Industrial automation control system and method applying Internet of Things intelligent sensing technology

Abstract

The invention discloses an industrial automation control system and method applying an Internet of Things intelligent sensing technology, and relates to the field of industrial automation control, and the method comprises the steps: extracting the operation data features of automation equipment, and building an operation data feature vector set of the industrial automation equipment; carrying out denoising and normalization processing on the data, and eliminating the influence of an abnormal peak value and a dimensional difference; analyzing weights of different industrial automation equipment operation data characteristics influencing industrial automation equipment control; determining the correlation degree between the operation data characteristics of different industrial automation devices and the reference operation data; establishing an industrial automation equipment operation data comprehensive evaluation model, and judging the comprehensive operation quality of the industrial automation equipment; an industrial automatic control man-machine interaction platform is established based on the intelligent sensing technology of the Internet of Things. The method has the advantages that the comprehensive quality evaluation precision of operation of the industrial automation equipment is effectively improved, and the stability and reliability of industrial automation control are improved.

Description

Technical Field

[0001] The present invention relates to the field of industrial automation control, and in particular to an industrial automation control system and method using the Internet of Things intelligent sensing technology. Background Art

[0002] With the rapid development of the intelligent era, monitoring the operating status and quality of industrial automation equipment through sensing technology is an important guarantee for ensuring safe production of industrial automation. The industrial automation control system can accurately control each link in the production process and reduce errors and delays caused by human factors, thereby significantly improving production efficiency, optimizing production processes and maximizing the use of comprehensive resources, and further improving overall production efficiency. With the development of the Internet of Things intelligent sensing technology, combining the Internet of Things intelligent sensing technology with industrial automation control can effectively improve the remote monitoring capability of industrial automation control, the comprehensive evaluation capability of the operating quality of industrial automation equipment, and the early warning capability of abnormal events. Therefore, industrial automation control is of great significance for improving production efficiency, reducing costs, improving product quality, enhancing production safety, promoting technological innovation, promoting industrial upgrading, and achieving sustainable development.

[0003] The existing application of IoT intelligent sensing technology and industrial automation control technology mainly focuses on collecting the operating data of industrial automation equipment by setting up multiple groups of monitoring equipment. There is a lack of unified evaluation standards and overall comprehensive evaluation in the processing of operating data of various industrial automation equipment. As a result, when evaluating the operating data of different industrial automation equipment, the system has poor compatibility, data scheduling difficulties, and reduced accuracy and reliability of equipment operation quality control, which makes the correlation between the operating data of various industrial automation equipment low, resulting in deviations in the final judgment results and the issuance of error prompts, causing a waste of manpower and material resources. Summary of the invention

[0004] In order to solve the above technical problems, an industrial automation control system and method using the Internet of Things intelligent sensing technology are provided. The technical solution solves the problem of lack of unified evaluation standards and overall comprehensive evaluation proposed in the above background technology, which leads to poor system compatibility, difficulty in data scheduling and reduced accuracy and reliability of equipment operation quality control when evaluating the operating data of different industrial automation equipment, resulting in low correlation between the operating data of each industrial automation equipment, resulting in deviations in the final judgment results and the issuance of error prompts, causing waste of manpower and material resources.

[0005] In order to achieve the above objectives, the technical solution adopted by the present invention is: an industrial automation control method using the intelligent sensing technology of the Internet of Things, characterized in that it includes: Based on big data, the historical operation data of industrial automation equipment is obtained, and the operation data features of automation equipment are extracted to establish the feature vector set of industrial automation equipment operation data; De-noising and normalizing the data in the characteristic vector set of industrial automation equipment operation data to eliminate the influence of abnormal peaks and dimensional differences; Based on the entropy method, the weights of the operating data characteristics of different industrial automation equipment that affect the control of industrial automation equipment are analyzed; Based on the objective evaluation method of grey theory, the correlation between the operating data characteristics of different industrial automation equipment and the reference operating data is determined; according to the weight coefficients of the operating data characteristics of different industrial automation equipment and the correlation with the reference operating data, combined with the softmax loss function and the center loss function, the comprehensive evaluation parameters of the operating data of industrial automation equipment are established, and based on the machine learning algorithm model, the comprehensive evaluation model of the operating data of industrial automation equipment is established to judge the comprehensive quality of the operation of industrial automation equipment; Based on the intelligent sensing technology of the Internet of Things, an industrial automation control human-computer interaction platform is established to receive, store and display the data of the operation of industrial automation equipment, and to issue alarm prompts through the prompt device according to the feedback of abnormal information.

[0006] Preferably, the acquisition of historical operation data of industrial automation equipment based on big data, extraction of automation equipment operation data features, and establishment of an industrial automation equipment operation data feature vector set specifically include: Based on big data, obtain historical operation data and reference operation data of industrial automation equipment; According to the type and parameters of industrial automation equipment operation, extract the automation equipment operation data characteristics that affect the operation of automation equipment; According to the type of operation of industrial automation equipment, a time interval sequence of the operation data characteristics of the automation equipment is established respectively; The operation data characteristics of automation equipment are classified and counted in the time interval sequence, and the feature vector set of industrial automation equipment operation data is established.

