefficient reference threshold range by using the abstract evaluation coefficient within the specified time that is not within the abstract evaluation coefficient reference threshold range when the first evaluation coefficient indicator parameter exceeds the preset first coefficient evaluation parameter threshold.

[0165] The technical effect of the above technical solution is that when the comprehensive evaluation coefficient exceeds the preset threshold, the first abstract evaluation coefficient retrieval module can quickly extract the abstract evaluation coefficient within the specified time within the reference threshold range of the abstract evaluation coefficient, providing an accurate data basis for subsequent analysis and adjustment. Through the first evaluation coefficient indicator parameter acquisition module, the first evaluation coefficient indicator parameter is calculated using the above formula. The parameter comprehensively considers multiple dimensions such as the value, difference and standard deviation of the abstract evaluation coefficient, and realizes the refined analysis of the evaluation coefficient. The coefficient indicator parameter comparison module and the first abstract evaluation coefficient reference threshold range adjustment execution module in the range adjustment judgment module can flexibly adjust the abstract evaluation coefficient reference threshold range according to the comparison result between the first evaluation coefficient indicator parameter and the preset threshold, thereby enhancing the adaptability and accuracy of the evaluation system. The multiple parameters (such as difference, difference standard deviation, etc.) and complex calculation process introduced in the formula enable the first evaluation coefficient indicator parameter to more comprehensively reflect the characteristics and trends of the abstract evaluation coefficient, thereby improving the accuracy and reliability of the evaluation. Through the upper limit and lower limit formulas corresponding to the adjusted reference threshold range of the abstract evaluation coefficient, the threshold range can be quantitatively adjusted according to the first evaluation coefficient indicator parameter, thereby avoiding the subjectivity and uncertainty of human intervention. This technical solution realizes automatic adjustment and monitoring of the reference threshold range of the abstract evaluation coefficient through modular design and automated processes, reducing the complexity and workload of manual operations. When the first evaluation coefficient indicator parameter exceeds the preset threshold, the range adjustment module can automatically adjust the abstract evaluation coefficient within the specified time that is not within the reference threshold range of the abstract evaluation coefficient, reflecting the characteristics of intelligence. The formula and parameter design in this technical solution have certain flexibility and scalability, and can be adjusted and optimized according to the needs of actual application scenarios.

[0166] In summary, the technical effects of the above technical solutions on performance indicators are mainly reflected in fine-tuning and adaptability, improving assessment accuracy and reliability, automation and intelligence, as well as scalability and flexibility. These technical effects jointly enhance the scientificity and practicality of the assessment system and provide strong support for decision-making and management in related fields.

[0167] Specifically, the range adjustment module includes:

[0168] A second abstract evaluation coefficient retrieving module, configured to retrieve an abstract evaluation coefficient within a specified time period that is not within a range of an abstract evaluation coefficient reference threshold value when the first evaluation coefficient indicator parameter exceeds a preset first coefficient evaluation parameter threshold value;

[0169] A second evaluation coefficient indicator parameter acquisition module, used to acquire a second evaluation coefficient indicator parameter using the abstract evaluation coefficient within the specified time that is not within the abstract evaluation coefficient reference threshold range;

[0170] The second evaluation coefficient index parameter is obtained by the following formula:

[0171]

[0172] Among them, P 02 represents the second evaluation coefficient indicator parameter; k represents the number of abstract evaluation coefficients within the specified time within the abstract evaluation coefficient reference threshold range; S ki represents the value of the abstract evaluation coefficient within the specified time within the reference threshold range of the abstract evaluation coefficient; S kci represents the difference between the abstract evaluation coefficient within the i-th specified time within the abstract evaluation coefficient reference threshold range and its nearest abstract evaluation coefficient reference threshold range boundary value; r represents the number of abstract evaluation coefficients within the specified time that are not within the abstract evaluation coefficient reference threshold range; S ri represents the value of the abstract evaluation coefficient within the specified time that is not within the reference threshold range of the abstract evaluation coefficient; S rci represents the difference between the i-th abstract evaluation coefficient within the specified time that is not within the abstract evaluation coefficient reference threshold range and its nearest abstract evaluation coefficient reference threshold range boundary value; S kcbi represents the standard deviation of the difference between the i-th abstract evaluation coefficient within the abstract evaluation coefficient reference threshold range and its nearest abstract evaluation coefficient reference threshold range boundary value within the specified time; S cb It represents the standard deviation of the difference between the abstract evaluation coefficient of n targets within a specified time and the boundary value of the abstract evaluation coefficient reference threshold range; S rcb represents the standard deviation of the difference between the abstract evaluation coefficients within a specified time period that are not within the abstract evaluation coefficient reference threshold range and their nearest abstract evaluation coefficient reference threshold range boundary values; S rbi represents the numerical standard deviation of the abstract evaluation coefficient within the specified time when the i-th abstract evaluation coefficient is not within the reference threshold range; S kb represents the standard deviation of the values ​​of the abstract evaluation coefficients within the reference threshold range of the abstract evaluation coefficients within a specified time;

