Method and system for evaluating working state of measurement object based on pressure sensor

Abstract

The invention discloses a method and a system for evaluating the working state of a measured object based on a pressure sensor, belongs to the technical field of state evaluation, and solves the problem that the evaluation requirement based on the pressure sensor is difficult to adapt due to the fact that evaluation is carried out based on a single or few similarity indexes when the on-duty state of a to-be-audited employee is judged by an existing method. The method comprises the following steps: preprocessing a time sequence pressure electric signal based on a characteristic frequency in combination with an adaptive filtering algorithm to obtain a preprocessing set, identifying and analyzing the preprocessing set by a state evaluation model, and outputting a working state evaluation result of a measurement object; evaluating whether a comprehensive evaluation value in the result exceeds a preset evaluation threshold value or not based on the working state; in the invention, the working state evaluation result generated by combining the state evaluation model with the adaptive filtering algorithm has higher accuracy, and the state evaluation model can realize the order-lifting reconstruction function of the sequential pressure electric signal, so that the working state of the measured object is comprehensively reflected.

Description

Technical Field

[0001] The present invention belongs to the technical field of state evaluation, and in particular relates to a method and system for evaluating the working state of a measurement object based on a pressure sensor. Background Art

[0002] At present, many office environments need to know whether the staff are at their work stations, which can facilitate the transfer of calls or handover of work. However, the attendance status of office staff is usually counted through attendance punching equipment, which can usually only count the time of going to and from get off work, and lacks real-time statistical positioning of the staff's on-the-job status.

[0003] Chinese patent CN116798087A discloses a method and system for detecting the on-the-job status of employees, the method comprising: inputting an image of an employee to be audited into a target detection model to obtain first feature data of the image of the employee to be audited; based on a target similarity function, calculating the similarity between the first feature data and the second feature data corresponding to each employee image pre-stored in a database to determine the employee identity information corresponding to the employee image with the highest similarity; judging the on-the-job status of the employee to be audited based on the employee identity information and the workstation information of the employee to be audited; however, the existing method uses a target similarity function to judge the on-the-job status of the employee to be audited based on a single or a few similarity indicators, which is difficult to adapt to the evaluation requirements based on pressure sensors. In view of the above problems, we propose a method and system for evaluating the working status of a measured object based on a pressure sensor. Summary of the invention

[0004] The purpose of the present invention is to address the shortcomings of the prior art and provide a method and system for evaluating the working status of a measurement object based on a pressure sensor, thereby solving the problem that the existing method uses a target similarity function to judge the on-the-job status of an employee to be audited based on a single or a few similarity indicators, which is difficult to adapt to the evaluation needs based on a pressure sensor.

[0005] The present invention is implemented by a method for evaluating the working state of a measurement object based on a pressure sensor, the method for evaluating the working state of a measurement object based on a pressure sensor comprising: Acquire a time-series pressure electrical signal based on a pressure sensor, pre-process the time-series pressure electrical signal based on a characteristic frequency combined with an adaptive filtering algorithm to obtain a pre-processing set, and upload the pre-processing set to a state database; Pre-build the state assessment model, extract the modeling sample set from the state database, divide the modeling sample set into a training set and a test set in a ratio of 3:1, use the training set and the test set to train the state assessment model, and output the converged state assessment model; The preprocessing set is loaded in real time, and the state assessment model is executed with the preprocessing set as input. The state assessment model identifies and analyzes the preprocessing set and outputs the working state assessment result of the measured object; Obtain the work status assessment result, and based on whether the comprehensive assessment value in the work status assessment result exceeds the preset assessment threshold, if it exceeds the preset assessment threshold, trigger the work status warning instruction.

[0006] Preferably, the method for preprocessing the temporal pressure electrical signal based on characteristic frequency combined with an adaptive filtering algorithm specifically includes: Loading a time-series pressure electrical signal, dividing the time-series pressure electrical signal into at least one set of characteristic frequency sets based on a preset sampling period, and processing abnormal values ​​and missing values ​​of the characteristic frequency sets; Load the characteristic frequency set, identify the discrete frequency distribution, continuous frequency distribution, and stress-free frequency distribution in the characteristic frequency set based on the preset judgment period, and assign labels to the sampling periods corresponding to the discrete frequency distribution, continuous frequency distribution, and stress-free frequency distribution, wherein the discrete frequency distribution is marked as the working state, the continuous frequency distribution is marked as the state to be identified, and the stress-free frequency distribution is marked as the state of leaving the workstation; Load the continuous frequency distribution, obtain the spectrum sequence corresponding to the continuous frequency distribution based on the fast Fourier transform, and calculate the amplitude energy and phase of the spectrum sequence; The amplitude energy of the spectrum sequence is calculated by the following formula: (1) (2) in, represents the amplitude energy of the spectrum sequence, is the phase of the spectrum sequence, Indicates the number of consecutive signal points, represents the continuous frequency distribution based on the fast Fourier transform input representation, is the signal frequency; A clustering algorithm is used to identify the central amplitude energy within a preset judgment period, and the amplitude energy and phase of the spectrum sequence are loaded to determine whether there is an approximate signal frequency within the preset judgment period; If there is no approximate frequency, the signal frequency suppression filtering process within the preset judgment period is not performed; If there is an approximate frequency, the approximate signal frequency is suppressed based on a low-pass filter, the amplitude energy corresponding to the approximate signal frequency is obtained by combining the low-pass filter, and the continuous frequency distribution after the suppression filtering is output; The continuous frequency distribution, discrete frequency distribution, stress-free frequency distribution and corresponding marking states after loading suppression filtering are integrated to obtain the preprocessing set.

