An intelligent industrial control board screen parameter setting system and method

Abstract

The present invention belongs to the technical field of automatic control. The present invention discloses an intelligent industrial control board screen parameter setting system and method; an intelligent screen parameter configuration assistant is constructed. The intelligent screen parameter configuration assistant includes a parameter configuration module for collecting display screen parameter data of different models and corresponding screen parameter setting data; preprocessing the display screen parameter data of different models and the corresponding screen parameter setting data to obtain a screen parameter template database; extracting features from the data in the screen parameter template database to obtain a comprehensive feature data set; a command parsing module for obtaining a configuration command and parsing it through the intelligent screen parameter configuration assistant to determine the command type; an automatic adaptation module for executing the command and performing screen parameter setting matching; a display effect evaluation model is constructed, and the obtained comprehensive feature data set is input into the trained display effect evaluation model to obtain the display effect of the display screen; the workload and time of manual configuration are reduced, and the configuration efficiency is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic control, and more specifically, to an intelligent industrial control board screen parameter setting system and method. Background Art

[0002] In today's industrial automation field, as a core component, the industrial control board is widely used in various industrial equipment and production lines, responsible for realizing functions such as automatic control, data processing, and communication of the equipment. With the advancement of Industry 4.0 and intelligent manufacturing, the performance and function requirements of the industrial control board are getting higher and higher, and its supporting display screen has increasingly become an important interface for operators to interact with the equipment.

[0003] The patent with the application publication number CN111708502A discloses a screen adaptation method and device. The method includes: for each pre-set display screen pixel parameter type, generating a corresponding configuration file respectively; according to the configuration file corresponding to the display screen pixel width type of the current device, performing screen adaptation on the image to be displayed; wherein, the display screen pixel parameter type includes the pixel parameter type of a standard size display screen and the pixel parameter type of a non-standard size display screen; the configuration file contains an equal ratio calculated according to the display screen pixel parameter type corresponding to the configuration file and the set reference display screen pixel parameter type. The above technical solution can perform screen adaptation on the image according to the pixel parameter type of the display screen.

[0004] For existing industrial control boards, it is necessary to separately build versions according to the interface mode, resolution, refresh rate, etc. of the display screen. If multiple display screens are assembled, multiple software versions need to be maintained simultaneously, resulting in an increase in the workload and cost of software version maintenance; different brands and models of display screens often have different parameter settings, and compatibility testing and configuration between the industrial control board and the display screen often require professional developers to provide on-site technical support, resulting in more technical support costs being invested during the operation of the product;

[0005] If features with variances less than the variance threshold are not removed, the model may be interfered by noise and unimportant information, resulting in a decrease in prediction accuracy. If the linear correlation between the remaining features and the target variable is not evaluated, features that have an important impact on model prediction may be ignored, which also affects the model performance; if the target trigger function is not preset, the data processing process may not be flexible enough to automatically adjust the preprocessing strategy according to the changes in real-time data.

[0006] In view of this, the present invention proposes an intelligent industrial control board screen parameter setting system and method to solve the above problems. Summary of the Invention

[0007] To overcome the above defects of the prior art and to achieve the above object, the present invention provides the following technical solution: An intelligent industrial control board screen parameter setting system, comprising: constructing an intelligent screen parameter configuration assistant, and the intelligent screen parameter configuration assistant includes:

[0008] A parameter configuration module, configured to collect display screen parameter data of different models and corresponding screen parameter setting data; preprocess the display screen parameter data of different models and the corresponding screen parameter setting data to obtain a screen parameter template database; extract features from the data in the screen parameter template database to obtain a comprehensive feature data set;

[0009] A command parsing module, configured to obtain a configuration command and parse it through the intelligent screen parameter configuration assistant to determine the command type;

[0010] An automatic adaptation module, configured to execute the command and perform screen parameter setting matching; construct a display effect evaluation model, input the obtained comprehensive feature data set into the trained display effect evaluation model to obtain the display effect of the display screen;

[0011] An effect evaluation module, configured to compare the predicted display effect with a preset display effect threshold to determine whether the matched screen parameter setting data is applicable to the currently connected display screen; if it does not exceed the preset threshold, the matched screen parameter setting data is applicable to the currently connected display screen; if it exceeds the preset threshold, the matched screen parameter setting data is not applicable to the currently connected display screen;

[0012] A screen parameter setting optimization module, configured to, when the matched screen parameter setting data is not applicable to the currently connected display screen, send a calibration instruction through the intelligent screen parameter configuration terminal to reconfigure the screen parameter setting data to match the connected display screen; each module is connected in a wired and / or wireless manner.

[0013] Further, the parameter data of the different model display screens includes resolution, refresh rate, screen model, interface type, pixel depth, and timing parameters; the screen parameter setting data includes default screen parameter setting data and user preference data;

[0014] The default screen parameter setting data includes screen color configuration, contrast setting, brightness adjustment, and color temperature setting; the user preference data includes the user-preferred screen color configuration, contrast setting, brightness adjustment, and color temperature setting.

