Real-time monitoring of automatic door operation status and fault warning management system

Abstract

The present invention relates to a real-time monitoring and fault warning management system for the operation status of an automatic door. The system includes a sensor module, a data processing unit, a storage module, a display module and a communication module. The sensor module is configured to collect the position, speed, acceleration, motor temperature and motor current data of the automatic door in real time. The data processing unit is electrically connected to the sensor module, and is used to receive and process these data, generate real-time operation status information, and perform fault detection and warning analysis based on real-time information and historical data. The storage module is communicatively connected to the data processing unit, and is used to store real-time operation status information and historical data. The display module is communicatively connected to the data processing unit, and is used to display the operation status information of the automatic door in real time. The present invention realizes real-time monitoring and fault warning of the operation status of the automatic door through multi-sensor data fusion and advanced fault detection algorithms, thereby improving the reliability and safety of the automatic door system.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic doors, and in particular to a real-time monitoring and fault warning management system for automatic door operation status. Background Art

[0002] Automatic door systems are now widely used in commercial, residential and industrial applications. These systems usually include a variety of sensors to detect the position, speed and acceleration of the door to ensure smooth operation of the automatic door. In addition, the automatic door system may also be equipped with motor temperature sensors and current sensors to monitor the working status of the motor to prevent overheating or overloading.

[0003] However, existing automatic door monitoring systems often have problems such as limited data processing capabilities and delayed fault detection. Most systems can only monitor and record real-time data, lacking the ability to conduct in-depth analysis and comprehensive processing of data. In addition, the fault warning mechanism usually relies on fixed threshold judgments, which are prone to false alarms or missed alarms, and cannot warn potential faults in a timely and accurate manner.

[0004] Therefore, it is necessary to develop an improved automatic door operating status real-time monitoring and fault warning management system. Summary of the invention

[0005] The present application provides a real-time monitoring system for the operation status of an automatic door and a fault warning system to improve the reliability and safety of the automatic door system.

[0006] The present application provides a real-time monitoring system for the operation status of an automatic door and a fault warning system, comprising:

[0007] The sensor module is configured to collect the running status data of the automatic door in real time, and the sensor module includes a position sensor for detecting the position status of the automatic door; a speed sensor for detecting the running speed of the automatic door; an acceleration sensor for detecting the acceleration of the automatic door; a temperature sensor for detecting the temperature of the automatic door motor; and a current sensor for detecting the working current of the automatic door motor.

[0008] A data processing unit, electrically connected to the sensor module, for receiving and processing the operating status data from the sensor module, generating real-time operating status information; and performing fault detection and early warning analysis based on the real-time operating status information and historical operating status data;

[0009] A storage module, connected to the data processing unit for storing the real-time operation status information and historical operation status data;

[0010] A display module, connected to the data processing unit for displaying the operating status information of the automatic door in real time;

[0011] The communication module is connected to the data processing unit for sending the warning signal generated by the warning analysis to the remote management terminal.

[0012] Furthermore, the data processing unit is specifically used for:

[0013] Based on the real-time data from multiple sensors, the Kalman filter algorithm is used to perform state estimation to obtain the operating state estimation of the automatic door;

[0014] According to the automatic door running state estimation, a support vector machine is used for classification to obtain a fault classification result;

[0015] Based on historical sensor data, historical fault classification results, real-time sensor data, and real-time Kalman filter automatic door operation state estimation, a pre-trained hybrid model based on variational autoencoder and long short-term memory network is used to obtain fault prediction results;

[0016] According to the automatic door operation state estimation, fault classification result and fault prediction result, a Bayesian network is used for fusion to obtain a comprehensive fault warning index;

[0017] If the comprehensive fault warning index is greater than a preset threshold, a warning signal is generated and sent to a remote management terminal through a communication module to notify maintenance personnel to conduct inspection and repair.

[0018] Furthermore, the Kalman filter algorithm uses the Kalman filter formula provided by the following formula 1 to estimate the operating state of the automatic door:

[0019]

[0020] in, is the state estimate at time k; is the predicted state; K k is the Kalman gain; k is the observed value; H is the observation matrix;

[0021] The Kalman filter algorithm uses the adaptive noise correction mechanism provided by the following formula 2:

[0022]

[0023] Among them, Q k is the process noise covariance; α is the adaptive coefficient; e k is the estimation error.

[0024] Furthermore, the support vector machine uses the mixed Gaussian kernel function provided by the following formula 3:

[0025]

[0026] Among them, σ and γ are adjustment parameters; η is the adaptive coefficient;

[0027] The support vector machine adopts the objective function provided by the following formula 4:

[0028]

[0029] Among them, w is the weight vector; b is the bias; ξ i is the slack variable; C1 and C2 are regularization parameters; x i and x j is the input sample vector; ∈ is a constant.

[0030] Furthermore, the hybrid model based on variational autoencoder and long short-term memory network includes a variational autoencoder part, a long short-term memory network part, a fusion layer and an output layer;

[0031] The variational autoencoder part includes an encoder network and a decoder network; the encoder network is used to encode input data into latent variables; the decoder network is used to decode the latent variables into reconstructed data;

[0032] The long short-term memory network part includes a first input layer, multiple LSTM layers and a first output layer; the input layer is used to receive the reconstructed data provided by the decoder network in the variational autoencoder, as well as the real-time sensor data and the automatic door operation state estimation after the real-time Kalman filter; the multiple LSTM layers are used to process time series data and capture long-term dependencies; the first output layer is used to map the output of the LSTM layer to the prediction result;

[0033] The fusion layer is used to fuse information from the variational autoencoder part and the long short-term memory network part;

[0034] The output layer is used to generate a fault prediction result based on the output of the fusion layer.

[0035] Furthermore, the storage module includes a solid-state memory and a distributed database, the solid-state memory is used to cache real-time operation status information, and the distributed database is used to store historical operation status data for a long time.

[0036] This application has the following beneficial technical effects:

[0037] (1) By configuring a variety of sensor modules including position sensors, speed sensors, acceleration sensors, temperature sensors and current sensors, various operating status data of the automatic door can be collected in real time, and comprehensive monitoring of the automatic door position, speed, acceleration, motor temperature and current can be achieved.

[0038] (2) The data processing unit is electrically connected to the sensor module and is capable of receiving and processing the operating status data from the sensor to generate real-time operating status information. At the same time, fault detection and early warning analysis are performed based on the real-time operating status information and historical data, thereby improving the accuracy and timeliness of fault detection and reducing the occurrence of system operation failures.