[0007] Preferably, the denoising and normalizing of the data in the industrial automation equipment operation data feature vector set to eliminate the influence of abnormal peaks and dimensional differences specifically includes: Based on the first-order Kalman filter algorithm, the data in the characteristic vector set of the industrial automation equipment operation data is filtered and denoised; according to the normalization formula, the influence of the data dimension difference in the characteristic vector set of the industrial automation equipment operation data is eliminated; The normalization formula is: In the formula, For the Time point The data after the normalization of the operating data characteristics of industrial automation equipment, For the Time point The original data of the operation data characteristics of industrial automation equipment, For the The minimum value of the characteristic data of the operation data of industrial automation equipment, For the Preferably, the entropy method is used to analyze the weights of different industrial automation equipment operation data characteristics that affect the control of industrial automation equipment, including: According to the data processed by the feature vector set of industrial automation equipment operation data, calculate the Time point The proportion of operating data characteristics of industrial automation equipment; According to Time point The proportion of the operating data characteristics of industrial automation equipment is calculated The information entropy of the operating data characteristics of industrial automation equipment; According to The information entropy of the operating data characteristics of industrial automation equipment is calculated. The effective value of the characteristic data of the operation data of industrial automation equipment; according to the The effective value of the operating data characteristics of each industrial automation equipment is used to calculate the weight of the operating data characteristics of each industrial automation equipment; According to the weights of the operating data features of each industrial automation equipment, a weight matrix of the operating data features of the industrial automation equipment is established; The said Time point The weight expression of the operating data characteristics of industrial automation equipment is:

[0008] In the formula, For the Time point The proportion of the operating data characteristics of industrial automation equipment, For the Time point The number of industrial automation equipment operation data features, wherein i is the i-th sequence number in the time interval sequence of the automation equipment operation data features, and j is the j-th type of the industrial automation equipment operation data features; the The information entropy expression of the operating data characteristics of industrial automation equipment is: In the formula, For the The information entropy value of the characteristic information of the operation data of the industrial automation equipment is: In the formula, For the The effective value of the operating data feature data of each industrial automation equipment; the weight expression of the operating data feature of each industrial automation equipment is: In the formula, For the The weight of the operating data features of industrial automation equipment.

[0009] Preferably, the objective evaluation method based on grey theory to determine the correlation between the operating data characteristics of different industrial automation equipment and the reference operating data specifically includes: Determine the first The absolute difference between the characteristic data of the industrial automation equipment operation data and the reference operation data at a time point; Based on big data, obtain the resolution coefficients of the operating data characteristics and reference operating data of different industrial automation equipment; According to the absolute difference between the characteristic data of the operation data of the industrial automation equipment and the reference operation data, the correlation coefficient between the characteristics of the operation data of different industrial automation equipment and the reference operation data is calculated; Calculate the correlation between the operating data characteristics of different industrial automation equipment and the reference operating data according to the correlation coefficient between the operating data characteristics of different industrial automation equipment and the reference operating data; According to the correlation between the operating data characteristics of different industrial automation equipment and the reference operating data, a correlation matrix between the operating data characteristics of industrial automation equipment and the reference operating data is established; The determination The absolute difference between the characteristic data of the industrial automation equipment operation data and the reference operation data at a time point is expressed as: In the formula, For the Time point The absolute difference between the characteristic data of the operation data of an industrial automation equipment and the reference operation data, is the normalized data of the jth industrial automation equipment operation data at the i-th time point, For the Time point The reference operating data of the operating data characteristics of industrial automation equipment; the correlation coefficient expression between the operating data characteristics of the industrial automation equipment and the reference operating data is: In the formula, For the Time point The correlation coefficient between the characteristic data of the industrial automation equipment operation data and the reference operation data, It is the resolution coefficient between the operation data characteristics of industrial automation equipment and the reference operation data; The correlation between the operating data characteristics of different industrial automation equipment and the reference operating data is expressed as: In the formula, For the The correlation between the operating data characteristics of an industrial automation equipment and the reference operating data.

[0010] Preferably, the weight coefficients of the operation data characteristics of different industrial automation equipment and the correlation with the reference operation data are combined with the softmax loss function and the center loss function to establish the comprehensive evaluation parameters of the operation data of the industrial automation equipment, and based on the machine learning algorithm model, a comprehensive evaluation model of the operation data of the industrial automation equipment is established to judge the comprehensive quality and abnormal type of the operation of the industrial automation equipment. Specifically, it includes: based on the softmax loss function formula, establishing the loss function of the predicted value of the operation data characteristics of the industrial automation equipment and the reference operation data; Based on the center loss function, all distances between the center of each industrial automation equipment operation data feature class and the samples within the class are calculated; according to the weight coefficients of different industrial automation equipment operation data features and the correlation with the reference operation data, the softmax loss function and the center loss function are combined to establish the comprehensive evaluation parameters of industrial automation equipment operation data; Based on the machine learning algorithm model, the feature vector set of industrial automation equipment operation data is trained and learned, and a comprehensive evaluation model for industrial automation equipment operation data is established; Based on the comprehensive evaluation model of industrial automation equipment operation data, the boundary threshold of the center of the characteristic class of each industrial automation equipment operation data is set; According to the weight coefficient matrix of different industrial automation equipment operation data characteristics and the correlation matrix with the reference operation data, combined with the comprehensive evaluation parameters of industrial automation equipment operation data, the comprehensive quality and abnormal type of industrial automation equipment operation are judged; whether the predicted value of the comprehensive evaluation model of industrial automation equipment operation data exceeds the boundary threshold of the center of each industrial automation equipment operation data characteristic class, if so, it means that the industrial automation equipment operation data characteristic is abnormal, an alarm is raised, and the abnormal type is judged and prompted, if not, it means that the industrial automation equipment is operating normally; The loss function of the predicted value of the industrial automation equipment operation data feature and the reference operation data is: In the formula, For the The loss value of the predicted value of the operating data characteristics of industrial automation equipment and the reference operating data, The number of data sets for the feature vector set of industrial automation equipment operation data, For the Industrial automation equipment operation data feature bias items; the distance expressions between the center of each industrial automation equipment operation data feature class and the samples within the class are: In the formula, For the All distances between the center of the characteristic class of industrial automation equipment operation data and the samples within the class, The number of data sets for the feature vector set of industrial automation equipment operation data, For the Industrial automation equipment operation data feature center, among which: It is the Euclidean L2 norm of all distances between the center of each industrial automation equipment operation data feature class and the samples within the class. The expansion is: ; The comprehensive evaluation parameter expression of the industrial automation equipment operation data is: In the formula, Comprehensive evaluation parameters for industrial automation equipment operation data. is a hyperparameter used to balance the softmax loss function and the center loss function.