[0015] Further, the method for preprocessing the display screen parameter data of different models and the corresponding screen parameter setting data includes;

[0016] Identifying and removing abnormal data in the display screen parameter data and the corresponding screen parameter setting data through the LOF algorithm to obtain a processed display screen parameter feature data set and a corresponding screen parameter setting feature data set;

[0017] Normalize the display screen parameter feature data set and the corresponding screen parameter setting feature data set, convert them into a standard normal distribution, and obtain the normalized display screen parameter feature data set and the corresponding screen parameter setting feature data set; integrate the normalized display screen parameter feature data set and the corresponding screen parameter setting feature data set to obtain a screen parameter template database.

[0018] Further, the method for extracting feature data from the data in the screen parameter template database to obtain a comprehensive feature data set includes:

[0019] The data in the screen parameter template database includes a display screen parameter feature data set and a corresponding screen parameter setting feature data set; a preset variance threshold is θ, and the data in the screen parameter template database is used with a variance threshold formula to remove features with a variance less than the variance threshold θ, obtaining the remaining features X;

[0020] The variance threshold formula is: ; where X j is the data feature in the jth screen parameter template database; x i is the ith data point; n is the total number of data points; μ is the mean of the data in the screen parameter template database;

[0021] Preset a target variable as Y, and calculate the Pearson correlation coefficient r between the remaining features X and the target variable Y to evaluate the linear correlation between the two;

[0022] The specific formula is ; where X i and Y i are the ith remaining feature value and the target variable value respectively, and are the remaining feature mean and the target variable mean respectively; i is the index of the feature value;

[0023] Use the recursive feature elimination method to remove unimportant features, and select the most unimportant feature in each iteration; use the principal component analysis method for dimensionality reduction to reduce the number of features by retaining the largest variance in the data;

[0024] Preset a target trigger function, and when the running target trigger function reaches the influence coefficient threshold of the preset association model, automatically trigger the principal component analysis to preprocess the remaining features;

[0025] The association model is:

[0026] ; where Y' is the dependent variable of the association model; P(Y' = 1) is the probability that the dependent variable of the association model is 1; is the value of the dependent variable when the independent variable of the association model is 0; is the independent variable of the correlation model; is the coefficient of the independent variable;

[0027] The target trigger function is:

[0028] ; where b 1 is the dataset of display screen parameter features obtained in real time; is the preset dataset of display screen parameter features; b 2 is the dataset of screen parameter setting features obtained in real time; is the preset dataset of screen parameter setting features;

[0029] Calculate the covariance matrix, eigenvalues, and eigenvectors of the remaining features through the covariance calculation formula, and project the data into a new feature space composed of the remaining eigenvectors; the covariance calculation formula is: ; where C is the covariance matrix of the remaining features; is the transpose of the remaining feature X matrix;

[0030] Perform eigenvalue decomposition on the covariance matrix C of the remaining features to obtain the remaining eigenvalues and eigenvectors: CW i = λ i W i ; where λ i is the i-th eigenvalue, and W i is the i-th eigenvector;

[0031] Sort the remaining eigenvalues from largest to smallest, and calculate the cumulative variance explained rate of the data in the screen parameter template database: ; where PLE is the cumulative variance explained rate of the data in the screen parameter template database; d is the total number of original remaining features; k is the number of selected principal components;

[0032] Preset the cumulative variance explained rate threshold, select the smallest k such that the cumulative variance explained rate is greater than the cumulative variance explained rate threshold; project the original remaining features X into a new low-dimensional space using the selected k eigenvectors to obtain the comprehensive feature dataset.

[0033] Furthermore, the method for parsing and judging the command type by the intelligent screen parameter configuration assistant includes:

[0034] If it is a read command, read out the screen parameters currently used by the intelligent industrial control board, and transmit the read screen parameters to the display screen through the data communication module;

[0035] If it is a write command, initialize the screen parameters, match the screen parameter settings according to the identified display screen parameter data, and transmit the matched screen parameter settings to the display screen through the data communication module.

[0036] Further, the training method of the display effect evaluation model includes:

[0037] Divide the data set into a training set, a validation set, and a test set, train the model and evaluate the model performance; construct a display effect evaluation model, including an input layer, a hidden layer, and an output layer; use the ReLU activation function for the hidden layer;

[0038] The input layer of the display effect evaluation model is the historical comprehensive feature data set, and the number of neurons in the input layer should match the number of features in the historical comprehensive feature data set; the output layer of the model is the display effect of the display screen, and the number of neurons in the output layer corresponds to the number of prediction targets, and a neuron is used to output the predicted value; the display effect evaluation model is a fully connected neural network model;

[0039] Use the mean square error as the loss function to measure the error between the predicted value and the actual value of the model; the mean square error loss function is: ; where n' is the number of data sets; Y f is the actual value of the data point f in the data set; is the predicted value of the data point f in the data set;

[0040] Use the training set data to train the model, minimize the loss function through the Adam optimizer, and tune the hyperparameters of the model;

[0041] Evaluate the model through the test set, stop the test when the performance of the model in the prediction task reaches the preset performance threshold, and obtain the display effect evaluation model; input the current comprehensive feature data set into the display effect evaluation model to obtain the display effect of the display screen.