[0039] (3) The storage module is connected to the data processing unit for storing real-time operation status information and historical operation status data, ensuring data integrity and traceability, and facilitating historical data analysis and system performance optimization.

[0040] (4) The communication module is connected to the data processing unit to send the warning signal generated by the warning analysis to the remote management terminal, so as to promptly notify the maintenance personnel to conduct inspection and repair, prevent the fault from expanding, and improve the safety and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of a real-time monitoring system for the operation status of an automatic door and a fault warning management system provided in the first embodiment of the present application. DETAILED DESCRIPTION

[0042] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0043] The first embodiment of the present application provides a real-time monitoring system for the operation status of an automatic door and a fault warning system. Figure 1 , which is a schematic diagram of the first embodiment of the present application. Figure 1 The first embodiment of the present application provides a real-time monitoring system for the operation status of an automatic door and a fault warning management system, which is described in detail.

[0044] The automatic door operation status real-time monitoring and fault warning management system comprises a sensor module 101 , a data processing unit 102 , a storage module 103 , a display module 104 and a communication module 105 .

[0045] The sensor module 101 is configured to collect the operating status data of the automatic door in real time. The sensor module includes a position sensor for detecting the position status of the automatic door; a speed sensor for detecting the operating speed of the automatic door; an acceleration sensor for detecting the acceleration of the automatic door; a temperature sensor for detecting the temperature of the automatic door motor; and a current sensor for detecting the working current of the automatic door motor.

[0046] The sensor module 101 is a core component for real-time collection of automatic door operation status data. Its design purpose is to provide accurate operation parameters for the data processing unit to ensure the real-time monitoring and fault warning functions of the system. The module contains multiple different types of sensors, each of which is responsible for monitoring different aspects of the status information during the operation of the automatic door.

[0047] First, the sensor module 101 includes a position sensor, which can be an inductive position sensor or a photoelectric position sensor, and its main function is to detect the current position of the automatic door. The position sensor generates position status data by measuring the position of the automatic door relative to a predetermined reference point. This sensor is usually installed on the motion track of the automatic door to ensure that the position change of the door can be continuously and accurately monitored.

[0048] Secondly, the sensor module 101 is also equipped with a speed sensor. The speed sensor can be a Hall effect sensor or a laser speed sensor, which is responsible for measuring the operating speed of the automatic door. By detecting the distance the automatic door moves per unit time, the speed sensor generates real-time speed data, which is essential for monitoring the smooth operation of the door and identifying abnormal acceleration or deceleration.

[0049] In addition, the acceleration sensor is also an important component of the sensor module 101. The acceleration sensor is generally manufactured using MEMS (micro-electromechanical system) technology and can detect the acceleration of the automatic door. The information provided by the acceleration sensor helps to determine the dynamic behavior of the automatic door during the start and stop process and can identify potential mechanical failures, such as vibration or impact.

[0050] The sensor module 101 also includes a temperature sensor, which is used to monitor the temperature of the automatic door motor. The temperature sensor can be a thermocouple, a thermistor or an infrared temperature sensor. It is installed in the motor or its vicinity to monitor the temperature change of the motor in real time when it is working to prevent malfunctions caused by overheating.

[0051] Finally, the current sensor is another key component of the sensor module 101, which is mainly used to detect the working current of the automatic door motor. The current sensor can be a Hall effect current sensor or a shunt resistor current sensor, which is installed on the power supply line of the motor. By measuring the current size when the motor is running, the information provided by the current sensor can reflect the load condition of the motor and help identify problems such as motor overload or short circuit.

[0052] The data of all these sensors are transmitted to the data processing unit 102 through electrical connections. Each sensor of the sensor module 101 needs to be calibrated regularly to ensure its accuracy and reliability. The sensors can be calibrated and maintained by standard sensor calibration methods, such as using known reference signals or standard test devices.

[0053] In summary, the sensor module 101 realizes comprehensive monitoring of the automatic door position, speed, acceleration, motor temperature and motor current by integrating multiple sensors, ensuring that the system can obtain and process the operating status data of the automatic door in real time, and providing a reliable data basis for fault detection and early warning analysis.

[0054] The data processing unit 102 is electrically connected to the sensor module, and is used to receive and process the operating status data from the sensor module to generate real-time operating status information; and perform fault detection and early warning analysis based on the real-time operating status information and historical operating status data.

[0055] The data processing unit 102 is the core component of the real-time monitoring and fault warning management system for the automatic door operation status. It is responsible for receiving and processing the operation status data from the sensor module 101 and generating real-time operation status information. It also performs fault detection and warning analysis based on these real-time information and historical operation data to ensure the reliability and safety of the system.

[0056] The data processing unit 102 is electrically connected to the sensor module 101 and can acquire data from the position sensor, velocity sensor, acceleration sensor, temperature sensor and current sensor in real time. These sensor data are first pre-processed by a data acquisition module, which includes an analog-to-digital converter (ADC) and a signal conditioning circuit to ensure the accuracy and stability of the sensor data.

[0057] After the data acquisition module, the data processing unit 102 uses a high-performance processor (such as an ARM Cortex-M series processor or a similar embedded microcontroller) for data processing. The processor runs specially designed software algorithms, which include data filtering, data fusion and data analysis. First, the data filtering algorithm is used to remove noise from the sensor data, such as using Kalman filtering or low-pass filtering techniques to obtain smooth real-time data.

[0058] Next, the data fusion algorithm integrates the data from different sensors to form a comprehensive operating status information. For example, the data from the position, velocity and acceleration sensors can be fused to provide the motion trajectory and dynamic characteristics of the automatic door; the data from the temperature and current sensors can be fused to provide the operating status and load conditions of the motor.

[0059] The data processing unit 102 also includes a fault detection module that performs analysis based on real-time operating status information and historical operating data. The fault detection algorithm can adopt a variety of methods, including rule-based detection, statistical analysis, machine learning, etc. For example, the system can preset some operating status thresholds, and when the sensor data exceeds these thresholds, the system will identify potential faults. In addition, statistical analysis based on historical data can help detect abnormal patterns and trends. Advanced machine learning algorithms, such as support vector machines (SVM) and neural networks, can further improve the accuracy of fault detection.