[0011] Preferably, the industrial automation control human-machine interaction platform is established based on the intelligent sensing technology of the Internet of Things, which is used to receive, store and display the data of the operation of industrial automation equipment, and make an alarm through a prompt device according to the feedback abnormal information. Specifically, it includes: based on the comprehensive evaluation model of the operation data of industrial automation equipment, an industrial automation control human-machine interaction platform is established to build the operation environment of the comprehensive evaluation model of the operation data of industrial automation equipment; According to the type of industrial automation equipment, multiple groups of monitoring equipment are set up to collect data on the operating data characteristics of the industrial automation equipment; Based on the intelligent sensing technology of the Internet of Things, an industrial automation control human-computer interaction platform is established to receive, store and display the data of the operation of industrial automation equipment; Based on the industrial automation control human-computer interaction platform, it is used to update the parameters of the comprehensive evaluation model of industrial automation equipment operation data and predict the comprehensive quality and abnormal type of industrial automation equipment operation through parameter adjustment; A human-machine interaction platform based on industrial automation control is set up, and an alarm is issued through a prompt device according to the feedback of abnormal information. Furthermore, this scheme proposes an industrial automation control system using the intelligent sensing technology of the Internet of Things, which is used to implement the industrial automation control method using the intelligent sensing technology of the Internet of Things as mentioned above, including: A data processing module, which is used to obtain historical operation data of industrial automation equipment based on big data, extract the characteristics of automation equipment operation data, and establish a feature vector set of industrial automation equipment operation data; denoise and normalize the data in the feature vector set of industrial automation equipment operation data to eliminate the influence of abnormal peaks and dimensional differences; A comprehensive evaluation module, which is used to analyze the weights of different industrial automation equipment operation data characteristics that affect the control of industrial automation equipment based on the entropy method; determine the correlation between different industrial automation equipment operation data characteristics and reference operation data based on the objective evaluation method of grey theory; establish comprehensive evaluation parameters for industrial automation equipment operation data based on the weight coefficients of different industrial automation equipment operation data characteristics and the correlation with the reference operation data, combined with the softmax loss function and the center loss function, and establish a comprehensive evaluation model for industrial automation equipment operation data based on the machine learning algorithm model to judge the comprehensive quality of industrial automation equipment operation; a platform processing module, which is used to establish an industrial automation control human-computer interaction platform based on the intelligent perception technology of the Internet of Things, which is used to receive, store and display the operation data of industrial automation equipment, and make an alarm through a prompt device based on the feedback of abnormal information.

[0012] Preferably, the data processing module specifically includes: A feature extraction unit, the feature extraction unit is used to obtain historical operation data of industrial automation equipment based on big data, extract features of the automation equipment operation data, and establish a feature vector set of the industrial automation equipment operation data; The denoising and normalization unit is used to perform denoising and normalization processing on the data in the characteristic vector set of the industrial automation equipment operation data to eliminate the influence of abnormal peaks and dimensional differences.

[0013] Preferably, the comprehensive evaluation module specifically includes: A feature weight unit, the feature weight unit is used to analyze the weights of different industrial automation equipment operation data features that affect the control of the industrial automation equipment based on an entropy method; A correlation determination unit is used to determine the correlation between the operating data characteristics of different industrial automation equipment and the reference operating data based on the objective evaluation method of grey theory; a comprehensive evaluation unit is used to establish comprehensive evaluation parameters of the operating data of industrial automation equipment according to the weight coefficients of the operating data characteristics of different industrial automation equipment and the correlation with the reference operating data, combined with the softmax loss function and the center loss function, and to establish a comprehensive evaluation model for the operating data of industrial automation equipment based on the machine learning algorithm model to judge the comprehensive quality of the operation of industrial automation equipment.

[0014] Compared with the prior art, the present invention has the following beneficial effects: Based on big data, the historical operation data of industrial automation equipment is obtained, and the operation data characteristics of industrial automation equipment are extracted. By analyzing the operation data characteristics of industrial automation equipment, based on the entropy method, the weights of different operation data characteristics of industrial automation equipment that affect the control of industrial automation equipment are analyzed, and the weight matrix of the operation data characteristics of industrial automation equipment is established. Secondly, through the objective evaluation method of grey theory, the correlation between the operation data characteristics of different industrial automation equipment and the reference operation data is determined, and the correlation matrix between the operation data characteristics of industrial automation equipment and the reference operation data is established. Finally, through the weight coefficients of the operation data characteristics of different industrial automation equipment and the correlation with the reference operation data, a comprehensive evaluation model for the operation data of industrial automation equipment is established, and according to the input values ​​of the weight matrix of the operation data characteristics of industrial automation equipment and the correlation matrix of the operation data characteristics of industrial automation equipment and the reference operation data, the comprehensive quality of the operation of industrial automation equipment is judged, thereby effectively improving the correlation of the operation data of each industrial automation equipment and the accuracy of the comprehensive quality evaluation of the operation of industrial automation equipment, and increasing the stability and reliability of industrial automation control. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of an industrial automation control method using the Internet of Things intelligent sensing technology of the present invention; Figure 2 The weighted flow chart of analyzing the operating data characteristics of different industrial automation equipment that affect the control of industrial automation equipment based on the entropy value method of the present invention; Figure 3 The objective evaluation method based on grey theory of the present invention is a flowchart for determining the correlation between the operating data characteristics of different industrial automation equipment and the reference operating data; Figure 4The present invention establishes comprehensive evaluation parameters for the operation data of industrial automation equipment based on the weight coefficients of the operation data characteristics of different industrial automation equipment and the degree of correlation with the reference operation data, combines the softmax loss function and the center loss function, and establishes a comprehensive evaluation model for the operation data of industrial automation equipment based on the machine learning algorithm model to judge the comprehensive quality and abnormal type of the operation of industrial automation equipment. DETAILED DESCRIPTION