[0042] Further, the method for tuning the hyperparameters of the model includes:

[0043] For the display effect evaluation model, set a grid space, and the grid space includes at least two groups of hyperparameter combinations, and each group of hyperparameters varies within a preset range;

[0044] For each group of hyperparameter combinations in the grid space, use these hyperparameters to configure and train the model, and use the accuracy to evaluate the performance of the model; compare the model performance corresponding to each group of hyperparameters, and select the group of hyperparameters with the highest accuracy as the optimal hyperparameters of the display effect evaluation model.

[0045] Further, the method for comparing the predicted display effect with the preset display effect threshold to determine whether the matching screen parameter setting data is applicable to the currently connected display screen includes:

[0046] If the predicted display effect is less than the preset display effect threshold, it is determined that the matched screen parameter setting data is not applicable to the currently connected display screen;

[0047] If the predicted display effect is greater than or equal to the preset display effect threshold, it is determined that the matched screen parameter setting data is applicable to the currently connected display screen.

[0048] Further, when the matched screen parameter setting data is not applicable to the currently connected display screen, the method of sending a calibration instruction through the intelligent screen parameter configuration terminal to reconfigure the screen parameter setting data to match the connected display screen includes:

[0049] The intelligent screen parameter configuration terminal makes a preliminary analysis of the mismatch reasons, and the mismatch reasons include resolution mismatch, color mode setting error, and refresh rate setting improper;

[0050] The steps of the preliminary analysis are: check whether the resolution setting in the current screen parameter configuration matches the physical resolution of the display screen. If not, try to adjust the resolution setting to a suitable range and observe whether the display effect is improved;

[0051] Check whether the color mode setting in the current screen parameter configuration is correct, whether the color mode matching the display screen or application scenario is selected, and judge whether the color mode setting affects the display effect by comparing the color performance before and after adjustment;

[0052] Check whether the refresh rate setting in the current screen parameter configuration matches the support range of the display screen, and observe the smoothness and stability of the display screen when playing dynamic content to judge whether the refresh rate setting is appropriate;

[0053] According to the above troubleshooting results, comprehensively analyze the specific reasons for the mismatch. For the analyzed specific reasons, make corresponding optimization adjustments to the screen parameter setting data; after the adjustment is completed, verify the display effect again until it matches the connected display screen.

[0054] Further, the described method for setting screen parameters of an intelligent industrial control board includes:

[0055] S1. Build an intelligent screen parameter configuration assistant, and the intelligent screen parameter configuration assistant is used to implement S2 to S6;

[0056] S2. Collect the display screen parameter data of different models and the corresponding screen parameter setting data; preprocess the display screen parameter data of different models and the corresponding screen parameter setting data to obtain a screen parameter template database; extract features from the data in the screen parameter template database to obtain a comprehensive feature data set;

[0057] S3. Obtain a configuration command and parse and judge the command type through the intelligent screen parameter configuration assistant;

[0058] S4. Execute the command to perform screen parameter setting matching; construct a display effect evaluation model, and input the obtained comprehensive feature dataset into the trained display effect evaluation model to obtain the display effect of the display screen.

[0059] S5. Compare the predicted display effect with the preset display effect threshold to determine whether the matched screen parameter setting data is applicable to the currently connected display screen; if it does not exceed the preset threshold, the matched screen parameter setting data is applicable to the currently connected display screen; if it exceeds the preset threshold, the matched screen parameter setting data is not applicable to the currently connected display screen.

[0060] S6. When the matched screen parameter setting data is not applicable to the currently connected display screen, send a calibration instruction through the intelligent screen parameter configuration terminal to reconfigure the screen parameter setting data to match the connected display screen.

[0061] The technical effects and advantages of an intelligent industrial control board screen parameter setting system and method of the present invention:

[0062] By removing features with variances less than the variance threshold, the present invention can reduce noise and unimportant information, enabling the model to focus more on features strongly correlated with the target variable; by calculating the Pearson correlation coefficient, the linear correlation between the remaining features and the target variable can be evaluated, further screening out features that have an important impact on model prediction; using the recursive feature elimination method to remove unimportant features can reduce the complexity of the model and lower the computational cost.