[0007] Preferably, the method for suppressing the frequency of the approximate signal based on a low-pass filter further includes: Loading the approximate signal frequency and the amplitude energy corresponding to the approximate signal frequency within a preset judgment period, and calculating the overlapping similarity value between the approximate signal frequency and the center signal frequency corresponding to the center amplitude energy; Based on the low-pass filter combined with the overlapping similarity value, the harmonic suppression of the approximate signal frequency is performed, and the filtered approximate signal frequency is output; Obtain the filtered approximate signal frequency, and use the filtered approximate signal frequency to perform inverse fast Fourier transform to suppress the approximate signal frequency; Among them, the overlap similarity value is calculated by the following formula: (3) in, represents the overlap similarity value, is the number of iterative filtering times of the low-pass filter, Respectively represent the amplitude energy and center amplitude energy corresponding to the approximate signal frequency, are the approximate signal frequency and the center signal frequency respectively; When the inverse fast Fourier transform is performed using the filtered approximate signal frequency, the inverse fast Fourier transform formula is: (4) in, represents the overlap similarity value, is the sampling angle difference of the approximate signal frequency, is the sampling frequency of the approximate signal.

[0008] Preferably, the method of using a training set and a test set to train a state evaluation model specifically includes: Load the pre-built state assessment model, training set, and test set, and set the hyperparameters, iteration rounds, and training batches of the state assessment model; Obtain the training set, use the cross entropy loss function to optimize the performance of the state evaluation model, and adjust the connection weights between the encoder, decoder, and convolutional layer in the hidden layer in combination with the back propagation algorithm; The root mean square error loss function is used to train the state classifier in the state evaluation model. The embedded feature fusion results generated by the feature fusion layer are compared with the true classification results to obtain the mean square error loss. The root mean square error loss function is expressed as: (5) in, Respectively represent the embedded feature fusion results and the real feature fusion results in the feature fusion matrix Middle Row, No. The elements of the column, Respectively represent the embedded feature fusion label and the real feature fusion label in the feature fusion matrix Middle Row, No. Elements of a column; Based on the state evaluation model outputted for training convergence within the preset iteration round, a test set is obtained, the state evaluation model is tested based on the test set, and the test results are output; Load the test results, and verify whether the state assessment model meets the preset model accuracy based on the test results. If it meets the preset model accuracy, output the converged state assessment model; If the preset model accuracy is not met, the Nadam optimizer is used to update the learning rate and hyperparameters of the state evaluation model, and the state evaluation model is iteratively trained through the training set.

[0009] Preferably, when the Nadam optimizer is used to update the learning rate and hyperparameters of the state evaluation model, the first-order moment and second-order moment of the Nadam optimizer tracking gradient are expressed as: (6) (7) (8) in, represents the hyperparameters of the state assessment model, is the learning rate, Evaluate model hyperparameters for loss function in state The gradient at are the first-order and second-order moment estimates of the gradient, are the first and second attenuation rate parameters.

[0010] Preferably, the state assessment model uses a multilayer perceptron as an initial model, the initial model consists of an input layer, a hidden layer and an output layer, a staggered time function is introduced into the input layer, the hidden layer is improved, an encoder and a decoder are introduced into the hidden layer, and three convolution layers are arranged between the encoder and the decoder, the convolution layer is a 3×3 convolution, and the activation function of the hidden layer is a ReLU activation function; The encoder is composed of two groups of maximum pooling layers and fully connected layers, and the fully connected layers are respectively connected to the maximum pooling layers. The decoder is composed of two groups of average pooling layers and deconvolution layers, and the deconvolution kernel size of the deconvolution layer is 3×3; When pre-building the state assessment model, the output layer of the initial model is frozen, and the output layer of the initial model is replaced by the feature fusion layer and the state classifier. The state classifier uses a three-layer multi-layer perceptron to output the state classification result. The state classifier is expressed as: (9) in, represents the embedded feature fusion result output by the feature fusion layer, Indicates the status classification result, Output for the third layer Neck network The characteristics of the node, is the number of nodes in the Neck network.

[0011] Preferably, the method for the state assessment model to identify and analyze the preprocessing set specifically includes: Load the preprocessing set, and the input layer determines the state to be identified corresponding to the continuous frequency distribution in the preprocessing set based on the peak time function. The peak time function captures the characteristic frequency of the continuous frequency distribution and determines and marks the working state of the continuous frequency distribution; Among them, the peak time function is expressed as: (10) in, represents the peak time function, Represent the approximate signal frequency points in the continuous frequency distribution The frequency timestamp between Indicates frequency preset delay, is the function attenuation coefficient; Obtain the characteristic frequency of the continuous frequency distribution and determine the mark, the encoder uses the Gauss-Newton method to matrix the characteristic frequency of the continuous frequency distribution, performs a convolution operation on the characteristic frequency of the matrixed raised-order expression, and outputs the convolution operation result; Load the convolution operation results, and the decoder concatenates the convolution operation results based on skip connections and average pooling, and outputs the frequency reconstruction results; Obtain the frequency reconstruction result, the feature fusion layer performs horizontal splicing of the frequency reconstruction result in terms of dimension and feature, and the state classifier outputs the state classification result based on the Neck network; Evaluate the state classification results based on cascading failure combined with structural similarity algorithm, calculate the comprehensive evaluation value, and output the comprehensive evaluation value; The comprehensive evaluation value is calculated by the following formula: (11) in, Represents the comprehensive evaluation value, Cascading Failure Node The weight of Indicates the status classification result, is the structural similarity index, is the bias constant.

[0012] On the other hand, the present invention further provides a system for evaluating the working state of a measurement object based on a pressure sensor, the system for evaluating the working state of a measurement object based on a pressure sensor comprising: A preprocessing module, which obtains a time-series pressure electrical signal based on a pressure sensor, preprocesses the time-series pressure electrical signal based on a characteristic frequency combined with an adaptive filtering algorithm, obtains a preprocessing set, and uploads the preprocessing set to a state database; The model building module is used to pre-build the state assessment model, extract the modeling sample set from the state database, divide the modeling sample set into a training set and a test set in a ratio of 3:1, use the training set and the test set to train the state assessment model, and output the converged state assessment model; The state assessment module is used to load the preprocessing set in real time, take the preprocessing set as input, execute the state assessment model, the state assessment model identifies and analyzes the preprocessing set, and outputs the working state assessment result of the measured object; The status judgment module is used to obtain the working status evaluation result, based on whether the comprehensive evaluation value in the working status evaluation result exceeds the preset evaluation threshold. If it exceeds the preset evaluation threshold, the working status early warning instruction is triggered.