[0016] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0017] Reference Figure 1 As shown, an industrial automation control method using the Internet of Things intelligent sensing technology includes: Based on big data, the historical operation data of industrial automation equipment is obtained, and the characteristics of the operation data of automation equipment are extracted to establish the characteristic vector set of the operation data of industrial automation equipment; the data in the characteristic vector set of the operation data of industrial automation equipment is denoised and normalized to eliminate the influence of abnormal peaks and dimensional differences; Based on the entropy method, the weights of the operating data characteristics of different industrial automation equipment that affect the control of industrial automation equipment are analyzed; Based on the objective evaluation method of grey theory, the correlation between the operating data characteristics of different industrial automation equipment and the reference operating data is determined; According to the weight coefficients of the operating data characteristics of different industrial automation equipment and the correlation with the reference operating data, combined with the softmax loss function and the center loss function, the comprehensive evaluation parameters of the operating data of industrial automation equipment are established, and based on the machine learning algorithm model, the comprehensive evaluation model of the operating data of industrial automation equipment is established to judge the comprehensive quality of the operation of industrial automation equipment; Based on the intelligent sensing technology of the Internet of Things, an industrial automation control human-computer interaction platform is established to receive, store and display the data of the operation of industrial automation equipment, and to issue alarm prompts through the prompt device according to the feedback of abnormal information.

[0018] It can be explained that this scheme is based on big data, obtains historical operation data of industrial automation equipment, extracts the characteristics of industrial automation equipment operation data, and analyzes the characteristics of industrial automation equipment operation data. Based on the entropy method, the weights of different industrial automation equipment operation data characteristics that affect the control of industrial automation equipment are analyzed, and the weight matrix of industrial automation equipment operation data characteristics is established. Secondly, through the objective evaluation method of gray theory, the correlation between different industrial automation equipment operation data characteristics and reference operation data is determined, and the correlation matrix between industrial automation equipment operation data characteristics and reference operation data is established. Finally, through the weight coefficients of different industrial automation equipment operation data characteristics and the correlation with reference operation data, a comprehensive evaluation model for industrial automation equipment operation data is established, and according to the input values ​​of the weight matrix of industrial automation equipment operation data characteristics and the correlation matrix of industrial automation equipment operation data characteristics and reference operation data, the comprehensive quality of industrial automation equipment operation is judged, thereby effectively improving the correlation of each industrial automation equipment operation data and the comprehensive quality evaluation accuracy of industrial automation equipment operation, and increasing the stability and reliability of industrial automation control. Reference Figure 2 As shown, the entropy method is used to analyze the weights of different industrial automation equipment operation data features that affect the control of industrial automation equipment, specifically including: According to the data processed by the feature vector set of industrial automation equipment operation data, calculate the Time point The proportion of operating data characteristics of industrial automation equipment; According to Time point The proportion of the operating data characteristics of industrial automation equipment is calculated The information entropy of the operating data characteristics of industrial automation equipment; According to The information entropy of the operating data characteristics of industrial automation equipment is calculated. The effective value of the characteristic data of the operation data of industrial automation equipment; According to The effective value of the operating data characteristics of each industrial automation equipment is used to calculate the weight of the operating data characteristics of each industrial automation equipment; According to the weights of the operating data features of each industrial automation equipment, a weight matrix of the operating data features of the industrial automation equipment is established; the first Time point The weight expression of the operating data characteristics of industrial automation equipment is: In the formula, For the Time point The proportion of the operating data characteristics of industrial automation equipment, For the Time point The number of industrial automation equipment operation data features, wherein i is the i-th sequence number in the time interval sequence of the automation equipment operation data features, and j is the j-th type of the industrial automation equipment operation data features; the The information entropy expression of the operating data characteristics of industrial automation equipment is: In the formula, For the The information entropy value of the characteristic data of the industrial automation equipment operation; The effective value expression of the characteristic data of the operation data of industrial automation equipment is: Where, is the effective value of the data characteristic of the operation data of the th industrial automation equipment; the weight expression of the operation data characteristics of each industrial automation equipment is: In the formula, For the The weight of the operating data features of industrial automation equipment.