[0063] By retaining the largest variance in the data through the principal component analysis method to reduce the number of features, the model is further simplified and the computational efficiency is improved; by presetting a target trigger function, when the real-time data reaches the preset condition, the principal component analysis is automatically triggered to preprocess the remaining features, making the data processing process more flexible and adaptive; through a strict feature selection and dimensionality reduction process, the risk of overfitting can be reduced, and the generalization ability of the model on new data can be enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a schematic structural diagram of an intelligent industrial control board screen parameter setting system of the present invention;

[0065] Figure 2 It is a schematic flowchart of an intelligent industrial control board screen parameter setting method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0066] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0067] Embodiment 1

[0068] Please refer to Figure 1 As shown, an intelligent industrial control board screen parameter setting system described in this embodiment includes: constructing an intelligent screen parameter configuration assistant, and the intelligent screen parameter configuration assistant includes:

[0069] A parameter configuration module, which is used to collect parameter data of display screens of different models and corresponding screen parameter setting data; preprocess the parameter data of display screens of different models and corresponding screen parameter setting data to obtain a screen parameter template database; extract features from the data in the screen parameter template database to obtain a comprehensive feature data set;

[0070] A command parsing module, which is used to obtain a configuration command and parse and judge the command type through the intelligent screen parameter configuration assistant;

[0071] An automatic adaptation module, which is used to execute commands and perform screen parameter setting matching; construct a display effect evaluation model, and input the obtained comprehensive feature data set into the trained display effect evaluation model to obtain the display effect of the display screen;

[0072] An effect evaluation module, which is used to compare the predicted display effect with a preset display effect threshold to judge whether the matched screen parameter setting data is applicable to the currently connected display screen; if it does not exceed the preset threshold, the matched screen parameter setting data is applicable to the currently connected display screen; if it exceeds the preset threshold, the matched screen parameter setting data is not applicable to the currently connected display screen;

[0073] A screen parameter setting optimization module, which is used to send a calibration instruction through the intelligent screen parameter configuration terminal when the matched screen parameter setting data is not applicable to the currently connected display screen, and reconfigure the screen parameter setting data to match the connected display screen; each module is connected by wired and / or wireless means.

[0074] The parameter data of display screens of different models includes resolution, refresh rate, screen model, interface type, pixel depth, and timing parameters; the screen parameter setting data includes default screen parameter setting data and user preference data;

[0075] The default screen parameter setting data includes screen color configuration, contrast setting, brightness adjustment, and color temperature setting; the user preference data includes the screen color configuration, contrast setting, brightness adjustment, and color temperature setting preferred by the user.

[0076] The parameter data of the different models of display screens are obtained by referring to the product manual; the default screen parameter setting data are obtained by querying the operating system settings; the user preference data are obtained by recording through third-party software;

[0077] The method for preprocessing the parameter data of different models of display screens and the corresponding screen parameter setting data includes;

[0078] Identifying and removing abnormal data in the display screen parameter data and the corresponding screen parameter setting data through the LOF algorithm to obtain the processed display screen parameter feature data set and the corresponding screen parameter setting feature data set;

[0079] Normalizing the display screen parameter feature data set and the corresponding screen parameter setting feature data set, converting them into a standard normal distribution, to obtain the normalized display screen parameter feature data set and the corresponding screen parameter setting feature data set; integrating the normalized display screen parameter feature data set and the corresponding screen parameter setting feature data set together to obtain a screen parameter template database.

[0080] The method for extracting feature data from the data in the screen parameter template database to obtain a comprehensive feature data set includes:

[0081] The data in the screen parameter template database include the display screen parameter feature data set and the corresponding screen parameter setting feature data set; a preset variance threshold is θ, and the features with variances less than the variance threshold θ are removed from the data in the screen parameter template database using the variance threshold formula to obtain the remaining features X;

[0082] The variance threshold formula is: ; where X j is the data feature in the jth screen parameter template database; x i is the ith data point; n is the total number of data points; μ is the mean of the data in the screen parameter template database;

[0083] Preset a target variable as Y, and calculate the Pearson correlation coefficient r between the remaining features X and the target variable Y to evaluate the linear correlation between the two;

[0084] The specific formula is ; where X i and Y i are the ith remaining feature value and the target variable value respectively, and are the mean of the remaining features and the mean of the target variable respectively; i is the index of the feature value;

[0085] Remove unimportant features using recursive feature elimination, and select the least important feature in each iteration; use principal component analysis for dimensionality reduction to reduce the number of features by retaining the largest variance in the data;

[0086] Preset a target trigger function. When the running target trigger function reaches the influence coefficient threshold of the preset correlation model, automatically trigger the principal component analysis to preprocess the remaining features;

[0087] The correlation model is:

[0088] ; where Y' is the dependent variable of the correlation model; P(Y' = 1) is the probability that the dependent variable of the correlation model is 1; is the value of the dependent variable when the independent variable of the correlation model is 0; is the independent variable of the correlation model; is the coefficient of the independent variable;

[0089] The target trigger function is:

[0090] ; where b 1 is the dataset of display screen parameter features obtained in real time; is the preset dataset of display screen parameter features; b 2 is the dataset of screen parameter setting features obtained in real time; is the preset dataset of screen parameter setting features;

[0091] Calculate the covariance matrix, eigenvalues, and eigenvectors of the remaining features through the covariance calculation formula, and project the data into a new feature space composed of the remaining eigenvectors; the covariance calculation formula is: ; where C is the covariance matrix of the remaining features; is the transpose of the remaining feature X matrix;

[0092] Perform eigenvalue decomposition on the covariance matrix C of the remaining features to obtain the remaining eigenvalues and eigenvectors: CW i = λ i W i ; where λ i is the i-th eigenvalue, and W i is the i-th eigenvector;

[0093] Sort the remaining eigenvalues from largest to smallest, and calculate the cumulative variance explained rate of the data in the screen parameter template database: ; where PLE is the cumulative variance explained rate of the data in the screen parameter template database; d is the total number of original remaining features; k is the number of principal components selected;

[0094] Preset the cumulative variance explanation rate threshold, select the smallest k such that the cumulative variance explanation rate is greater than the cumulative variance explanation rate threshold; project the original remaining features X onto a new low-dimensional space using the selected k eigenvectors to obtain a comprehensive feature dataset.