[0173] A first evaluation coefficient indicator parameter retrieving module, used to retrieve the first evaluation coefficient indicator parameter;

[0174] A second abstract evaluation coefficient reference threshold range adjustment execution module is used to adjust the abstract evaluation coefficient reference threshold range by using the first evaluation coefficient indicator parameter and the second evaluation coefficient indicator parameter to obtain an adjusted abstract evaluation coefficient reference threshold range;

[0175] The upper limit and lower limit corresponding to the adjusted abstract evaluation coefficient reference threshold range are obtained by the following formula:

[0176]

[0177] Among them, X up and X down Indicates the upper and lower limits of the adjusted abstract evaluation coefficient reference threshold range; X up0 and X down0 represents the upper and lower limits of the reference threshold range of the abstract evaluation coefficient before adjustment; P 01 Represents the first evaluation coefficient index parameter; P 02 Represents the second evaluation coefficient indicator parameter.

[0178] The technical effect of the above technical solution is: the technical solution comprehensively analyzes and evaluates the abstract evaluation coefficient within the specified time that is not within the reference threshold range of the abstract evaluation coefficient through the second abstract evaluation coefficient retrieval module and the second evaluation coefficient index parameter acquisition module. This not only takes into account the coefficients within the threshold range, but also incorporates the coefficients beyond the threshold range, thereby providing a more comprehensive evaluation perspective. The formula comprehensively considers a variety of factors, such as coefficient values, differences, standard deviations of differences, etc., so that the second evaluation coefficient index parameter can more accurately reflect the overall characteristics and trends of the evaluation coefficient. When the first evaluation coefficient index parameter exceeds the preset first coefficient evaluation parameter threshold, the range adjustment module can automatically trigger the second abstract evaluation coefficient retrieval and the calculation of the second evaluation coefficient index parameter, reflecting the characteristics of dynamic adjustment. Through the joint action of the first evaluation coefficient index parameter and the second evaluation coefficient index parameter, the second abstract evaluation coefficient reference threshold range adjustment execution module can make more accurate and reasonable adjustments to the abstract evaluation coefficient reference threshold range, thereby enhancing the adaptability and flexibility of the evaluation system. The introduction of the above formula and multiple parameters enables the second evaluation coefficient index parameter to more comprehensively reflect the actual situation of the evaluation coefficient, thereby improving the accuracy and reliability of the evaluation. The upper and lower limit formulas corresponding to the adjusted abstract evaluation coefficient reference threshold range avoid the subjectivity and uncertainty of human intervention through quantitative adjustment, further improving the objectivity of the evaluation results. This technical solution realizes the automatic adjustment and monitoring of the abstract evaluation coefficient reference threshold range through modular design and automated processes, reducing the complexity and workload of manual operations. When the evaluation index parameter exceeds the preset threshold, the corresponding adjustment process can be automatically triggered, reflecting the characteristics of intelligence.

[0179] The formula and parameter design in this technical solution have certain flexibility and scalability, and can be adjusted and optimized according to the needs of actual application scenarios.

[0180] In summary, the technical effects of the above technical solutions on performance indicators are mainly reflected in comprehensive evaluation and adjustment mechanisms, dynamic adjustment and adaptability, improved evaluation accuracy and reliability, automation and intelligence, as well as scalability and flexibility. These technical effects jointly enhance the scientificity and practicality of the evaluation system and provide strong support for decision-making and management in related fields. At the same time, the technical solution also demonstrates that when dealing with complex evaluation problems, the accuracy and reliability of the evaluation can be effectively improved by comprehensively considering multiple factors and introducing quantitative adjustment methods.