[0019] It can be explained that there are many factors that affect the operation of industrial automation equipment. Different industrial automation equipment operation factors have different degrees of influence on the operation of industrial automation equipment. It is necessary to determine the weights of each industrial automation equipment operation factor, and then improve the system's judgment on the operating status of industrial automation equipment through the weights of different industrial automation equipment operation data features. This scheme uses the entropy method, based on the actual sample set data of industrial automation equipment operation data features, through sorting and analysis, to effectively obtain the weights of different industrial automation equipment operation data features, avoiding the subjective influence of human factors, thereby improving the reliability of the weights of industrial automation equipment operation data features. Figure 3 As shown, the objective evaluation method based on grey theory to determine the correlation between the operating data characteristics of different industrial automation equipment and the reference operating data specifically includes: Determine the first The absolute difference between the characteristic data of the industrial automation equipment operation data and the reference operation data at a time point; Based on big data, obtain the resolution coefficients of the operating data characteristics and reference operating data of different industrial automation equipment; According to the absolute difference between the characteristic data of the operation data of the industrial automation equipment and the reference operation data, the correlation coefficient between the characteristics of the operation data of different industrial automation equipment and the reference operation data is calculated; Calculate the correlation between the operating data characteristics of different industrial automation equipment and the reference operating data according to the correlation coefficient between the operating data characteristics of different industrial automation equipment and the reference operating data; According to the correlation between the operating data characteristics of different industrial automation equipment and the reference operating data, a correlation matrix between the operating data characteristics of industrial automation equipment and the reference operating data is established; the determination The absolute difference between the characteristic data of the industrial automation equipment operation data and the reference operation data at a time point is expressed as: In the formula, For the Time point The absolute difference between the characteristic data of the operation data of an industrial automation equipment and the reference operation data, is the normalized data of the jth industrial automation equipment operation data at the i-th time point, For the Time point The reference operating data of the operating data characteristics of industrial automation equipment; the correlation coefficient expression between the operating data characteristics of the industrial automation equipment and the reference operating data is: In the formula, For the Time point The correlation coefficient between the characteristic data of the industrial automation equipment operation data and the reference operation data, It is the resolution coefficient between the operation data characteristics of industrial automation equipment and the reference operation data; The correlation between the operating data characteristics of different industrial automation equipment and the reference operating data is expressed as: In the formula, For the The correlation between the operating data characteristics of an industrial automation equipment and the reference operating data.

[0020] It can be explained that when modeling the operating data characteristics of industrial automation equipment, some industrial automation equipment data will have problems with small samples and poor information, or when there are uncertain factors in the operating data of various industrial automation equipment, it is difficult to quantify and establish correlation when identifying and processing the operating data characteristics of industrial automation equipment. This solution uses the objective evaluation method of grey theory to determine the correlation between the operating data characteristics of different industrial automation equipment and the reference operating data. Through the overall correlation of the operating data characteristics of various industrial automation equipment, the internal connection and dynamic change law of the operating data characteristics of various industrial automation equipment can be effectively determined, thereby improving the reliability and correlation of the operating data characteristics of industrial automation equipment. Figure 4As shown, according to the weight coefficients of the operating data characteristics of different industrial automation equipment and the correlation with the reference operating data, combined with the softmax loss function and the center loss function, the comprehensive evaluation parameters of the operating data of industrial automation equipment are established, and based on the machine learning algorithm model, the comprehensive evaluation model of the operating data of industrial automation equipment is established to judge the comprehensive quality and abnormal type of the operation of industrial automation equipment. Specifically, it includes: Based on the softmax loss function formula, the loss function of the predicted value of the industrial automation equipment operation data feature and the reference operation data is established; based on the center loss function, all distances between the center of each industrial automation equipment operation data feature class and the samples within the class are calculated; According to the weight coefficients of the operating data characteristics of different industrial automation equipment and the correlation with the reference operating data, the comprehensive evaluation parameters of the operating data of industrial automation equipment are established by combining the softmax loss function and the central loss function. Based on the machine learning algorithm model, the feature vector set of industrial automation equipment operation data is trained and learned, and a comprehensive evaluation model for industrial automation equipment operation data is established; Based on the comprehensive evaluation model of industrial automation equipment operation data, the boundary threshold of the center of the characteristic class of each industrial automation equipment operation data is set; According to the weight coefficient matrix of different industrial automation equipment operation data characteristics and the correlation matrix with the reference operation data, combined with the comprehensive evaluation parameters of industrial automation equipment operation data, the comprehensive quality and abnormal type of industrial automation equipment operation are judged; Determine whether the predicted value of the comprehensive evaluation model of the operation data of the industrial automation equipment exceeds the boundary threshold of the center of the characteristic class of the operation data of each industrial automation equipment. If so, it means that the operation data characteristic of the industrial automation equipment is abnormal, an alarm is raised, and the abnormal type is determined and prompted. If not, it means that the industrial automation equipment is operating normally; The loss function of the predicted value of the industrial automation equipment operation data feature and the reference operation data is: In the formula, For the The loss value of the predicted value of the operating data characteristics of industrial automation equipment and the reference operating data, The number of data sets for the feature vector set of industrial automation equipment operation data, For the Industrial automation equipment operation data feature bias items; the distance expressions between the center of each industrial automation equipment operation data feature class and the samples within the class are: In the formula, For the All distances between the center of the characteristic class of industrial automation equipment operation data and the samples within the class, The number of data sets for the feature vector set of industrial automation equipment operation data, For the Industrial automation equipment operation data feature center, among which: It is the Euclidean L2 norm of all distances between the center of each industrial automation equipment operation data feature class and the samples within the class. The expansion is: The comprehensive evaluation parameter expression of the industrial automation equipment operation data is: In the formula, Comprehensive evaluation parameters for industrial automation equipment operation data. is a hyperparameter used to balance the softmax loss function and the center loss function.

[0021] It can be explained that the center loss enhances the intra-class compactness of the model by minimizing the distance between the features of similar samples. Combining Softmax Loss with the center loss can achieve intra-class compactness and inter-class separation while ensuring class separability. When processing the feature data of industrial automation equipment operation data, it can effectively identify the features of different industrial automation equipment operation data and make the feature samples of each industrial automation equipment operation data more compact in the feature space. This scheme introduces the weight coefficients of different industrial automation equipment operation data features and the correlation with the reference operation data into the traditional softmax loss function combined with the center loss function, and establishes the comprehensive evaluation parameters of the industrial automation equipment operation data, thereby improving the accuracy and reliability of the prediction of the comprehensive evaluation model of the industrial automation equipment operation data, effectively improving the correlation of the operation data of each industrial automation equipment and the comprehensive quality evaluation accuracy of the industrial automation equipment operation, and increasing the stability and reliability of industrial automation control.