[0095] The method for parsing and judging the command type through the intelligent screen parameter configuration assistant includes:

[0096] If it is a read command, read out the screen parameters currently used by the intelligent industrial control board, and transmit the read screen parameters to the display screen through the data communication module;

[0097] If it is a write command, initialize the screen parameters, match the screen parameter settings according to the recognized display screen parameter data, and transmit the matched screen parameter settings to the display screen through the data communication module.

[0098] The training method of the display effect evaluation model includes:

[0099] Divide the dataset into a training set, a validation set, and a test set, train the model and evaluate the model performance; construct a display effect evaluation model, including an input layer, a hidden layer, and an output layer; use the ReLU activation function for the hidden layer;

[0100] The input layer of the display effect evaluation model is the historical comprehensive feature dataset, and the number of neurons in the input layer should match the number of features in the historical comprehensive feature dataset; the output layer of the model is the display effect of the display screen, and the number of neurons in the output layer corresponds to the number of prediction targets, and a single neuron is used to output the predicted value; the display effect evaluation model is a fully connected neural network model;

[0101] Use the mean square error as the loss function to measure the error between the predicted value and the actual value of the model; the mean square error loss function is: ; where n' is the number of datasets; Y f is the actual value of the data point f in the dataset; is the predicted value of the data point f in the dataset;

[0102] Use the training set data to train the model, minimize the loss function through the Adam optimizer, and tune the hyperparameters of the model;

[0103] Evaluate the model through the test set, stop the test when the performance of the model in the prediction task reaches the preset performance threshold to obtain the display effect evaluation model; input the current comprehensive feature dataset into the display effect evaluation model to obtain the display effect of the display screen.

[0104] The method for tuning the hyperparameters of the model includes:

[0105] For the display effect evaluation model, a grid space is set, and the grid space includes at least two sets of hyperparameter combinations, with each set of hyperparameters varying within a preset range;

[0106] For each set of hyperparameter combinations in the grid space, use these hyperparameters to configure and train the model, and evaluate the performance of the model using the accuracy rate; compare the model performances corresponding to each set of hyperparameters, select the set of hyperparameters with the highest accuracy, and set it as the optimal hyperparameters of the display effect evaluation model.

[0107] For example, set a grid space that contains the hyperparameter combinations to be explored. Suppose two hyperparameters are selected for tuning: the learning rate and the batch size. The preset range of the learning rate may be from 0.001 to 0.01, and the preset range of the batch size may be from 32 to 128.

[0108] In this grid space, multiple sets of hyperparameter combinations can be defined. For example:

[0109] Combination 1: learning rate = 0.001, batch size = 32; Combination 2: learning rate = 0.005, batch size = 32; Combination 3: learning rate = 0.001, batch size = 64;... (other combinations)

[0110] Next, for each set of hyperparameter combinations in the grid space, use these hyperparameters to configure and train the display effect evaluation model. After training is completed, use the accuracy rate to evaluate the model performance corresponding to each set of hyperparameters.

[0111] Suppose the following results are obtained:

[0112] The model accuracy rate corresponding to Combination 1 is 80%; the model accuracy rate corresponding to Combination 2 is 85%; the model accuracy rate corresponding to Combination 3 is 82%;... (results of other combinations)

[0113] By comparing the model performances corresponding to each set of hyperparameters, the set of hyperparameters with the highest accuracy can be selected. In this example, the model accuracy rate corresponding to Combination 2 (learning rate = 0.005, batch size = 32) is the highest, at 85%.

[0114] Therefore, set Combination 2 as the optimal hyperparameters of the display effect evaluation model, and use this set of hyperparameters to configure the model in subsequent training and prediction. In this way, the hyperparameter tuning process of the display effect evaluation model is completed.

[0115] The method of comparing the predicted display effect with a preset display effect threshold to determine whether the matching screen parameter setting data is applicable to the currently connected display screen includes:

[0116] If the predicted display effect is less than the preset display effect threshold, it is determined that the matched screen parameter setting data is not applicable to the currently connected display screen;

[0117] If the predicted display effect is greater than or equal to the preset display effect threshold, it is determined that the matched screen parameter setting data is applicable to the currently connected display screen.