[0181] In summary, the equipment model parameter configuration system of the present invention can ensure the accuracy and consistency of the equipment characteristic parameter data by pre-processing the cleaning, integration and mining of the collected equipment characteristic parameter data, thereby improving the data processing efficiency and the value of the data. By optimizing the equipment model, it can better adapt to different data sets, reduce prediction errors, make the results closer to the actual situation, improve the generalization ability of the equipment model, and enable the equipment model to make accurate predictions when facing new data, thereby enhancing its applicability in practical applications. By optimizing the equipment model, the calculation complexity of the model can be reduced, the operation efficiency of the model can be improved, and the calculation time can be reduced. It can also speed up the operation of the model and improve the overall performance. In the equipment manufacturing industry, the automation and intelligence of the production process can be achieved by optimizing the production process and equipment management. Technical means such as intelligent production scheduling, automated quality detection and equipment predictive maintenance can reduce waiting time and resource waste in production and significantly improve production efficiency. Optimizing parameters during parametric configuration of equipment models can improve the efficiency and performance of equipment, reduce waste of energy and raw materials, extend the service life of equipment, improve the quality and efficiency of the production process, reduce production and maintenance costs, reduce failure rates, and ensure the stability and continuity of the equipment production process.

[0182] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or equipment including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or equipment.

[0183] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. Equipment model parameterized configuration system, characterized in that: include: A data processing module is used to obtain characteristic parameter data of equipment, process the obtained characteristic parameter data of equipment, and integrate the processed characteristic parameter data of equipment; A model building module is used to input characteristic parameter data into the equipment characterization script library and the equipment characteristic component model library to generate equipment characteristic component models, integrate the equipment characteristic component models to generate equipment whole machine models, and build equipment models that simulate the real behavior of the equipment based on the equipment whole machine models; The parameterized configuration module is used to optimize the parameterized configuration data of the equipment model, parameterize the equipment model according to the optimized parameterized configuration data, and generate an abstract evaluation coefficient during equipment operation, extract the difference between the abstract evaluation coefficient within a specified time and its nearest abstract evaluation coefficient reference threshold range boundary value, and compare it with a preset difference threshold to obtain the abstract evaluation coefficient within the target specified time, extract the time interval between each two adjacent abstract evaluation coefficients within the target specified time to obtain a comprehensive evaluation coefficient, compare the comprehensive evaluation coefficient with a preset comprehensive evaluation coefficient threshold, and determine whether the reference threshold range of the abstract evaluation coefficient needs to be adjusted based on the comparison result.

2. The equipment model parameter configuration system according to claim 1, characterized in that: The data processing module comprises: The data cleaning module is used to collect and clean the equipment characteristic parameter data, check the data consistency of the equipment characteristic parameter data, remove invalid values ​​or missing values ​​contained in the equipment characteristic parameter data, and determine the characteristic parameter data that is valuable for equipment model construction; The data integration module is used to integrate the remaining equipment characteristic parameter data valuable for equipment model construction after cleaning, and determine the equipment characteristic parameter data of a unified data view.

3. The equipment model parameter configuration system according to claim 1, characterized in that: The model building module comprises: A sample acquisition module is used to acquire a plurality of characteristic parameter data training samples of the equipment, and record the acquired plurality of characteristic parameter data training samples as first sample data, wherein the plurality of characteristic parameter data of the equipment includes operation parameter data, structure parameter data, electrical parameter data, chemical parameter data, thermodynamic parameter data and property parameter data; A data input module is used to input the processed characteristic parameter data into the equipment characterization script library and the equipment characteristic component model library to generate the equipment characteristic component model; The model generation module is used to integrate the equipment characteristic component models to generate the equipment whole machine model, and to build the equipment model that simulates the real behavior of the equipment based on the equipment whole machine model; A model optimization module is used to optimize the equipment model by using multiple characteristic parameter data training samples of the equipment to obtain an optimized equipment model; The model optimization module comprises: Acquire multiple characteristic parameter data training samples of the equipment, and record the acquired multiple characteristic parameter data training samples as first sample data; Extract features from the plurality of first sample data respectively to obtain a plurality of feature vectors corresponding to the plurality of first sample data one by one; For any one of the multiple eigenvectors, calculate the value of the augmented entropy loss function corresponding to the eigenvector; Filtering out a plurality of second sample data from a plurality of first sample data according to a value of the augmented entropy loss function corresponding to each eigenvector; Each second sample data is the first sample data corresponding to a feature vector whose value is less than a preset threshold; Based on the plurality of second sample data and the corresponding augmented entropy loss function, the equipment model is optimized to obtain an optimized equipment model.