[0060] After detecting a potential fault, the data processing unit 102 generates warning information. The warning information includes the fault type, fault location, and recommended maintenance measures. This information is generated by the built-in logic judgment module of the data processing unit, and is transmitted to the storage module 103 for storage, and is sent to the display module 104 and the communication module 105 at the same time.

[0061] The design of the data processing unit 102 ensures that it can efficiently process large amounts of real-time sensor data and perform complex fault analysis and early warning. Its hardware architecture and software algorithms are optimized to ensure the stability and reliability of the system under various operating environments. In order to adapt to different application scenarios, the data processing unit 102 can be modularly designed to facilitate upgrading and expansion according to actual needs.

[0062] Furthermore, the data processing unit is specifically used for:

[0063] Based on the real-time data from multiple sensors, the Kalman filter algorithm is used to perform state estimation to obtain the operating state estimation of the automatic door;

[0064] According to the automatic door running state estimation, a support vector machine is used for classification to obtain a fault classification result;

[0065] Based on historical sensor data, historical fault classification results, real-time sensor data, and real-time Kalman filter automatic door operation state estimation, a pre-trained hybrid model based on variational autoencoder and long short-term memory network is used to obtain fault prediction results;

[0066] According to the automatic door operation state estimation, fault classification result and fault prediction result, a Bayesian network is used for fusion to obtain a comprehensive fault warning index;

[0067] If the comprehensive fault warning index is greater than a preset threshold, a warning signal is generated and sent to a remote management terminal through a communication module to notify maintenance personnel to conduct inspection and repair.

[0068] The data processing unit has multiple functions and processing capabilities to ensure that the system can accurately monitor the operating status of the automatic door and issue early warning signals when necessary. First, the unit receives real-time data from multiple sensors, including parameters such as position, velocity, acceleration, temperature and current. By applying the Kalman filter algorithm, the data processing unit is able to fuse and process these sensor data to generate an estimate of the operating state of the automatic door. The Kalman filter is a recursive algorithm that can provide an optimal estimate of the state of a dynamic system in the presence of noise through a prediction-update cycle.

[0069] Next, the data processing unit uses the generated operating status estimate to perform classification using a support vector machine (SVM). SVM is a supervised learning model used for classification and regression analysis. By pre-training the system, the SVM model is able to classify the real-time operating status data into normal operation or fault status and identify the specific type of fault. This step ensures that the system can detect and identify abnormal conditions in operation in real time.

[0070] In addition, the data processing unit also uses a pre-trained hybrid model based on variational autoencoders (VAE) and long short-term memory networks (LSTM) to predict faults based on historical sensor data, historical fault classification results, and real-time sensor data. The variational autoencoder is a generative model that can capture the potential distribution characteristics of data through encoding and decoding processes. The long short-term memory network is a special recursive neural network that is good at processing time series data and can capture long-term dependencies in the data. By combining the advantages of VAE and LSTM, the hybrid model can analyze and predict possible future failures of the automatic door and provide early warning for the system.

[0071] The data processing unit further combines the automatic door's operating state estimation, fault classification results, and fault prediction results, and uses the Bayesian network for fusion to generate a comprehensive fault warning index. The Bayesian network is a probabilistic graphical model that can effectively integrate multi-source information and calculate the system's failure risk by representing the conditional dependencies between variables. The comprehensive fault warning index reflects the overall health of the automatic door's current operating state. The higher the index, the greater the risk of failure.

[0072] The following is the reference implementation code of the Bayesian network, which combines the operating state estimation, fault classification results and fault prediction results of the automatic door to generate a comprehensive fault warning index.

[0073]

[0074]

[0075]

[0076] When the comprehensive fault warning index exceeds the preset threshold, the data processing unit generates a warning signal. The warning signal is sent to the remote management terminal through the communication module to notify the maintenance personnel to conduct inspection and repair. The communication module can use a variety of communication technologies, such as cellular networks, Wi-Fi, Ethernet, etc., to ensure that the warning signal can be quickly and reliably delivered to the management personnel. Through this series of processing and analysis, the data processing unit plays a core role in the automatic door operation status monitoring and fault warning system, ensuring the efficient and safe operation of the system.

[0077] Furthermore, the Kalman filter algorithm uses the Kalman filter formula provided by the following formula 1 to estimate the operating state of the automatic door:

[0078]

[0079] in, is the state estimate at time k; is the predicted state; K k is the Kalman gain; k is the observed value; H is the observation matrix;

[0080] The Kalman filter algorithm uses the adaptive noise correction mechanism provided by the following formula 2:

[0081]

[0082] Among them, Q k is the process noise covariance; α is the adaptive coefficient; e k is the estimation error.

[0083] In the real-time monitoring and fault warning management system of the automatic door operation status, the Kalman filter algorithm uses a specific formula to estimate the operation status of the automatic door and perform adaptive noise correction. Kalman filtering is a recursive estimation algorithm that is widely used in state estimation of dynamic systems, especially in the presence of noise and uncertainty.

[0084] First, the Kalman filter algorithm performs state estimation using formula (1):

[0085]

[0086] In the above formula, represents the estimate of the system state at time k. This estimate is obtained by combining the previous predicted state and the current observation value and making corrections. Specifically, is the predicted state at time k, which is based on the state estimate at time k-1 and is derived from the system's state transition equation. kis the Kalman gain, which determines the weight of the difference between the prediction error and the actual observation value. By adjusting the Kalman gain, an optimal balance can be found between the prediction value and the observation value, making the state estimation more accurate. k is the observation value at time k, that is, the data collected by the sensor in real time. H is the observation matrix, which is used to map the state variables in the state space to the observation space.

[0087] Kalman gain K k It is a key parameter in the Kalman filter algorithm. Its calculation usually depends on the state covariance matrix and the observation noise covariance matrix, which have been adjusted and optimized.

[0088] Secondly, the Kalman filter algorithm also uses formula (2) for adaptive noise correction:

[0089]

[0090] In this formula, Q k represents the process noise covariance, which describes the statistical characteristics of the internal noise of the system. The process noise covariance is updated at each time k to reflect the actual noise level of the current system. α is the adaptive coefficient, which ranges from 0 to 1. The adaptive coefficient determines the historical noise covariance Q k-1 And the contribution ratio of the current estimation error to the new process noise covariance. When α is large, the current estimation error contributes to Q k The effect of is greater, making the process noise covariance respond faster to changes in system noise.