[0118] When the matched screen parameter setting data is not applicable to the currently connected display screen, the method of sending a calibration instruction through the intelligent screen parameter configuration terminal to reconfigure the screen parameter setting data to match the connected display screen includes:

[0119] The intelligent screen parameter configuration terminal conducts a preliminary analysis of the mismatch reasons, and the mismatch reasons include resolution mismatch, incorrect color mode setting, and improper refresh rate setting;

[0120] The steps of the preliminary analysis are as follows: Check whether the resolution setting in the current screen parameter configuration matches the physical resolution of the display screen. If not, try to adjust the resolution setting to an appropriate range and observe whether the display effect improves;

[0121] Check whether the color mode setting in the current screen parameter configuration is correct, whether the color mode matching the display screen or application scenario is selected, and judge whether the color mode setting affects the display effect by comparing the color performance before and after adjustment;

[0122] Check whether the refresh rate setting in the current screen parameter configuration matches the support range of the display screen, and observe the smoothness and stability of the display screen when playing dynamic content to judge whether the refresh rate setting is appropriate;

[0123] According to the above troubleshooting results, comprehensively analyze the specific reasons for the mismatch. For the analyzed specific reasons, make corresponding optimization adjustments to the screen parameter setting data; After the adjustment is completed, verify the display effect again until it matches the connected display screen.

[0124] The preset display effect threshold is set by the staff. Different display effects are collected through the intelligent screen parameter configuration assistant, and the average value of multiple display effects is taken as the preset display effect threshold; Similarly, set the preset cumulative variance interpretation rate threshold and performance threshold.

[0125] In this embodiment, by removing the features with variance less than the variance threshold, noise and unimportant information can be reduced, enabling the model to focus more on the features strongly correlated with the target variable; By calculating the Pearson correlation coefficient, the linear correlation between the remaining features and the target variable can be evaluated, and further screen out the features that have an important impact on model prediction; Using the recursive feature elimination method to remove unimportant features can reduce the complexity of the model and lower the calculation cost;

[0126] By using the principal component analysis method to retain the largest variance in the data to reduce the number of features, the model is further simplified and the computational efficiency is improved. By presetting a target trigger function, when the real-time data reaches the preset conditions, the principal component analysis is automatically triggered to preprocess the remaining features, making the data processing process more flexible and adaptive. Through a strict feature selection and dimensionality reduction process, the risk of overfitting can be reduced and the generalization ability of the model on new data can be enhanced.

[0127] Embodiment 2

[0128] Please refer to Figure 2 As shown, for the parts not described in detail in this embodiment, refer to the description in Embodiment 1. A method for setting the screen parameters of an intelligent industrial control board is provided, including:

[0129] S1. Build an intelligent screen parameter configuration assistant, which is used to implement S2 to S6;

[0130] S2. Collect the display screen parameter data of different models and the corresponding screen parameter setting data; preprocess the display screen parameter data of different models and the corresponding screen parameter setting data to obtain a screen parameter template database; perform feature extraction on the data in the screen parameter template database to obtain a comprehensive feature data set;

[0131] S3. Obtain a configuration command and parse it through the intelligent screen parameter configuration assistant to determine the command type;

[0132] S4. Execute the command to perform screen parameter setting matching; build a display effect evaluation model, and input the obtained comprehensive feature data set into the trained display effect evaluation model to obtain the display effect of the display screen;

[0133] S5. Compare the predicted display effect with the preset display effect threshold to determine whether the matched screen parameter setting data is applicable to the currently connected display screen; if it does not exceed the preset threshold, the matched screen parameter setting data is applicable to the currently connected display screen; if it exceeds the preset threshold, the matched screen parameter setting data is not applicable to the currently connected display screen;

[0134] S6. When the matched screen parameter setting data is not applicable to the currently connected display screen, send a calibration instruction through the intelligent screen parameter configuration terminal to reconfigure the screen parameter setting data to match the connected display screen.

[0135] Since the electronic device introduced in this embodiment is the electronic device adopted in the intelligent industrial control board screen parameter setting system and method in the embodiments of the present application, based on the intelligent industrial control board screen parameter setting system and method introduced in the embodiments of the present application, those skilled in the art can understand the specific implementation manners and various variations of the electronic device in this embodiment. Therefore, the specific implementation of how this electronic device implements the method in the embodiments of the present application will not be described in detail herein. As long as those skilled in the art implement the electronic device adopted in the intelligent industrial control board screen parameter setting system and method in the embodiments of the present application, it falls within the scope of protection of the present application.

[0136] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula that is closest to the actual situation. The preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.

[0137] The above is only the preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions falling within the concept of the present invention belong to the protection scope of the present invention. It should be noted that for ordinary technical users in the technical field, several improvements and refinements made without departing from the principle of the present invention should also be regarded as within the protection scope of the present invention.