[0022] Further, based on the same inventive concept as the above-mentioned industrial automation control method using the Internet of Things intelligent sensing technology, this solution proposes an industrial automation control system using the Internet of Things intelligent sensing technology, including: A data processing module, the data processing module is used to obtain the historical operation data of industrial automation equipment based on big data, and extract the characteristics of automation equipment operation data, and establish a characteristic vector set of industrial automation equipment operation data; denoise and normalize the data in the characteristic vector set of industrial automation equipment operation data to eliminate the influence of abnormal peaks and dimensional differences; a comprehensive evaluation module, the comprehensive evaluation module is used to analyze the weights of different industrial automation equipment operation data characteristics that affect the control of industrial automation equipment based on the entropy method; determine the correlation between different industrial automation equipment operation data characteristics and reference operation data based on the objective evaluation method of grey theory; according to the weight coefficients of different industrial automation equipment operation data characteristics and the correlation with the reference operation data, combined with the softmax loss loss function and the center loss function, establish the comprehensive evaluation parameters of industrial automation equipment operation data, and establish the comprehensive evaluation model of industrial automation equipment operation data based on the machine learning algorithm model to judge the comprehensive quality of industrial automation equipment operation; The platform processing module is used to establish an industrial automation control human-computer interaction platform based on the intelligent perception technology of the Internet of Things, and is used to receive, store and display the data of the operation of industrial automation equipment, and to make an alarm through a prompt device according to the feedback of abnormal information; the data processing module specifically includes: A feature extraction unit, the feature extraction unit is used to obtain historical operation data of industrial automation equipment based on big data, extract features of the automation equipment operation data, and establish a feature vector set of the industrial automation equipment operation data; A denoising and normalization unit, which is used to perform denoising and normalization processing on the data in the characteristic vector set of the industrial automation equipment operation data to eliminate the influence of abnormal peaks and dimensional differences; The comprehensive evaluation module specifically includes: A feature weight unit, the feature weight unit is used to analyze the weights of different industrial automation equipment operation data features that affect the control of the industrial automation equipment based on an entropy method; A correlation determination unit, wherein the correlation determination unit is used to determine the correlation between the operating data characteristics of different industrial automation equipment and the reference operating data based on a grey theory objective evaluation method; A comprehensive evaluation unit is used to establish comprehensive evaluation parameters of industrial automation equipment operation data according to weight coefficients of different industrial automation equipment operation data characteristics and correlation with reference operation data, combined with softmax loss function and center loss function, and to establish a comprehensive evaluation model for industrial automation equipment operation data based on a machine learning algorithm model to judge the comprehensive quality of industrial automation equipment operation.

[0023] In summary, the advantages of the present invention are: based on big data, the historical operation data of industrial automation equipment is obtained, the operation data characteristics of industrial automation equipment are extracted, and by analyzing the operation data characteristics of industrial automation equipment, based on the entropy method, the weights of different operation data characteristics of industrial automation equipment that affect the control of industrial automation equipment are analyzed, and a weight matrix of the operation data characteristics of industrial automation equipment is established. Secondly, through the objective evaluation method of grey theory, the correlation between the operation data characteristics of different industrial automation equipment and the reference operation data is determined, and a correlation matrix between the operation data characteristics of industrial automation equipment and the reference operation data is established. Finally, through the weight coefficients of the operation data characteristics of different industrial automation equipment and the correlation with the reference operation data, an industrial automation equipment operation data comprehensive evaluation model is established, and according to the input values ​​of the weight matrix of the operation data characteristics of industrial automation equipment and the correlation matrix of the operation data characteristics of industrial automation equipment and the reference operation data, the comprehensive quality of the operation of industrial automation equipment is judged, thereby effectively improving the correlation of the operation data of each industrial automation equipment and the comprehensive quality evaluation accuracy of the operation of industrial automation equipment, and increasing the stability and reliability of industrial automation control.

[0024] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. An industrial automation control method using the Internet of Things intelligent sensing technology, characterized in that: include: Based on big data, the historical operation data of industrial automation equipment is obtained, and the operation data features of automation equipment are extracted to establish the feature vector set of industrial automation equipment operation data; De-noising and normalizing the data in the characteristic vector set of industrial automation equipment operation data to eliminate the influence of abnormal peaks and dimensional differences; Based on the entropy method, the weights of the operating data characteristics of different industrial automation equipment that affect the control of industrial automation equipment are analyzed; Based on the objective evaluation method of grey theory, the correlation between the operating data characteristics of different industrial automation equipment and the reference operating data is determined; According to the weight coefficients of the operating data characteristics of different industrial automation equipment and the correlation with the reference operating data, combined with the softmax loss function and the center loss function, the comprehensive evaluation parameters of the operating data of industrial automation equipment are established, and based on the machine learning algorithm model, the comprehensive evaluation model of the operating data of industrial automation equipment is established to judge the comprehensive quality of the operation of industrial automation equipment; Based on the intelligent sensing technology of the Internet of Things, an industrial automation control human-computer interaction platform is established to receive, store and display the data of the operation of industrial automation equipment, and to issue alarm prompts through the prompt device according to the feedback of abnormal information.

2. The industrial automation control method using the Internet of Things intelligent sensing technology according to claim 1 is characterized in that: The method of obtaining the historical operation data of industrial automation equipment based on big data, extracting the operation data features of the automation equipment, and establishing the operation data feature vector set of the industrial automation equipment specifically includes: Based on big data, obtain historical operation data and reference operation data of industrial automation equipment; According to the type and parameters of industrial automation equipment operation, extract the automation equipment operation data characteristics that affect the operation of automation equipment; According to the type of operation of industrial automation equipment, a time interval sequence of the operation data characteristics of the automation equipment is established respectively; The operation data characteristics of automation equipment are classified and counted in the time interval sequence, and the feature vector set of industrial automation equipment operation data is established.