[0013] Preferably, the state judgment module includes: A result recognition unit, used to obtain a work status evaluation result; A state judgment unit, based on whether the comprehensive evaluation value in the working state evaluation result exceeds a preset evaluation threshold; The status warning unit is used to trigger a working status warning instruction when the working status evaluation result exceeds a preset evaluation threshold.

[0014] Compared with the prior art, the embodiments of the present application have the following beneficial effects: In the embodiment of the present invention, the temporal pressure electric signal is preprocessed based on the characteristic frequency combined with the adaptive filtering algorithm, so that the interference signal in the temporal pressure electric signal interference can be effectively suppressed, and the misjudgment caused by interference can be reduced, thereby improving the accuracy of the state assessment. The state assessment model combined with the adaptive filtering algorithm generates a working state assessment result with higher accuracy. The state assessment model can realize the function of ascending reconstruction of the temporal pressure electric signal, thereby realizing a comprehensive reflection of the working state of the measured object. It overcomes the problem that the existing method uses the target similarity function to judge the on-the-job status of the audited employee based on a single or a few similarity indicators, which is difficult to adapt to the assessment needs based on the pressure sensor and cannot fully reflect the working state of the measured object.

[0015] In an embodiment of the present invention, when preprocessing the time-series pressure electrical signal based on the characteristic frequency combined with an adaptive filtering algorithm, labels are assigned to the sampling periods corresponding to the discrete frequency distribution, the continuous frequency distribution, and the pressure-free frequency distribution, thereby facilitating the state assessment model to quickly identify the response preprocessing set. At the same time, a low-pass filter is combined to obtain the amplitude energy corresponding to the approximate signal frequency, and the continuous frequency distribution after suppression filtering is output, thereby effectively eliminating the influence of interference signals on the pressure electrical signal, thereby ensuring the assessment accuracy and efficiency of the state assessment model.

[0016] In the embodiment of the present invention, by filtering out high-frequency noise, the low-pass filter helps to retain the low-frequency components in the signal, thereby improving the overall quality of the signal and further reducing noise interference. The low-pass filter can effectively remove interference noise, making the signal clearer and facilitating subsequent analysis and processing by the state assessment model. When the low-pass filter suppresses approximate signal frequency harmonics, the overlapping similarity value is introduced to ensure that the low-frequency characteristics in the signal are not lost, avoid the loss of important information due to excessive filtering, and ensure the integrity of the pressure electrical signal.

[0017] In an embodiment of the present invention, a state assessment model and a training method are provided. A staggered time function is introduced into the state assessment model to facilitate the identification and marking of abnormal states. At the same time, an encoder and a decoder are introduced into the hidden layer to improve the feature extraction capability. A decoder network hierarchy is designed through a jump connection mechanism to achieve effective capture and reconstruction of the behavioral features of the measured object, thereby capturing more global feature information. At the same time, a feature fusion layer and a state classifier are used to replace the output layer of the initial model to further effectively neutralize the impact of noise signals on state assessment and a feature fusion method is proposed to constrain the state classifier to ensure its applicability and accuracy in state assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of the implementation flow of the method for evaluating the working state of a measurement object based on a pressure sensor provided by the present invention.

[0019] Figure 2 The figure shows a schematic diagram of the implementation process of a method for preprocessing a temporal pressure electric signal based on characteristic frequency combined with an adaptive filtering algorithm.

[0020] Figure 3 The figure shows a schematic diagram of the implementation process of the method for suppressing the frequency of an approximate signal based on a low-pass filter.

[0021] Figure 4 A schematic diagram of the implementation process of a method for training a state evaluation model using a training set and a test set is shown.

[0022] Figure 5A schematic diagram of the implementation flow of the state assessment model for the preprocessing set identification and analysis method is shown.

[0023] Figure 6 It is a structural schematic diagram of a system for evaluating the working state of a measurement object based on a pressure sensor provided by the present invention. DETAILED DESCRIPTION

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0025] The existing methods use the target similarity function to judge the on-the-job status of the employees to be audited based on a single or a few similarity indicators for evaluation, which is difficult to adapt to the evaluation needs based on pressure sensors. To address the above problems, we propose a method and system for evaluating the working status of the measured object based on pressure sensors. When implementing the method for evaluating the working status of the measured object based on pressure sensors, the time-series pressure electrical signal is first obtained based on the pressure sensor, and the time-series pressure electrical signal is pre-processed based on the characteristic frequency combined with an adaptive filtering algorithm. At the same time, a state evaluation model is pre-built, and then the state evaluation model is executed. The state evaluation model identifies and analyzes the pre-processed set and outputs the working status evaluation result of the measured object. Finally, based on whether the comprehensive evaluation value in the working status evaluation result exceeds the preset evaluation threshold, if it exceeds the preset evaluation threshold, a working status warning instruction is triggered. In the embodiment of the present invention, the temporal pressure electric signal is preprocessed based on the characteristic frequency combined with the adaptive filtering algorithm, so that the interference signal in the temporal pressure electric signal interference can be effectively suppressed, and the misjudgment caused by interference can be reduced, thereby improving the accuracy of the state assessment. The state assessment model combined with the adaptive filtering algorithm generates a working state assessment result with higher accuracy. The state assessment model can realize the function of ascending reconstruction of the temporal pressure electric signal, thereby realizing a comprehensive reflection of the working state of the measured object. It overcomes the problem that the existing method uses the target similarity function to judge the on-the-job status of the audited employee based on a single or a few similarity indicators, which is difficult to adapt to the assessment needs based on the pressure sensor and cannot fully reflect the working state of the measured object.