[0091] Estimation error e k It is expressed as the difference between the observed value and the predicted value at the current time k, that is:

[0092]

[0093] Among them, z k is the observed value at time k, It is the result of mapping the predicted state to the observation space through the observation matrix H. The estimated error e k The outer product of It provides information about the size and direction of the error, which is incorporated into the update of the process noise covariance through the weighting of the adaptive coefficient α, so that Q k Able to dynamically adjust to more accurately reflect the actual noise level of the system.

[0094] This adaptive noise correction mechanism enables the Kalman filter algorithm to not only provide accurate state estimation under a fixed noise level, but also automatically adjust the process noise covariance to maintain the accuracy and robustness of the estimation when the system noise level changes.

[0095] Furthermore, the support vector machine uses the mixed Gaussian kernel function provided by the following formula 3:

[0096]

[0097] Among them, σ and γ are adjustment parameters; η is the adaptive coefficient;

[0098] The support vector machine adopts the objective function provided by the following formula 4:

[0099]

[0100] Among them, w is the weight vector; b is the bias; ξ i is the slack variable; C1 and C2 are regularization parameters; x i and x j is the input sample vector; ∈ is a constant.

[0101] Support vector machine (SVM) achieves fault classification through a specific mixture Gaussian kernel function and objective function. First, the mixture Gaussian kernel function is used to calculate the similarity between input sample vectors. This similarity measure is very critical in SVM because it determines how samples are mapped in high-dimensional space.

[0102] The expression of the mixed Gaussian kernel function is:

[0103]

[0104] In this formula, K(x i ,x j ) represents the sample x i and x j The kernel function value between reflects the similarity between the two in high-dimensional space. Specifically: is the first Gaussian kernel function term, where σ is an adjustment parameter that controls the width of the kernel function. This term mainly captures the local similarity between samples. When the sample distance is close, the kernel function value is larger, otherwise it is smaller.

[0105] is the second Gaussian kernel function term, where β is the mixing scale coefficient and γ is a tuning parameter. This term is similar to the first Gaussian kernel function, but has a different width parameter γ to capture similarities at different scales.

[0106] is a normalized polynomial term, where η is the adaptive coefficient. This term provides a similarity measure different from the Gaussian kernel function by normalizing the distance between samples, and can capture the global relationship between samples.

[0107] This hybrid kernel function combines local and global similarities and can flexibly adapt to different data distributions and improve classification accuracy by adjusting parameters σ, γ, and η.

[0108] Next, the objective function of the support vector machine is used to determine the optimal parameters of the classification model. The objective function is in the form of:

[0109]

[0110] In this objective function:

[0111] w is the weight vector, indicating the direction of the classification hyperplane.

[0112] b is the bias, which determines the intercept of the classification hyperplane.

[0113] ξ i is a slack variable used to allow some samples to violate the classification hyperplane to handle inseparable data.

[0114] C1 and C2 are regularization parameters that control the weights of two different penalty terms.

[0115] ∈ is a small constant that prevents division by zero errors.

[0116] The first part of the objective function is the SVM regularization term, which aims to minimize the norm of the weight vector and thus find the optimal classification hyperplane. It is a slack variable penalty term, which is used to process data that is not completely linearly separable and ensure the fault tolerance of the classifier. is an adaptive penalty term, which is weighted by the distance between samples, so that the closer the distance between samples, the greater the penalty, and vice versa. The introduction of this term increases the penalty for locally similar samples, thereby improving the accuracy of the classifier in local decision-making.

[0117] Furthermore, the hybrid model based on variational autoencoder and long short-term memory network includes a variational autoencoder part, a long short-term memory network part, a fusion layer and an output layer;

[0118] The variational autoencoder part includes an encoder network and a decoder network; the encoder network is used to encode input data into latent variables; the decoder network is used to decode the latent variables into reconstructed data;

[0119] The long short-term memory network part includes a first input layer, multiple LSTM layers and a first output layer; the input layer is used to receive the reconstructed data provided by the decoder network in the variational autoencoder, as well as the real-time sensor data and the automatic door operation state estimation after the real-time Kalman filter; the multiple LSTM layers are used to process time series data and capture long-term dependencies; the first output layer is used to map the output of the LSTM layer to the prediction result;

[0120] The fusion layer is used to fuse information from the variational autoencoder part and the long short-term memory network part;

[0121] The output layer is used to generate a fault prediction result based on the output of the fusion layer.

[0122] The hybrid model based on variational autoencoder and long short-term memory network specifically includes variational autoencoder part, long short-term memory network part, fusion layer and output layer. Through multi-level data processing and complex algorithms, the hybrid model can effectively predict faults and ensure the reliable operation of the system.

[0123] The variational autoencoder part includes an encoder network and a decoder network. The main function of the encoder network is to encode the input data into latent variables. The input data can include historical sensor data, historical fault classification results, and real-time sensor data. The encoder network maps high-dimensional input data to a low-dimensional latent space through a series of fully connected layers and nonlinear activation functions. These latent variables (representations of the latent space) retain the main features of the original data while removing noise and redundant information.

[0124] Specifically, the encoder network first passes the input data to the first fully connected layer, which converts the data into intermediate feature representations through linear transformations and nonlinear activation functions (such as ReLU). These intermediate feature representations are then processed layer by layer through several fully connected layers to ultimately generate the mean vector and variance vector of the latent variables. These means and variances represent the distribution characteristics of the input data in the latent space. Through the reparameterization technique, these means and variances further generate latent variables.

[0125] The role of the decoder network is to decode the latent variables into reconstructed data. The dimension of the reconstructed data is the same as the original input data, and the goal is to make the reconstructed data as close to the original input data as possible. The structure of the decoder network is opposite to that of the encoder network. The latent variables are first passed to the first fully connected layer, and intermediate feature representations are generated through linear transformation and nonlinear activation functions. Then, these intermediate feature representations are passed layer by layer, processed through several fully connected layers, and finally the reconstructed data is generated.

[0126] The long short-term memory network part includes the first input layer, multiple LSTM layers, and the first output layer. The first input layer is used to receive the reconstructed data from the variational autoencoder, as well as the real-time sensor data and the automatic door operation state estimation after the real-time Kalman filter. The LSTM network is a recursive neural network that can process and analyze time series data and capture long-term dependencies in the data. Multiple LSTM layers are connected in series to process the input data layer by layer, and each layer can remember and update important time series information. The LSTM layer effectively solves the gradient vanishing problem that is prone to occur in traditional recursive neural networks when processing long time series through memory units and gating mechanisms.