3. The industrial automation control method using the Internet of Things intelligent sensing technology according to claim 2 is characterized in that: The denoising and normalizing of the data in the characteristic vector set of the industrial automation equipment operation data to eliminate the influence of abnormal peaks and dimensional differences specifically includes: Based on the first-order Kalman filter algorithm, the data in the characteristic vector set of the operation data of industrial automation equipment is filtered and denoised; According to the normalization formula, the influence of data dimension difference in the characteristic vector set of the operation data of industrial automation equipment is eliminated; The normalization formula is: In the formula, For the Time point The data after the normalization of the operating data characteristics of industrial automation equipment, For the Time point The original data of the operation data characteristics of industrial automation equipment, For the The minimum value of the characteristic data of the operation data of industrial automation equipment, For the The maximum value of the characteristic data of the operation data of industrial automation equipment.

4. The industrial automation control method using the Internet of Things intelligent sensing technology according to claim 3 is characterized in that: The entropy method is used to analyze the weights of different industrial automation equipment operation data features that affect the control of industrial automation equipment, specifically including: According to the data processed by the feature vector set of industrial automation equipment operation data, calculate the Time point The proportion of operating data characteristics of industrial automation equipment; According to Time point The proportion of the operating data characteristics of industrial automation equipment is calculated The information entropy of the operating data characteristics of industrial automation equipment; According to The information entropy of the operating data characteristics of industrial automation equipment is calculated. The effective value of the characteristic data of the operation data of industrial automation equipment; According to The effective value of the operating data feature data of each industrial automation equipment is calculated, and the weight of the operating data feature of each industrial automation equipment is calculated; according to the weight of the operating data feature of each industrial automation equipment, a weight matrix of the operating data feature of the industrial automation equipment is established; The said Time point The weight expression of the operating data characteristics of industrial automation equipment is: In the formula, For the Time point The proportion of the operating data characteristics of industrial automation equipment, For the Time point The number of industrial automation equipment operation data features, wherein i is the i-th sequence number in the time interval sequence of the automation equipment operation data features, and j is the j-th type of the industrial automation equipment operation data features; the The information entropy expression of the operating data characteristics of industrial automation equipment is: In the formula, For the The information entropy value of the operating data characteristics of industrial automation equipment; The said The effective value expression of the characteristic data of the operation data of industrial automation equipment is: In the formula, For the The effective value of the characteristic data of the operation data of industrial automation equipment; The weight expression of the operating data characteristics of each industrial automation equipment is: In the formula, For the The weight of the operating data features of industrial automation equipment.

5. The industrial automation control method using the Internet of Things intelligent sensing technology according to claim 4 is characterized in that: The objective evaluation method based on grey theory to determine the correlation between the operating data characteristics of different industrial automation equipment and the reference operating data specifically includes: Determine the first The absolute difference between the characteristic data of the industrial automation equipment operation data and the reference operation data at a time point; Based on big data, obtain the resolution coefficients of the operating data characteristics and reference operating data of different industrial automation equipment; According to the absolute difference between the characteristic data of the operation data of the industrial automation equipment and the reference operation data, the correlation coefficient between the characteristics of the operation data of different industrial automation equipment and the reference operation data is calculated; According to the correlation coefficient between the operating data characteristics of different industrial automation equipment and the reference operating data, the correlation between the operating data characteristics of different industrial automation equipment and the reference operating data is calculated; according to the correlation between the operating data characteristics of different industrial automation equipment and the reference operating data, the correlation matrix between the operating data characteristics of industrial automation equipment and the reference operating data is established; The determination The absolute difference between the characteristic data of the industrial automation equipment operation data and the reference operation data at a time point is expressed as: In the formula, For the Time point The absolute difference between the characteristic data of the operation data of an industrial automation equipment and the reference operation data, is the normalized data of the jth industrial automation equipment operation data at the i-th time point, For the Time point Reference operating data of the operating data characteristics of industrial automation equipment; The correlation coefficient expression between the industrial automation equipment operation data characteristics and the reference operation data is: In the formula, For the Time point The correlation coefficient between the characteristic data of the industrial automation equipment operation data and the reference operation data, It is the resolution coefficient between the operation data characteristics of industrial automation equipment and the reference operation data; The correlation between the operating data characteristics of different industrial automation equipment and the reference operating data is expressed as: In the formula, For the The correlation between the operating data characteristics of an industrial automation equipment and the reference operating data.