[0026] The embodiment of the present invention provides a method for evaluating the working state of a measurement object based on a pressure sensor. Figure 1A schematic diagram of the implementation process of a method for evaluating the working state of a measurement object based on a pressure sensor is shown. The method for evaluating the working state of a measurement object based on a pressure sensor specifically includes: Step S10, obtaining a time-series pressure electrical signal based on a pressure sensor, preprocessing the time-series pressure electrical signal based on a characteristic frequency combined with an adaptive filtering algorithm to obtain a preprocessing set, and uploading the preprocessing set to a state database; It should be noted that the measurement objects referred to in this embodiment can be workers, drivers, athletes, medical staff, and office staff. For example, the pressure sensor can be integrated into an office chair or keyboard to monitor the pressure distribution of office staff when using a computer, helping them adjust their sitting posture and reduce physical discomfort caused by sitting for a long time. At the same time, the measurement object can also be mechanical equipment, medical equipment, electronic equipment, building structures, etc. In this embodiment, the pressure sensor can be a CS-iTWO-05 pressure sensor, and the pressure sensor supports OTAA and ABP network access methods. The network access parameters can use the factory default parameters. The user can provide the network access parameters to the supplier and write the parameters when the product leaves the factory. The user can also choose to configure the network access parameters by himself. The pressure sensor can be installed in a flange, bolt, buckle or embedded installation.

[0027] In this embodiment, the state database can be a SQL Server 2019 database, which facilitates data exchange and business docking between various system platforms and ensures the compatibility and consistency of the system.

[0028] Step S20, pre-constructing a state assessment model, extracting a modeling sample set from a state database, dividing the modeling sample set into a training set and a test set at a ratio of 3:1, using the training set and the test set to train the state assessment model, and outputting a converged state assessment model; Step S30, loading the preprocessing set in real time, taking the preprocessing set as input, executing the state assessment model, the state assessment model identifies and analyzes the preprocessing set, and outputs the working state assessment result of the measured object; Step S40, obtaining the working status evaluation result, based on whether the comprehensive evaluation value in the working status evaluation result exceeds a preset evaluation threshold; in this embodiment, the preset evaluation threshold may be 0.6-0.8.

[0029] Step S50: If the preset evaluation threshold is exceeded, a working status warning instruction is triggered.

[0030] If the preset assessment threshold is not exceeded, the work status assessment result is uploaded to the status database.

[0031] In the embodiment of the present invention, the temporal pressure electric signal is preprocessed based on the characteristic frequency combined with the adaptive filtering algorithm, so that the interference signal in the temporal pressure electric signal interference can be effectively suppressed, and the misjudgment caused by interference can be reduced, thereby improving the accuracy of the state assessment. The state assessment model combined with the adaptive filtering algorithm generates a working state assessment result with higher accuracy. The state assessment model can realize the function of ascending reconstruction of the temporal pressure electric signal, thereby realizing a comprehensive reflection of the working state of the measured object. It overcomes the problem that the existing method uses the target similarity function to judge the on-the-job status of the audited employee based on a single or a few similarity indicators, which is difficult to adapt to the assessment needs based on the pressure sensor and cannot fully reflect the working state of the measured object.

[0032] The embodiment of the present invention provides a method for preprocessing a temporal pressure electric signal based on characteristic frequency combined with an adaptive filtering algorithm. Figure 2 The figure shows a schematic diagram of the implementation process of a method for preprocessing a temporal pressure electric signal based on a characteristic frequency combined with an adaptive filtering algorithm. The method for preprocessing a temporal pressure electric signal based on a characteristic frequency combined with an adaptive filtering algorithm specifically includes: Step S101, loading a time-series pressure electrical signal, dividing the time-series pressure electrical signal into at least one set of characteristic frequency sets based on a preset sampling period, and processing abnormal values ​​and missing values ​​of the characteristic frequency sets; In this embodiment, the method for processing outliers in the characteristic frequency set can be direct deletion (for outliers that obviously deviate from the normal range, these records can be directly deleted) or mean value correction (using the average of the two previous and subsequent observations to correct the outlier), and the method for processing missing values ​​in the characteristic frequency set can be interpolation or replacement.

[0033] Step S102, loading a characteristic frequency set, identifying discrete frequency distribution, continuous frequency distribution, and pressure-free frequency distribution in the characteristic frequency set based on a preset judgment period, assigning labels to the sampling periods corresponding to the discrete frequency distribution, the continuous frequency distribution, and the pressure-free frequency distribution, wherein the discrete frequency distribution is marked as a working state, the continuous frequency distribution is marked as a state to be identified, and the pressure-free frequency distribution is marked as a state of leaving the workstation; It should be noted that the sampling period can be 0.01-0.5 seconds, and in this embodiment, the discrete frequency distribution in the characteristic frequency concentration is regarded as the continuous activity of the measurement object, and then the current sampling period is assigned to the working state, while the continuous frequency distribution is regarded as the continuous activity / sleep of the measurement object, so the continuous frequency distribution is marked as a state to be identified.

[0034] Step S103, loading the continuous frequency distribution, obtaining a spectrum sequence corresponding to the continuous frequency distribution based on fast Fourier transform, and calculating the amplitude energy and phase of the spectrum sequence; The amplitude energy of the spectrum sequence is calculated by the following formula: (1) (2) in, represents the amplitude energy of the spectrum sequence, is the phase of the spectrum sequence, Indicates the number of consecutive signal points, represents the continuous frequency distribution based on the fast Fourier transform input representation, is the signal frequency; Step S104, using a clustering algorithm to identify the central amplitude energy within a preset judgment period, and loading the amplitude energy and phase of the spectrum sequence; In this embodiment, a hierarchical clustering algorithm is used to cluster the signals. After clustering is completed, the characteristics of each cluster, especially the characteristics of the center point or representative point of the cluster, are analyzed. These center points or representative points often represent the typical characteristics of the signals in the cluster, including the center amplitude energy. By comparing the center amplitude energies of different clusters, a signal cluster with a specific center amplitude energy within a preset judgment period can be identified.

[0035] Step S105, determining whether there is an approximate signal frequency within a preset determination period; It should be noted that when judging whether there is an approximate signal frequency within the preset judgment period, factors such as the periodicity, stability, frequency component, sampling and aliasing of the signal need to be considered, and LabVIEW software is used for analysis and verification.

[0036] Step S106, if there is no approximate frequency, the signal frequency within the preset judgment period is not subjected to filtering; Step S107, if there is an approximate frequency, suppress the approximate signal frequency based on a low-pass filter, obtain the amplitude energy corresponding to the approximate signal frequency in combination with the low-pass filter, and output the continuous frequency distribution after the suppression filtering process; Step S108, loading the continuous frequency distribution, discrete frequency distribution, stress-free frequency distribution and corresponding marking states after the suppression filtering process, and integrating them to obtain a preprocessing set.