[0127] During the processing, the first input layer first integrates the reconstructed data and the real-time data and passes them to the first LSTM layer. Each LSTM layer consists of several LSTM units, each of which has an input gate, a forget gate, and an output gate. These gating mechanisms determine the flow of information within the unit. The LSTM layer gradually captures the time-dependent characteristics of the data through processing of multiple time steps, and finally generates a high-level representation of the time series.

[0128] The first output layer is used to map the output of the LSTM layer to the prediction results. The output layer is usually a fully connected layer that converts the high-dimensional time series representation into a fault prediction result. This layer generates one or more prediction values ​​through linear transformation and activation function, indicating the possibility of future failure or specific fault category.

[0129] The fusion layer is used to fuse the information from the variational autoencoder and the long short-term memory network. The fusion layer can be designed in many ways, such as simple weighted averaging, concatenation, or fusion processing through a fully connected layer. The goal of the fusion layer is to combine the advantages of the two parts of the network to generate a more accurate and reliable fault prediction feature representation.

[0130] Finally, the output layer generates the final fault prediction results based on the output of the fusion layer. The output layer converts the fusion feature representation into specific prediction values ​​through further processing and calculation. These prediction values ​​can be expressed as the probability of a fault occurring in the future or the specific fault type and severity.

[0131] The following is the reference implementation code of the hybrid model based on variational autoencoder and long short-term memory network:

[0132] import torch

[0133] import torch.nn as nn

[0134] import torch.nn.functional as F

[0135] #Encoder part of the variational autoencoder (VAE)

[0136] class Encoder(nn.Module):

[0137] def__init__(self,input_dim,hidden_dim,latent_dim):

[0138]

[0139]

[0140]

[0141]

[0142] The hybrid model based on variational autoencoder (VAE) and long short-term memory network (LSTM) includes multiple key parts: variational autoencoder part, long short-term memory network part, fusion layer and output layer. In order to implement the model, the following is a detailed description of the training steps.

[0143] First, the variational autoencoder part consists of an encoder network and a decoder network. The encoder network encodes the input data into latent variables, and the decoder network decodes these latent variables into reconstructed data. During the training process, the goal of VAE is to minimize the reconstruction error and the degree to which the distribution of the latent variables deviates from the standard normal distribution.

[0144] At the beginning of training, input data (such as historical sensor data, historical fault classification results, and real-time sensor data) is passed to the encoder network. The encoder converts high-dimensional input data into low-dimensional latent space representations through multiple fully connected layers and activation functions (such as ReLU). These latent variables include mean vectors and variance vectors, and specific latent variables are generated through reparameterization techniques.

[0145] These latent variables are then passed to the decoder network, which converts the latent variables into reconstructed data through multiple fully connected layers and activation functions. The dimensions of the reconstructed data are the same as the original input data. The goal of the decoder is to make the reconstructed data as close to the original input data as possible. During training, the parameters of the encoder and decoder are optimized by minimizing the reconstruction error (such as mean squared error) and KL divergence (a measure of the difference between the distribution of the latent variables and the standard normal distribution).

[0146] Next, the long short-term memory network part processes the time series data to capture the long-term dependencies in the data. The LSTM network includes the first input layer, multiple LSTM layers, and the first output layer. The first input layer receives the reconstructed data generated by the VAE decoder, as well as the real-time sensor data and the automatic door operation state estimation after the real-time Kalman filter. The data is passed to the LSTM layer, which processes the sequence data through its special unit structure (including input gate, forget gate, and output gate) to capture the time dependency.

[0147] During the training process, the parameters of the LSTM layer are optimized through the back-propagation algorithm. The output of the LSTM layer is passed to the first output layer, which is usually a fully connected layer that maps the high-dimensional time series representation of the LSTM layer to specific fault prediction results. The training goal is to minimize the prediction error, such as cross entropy loss or mean square error, and the appropriate loss function is selected according to the specific prediction task.

[0148] The fusion layer fuses the information from VAE and LSTM to generate a more accurate and reliable fault prediction feature representation. The fusion layer can use weighted averaging, concatenation, or a fully connected layer. The fused features are passed to the output layer, which further processes these features to generate the final fault prediction results. These prediction results can be expressed as the probability of future failures or specific fault categories and severity.

[0149] During the entire training process, the model parameters are updated using an optimization algorithm (such as Adam or SGD). In each iteration, the loss of the current batch is calculated, the gradient is calculated through backpropagation, and the parameters are updated based on the gradient. Training is performed on the training set, and the validation set is used to monitor the model performance and prevent overfitting.

[0150] During the training process, data augmentation techniques or regularization methods (such as Dropout or L2 regularization) may be used to improve the generalization ability of the model. After the training is completed, the model parameters are saved so that they can be loaded and used in actual applications.

[0151] The storage module 103 is in communication with the data processing unit and is used to store the real-time operation status information and historical operation status data.

[0152] The storage module 103 is one of the key components of the real-time monitoring and fault warning management system for the automatic door operation status. Its main function is to store the real-time operation status information and historical operation status data from the data processing unit 102 to support the system's fault detection and warning analysis. The design and implementation of the storage module needs to consider multiple aspects such as data accuracy, integrity, access speed, and storage capacity.

[0153] The storage module 103 includes two parts: a cache memory and a long-term storage device. The cache memory uses a solid-state memory (such as RAM or FRAM) to temporarily store real-time operating status information. This memory has the characteristics of fast reading and writing speed, and can quickly respond to the storage and reading requests of the data processing unit to ensure efficient real-time data processing. For example, when the data processing unit receives new operating status data from the sensor module 101, it will first write these data into the cache memory for fast access and processing.

[0154] Long-term storage devices use non-volatile memory (such as NAND Flash, eMMC or SSD) or distributed databases to store historical operating status data. These storage devices have large capacity and persistence, and can reliably save a large amount of historical data, providing a basis for subsequent data analysis and fault prediction. The storage of historical operating status data includes not only raw sensor data, but also operating status information and early warning analysis results generated by the data processing unit. These data are organized and stored in chronological order to ensure fast retrieval and query.