4. The equipment model parameter configuration system according to claim 3, characterized in that: The specific process of the model building module includes: Input the processed feature parameter data into the equipment characterization script library and the equipment feature component model library to generate the equipment feature component model; Integrate the equipment characteristic component models to generate the equipment whole machine model, and build the equipment model that simulates the real behavior of the equipment based on the equipment whole machine model; Acquire multiple characteristic parameter data training samples of the equipment, record the acquired multiple characteristic parameter data training samples as first sample data, and select multiple second sample data from the multiple first sample data; Based on the plurality of second sample data and the corresponding augmented entropy loss function, the equipment model is optimized to obtain an optimized equipment model.

5. The equipment model parameter configuration system according to claim 1, characterized in that: The parameterized configuration module includes: The template creation module is used to classify the characteristic parameter data of the equipment in detail, define the parameter configuration rules of each characteristic parameter data according to industry standards and specifications, and create a basic model template for each characteristic parameter data for each type of characteristic parameter data; A configuration module is used to optimize the parameterized configuration data of the equipment model and perform parameterized configuration of the equipment model according to the optimized parameterized configuration data; The early warning module is used to monitor the process of equipment model parameter configuration in real time, ensure that the equipment model parameter configuration is successful within the specified time, and issue early warning prompts in the event of unsuccessful parameter configuration.

6. The equipment model parameter configuration system according to claim 5, characterized in that: The configuration module includes: Obtaining an original data set set, the original data set set consisting of standard data of digital configuration of each historical characteristic parameter of equipment and minimum data and maximum data of digital configuration of each historical characteristic parameter of equipment; According to the parameterized configuration item list, the lowest data and the highest data item of the digitized configuration of each historical characteristic parameter of the equipment are deleted to determine the target data set of the digitized configuration of each historical characteristic parameter of the equipment; Edit the target data set of each historical characteristic parameter data configuration of the equipment in the basic model template of each characteristic parameter data to obtain a preset parameter configuration list; Screen the preset parameterized configuration list to determine the target data set for the digital configuration of each characteristic parameter of the equipment; According to the target data set of the digital configuration of each characteristic parameter of the equipment, the minimum value and the maximum value of the target data of the parameter configuration of the equipment model are obtained; If the value of the equipment model parameterized configuration data is between the lowest value and the highest value of the equipment model parameterized configuration target data, then determining a group of parameterized configuration items corresponding to the value of the equipment model parameterized configuration data as optimized parameterized configuration data; The equipment model is parameterized according to the optimized parameterized configuration data.

7. The equipment model parameter configuration system according to claim 5, characterized in that: The early warning module comprises: When the equipment is started or running, the abstract evaluation coefficient generated in each monitoring cycle is obtained through the data analysis mechanism, and the abstract evaluation coefficient is compared and analyzed with the reference threshold range of the abstract evaluation coefficient; If the abstract evaluation coefficient is within the abstract evaluation coefficient reference threshold range within the specified time, a signal of successful parameterized configuration of the equipment model is generated, and efficient adaptation of industrial software compatibility is continued based on the equipment model; If the abstract evaluation coefficient is not within the abstract evaluation coefficient reference threshold range within the specified time, an equipment model parameter configuration failure signal is generated, and an early warning prompt is issued for this situation, indicating that the equipment model parameter configuration cannot reach the expected state.