[0037] In an embodiment of the present invention, when preprocessing the time-series pressure electrical signal based on the characteristic frequency combined with an adaptive filtering algorithm, labels are assigned to the sampling periods corresponding to the discrete frequency distribution, the continuous frequency distribution, and the pressure-free frequency distribution, thereby facilitating the state assessment model to quickly identify the response preprocessing set. At the same time, a low-pass filter is combined to obtain the amplitude energy corresponding to the approximate signal frequency, and the continuous frequency distribution after suppression filtering is output, thereby effectively eliminating the influence of interference signals on the pressure electrical signal, thereby ensuring the assessment accuracy and efficiency of the state assessment model.

[0038] The embodiment of the present invention provides a method for suppressing the frequency of an approximate signal based on a low-pass filter. Figure 3 The schematic diagram of the implementation process of the method for suppressing the frequency of an approximate signal based on a low-pass filter is shown. The method for suppressing the frequency of an approximate signal based on a low-pass filter specifically includes: Step S1071, loading the approximate signal frequency and the amplitude energy corresponding to the approximate signal frequency within a preset judgment period, and calculating the overlapping similarity value between the approximate signal frequency and the center signal frequency corresponding to the center amplitude energy; Step S1072, suppressing harmonics of the approximate signal frequency based on a low-pass filter combined with the overlapping similarity value, and outputting the filtered approximate signal frequency; Step S1073, obtaining the filtered approximate signal frequency, and using the filtered approximate signal frequency to perform inverse fast Fourier transform to suppress the approximate signal frequency; Among them, the overlap similarity value is calculated by the following formula: (3) in, represents the overlap similarity value, It is the number of low-pass filter iterations, which can be 5-15. Respectively represent the amplitude energy and center amplitude energy corresponding to the approximate signal frequency, are the approximate signal frequency and the center signal frequency respectively; When the inverse fast Fourier transform is performed using the filtered approximate signal frequency, the inverse fast Fourier transform formula is: (4) in, represents the overlap similarity value, is the sampling angle difference of the approximate signal frequency, is the sampling frequency of the approximate signal.

[0039] In the embodiment of the present invention, by filtering out high-frequency noise, the low-pass filter helps to retain the low-frequency components in the signal, thereby improving the overall quality of the signal and further reducing noise interference. The low-pass filter can effectively remove interference noise, making the signal clearer and facilitating subsequent analysis and processing by the state assessment model. When the low-pass filter suppresses approximate signal frequency harmonics, the overlapping similarity value is introduced to ensure that the low-frequency characteristics in the signal are not lost, avoid the loss of important information due to excessive filtering, and ensure the integrity of the pressure electrical signal.

[0040] The embodiment of the present invention provides a method for training a state evaluation model using a training set and a test set. Figure 4A schematic diagram of the implementation process of a method for training a state evaluation model using a training set and a test set is shown. The method for training a state evaluation model using a training set and a test set specifically includes: Step S201, loading the pre-built state assessment model, training set and test set, setting the hyperparameters, iteration rounds and training batches of the state assessment model; In this embodiment, a total of 800 pieces of data are collected for the training set and the test set, the iteration rounds are set to 120-150 times, and the training batches are 8-10.

[0041] Step S202, obtaining a training set, using a cross entropy loss function to optimize the performance of the state evaluation model, and combining a back propagation algorithm to adjust the connection weights between the encoder, decoder, and convolutional layer in the hidden layer; Step S203, using the root mean square error loss function to train the state classifier in the state evaluation model, for the embedded feature fusion results generated by the feature fusion layer, respectively, and the real classification results to obtain the mean square error loss, the root mean square error loss function is expressed as: (5) in, Respectively represent the embedded feature fusion results and the real feature fusion results in the feature fusion matrix Middle Row, No. The elements of the column, Respectively represent the embedded feature fusion label and the real feature fusion label in the feature fusion matrix Middle Row, No. Elements of a column; Step S204, based on the state evaluation model outputted during the preset iteration rounds, a test set is obtained, the state evaluation model is tested based on the test set, and the test result is output; Step S205, loading the test results, and verifying whether the state assessment model meets the preset model accuracy based on the test results; Step S206, if the preset model accuracy is met, output a converged state assessment model; Step S207: If the preset model accuracy is not met, the learning rate and hyperparameters of the state assessment model are updated using the Nadam optimizer, and the process returns to step S202 to continue iteratively training the state assessment model using the training set.

[0042] It should be noted that the model accuracy is set to 0.92-0.98, and the model accuracy evaluation indicators can be accuracy, precision, and recall. In the embodiment of the present invention, the accuracy, precision, and recall of the state assessment model are 0.9315, 0.9522, and 0.9345, respectively, indicating that the state assessment model trained in this embodiment has good accuracy and robustness, verifying that the state assessment model has a good effect on preprocessing set recognition and analysis.

[0043] In this embodiment, when the Nadam optimizer is used to update the learning rate and hyperparameters of the state evaluation model, the first-order moment and second-order moment of the gradient tracked by the Nadam optimizer are expressed as: (6) (7) (8) in, represents the hyperparameters of the state assessment model, is the learning rate. In this embodiment, the learning rate is set to 0.02. Evaluate model hyperparameters for loss function in state The gradient at are the first-order and second-order moment estimates of the gradient, are the first and second attenuation rate parameters. In this embodiment, the first and second attenuation rate parameters may be 0.2-0.5.

[0044] It should be noted that the Nadam optimizer is an optimizer that combines the advantages of the Adam algorithm and the Nesterov AcceleratedGradient (NAG) algorithm. It performs well in the training of deep learning models. Nadam introduces the concept of Nesterov momentum and takes into account the speed of the previous step, so that the direction of the next step can be "seen" in advance when calculating updates. This acceleration mechanism helps the model converge to the optimal solution faster, especially when dealing with high curvature, small but consistent gradients, or noisy gradients.