[0155] In order to ensure the integrity and consistency of data, the storage module 103 is designed with a data management and maintenance mechanism. First, the storage module uses data verification technology (such as CRC verification or hash function) to verify data during data writing and reading to detect and correct potential storage errors. Second, the storage module regularly performs data backup and copies key data to redundant storage devices or remote storage systems to prevent data loss.

[0156] The storage module includes a data compression module, which is used to compress and store historical operating status data to reduce storage space requirements while ensuring data integrity and availability.

[0157] The storage module 103 also includes a data compression function to reduce storage space requirements. The data compression module can use a lossless compression algorithm (such as LZ77, Huffman coding, etc.) to compress and store historical data, thereby improving storage efficiency. When reading data, the compressed data will be decompressed and restored to the original data to ensure the integrity and availability of the data.

[0158] To ensure data security, the storage module also uses encryption technology. Important operating status data and historical data are encrypted before storage and stored in non-volatile memory. Only authorized users and system components can decrypt and access this data, thereby protecting data confidentiality and preventing unauthorized access.

[0159] The storage module 103 realizes data interaction through the communication interface with the data processing unit 102. The communication interface adopts a standard high-speed data transmission protocol (such as SPI, I2C, UART or Ethernet) to ensure fast and reliable data transmission between the processing unit and the storage module. During the communication process, the data processing unit will write the real-time operation status information into the cache memory as needed, and write the sorted historical data in batches into the long-term storage device.

[0160] Furthermore, the storage module includes a solid-state memory and a distributed database, the solid-state memory is used to cache real-time operation status information, and the distributed database is used to store historical operation status data for a long time.

[0161] The storage module includes a solid-state memory and a distributed database, and is intended to effectively manage and store real-time operating status information and historical operating status data to ensure the timeliness, integrity and persistence of the data.

[0162] First, solid-state memory is used to cache real-time operating status information. Solid-state memory (such as SSD or NVMe memory) has the characteristics of high-speed reading and writing, and can quickly respond to real-time data requests generated by the data processing unit. In the automatic door system, various operating status data (such as position, speed, acceleration, motor temperature and current, etc.) collected in real time by the sensor module will be transmitted to the data processing unit for analysis and processing. In order to ensure the real-time and fast response capabilities of the system, these real-time data are first written to the solid-state memory for high-speed caching.

[0163] Through its high-speed cache mechanism, the solid-state memory can effectively cope with the frequent read and write operations of the data processing unit and ensure the immediate availability of data. For example, when the sensor module collects data hundreds of times per second, the solid-state memory can quickly store this data and quickly read it when needed to support the subsequent processing of the data processing unit. This efficient cache mechanism ensures the data processing performance of the automatic door system in high-speed operation, and will not affect the real-time monitoring and early warning functions of the system due to storage bottlenecks.

[0164] Secondly, distributed databases are used to store historical operating status data for a long time. Distributed database systems (such as Cassandra, HBase or MongoDB) are suitable for storing large-scale data due to their high scalability and high availability. A large amount of historical data generated during the operation of the automatic door system needs to be stored for a long time for subsequent analysis and fault prediction. Distributed databases achieve redundant backup and fast access to data by distributing and storing data on multiple nodes, thereby ensuring data security and reliability.

[0165] In the specific implementation, after the real-time operation status data is cached in the solid-state memory, it will be written into the distributed database in batches at regular intervals. This process is usually implemented through the scheduled tasks or batch processing mechanism of the data processing unit. The data storage structure and index mechanism in the distributed database can ensure efficient query and management of historical data. For example, the timestamp-based index can quickly locate the operation status data of a specific time period, supporting the system to perform historical data backtracking and trend analysis.

[0166] The display module 104 is connected to the data processing unit for displaying the operating status information of the automatic door in real time.

[0167] The display module 104 is an important part of the real-time monitoring and fault warning management system for the automatic door operation status, and is responsible for displaying the real-time operation status information and fault warning information of the automatic door in an intuitive manner, so that the operator can understand the system status in time and make corresponding processing. The display module 104 usually includes a high-resolution touch screen display and a graphical user interface (GUI), and is connected to the data processing unit 102 in communication.

[0168] The core component of the display module 104 is a touch screen display. The display usually adopts TFT-LCD or OLED technology, has high resolution and good viewing angle, and can clearly display complex graphics and text information. The size and resolution of the touch screen can be selected according to actual needs to ensure a good user experience in various environments. The touch screen also supports multi-touch function, allowing users to interact with the interface through gesture operation, improving the convenience and efficiency of operation.

[0169] In order to realize intuitive status display, the display module 104 integrates a graphical user interface (GUI) software. The GUI software is designed to provide users with an interface that is easy to understand and operate, including functions such as real-time data display, historical data playback, fault warning prompts and system settings. The real-time data display part displays the data processing results from the sensor module 101, such as the position, speed, acceleration, motor temperature and current of the automatic door, through intuitive graphics and values. The operator can monitor the operating status of the automatic door in real time through the interface and detect abnormal conditions in time.

[0170] The historical data playback function allows the user to query and review the historical operating status data stored in the storage module 103. Through the graphical timeline and data curve display, the user can easily view the system operation status within a specific time period and analyze the causes and trends of faults. This is of great significance for maintaining and optimizing the operating performance of the automatic door system.

[0171] The fault warning function is another key part of the display module 104. When the data processing unit 102 detects a potential fault and generates a warning signal, the display module 104 will immediately pop up an alarm prompt on the interface, including the fault type, occurrence time, and recommended treatment measures. The operator can quickly take corresponding inspection and maintenance actions based on the prompt information to prevent the fault from further expanding and ensure the safety and stable operation of the system.

[0172] In addition, the display module 104 also provides system settings and user management functions. The operator can adjust and configure system parameters through the touch screen interface, such as sensor calibration, data collection frequency, warning threshold setting, etc. The user management function allows users with different authority levels to log in and operate the system, ensuring that only authorized personnel can perform key settings and data access, thereby enhancing the security of the system.

[0173] The display module 104 is connected to the data processing unit 102 through a standard data transmission interface (such as USB, UART or Ethernet) to ensure real-time data transmission and synchronization. The design and implementation of the display module follows the ergonomic principles to ensure reliable performance and good user experience in various working environments.

[0174] In summary, the display module 104 provides rich functions and intuitive operation experience through a high-resolution touch screen display and a graphical user interface, helping operators to monitor the operating status of the automatic door in real time, respond to fault warning information in a timely manner, and perform system settings and data queries.