8. The equipment model parameter configuration system according to claim 7, characterized in that: The early warning module further includes: A difference data extraction module is used to extract the difference between the abstract evaluation coefficient within the abstract evaluation coefficient reference threshold range and its nearest abstract evaluation coefficient reference threshold range boundary value within a specified time; A difference comparison module, used for comparing the difference with a preset difference threshold; The target specified time abstract evaluation coefficient acquisition module is used to retrieve the abstract evaluation coefficient within the specified time corresponding to the difference value being lower than the preset difference threshold value when the difference value is lower than the preset difference threshold value as the abstract evaluation coefficient within the target specified time; A time interval extraction module is used to extract the time interval between the abstract evaluation coefficients of each two adjacent targets within a specified time; A comprehensive evaluation coefficient acquisition module, used to obtain a comprehensive evaluation coefficient by combining the abstract evaluation coefficient within the target specified time with the time interval between each two adjacent abstract evaluation coefficients within the target specified time; The comprehensive evaluation coefficient is obtained by the following formula: ； Among them, U represents the comprehensive evaluation coefficient; n represents the number of abstract evaluation coefficients within the target specified time; S i represents the coefficient value corresponding to the abstract evaluation coefficient within the specified time of the i-th target; T b represents the standard deviation corresponding to m time intervals; T p represents the average value corresponding to m time intervals; S b represents the standard deviation of the coefficients corresponding to the abstract evaluation coefficients of n targets within a specified time; S ci represents the difference between the abstract evaluation coefficient of the i-th target within the specified time and the boundary value of the abstract evaluation coefficient reference threshold range most recently; S cb represents the standard deviation of the difference between the abstract evaluation coefficients of n targets within a specified time and the boundary value of the reference threshold range of the abstract evaluation coefficients; m represents the total number of time intervals between the abstract evaluation coefficients of each adjacent target within a specified time; T i represents the time length value corresponding to the i-th time interval; S 01i and S 02i They represent the values ​​of the abstract evaluation coefficients of the two adjacent targets within the specified time corresponding to the i-th time interval; An evaluation coefficient comparison module, used for comparing the comprehensive evaluation coefficient with a preset comprehensive evaluation coefficient threshold; The range adjustment judgment module is used to determine that the abstract evaluation coefficient reference threshold range needs to be adjusted when the comprehensive evaluation coefficient exceeds the preset comprehensive evaluation coefficient threshold.

9. The equipment model parameter configuration system according to claim 8, characterized in that: The range adjustment judgment module includes: A first abstract evaluation coefficient retrieval module, configured to extract the abstract evaluation coefficient within a specified time within a reference threshold range of the abstract evaluation coefficient when the comprehensive evaluation coefficient exceeds the preset comprehensive evaluation coefficient threshold; A first evaluation coefficient indicator parameter acquisition module, used to acquire a first evaluation coefficient indicator parameter using the abstract evaluation coefficient within a specified time range within the abstract evaluation coefficient reference threshold value; The first evaluation coefficient index parameter is obtained by the following formula: ； Among them, P 01 represents the first evaluation coefficient indicator parameter; k represents the number of abstract evaluation coefficients within the specified time within the abstract evaluation coefficient reference threshold range; S ki represents the value of the abstract evaluation coefficient within the specified time within the reference threshold range of the abstract evaluation coefficient; S kci represents the difference between the i-th abstract evaluation coefficient within the abstract evaluation coefficient reference threshold range within the specified time and its nearest abstract evaluation coefficient reference threshold range boundary value; S kcbi represents the standard deviation of the difference between the i-th abstract evaluation coefficient within the abstract evaluation coefficient reference threshold range and its nearest abstract evaluation coefficient reference threshold range boundary value within the specified time; S cb It represents the standard deviation of the difference between the abstract evaluation coefficient of n targets within a specified time and the boundary value of the abstract evaluation coefficient reference threshold range; S kcb It represents the standard deviation of the difference between k abstract evaluation coefficients within the abstract evaluation coefficient reference threshold range within a specified time and their nearest abstract evaluation coefficient reference threshold range boundary value; a coefficient indicator parameter comparison module, configured to compare the first evaluation coefficient indicator parameter with a preset first coefficient evaluation parameter threshold; a first abstract evaluation coefficient reference threshold range adjustment execution module, configured to adjust the abstract evaluation coefficient reference threshold range using the first evaluation coefficient indicator parameter when the first evaluation coefficient indicator parameter does not exceed a preset first coefficient evaluation parameter threshold, and obtain an adjusted abstract evaluation coefficient reference threshold range; The upper limit and lower limit corresponding to the adjusted abstract evaluation coefficient reference threshold range are obtained by the following formula: ； Among them, X up and X down Indicates the upper and lower limits of the adjusted abstract evaluation coefficient reference threshold range; X up0 and X down0 represents the upper and lower limits of the reference threshold range of the abstract evaluation coefficient before adjustment; P 01 represents the first evaluation coefficient indicator parameter; The range adjustment module is used to adjust the abstract evaluation coefficient reference threshold range by using the abstract evaluation coefficient within the specified time that is not within the abstract evaluation coefficient reference threshold range when the first evaluation coefficient indicator parameter exceeds the preset first coefficient evaluation parameter threshold.