[0045] In this embodiment, the state assessment model uses a multilayer perceptron as an initial model, and the initial model consists of an input layer, a hidden layer, and an output layer. A staggered time function is introduced into the input layer, and the hidden layer is improved. An encoder and a decoder are introduced into the hidden layer, and three convolution layers are arranged between the encoder and the decoder. The convolution layer is a 3×3 convolution, and the activation function of the hidden layer is a ReLU activation function. The encoder is composed of two groups of maximum pooling layers and fully connected layers, and the fully connected layers are respectively connected to the maximum pooling layers. The decoder is composed of two groups of average pooling layers and deconvolution layers, and the deconvolution kernel size of the deconvolution layer is 3×3; When pre-building the state assessment model, the output layer of the initial model is frozen, and the output layer of the initial model is replaced by the feature fusion layer and the state classifier. The state classifier uses a three-layer multi-layer perceptron to output the state classification result. The state classifier is expressed as: (9) in, represents the embedded feature fusion result output by the feature fusion layer, Indicates the status classification result, Output for the third layer Neck network The characteristics of the node, is the number of nodes in the Neck network.

[0046] In an embodiment of the present invention, a state assessment model and a training method are provided. A staggered time function is introduced into the state assessment model to facilitate the identification and marking of abnormal states. At the same time, an encoder and a decoder are introduced into the hidden layer to improve the feature extraction capability. A decoder network hierarchy is designed through a jump connection mechanism to achieve effective capture and reconstruction of the behavioral features of the measured object, thereby capturing more global feature information. At the same time, a feature fusion layer and a state classifier are used to replace the output layer of the initial model to further effectively neutralize the impact of noise signals on state assessment and a feature fusion method is proposed to constrain the state classifier to ensure its applicability and accuracy in state assessment.

[0047] The embodiment of the present invention provides a method for identifying and analyzing a preprocessing set using a state assessment model. Figure 5 The schematic diagram of the implementation process of the state assessment model for the preprocessing set identification and analysis method is shown. The method of the state assessment model for the preprocessing set identification and analysis specifically includes: Step S301, loading the preprocessing set, the input layer determines the state to be identified corresponding to the continuous frequency distribution in the preprocessing set based on the peak time function, the peak time function captures the characteristic frequency of the continuous frequency distribution, and determines and marks the working state of the continuous frequency distribution; Among them, the peak time function is expressed as: (10) in, represents the peak time function, Represent the approximate signal frequency points in the continuous frequency distribution The frequency timestamp between Indicates frequency preset delay, is the function attenuation coefficient. In this embodiment, the function attenuation coefficient may be 0.02-0.08; Step S302, obtaining the characteristic frequency of the continuous frequency distribution and determining the mark, the encoder uses the Gauss-Newton method to matrix the characteristic frequency of the continuous frequency distribution, performs a convolution operation on the matrixed characteristic frequency, and outputs the convolution operation result; Step S303, loading the convolution operation results, the decoder splices the convolution operation results based on skip connection and average pooling, and outputs the frequency reconstruction results; Step S304, obtaining the frequency reconstruction result, the feature fusion layer performs horizontal splicing of the frequency reconstruction result in terms of dimension and feature, and the state classifier outputs the state classification result based on the Neck network; Step S305 , evaluating the state classification result based on the cascading failure combined with the structural similarity algorithm, calculating a comprehensive evaluation value, and outputting the comprehensive evaluation value.

[0048] In this embodiment, the comprehensive evaluation value is calculated by the following formula: (11) in, Represents the comprehensive evaluation value, Cascading Failure Node The weight of Indicates the status classification result, is the structural similarity index. In this embodiment, the structural similarity index is 0.75-0.9. is the bias constant, which can be 0.02-0.05.

[0049] On the other hand, an embodiment of the present invention further provides a system for evaluating the working state of a measurement object based on a pressure sensor. Figure 6 A schematic diagram of the structure of a system for evaluating the working state of a measurement object based on a pressure sensor is shown. The system for evaluating the working state of a measurement object based on a pressure sensor specifically includes: The preprocessing module 100 acquires a time-series pressure electrical signal based on a pressure sensor, preprocesses the time-series pressure electrical signal based on a characteristic frequency combined with an adaptive filtering algorithm, obtains a preprocessing set, and uploads the preprocessing set to a state database; The model building module 200 is used to pre-build a state assessment model, extract a modeling sample set from a state database, divide the modeling sample set into a training set and a test set according to a ratio of 3:1, train the state assessment model using the training set and the test set, and output a converged state assessment model; The state assessment module 300 is used to load the preprocessing set in real time, take the preprocessing set as input, execute the state assessment model, the state assessment model identifies and analyzes the preprocessing set, and outputs the working state assessment result of the measured object; The status judgment module 400 is used to obtain the working status evaluation result, and to judge whether the comprehensive evaluation value in the working status evaluation result exceeds the preset evaluation threshold. If it exceeds the preset evaluation threshold, the working status warning instruction is triggered.

[0050] In this embodiment, the state determination module 400 includes: A result identification unit 410 is used to obtain a work status evaluation result; A state judgment unit 420 is configured to judge whether a comprehensive evaluation value in a work state evaluation result exceeds a preset evaluation threshold value; The status warning unit 430 is used to trigger a working status warning instruction when the working status evaluation result exceeds a preset evaluation threshold.

[0051] It should be noted that the system for evaluating the working state of a measurement object based on a pressure sensor provided in an embodiment of the present invention corresponds to the method for evaluating the working state of a measurement object based on a pressure sensor, and the explanations, examples, beneficial effects, etc. of the relevant contents can refer to the corresponding contents in the method for evaluating the working state of a measurement object based on a pressure sensor, and will not be repeated here.

[0052] On the other hand, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer program instructions, and the computer program instructions can be executed by a processor. When the computer program instructions are executed, the method of any of the above embodiments is implemented.

[0053] In yet another aspect of the embodiments of the present invention, a computer device is provided. The computer device includes a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, the method of any one of the above embodiments is implemented.