[0175] Furthermore, the display module includes a touch screen display and a graphical user interface, and the graphical user interface is used to display the operating status information and fault warning information of the automatic door in a visual manner and support user interactive operations.

[0176] The display module includes a touch screen display and a graphical user interface. These components are designed and implemented to visually display the operating status information and fault warning information of the automatic door, while supporting user interactive operations to ensure the ease of use and functionality of the system.

[0177] The touch screen display is the core hardware part of the display module, usually using a high-resolution TFT-LCD or OLED screen to ensure clear image display and good color performance. The touch screen supports multi-touch function, allowing users to operate through gestures such as touch, slide, and zoom. This design not only improves the user experience, but also makes the operation more intuitive and convenient. The touch screen display is connected to the data processing unit through a data interface (such as HDMI, USB, I2C, etc.) to ensure that real-time operating status information and fault warning information can be displayed in a timely and accurate manner.

[0178] The Graphical User Interface (GUI) is the software part of the display module, which is used to display data in a visual way. The design of the GUI is based on the principle of human-computer interaction to ensure the intuitiveness of information display and the ease of operation. The Graphical User Interface includes multiple components, such as status panels, charts, alarm prompt windows, and control buttons. The status panel is used to display the current operating status of the automatic door in real time, including parameters such as position, speed, acceleration, motor temperature, and current. The chart component is used to display the historical trends of these parameters to help users analyze and judge the operating status of the system. The alarm prompt window will pop up immediately when a fault is detected, showing the fault type, occurrence time, and recommended treatment measures.

[0179] In order to support user interaction, the graphical user interface is designed with a series of interactive controls. Users can directly click and slide these controls through the touch screen to set system parameters, query data and handle faults. For example, users can click buttons in the status panel to switch to display different operating parameters; by sliding the timeline, they can view historical data within a specific time period; in the alarm prompt window, click the "Confirm" button to eliminate the alarm prompt, or click the "Details" button to view detailed information and handling suggestions for the fault.

[0180] The display module also has an adaptive layout function, which can automatically adjust the interface layout according to the screen resolution and orientation to adapt to different installation environments and usage requirements. Whether it is installed vertically or horizontally, the interface elements can be reasonably laid out to ensure clear information display and convenient operation.

[0181] In the specific implementation process, the hardware part of the touch screen display needs to select high-quality display screens and touch panels to ensure fast response speed, high touch sensitivity and strong durability. The graphical user interface needs to use advanced GUI development tools and frameworks (such as Qt, WxWidgets, JavaFX, etc.) to ensure beautiful interface, complete functions and stable performance.

[0182] Furthermore, the display module also includes a remote monitoring interface, which is used to remotely display the operating status information and fault warning information on the management terminal device through a network connection to facilitate remote monitoring and management.

[0183] The display module also includes a remote monitoring interface, which is used to remotely display the operation status information and fault warning information on the management terminal device through a network connection, thereby realizing remote monitoring and management.

[0184] The remote monitoring interface is an important part of the system. It transmits the operating status information and fault warning information of the automatic door to the remote management terminal device through a wired or wireless network connection. These terminal devices can be computers, tablets, smart phones, etc., which are convenient for managers to monitor and manage the automatic door system anytime and anywhere.

[0185] First of all, the remote monitoring interface needs to have a stable network connection capability. Usually, multiple connection methods such as Ethernet, Wi-Fi, and 4G / 5G cellular networks can be used to ensure reliable remote connection in different environments. The network interface communicates with the remote management terminal through the TCP / IP protocol to ensure the accuracy and timeliness of data transmission.

[0186] During the implementation process, the remote monitoring interface packages and transmits the operating status information and fault warning information of the automatic door through standardized data transmission protocols (such as HTTP, MQTT, WebSocket, etc.). The choice of these protocols depends on the actual application requirements and network environment. For example, the HTTP protocol is suitable for most conventional network applications, the MQTT protocol is suitable for scenarios that require low latency and high reliability in the IoT environment, and the WebSocket protocol is suitable for applications that require real-time two-way communication.

[0187] When the remote management terminal device receives the operating status information and fault warning information, it will display and process it through a dedicated software interface (such as a Web application or a mobile application). The software interface is usually designed as a user-friendly graphical interface that can intuitively display the operating status and fault warning information of the automatic door. Managers can view real-time data, historical data, and receive fault alarm prompts through this interface.

[0188] For example, the operating status information can be displayed in the form of charts, curves and numerical values, so that managers can understand the operating status of the automatic door. Fault warning information reminds managers in the form of pop-up windows or notifications, indicating the specific fault type, occurrence time and recommended treatment measures. Managers can remotely control and configure the system through the control buttons or input boxes on the interface, such as adjusting operating parameters, resetting fault alarms, starting or stopping automatic doors, etc.

[0189] The communication module 105 is connected to the data processing unit for transmitting the warning signal generated by the warning analysis to the remote management terminal.

[0190] The communication module 105 plays a vital role in the real-time monitoring of the automatic door operation status and the fault warning management system. It is responsible for sending the warning signal generated by the warning analysis to the remote management terminal to ensure that the abnormal status of the system can be discovered and processed in time. The design and implementation of this module need to consider the reliability, security and real-time performance of data transmission.

[0191] The communication module 105 is first connected to the data processing unit 102 through a standard interface (such as SPI, I2C, UART or Ethernet). The warning signal generated by the data processing unit is transmitted to the communication module through these interfaces to ensure that the information can be transmitted quickly and accurately. The communication module has a built-in data buffer to handle sudden data traffic and avoid data loss or transmission delay.

[0192] In order to achieve remote communication, the communication module 105 usually integrates a variety of communication technologies, including cellular networks (such as 4G / 5G), Wi-Fi, Ethernet and Bluetooth. Through these communication technologies, the system can achieve flexible remote data transmission in different environments. The cellular network module allows the system to transmit data within the coverage of the mobile network, which is very suitable for use in scenarios far away from fixed network facilities. The Wi-Fi module provides high-bandwidth wireless communication and is suitable for places with wireless network coverage such as offices and shopping malls. The Ethernet module is used in scenarios that require stable high-bandwidth connections, such as industrial control centers. The Bluetooth module can be used for short-range data transmission and device pairing, such as direct communication with the mobile devices of maintenance personnel.