10. The equipment model parameter configuration system according to claim 9, characterized in that: The range adjustment module comprises: A second abstract evaluation coefficient retrieving module, configured to retrieve an abstract evaluation coefficient within a specified time period that is not within a range of an abstract evaluation coefficient reference threshold value when the first evaluation coefficient indicator parameter exceeds a preset first coefficient evaluation parameter threshold value; A second evaluation coefficient indicator parameter acquisition module, used to acquire a second evaluation coefficient indicator parameter using the abstract evaluation coefficient within the specified time that is not within the abstract evaluation coefficient reference threshold range; The second evaluation coefficient index parameter is obtained by the following formula: ； Among them, P 02 represents the second evaluation coefficient indicator parameter; k represents the number of abstract evaluation coefficients within the specified time within the abstract evaluation coefficient reference threshold range; S ki represents the value of the abstract evaluation coefficient within the specified time within the reference threshold range of the abstract evaluation coefficient; S kci represents the difference between the abstract evaluation coefficient within the i-th specified time within the abstract evaluation coefficient reference threshold range and its nearest abstract evaluation coefficient reference threshold range boundary value; r represents the number of abstract evaluation coefficients within the specified time that are not within the abstract evaluation coefficient reference threshold range; S ri represents the value of the abstract evaluation coefficient within the specified time that is not within the reference threshold range of the abstract evaluation coefficient; S rci represents the difference between the i-th abstract evaluation coefficient within the specified time that is not within the abstract evaluation coefficient reference threshold range and its nearest abstract evaluation coefficient reference threshold range boundary value; S kcbi represents the standard deviation of the difference between the i-th abstract evaluation coefficient within the abstract evaluation coefficient reference threshold range and its nearest abstract evaluation coefficient reference threshold range boundary value within the specified time; S cb It represents the standard deviation of the difference between the abstract evaluation coefficient of n targets within a specified time and the boundary value of the abstract evaluation coefficient reference threshold range; S rcb represents the standard deviation of the difference between the abstract evaluation coefficients within a specified time period that are not within the abstract evaluation coefficient reference threshold range and their nearest abstract evaluation coefficient reference threshold range boundary values; S rbi represents the numerical standard deviation of the abstract evaluation coefficient within the specified time when the i-th abstract evaluation coefficient is not within the reference threshold range; S kb represents the standard deviation of the values ​​of the abstract evaluation coefficients within the reference threshold range of the abstract evaluation coefficients within a specified time; A first evaluation coefficient indicator parameter retrieving module, used to retrieve the first evaluation coefficient indicator parameter; A second abstract evaluation coefficient reference threshold range adjustment execution module is used to adjust the abstract evaluation coefficient reference threshold range by using the first evaluation coefficient indicator parameter and the second evaluation coefficient indicator parameter to obtain an adjusted abstract evaluation coefficient reference threshold range; The upper limit and lower limit corresponding to the adjusted abstract evaluation coefficient reference threshold range are obtained by the following formula: ； Among them, X up and X down Indicates the upper and lower limits of the adjusted abstract evaluation coefficient reference threshold range; X up0 and X down0 represents the upper and lower limits of the reference threshold range of the abstract evaluation coefficient before adjustment; P 01 Represents the first evaluation coefficient index parameter; P 02 Represents the second evaluation coefficient indicator parameter.

Images