[0054] As a non-volatile computer-readable storage medium, the memory can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as the program instructions / modules corresponding to the method for evaluating the working state of the measurement object based on the pressure sensor in the embodiment of the present application. The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created by the use of the method for evaluating the working state of the measurement object based on the pressure sensor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the local module via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0055] In summary, the present invention provides a method and system for evaluating the working state of a measurement object based on a pressure sensor. In an embodiment of the present invention, the temporal pressure electric signal is preprocessed based on the characteristic frequency combined with an adaptive filtering algorithm, so that the interference signal in the temporal pressure electric signal interference can be effectively suppressed, and the misjudgment caused by interference can be reduced, thereby improving the accuracy of the state evaluation. The state evaluation model combined with the adaptive filtering algorithm generates a working state evaluation result with higher accuracy. The state evaluation model can realize the function of ascending reconstruction of the temporal pressure electric signal, thereby realizing a comprehensive reflection of the working state of the measurement object. It overcomes the problem that the existing method uses a target similarity function to judge the on-the-job status of the audited employee based on a single or a few similarity indicators, which is difficult to adapt to the evaluation needs based on pressure sensors and cannot fully reflect the working state of the measurement object.

[0056] It should be noted that, for the above-mentioned embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions, because according to the present invention, some steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0057] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be in the form of telecommunication or other forms.

[0058] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the scope of protection of the invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on these embodiments, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in this field can still combine, add, delete or make other adjustments to the features in the various embodiments of the present invention according to the circumstances without conflict, without making creative work, so as to obtain different other technical solutions that do not deviate from the concept of the present invention in essence, and these technical solutions also belong to the scope of protection of the present invention.

Claims

1. A method for evaluating the working state of a measurement object based on a pressure sensor, characterized in that: The method for evaluating the working state of a measurement object based on a pressure sensor comprises: Acquire a time-series pressure electrical signal based on a pressure sensor, pre-process the time-series pressure electrical signal based on a characteristic frequency combined with an adaptive filtering algorithm to obtain a pre-processing set, and upload the pre-processing set to a state database; Pre-build the state assessment model, extract the modeling sample set from the state database, divide the modeling sample set into a training set and a test set in a ratio of 3:1, use the training set and the test set to train the state assessment model, and output the converged state assessment model; The preprocessing set is loaded in real time, and the state assessment model is executed with the preprocessing set as input. The state assessment model identifies and analyzes the preprocessing set and outputs the working state assessment result of the measured object; Obtain the work status assessment result, and based on whether the comprehensive assessment value in the work status assessment result exceeds the preset assessment threshold, if it exceeds the preset assessment threshold, trigger the work status warning instruction.

2. The method for evaluating the working state of a measurement object based on a pressure sensor according to claim 1, characterized in that: The method for preprocessing the temporal pressure electrical signal based on characteristic frequency combined with an adaptive filtering algorithm specifically includes: Loading a time-series pressure electrical signal, dividing the time-series pressure electrical signal into at least one set of characteristic frequency sets based on a preset sampling period, and processing abnormal values ​​and missing values ​​of the characteristic frequency sets; Load the characteristic frequency set, identify the discrete frequency distribution, continuous frequency distribution, and stress-free frequency distribution in the characteristic frequency set based on the preset judgment period, and assign labels to the sampling periods corresponding to the discrete frequency distribution, continuous frequency distribution, and stress-free frequency distribution, wherein the discrete frequency distribution is marked as the working state, the continuous frequency distribution is marked as the state to be identified, and the stress-free frequency distribution is marked as the state of leaving the workstation; Load the continuous frequency distribution, obtain the spectrum sequence corresponding to the continuous frequency distribution based on the fast Fourier transform, and calculate the amplitude energy and phase of the spectrum sequence; The amplitude energy of the spectrum sequence is calculated by the following formula: （1） （2） in, represents the amplitude energy of the spectrum sequence, is the phase of the spectrum sequence, Indicates the number of consecutive signal points, represents the continuous frequency distribution based on the fast Fourier transform input representation, is the signal frequency; A clustering algorithm is used to identify the central amplitude energy within a preset judgment period, and the amplitude energy and phase of the spectrum sequence are loaded to determine whether there is an approximate signal frequency within the preset judgment period; If there is no approximate frequency, the signal frequency suppression filtering process within the preset judgment period is not performed; If there is an approximate frequency, the approximate signal frequency is suppressed based on a low-pass filter, the amplitude energy corresponding to the approximate signal frequency is obtained by combining the low-pass filter, and the continuous frequency distribution after the suppression filtering is output; The continuous frequency distribution, discrete frequency distribution, stress-free frequency distribution and corresponding marking states after loading suppression filtering are integrated to obtain the preprocessing set.

3. The method for evaluating the working state of a measurement object based on a pressure sensor according to claim 2, characterized in that: The method for suppressing the frequency of the approximate signal based on the low-pass filter specifically includes: Loading the approximate signal frequency and the amplitude energy corresponding to the approximate signal frequency within a preset judgment period, and calculating the overlapping similarity value between the approximate signal frequency and the center signal frequency corresponding to the center amplitude energy; Based on the low-pass filter combined with the overlapping similarity value, the harmonic suppression of the approximate signal frequency is performed, and the filtered approximate signal frequency is output; Obtain the filtered approximate signal frequency, and use the filtered approximate signal frequency to perform inverse fast Fourier transform to suppress the approximate signal frequency; Among them, the overlap similarity value is calculated by the following formula: （3） in, represents the overlap similarity value, is the number of iterative filtering times of the low-pass filter, Respectively represent the amplitude energy and center amplitude energy corresponding to the approximate signal frequency, are the approximate signal frequency and the center signal frequency respectively; When the inverse fast Fourier transform is performed using the filtered approximate signal frequency, the inverse fast Fourier transform formula is: （4） in, represents the overlap similarity value, is the sampling angle difference of the approximate signal frequency, is the sampling frequency of the approximate signal.