[0193] Security is an important consideration in the design of the communication module 105. In order to ensure the security of the warning signal during transmission, the communication module adopts a variety of data encryption technologies, such as AES (Advanced Encryption Standard) and TLS (Transport Layer Security Protocol). These encryption technologies can effectively prevent data from being stolen or tampered with during transmission, and ensure the confidentiality and integrity of communications. The communication module also supports a two-way authentication mechanism to ensure that only authenticated remote terminals can receive and process warning signals to prevent unauthorized access. The communication module includes an encryption communication module for encrypting and transmitting the warning signal.

[0194] The communication module 105 also has data compression and transmission optimization functions to improve transmission efficiency and reduce network bandwidth usage. The data compression module uses a lossless compression algorithm to compress the warning signal and related data before transmission, and decompresses and restores the original data at the receiving end. This method can significantly reduce the time and cost of data transmission, especially when the network bandwidth is limited.

[0195] In terms of realizing the remote management function, the communication module 105 communicates with the remote management terminal through a pre-configured remote management protocol (such as MQTT, HTTP / HTTPS or CoAP). Early warning signals and operating status data can be sent to a remote server or cloud platform through these protocols for real-time monitoring and analysis by managers. The communication module also supports automatic reconnection and fault recovery functions. When the network connection is interrupted, the module will automatically try to re-establish the connection to ensure the continuity and reliability of data transmission.

[0196] In addition, the communication module 105 has remote configuration and firmware upgrade functions. Managers can configure the communication module through the remote management terminal, such as setting communication parameters, updating encryption keys, etc. These configurations are transmitted through a secure encrypted channel to ensure that they will not be obtained or modified by unauthorized personnel. The firmware upgrade function of the communication module enables the system to obtain the latest functions and security patches at any time, further improving the security and reliability of the system.

[0197] Although the present application is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

Claims

1. A real-time monitoring and fault warning management system for automatic door operation status, characterized in that: include: A sensor module is configured to collect the running status data of the automatic door in real time, and the sensor module includes a position sensor for detecting the position status of the automatic door; Speed ​​sensor, used to detect the running speed of the automatic door; An acceleration sensor is used to detect the acceleration of the automatic door; The temperature sensor is used to detect the temperature of the automatic door motor; the current sensor is used to detect the working current of the automatic door motor; a data processing unit, electrically connected to the sensor module, for receiving and processing the operation status data from the sensor module and generating real-time operation status information; Perform fault detection and early warning analysis based on the real-time operating status information and historical operating status data; A storage module, connected to the data processing unit for storing the real-time operation status information and historical operation status data; A display module, connected to the data processing unit for displaying the operating status information of the automatic door in real time; A communication module, which is in communication connection with the data processing unit and is used to send the warning signal generated by the warning analysis to the remote management terminal; Wherein, the data processing unit is specifically used for: Based on the real-time data from multiple sensors, the Kalman filter algorithm is used to perform state estimation to obtain the operating state estimation of the automatic door; According to the automatic door running state estimation, a support vector machine is used for classification to obtain a fault classification result; Based on historical sensor data, historical fault classification results, real-time sensor data, and real-time Kalman filter automatic door operation state estimation, a pre-trained hybrid model based on variational autoencoder and long short-term memory network is used to obtain fault prediction results; According to the automatic door operation state estimation, fault classification result and fault prediction result, a Bayesian network is used for fusion to obtain a comprehensive fault warning index; If the comprehensive fault warning index is greater than a preset threshold, a warning signal is generated and sent to a remote management terminal through a communication module to notify maintenance personnel to conduct inspection and repair; The Kalman filter algorithm uses the Kalman filter formula provided by the following formula 1 to estimate the operating state of the automatic door: ； in, For the moment state estimation; is the predicted state; For Kalman gain; is the observed value; is the observation matrix; The Kalman filter algorithm uses the adaptive noise correction mechanism provided by the following formula 2: ； in, is the process noise covariance; is the adaptive coefficient; is the estimation error; The support vector machine uses the mixed Gaussian kernel function provided by the following formula 3: ； in, and To adjust the parameters; is the adaptive coefficient; is the mixing ratio coefficient; The support vector machine adopts the objective function provided by the following formula 4: ； in, is the weight vector; is bias; is the slack variable; and is the regularization parameter; and is the input sample vector; is a constant; The hybrid model based on variational autoencoder and long short-term memory network includes a variational autoencoder part, a long short-term memory network part, a fusion layer and an output layer; The variational autoencoder part includes an encoder network and a decoder network; the encoder network is used to encode input data into latent variables; the decoder network is used to decode the latent variables into reconstructed data; The long short-term memory network part includes a first input layer, multiple LSTM layers and a first output layer; the input layer is used to receive the reconstructed data provided by the decoder network in the variational autoencoder, as well as the real-time sensor data and the automatic door operation state estimation after the real-time Kalman filter; the multiple LSTM layers are used to process time series data and capture long-term dependencies; the first output layer is used to map the output of the LSTM layer to the prediction result; The fusion layer is used to fuse information from the variational autoencoder part and the long short-term memory network part; The output layer is used to generate a fault prediction result based on the output of the fusion layer.

2. The system for real-time monitoring and fault warning management of automatic door operation status according to claim 1 is characterized in that: The storage module includes a solid-state memory and a distributed database, wherein the solid-state memory is used for caching real-time operation status information, and the distributed database is used for long-term storage of historical operation status data.

3. The system for real-time monitoring and fault warning management of automatic door operation status according to claim 1 is characterized in that: The storage module includes a data compression module, which is used to compress and store historical operating status data to reduce storage space requirements while ensuring data integrity and availability.

4. The system for real-time monitoring of automatic door operation status and fault early warning management according to claim 1 is characterized in that: The display module includes a touch screen display and a graphical user interface, and the graphical user interface is used to display the operating status information and fault warning information of the automatic door in a visual manner and support user interactive operations.

5. The system for real-time monitoring of automatic door operation status and fault early warning management according to claim 1 is characterized in that: The display module also includes a remote monitoring interface, which is used to remotely display the operating status information and fault warning information on the management terminal device through a network connection for remote monitoring and management.

6. The system for real-time monitoring of automatic door operation status and fault early warning management according to claim 1 is characterized in that: The communication module includes an encryption communication module for encrypting and transmitting the early warning signal.

Images