Claims

1. An intelligent industrial control panel screen parameter setting system, characterized in that: include: Construct an intelligent screen parameter configuration assistant, the intelligent screen parameter configuration assistant includes: The parameter configuration module is used to collect the parameter data of display screens of different models and the corresponding screen parameter setting data; pre-process the parameter data of display screens of different models and the corresponding screen parameter setting data to obtain a screen parameter template database; extract features from the data in the screen parameter template database to obtain a historical comprehensive feature data set; The command parsing module is used to obtain configuration commands and parse and determine the command type through the intelligent screen parameter configuration assistant; The automatic adaptation module is used to execute commands and match screen parameters; build a display effect evaluation model, input the acquired current comprehensive feature data set into the trained display effect evaluation model, and obtain the display effect of the display screen; The effect evaluation module is used to compare the predicted display effect with the preset display effect threshold to determine whether the matched screen parameter setting data is applicable to the currently connected display screen; if it does not exceed the preset threshold, the matched screen parameter setting data is applicable to the currently connected display screen; if it exceeds the preset threshold, the matched screen parameter setting data is not applicable to the currently connected display screen; The screen parameter setting optimization module is used to issue a calibration instruction through the intelligent screen parameter configuration terminal when the matched screen parameter setting data is not suitable for the currently connected display screen, and reconfigure the screen parameter setting data to match the connected display screen; each module is connected by wired and / or wireless means; The method for extracting features from data in the screen parameter template database to obtain a historical comprehensive feature data set includes: The data in the screen parameter template database includes a display screen parameter feature data set and a corresponding screen parameter setting feature data set; the preset variance threshold is θ, and the variance threshold formula is used to remove the features whose variance is less than the variance threshold θ from the data in the screen parameter template database to obtain the remaining features X; The variance threshold formula is: Among them, X j is the data feature in the jth screen parameter template database; x i is the i-th data point; n is the total number of data points; μ is the mean value of the data in the screen parameter template database; Preset a target variable as Y, calculate the Pearson correlation coefficient r between the remaining features X and the target variable Y to evaluate the linear correlation between the two; The specific formula is Among them, X i and Y i are the i-th residual eigenvalue and target variable value, respectively. and are the mean of the remaining features and the mean of the target variable respectively; i is the index of the feature value; Use recursive feature elimination to remove unimportant features, selecting the least important feature in each iteration; use principal component analysis to reduce dimensionality, reducing the number of features by retaining the largest variance in the data; A preset target trigger function is used. When the running target trigger function reaches the influence coefficient threshold of the preset association model, the principal component analysis is automatically triggered to pre-process the remaining features. The association model is: Among them, Y′ is the dependent variable of the association model; P(Y′=1) is the probability that the dependent variable of the association model is 1; a0 is the value of the dependent variable when the independent variable of the association model is 0; M1, M2, …, M n is the independent variable of the association model; a1, a2, …, an are the coefficients of the independent variables; The target trigger function is: Among them, b1 is the display parameter feature data set obtained in real time; is a preset display screen parameter feature data set; b2 is a screen parameter setting feature data set acquired in real time; Set feature data sets for preset screen parameters; The covariance matrix of the remaining features is calculated using the covariance calculation formula, the eigenvalues ​​and eigenvectors are calculated, and the data is projected into a new feature space composed of the remaining eigenvectors; the covariance calculation formula is: Among them, C is the covariance matrix of the remaining features; X T is the transpose of the remaining feature matrix X; Perform eigenvalue decomposition on the covariance matrix C of the remaining features to obtain the remaining eigenvalues ​​and eigenvectors: CW i =λ i W i ; Among them, λ i is the i-th eigenvalue, W i is the i-th eigenvector; Sort the remaining eigenvalues ​​from large to small, and calculate the cumulative variance explanation rate of the data in the screen parameter template database: Among them, PLE is the cumulative variance explanation rate of the data in the screen parameter template database; d is the total number of original remaining features; k is the number of principal components selected; The cumulative variance explanation rate threshold is preset, and the smallest k is selected so that the cumulative variance explanation rate is greater than the cumulative variance explanation rate threshold; the original remaining features X are projected into a new low-dimensional space using the selected k feature vectors to obtain a historical comprehensive feature data set.

2. According to claim 1, a smart industrial control panel screen parameter setting system is characterized in that: The parameter data of the display screens of different models include resolution, refresh rate, screen model, interface type, pixel depth and timing parameters; the screen parameter setting data includes default screen parameter setting data and user preference data; The default screen parameter setting data includes screen color configuration, contrast setting, brightness adjustment and color temperature setting; the user preference data includes user preferred screen color configuration, contrast setting, brightness adjustment and color temperature setting.

3. According to claim 1, a system and method for setting screen parameters of an intelligent industrial control board, characterized in that: The method for preprocessing display screen parameter data of different models and corresponding screen parameter setting data includes: The LOF algorithm is used to identify and eliminate abnormal data in the display screen parameter data and the corresponding screen parameter setting data, so as to obtain a processed display screen parameter feature data set and a corresponding screen parameter setting feature data set; The display screen parameter feature data set and the corresponding screen parameter setting feature data set are normalized and converted into a standard normal distribution to obtain a normalized display screen parameter feature data set and a corresponding screen parameter setting feature data set; the normalized display screen parameter feature data set and the corresponding screen parameter setting feature data set are integrated together to obtain a screen parameter template database.