4. The method for evaluating the working state of a measurement object based on a pressure sensor according to claim 1, characterized in that: The method of using a training set and a test set to train a state evaluation model specifically includes: Load the pre-built state assessment model, training set, and test set, and set the hyperparameters, iteration rounds, and training batches of the state assessment model; Obtain the training set, use the cross entropy loss function to optimize the performance of the state evaluation model, and adjust the connection weights between the encoder, decoder, and convolutional layer in the hidden layer in combination with the back propagation algorithm; The root mean square error loss function is used to train the state classifier in the state evaluation model. The embedded feature fusion results generated by the feature fusion layer are compared with the true classification results to obtain the mean square error loss. The root mean square error loss function is expressed as: （5） in, Respectively represent the embedded feature fusion results and the real feature fusion results in the feature fusion matrix Middle Row, No. Elements of the column, Respectively represent the embedded feature fusion label and the real feature fusion label in the feature fusion matrix Middle Row, No. Elements of a column; Based on the state evaluation model outputted for training convergence within the preset iteration round, a test set is obtained, the state evaluation model is tested based on the test set, and the test results are output; Load the test results, and verify whether the state assessment model meets the preset model accuracy based on the test results. If it meets the preset model accuracy, output the converged state assessment model; If the preset model accuracy is not met, the Nadam optimizer is used to update the learning rate and hyperparameters of the state evaluation model, and the state evaluation model is iteratively trained through the training set.

5. The method for evaluating the working state of a measurement object based on a pressure sensor according to claim 4, characterized in that: When the Nadam optimizer is used to update the learning rate and hyperparameters of the state evaluation model, the first-order moment and second-order moment of the gradient tracked by the Nadam optimizer are expressed as: （6） （7） （8） in, represents the hyperparameters of the state assessment model, is the learning rate, Evaluate model hyperparameters for loss function in state The gradient at are the first-order and second-order moment estimates of the gradient, are the first and second attenuation rate parameters.

6. The method for evaluating the working state of a measurement object based on a pressure sensor according to claim 4, characterized in that: The state assessment model uses a multi-layer perceptron as an initial model. The initial model consists of an input layer, a hidden layer, and an output layer. A staggered time function is introduced into the input layer, and the hidden layer is improved. An encoder and a decoder are introduced into the hidden layer. Three convolution layers are set between the encoder and the decoder. The convolution layer is a 3×3 convolution, and the activation function of the hidden layer is a ReLU activation function. The encoder is composed of two groups of maximum pooling layers and fully connected layers, and the fully connected layers are respectively connected to the maximum pooling layers. The decoder is composed of two groups of average pooling layers and deconvolution layers, and the deconvolution kernel size of the deconvolution layer is 3×3; When pre-building the state assessment model, the output layer of the initial model is frozen, and the output layer of the initial model is replaced by the feature fusion layer and the state classifier. The state classifier uses a three-layer multi-layer perceptron to output the state classification result. The state classifier is expressed as: （9） in, represents the embedded feature fusion result output by the feature fusion layer, Indicates the status classification result, Output for the third layer Neck network The characteristics of the node, is the number of nodes in the Neck network.

7. The method for evaluating the working state of a measurement object based on a pressure sensor according to claim 6, characterized in that: The method for the state assessment model to identify and analyze the preprocessing set specifically includes: Load the preprocessing set, and the input layer determines the state to be identified corresponding to the continuous frequency distribution in the preprocessing set based on the peak time function. The peak time function captures the characteristic frequency of the continuous frequency distribution and determines and marks the working state of the continuous frequency distribution; Among them, the peak time function is expressed as: （10） in, represents the peak time function, Represent the approximate signal frequency points in the continuous frequency distribution The frequency timestamp between Indicates frequency preset delay, is the function attenuation coefficient; Obtain the characteristic frequency of the continuous frequency distribution and determine the mark, the encoder uses the Gauss-Newton method to matrix the characteristic frequency of the continuous frequency distribution, performs a convolution operation on the characteristic frequency of the matrixed raised-order expression, and outputs the convolution operation result; Load the convolution operation results, and the decoder concatenates the convolution operation results based on skip connections and average pooling, and outputs the frequency reconstruction results; Obtain the frequency reconstruction result, the feature fusion layer performs horizontal splicing of the frequency reconstruction result in terms of dimension and feature, and the state classifier outputs the state classification result based on the Neck network; Based on the cascading failure combined with the structural similarity algorithm, the state classification results are evaluated, the comprehensive evaluation value is calculated, and the comprehensive evaluation value is output.

8. The method for evaluating the working state of a measurement object based on a pressure sensor according to claim 7, characterized in that: The comprehensive evaluation value is calculated by the following formula: （11） in, Represents the comprehensive evaluation value, Cascading Failure Node The weight of Indicates the status classification result, is the structural similarity index, is the bias constant.

9. A system for evaluating the working state of a measurement object based on a pressure sensor, used to implement the method for evaluating the working state of a measurement object based on a pressure sensor as claimed in any one of claims 1 to 8, characterized in that: The system for evaluating the working state of a measurement object based on a pressure sensor comprises: A preprocessing module, which obtains a time-series pressure electrical signal based on a pressure sensor, preprocesses the time-series pressure electrical signal based on a characteristic frequency combined with an adaptive filtering algorithm, obtains a preprocessing set, and uploads the preprocessing set to a state database; The model building module is used to pre-build the state assessment model, extract the modeling sample set from the state database, divide the modeling sample set into a training set and a test set in a ratio of 3:1, use the training set and the test set to train the state assessment model, and output the converged state assessment model; The state assessment module is used to load the preprocessing set in real time, take the preprocessing set as input, execute the state assessment model, the state assessment model identifies and analyzes the preprocessing set, and outputs the working state assessment result of the measured object; The status judgment module is used to obtain the working status evaluation result, based on whether the comprehensive evaluation value in the working status evaluation result exceeds the preset evaluation threshold. If it exceeds the preset evaluation threshold, the working status early warning instruction is triggered.

10. The system for evaluating the working state of a measurement object based on a pressure sensor according to claim 9, characterized in that: The state judgment module comprises: A result recognition unit, used to obtain a work status evaluation result; A state judgment unit, based on whether the comprehensive evaluation value in the working state evaluation result exceeds a preset evaluation threshold; The status warning unit is used to trigger a working status warning instruction when the working status evaluation result exceeds a preset evaluation threshold.

Images