6. The industrial automation control method using the Internet of Things intelligent sensing technology according to claim 5 is characterized in that: According to the weight coefficients of the operation data characteristics of different industrial automation equipment and the correlation with the reference operation data, combined with the softmax loss function and the center loss function, the comprehensive evaluation parameters of the operation data of industrial automation equipment are established, and based on the machine learning algorithm model, the comprehensive evaluation model of the operation data of industrial automation equipment is established to judge the comprehensive quality and abnormal type of the operation of industrial automation equipment. Specifically, the following are included: Based on the softmax loss function formula, the loss function of the predicted value of the operating data characteristics of industrial automation equipment and the reference operating data is established; Based on the center loss function, all distances between the center of each industrial automation equipment operation data feature class and the samples within the class are calculated; According to the weight coefficients of the operating data characteristics of different industrial automation equipment and the correlation with the reference operating data, the comprehensive evaluation parameters of the operating data of industrial automation equipment are established by combining the softmax loss function and the central loss function. Based on the machine learning algorithm model, the feature vector set of industrial automation equipment operation data is trained and learned, and a comprehensive evaluation model for industrial automation equipment operation data is established; Based on the comprehensive evaluation model of industrial automation equipment operation data, the boundary threshold of the center of the characteristic class of each industrial automation equipment operation data is set; According to the weight coefficient matrix of different industrial automation equipment operation data characteristics and the correlation matrix with the reference operation data, combined with the comprehensive evaluation parameters of industrial automation equipment operation data, the comprehensive quality and abnormal type of industrial automation equipment operation are judged; Determine whether the predicted value of the comprehensive evaluation model of the operation data of industrial automation equipment exceeds the boundary threshold of the center of each industrial automation equipment operation data feature class. If so, it means that the operation data feature of the industrial automation equipment is abnormal, an alarm is raised, and the abnormal type is determined and prompted. If not, it means that the industrial automation equipment is operating normally; the loss function of the predicted value of the industrial automation equipment operation data feature and the reference operation data is: In the formula, For the The loss value of the predicted value of the operating data characteristics of industrial automation equipment and the reference operating data, The number of data sets for the feature vector set of industrial automation equipment operation data, For the Industrial automation equipment operation data feature bias items; All distance expressions between the center of each industrial automation equipment operation data feature class and the samples within the class are: In the formula, For the All distances between the center of the characteristic class of industrial automation equipment operation data and the samples within the class, The number of data sets for the feature vector set of industrial automation equipment operation data, For the Industrial automation equipment operation data feature center, among which: It is the Euclidean L2 norm of all distances between the center of each industrial automation equipment operation data feature class and the samples within the class. The expansion is: ; The comprehensive evaluation parameter expression of the industrial automation equipment operation data is: In the formula, Comprehensive evaluation parameters for industrial automation equipment operation data. is a hyperparameter used to balance the softmax loss function and the center loss function.

7. The industrial automation control method using the Internet of Things intelligent sensing technology according to claim 6 is characterized in that: The industrial automation control human-machine interaction platform is established based on the intelligent sensing technology of the Internet of Things, which is used to receive, store and display the data of the operation of industrial automation equipment, and make an alarm through the prompt device according to the feedback of abnormal information. Specifically, it includes: Based on the comprehensive evaluation model of industrial automation equipment operation data, an industrial automation control human-computer interaction platform is established to build the operating environment of the comprehensive evaluation model of industrial automation equipment operation data; According to the type of industrial automation equipment, multiple groups of monitoring equipment are set up to collect data on the operating data characteristics of the industrial automation equipment; Based on the intelligent sensing technology of the Internet of Things, an industrial automation control human-computer interaction platform is established to receive, store and display the data of the operation of industrial automation equipment; Based on the industrial automation control human-computer interaction platform, it is used to update the parameters of the comprehensive evaluation model of industrial automation equipment operation data and predict the comprehensive quality and abnormal type of industrial automation equipment operation through parameter adjustment; A human-computer interaction platform based on industrial automation control is set up to issue an alarm through a prompt device based on the feedback of abnormal information.

8. An industrial automation control system using the Internet of Things intelligent sensing technology, characterized in that: The industrial automation control method using the Internet of Things intelligent sensing technology as described in any one of claims 1 to 7 comprises: A data processing module, the data processing module is used to obtain the historical operation data of industrial automation equipment based on big data, and extract the characteristics of automation equipment operation data, and establish a characteristic vector set of industrial automation equipment operation data; denoise and normalize the data in the characteristic vector set of industrial automation equipment operation data to eliminate the influence of abnormal peaks and dimensional differences; a comprehensive evaluation module, the comprehensive evaluation module is used to analyze the weights of different industrial automation equipment operation data characteristics that affect the control of industrial automation equipment based on the entropy method; determine the correlation between different industrial automation equipment operation data characteristics and reference operation data based on the objective evaluation method of grey theory; according to the weight coefficients of different industrial automation equipment operation data characteristics and the correlation with the reference operation data, combined with the softmax loss loss function and the center loss function, establish the comprehensive evaluation parameters of industrial automation equipment operation data, and establish the comprehensive evaluation model of industrial automation equipment operation data based on the machine learning algorithm model to judge the comprehensive quality of industrial automation equipment operation; The platform processing module is used to establish an industrial automation control human-computer interaction platform based on the Internet of Things intelligent sensing technology, and is used to receive, store and display data on the operation of industrial automation equipment, and to issue an alarm through a prompt device based on the feedback of abnormal information.

9. The industrial automation control system using the Internet of Things intelligent sensing technology according to claim 8 is characterized in that: The data processing module specifically includes: A feature extraction unit, the feature extraction unit is used to obtain historical operation data of industrial automation equipment based on big data, extract features of the automation equipment operation data, and establish a feature vector set of the industrial automation equipment operation data; The denoising and normalization unit is used to perform denoising and normalization processing on the data in the characteristic vector set of the operation data of the industrial automation equipment to eliminate the influence of abnormal peaks and dimensional differences.

10. The industrial automation control system using the Internet of Things intelligent sensing technology according to claim 9 is characterized in that: The comprehensive evaluation module specifically includes: A feature weight unit, the feature weight unit is used to analyze the weights of different industrial automation equipment operation data features that affect the control of the industrial automation equipment based on an entropy method; A correlation determination unit, wherein the correlation determination unit is used to determine the correlation between the operating data characteristics of different industrial automation equipment and the reference operating data based on a grey theory objective evaluation method; A comprehensive evaluation unit is used to establish comprehensive evaluation parameters of industrial automation equipment operation data according to weight coefficients of different industrial automation equipment operation data characteristics and correlation with reference operation data, combined with softmax loss function and center loss function, and to establish a comprehensive evaluation model for industrial automation equipment operation data based on a machine learning algorithm model to judge the comprehensive quality of industrial automation equipment operation.

Images