4. According to claim 3, a system and method for setting screen parameters of an intelligent industrial control board is characterized in that: The method for parsing and determining the command type by the intelligent screen parameter configuration assistant includes: If it is a read command, the screen parameters currently used by the intelligent industrial control board are read out, and the read screen parameters are transmitted to the display screen through the data communication module; If it is a write command, the screen parameters are initialized, the screen parameter settings are matched according to the identified display screen parameter data, and the matched screen parameter settings are transmitted to the display screen through the data communication module.

5. According to claim 4, a system and method for setting screen parameters of an intelligent industrial control board is characterized in that: The training method of the display effect evaluation model includes: Divide the data set into training set, validation set and test set, train the model and evaluate the model performance; build a display effect evaluation model, including input layer, hidden layer and output layer; use ReLU activation function in the hidden layer; The input layer of the display effect evaluation model is a historical comprehensive feature data set, and the number of neurons in the input layer should match the number of features in the historical comprehensive feature data set; the output layer of the model is the display effect of the display screen, and the number of neurons in the output layer corresponds to the number of predicted targets, and the predicted value is output through one neuron; the display effect evaluation model is a fully connected neural network model; The mean square error is used as the loss function to measure the error between the model's predicted value and the actual value; the mean square error loss function is: Where n′ is the number of data sets; Y f is the actual value of the data point f in the data set; is the predicted value of data point f in the data set; Use the training set data to train the model, minimize the loss function through the Adam optimizer, and tune the model's hyperparameters; The model is evaluated through the test set. When the performance of the model in the prediction task reaches the preset performance threshold, the test is stopped to obtain the display effect evaluation model; the current comprehensive feature data set is input into the display effect evaluation model to obtain the display effect of the display screen.

6. According to claim 5, a system and method for setting screen parameters of an intelligent industrial control board is characterized in that: The method for tuning the hyperparameters of the model includes: For the display effect evaluation model, a grid space is set, wherein the grid space includes at least two groups of hyperparameter combinations, and each group of hyperparameters varies within a preset range; For each set of hyperparameter combinations in the grid space, use these hyperparameters to configure the training model and use accuracy to evaluate the performance of the model; compare the model performance corresponding to each set of hyperparameters, select the set of hyperparameters with the highest accuracy, and set them as the optimal hyperparameters for the display effect evaluation model.

7. The intelligent industrial control panel screen parameter setting system and method according to claim 6, characterized in that: When the matched screen parameter setting data is not suitable for the currently connected display screen, the method of issuing a calibration instruction through the intelligent screen parameter configuration terminal to reconfigure the screen parameter setting data to match the connected display screen includes: The intelligent screen parameter configuration terminal conducts a preliminary analysis of the reasons for the mismatch, which include resolution mismatch, incorrect color mode setting, and improper refresh rate setting; The steps of the preliminary analysis are: check whether the resolution setting in the current screen parameter configuration matches the physical resolution of the display screen; if not, try to adjust the resolution setting to a suitable range and observe whether the display effect is improved; Check whether the color mode setting in the current screen parameter configuration is correct and whether the color mode matching the display or application scenario is selected. By comparing the color performance before and after adjustment, determine whether the color mode setting has an impact on the display effect; Check whether the refresh rate setting in the current screen parameter configuration matches the supported range of the display, and observe the smoothness and stability of the display when playing dynamic content to determine whether the refresh rate setting is appropriate; According to the above troubleshooting results, the specific reasons for the mismatch are comprehensively analyzed, and the screen parameter setting data is optimized and adjusted accordingly according to the analyzed specific reasons; after the adjustment is completed, the display effect is verified again until it matches the connected display.

8. A method for setting screen parameters of an intelligent industrial control board, used to implement a system for setting screen parameters of an intelligent industrial control board as claimed in any one of claims 1 to 7, characterized in that: include: S1. Build an intelligent screen parameter configuration assistant, which is used to implement S2 to S6; S2. Collecting display screen parameter data of different models and corresponding screen parameter setting data; pre-processing the display screen parameter data of different models and corresponding screen parameter setting data to obtain a screen parameter template database; Extract features from the data in the screen parameter template database to obtain a historical comprehensive feature data set; S3. Get the configuration command and use the intelligent screen parameter configuration assistant to parse and determine the command type; S4, execute the command to set and match the screen parameters; build a display effect evaluation model, input the acquired current comprehensive feature data set into the trained display effect evaluation model, and obtain the display effect of the display screen; S5, comparing the predicted display effect with a preset display effect threshold to determine whether the matching screen parameter setting data is applicable to the currently connected display screen; If the preset threshold is not exceeded, the matched screen parameter setting data is applicable to the currently connected display screen; If the preset threshold is exceeded, the matching screen parameter setting data is not applicable to the currently connected display; S6. When the matched screen parameter setting data is not suitable for the currently connected display screen, a calibration instruction is issued through the intelligent screen parameter configuration terminal to reconfigure the screen parameter setting data to match the connected display screen.

Images