Escalator monitoring operation and maintenance method and system based on multi-source data fusion

Abstract

The invention discloses an escalator monitoring operation and maintenance method and system based on multi-source data fusion, and relates to the technical field of escalator operation and maintaining.The method comprises the steps that multi-source parameter collection is conducted on a target escalator, and a multi-source sensing data set is generated; transmitting the multi-source sensing data set to a data fusion processing center in real time; generating a fusion data set; running state monitoring of the target escalator is executed, and an early warning signal is sent out according to the monitoring risk value; and performing performance evaluation and risk grade division on the target escalator, executing a preventive maintenance decision, and sending the preventive maintenance decision to an operation and maintenance management user. The technical problems that in the prior art, monitoring of the running state of the escalator is not accurate, risks are difficult to perceive in time, and consequently the running safety and stability of the escalator are difficult to guarantee are solved, a perfect escalator intelligent operation and maintenance management system is constructed, and the safety and reliability of the escalator are improved. The technical effects of performance evaluation, risk grade division, preventive maintenance, environmental adaptability transformation, emergency response and service life evaluation are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of escalator operation and maintenance, and particularly to an escalator monitoring and operation and maintenance method and system based on multi-source data fusion. Background Art

[0002] Escalators are increasingly widely used in public places such as shopping malls, subway stations, and airports, and their safe and stable operation is crucial. However, there are many deficiencies in traditional escalator monitoring and operation and maintenance technologies. On the one hand, relying solely on single or a few types of sensors to collect data cannot comprehensively reflect the operating state of the escalator. For example, only monitoring the motor temperature makes it difficult to detect the wear of mechanical components and the impact of the operating environment change on the escalator. On the other hand, the data processing method is backward, and it is impossible to efficiently fuse and analyze a large amount of complex data, resulting in a lag in fault warning.

[0003] There are technical problems in the prior art that the monitoring of the operating state of escalators is inaccurate, it is difficult to detect risks in a timely manner, and it is difficult to ensure the safety and stability of escalator operation. Summary of the Invention

[0004] This application provides an escalator monitoring and operation and maintenance method and system based on multi-source data fusion, which is used to solve the technical problems in the prior art that the monitoring of the operating state of escalators is inaccurate, it is difficult to detect risks in a timely manner, and it is difficult to ensure the safety and stability of escalator operation.

[0005] In view of the above problems, this application provides an escalator monitoring and operation and maintenance method and system based on multi-source data fusion.

[0006] In the first aspect of this application, an escalator monitoring and operation and maintenance method based on multi-source data fusion is provided. The method includes:

[0007] Collect multi-source parameters of the target escalator through multi-source sensors to generate a multi-source sensing data set; transmit the multi-source sensing data set to the data fusion processing center in real time; in the data fusion processing center, call a multi-source data fusion model to perform fusion processing on the multi-source sensing data set to generate a fusion data set; perform real-time analysis and feature extraction on the fusion data set, monitor the operating state of the target escalator, and send a warning signal according to the monitoring risk value; perform performance evaluation and risk level classification on the target escalator based on the warning signal, and execute preventive maintenance decisions based on the evaluation results and send them to the operation and maintenance management user.

[0008] In the second aspect of this application, an escalator monitoring and operation and maintenance system based on multi-source data fusion is provided. The system includes:

[0009] A multi-source data acquisition module is used to collect multi-source parameters of a target escalator through multi-source sensors and generate a multi-source sensing data set; a data transmission module is used to transmit the multi-source sensing data set to a data fusion and processing center in real time; a data fusion and processing module is used to call a multi-source data fusion model in the data fusion and processing center to perform fusion processing on the multi-source sensing data set and generate a fusion data set; an intelligent monitoring and early warning module is used to perform real-time analysis and feature extraction on the fusion data set, monitor the operating state of the target escalator, and send out an early warning signal according to the monitoring risk value; an equipment management and intelligent evaluation module is used to perform performance evaluation and risk level classification on the target escalator based on the early warning signal, make a preventive maintenance decision based on the evaluation result, and send it to the operation and maintenance management user.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] Collect multi-source parameters of a target escalator through multi-source sensors to generate a multi-source sensing data set; transmit the multi-source sensing data set to a data fusion and processing center in real time; in the data fusion and processing center, call a multi-source data fusion model to perform fusion processing on the multi-source sensing data set to generate a fusion data set; perform real-time analysis and feature extraction on the fusion data set, monitor the operating state of the target escalator, and send out an early warning signal according to the monitoring risk value; perform performance evaluation and risk level classification on the target escalator based on the early warning signal, make a preventive maintenance decision based on the evaluation result, and send it to the operation and maintenance management user. It achieves the technical effect of constructing a perfect intelligent operation and maintenance management system for escalators, realizing performance evaluation, risk level classification, preventive maintenance, environmental adaptability transformation, emergency response, and life evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0013] Figure 1 It is a schematic flowchart of an escalator monitoring and operation and maintenance method based on multi-source data fusion provided by an embodiment of this application;

[0014] Figure 2 It is a schematic structural diagram of an escalator monitoring and operation and maintenance system based on multi-source data fusion provided by an embodiment of this application.

[0015] Description of reference numerals: multi-source data acquisition module 10, data transmission module 20, data fusion and processing module 30, intelligent monitoring and early warning module 40, equipment management and intelligent evaluation module 50. Detailed implementation manners

[0016] This application provides a method and system for monitoring and maintaining escalators based on multi-source data fusion, which is used to solve the technical problems in the prior art that the monitoring of the operating status of escalators is inaccurate, it is difficult to detect risks in a timely manner, and it is difficult to ensure the safety and stability of escalator operation.

[0017] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the protection scope of this application.

[0018] In the first embodiment, as Figure 1 shown, this application provides a method for monitoring and maintaining escalators based on multi-source data fusion, and the method includes:

[0019] Step S100: Collect multi-source parameters of the target escalator through multi-source sensors to generate a multi-source sensing data set.

[0020] Specifically, in order to comprehensively obtain the operating information of the target escalator, various types of sensors are installed at key parts of the escalator. The first type of sensors, such as temperature sensors, pressure sensors, vibration sensors, and flow sensors, respectively monitor the operating state parameters of key components during the operation of the escalator equipment, such as the temperature of key components, mechanical pressure, operating vibration amplitude, and the flow rate of lubricating oil or hydraulic oil, to determine whether the mechanical components of the equipment are operating normally. The second type of sensors, including humidity sensors, gas concentration sensors, and electromagnetic field strength sensors, are used to sense the humidity level of the escalator operating environment, the composition and concentration of surrounding gases, and the electromagnetic field strength, to understand the potential impact of environmental factors on escalator operation. The third type of sensors, namely displacement sensors and strain sensors, are responsible for monitoring the displacement changes and stress strains of the escalator structural components to evaluate the health status of the equipment structure. These multi-source sensors continuously and synchronously collect various parameters, convert the collected analog signals into digital signals, and then organize and store them in a specific data format, and finally generate a multi-source sensing data set covering various aspects such as the operating state of the equipment, the operating environment, and the structural health status.

[0021] Step S200: Transmit the multi-source sensing data set to the data fusion processing center in real time.

[0022] Specifically, to achieve the efficient transmission of multi-source sensing data sets, an Internet of Things technology is used to build a data communication network between multi-source sensors and a data fusion processing center. In this network architecture, appropriate communication modules are first configured for each multi-source sensor to enable it to have the function of sending data. At the same time, corresponding receiving interfaces and data buffer areas are set for the data fusion processing center. The communication module encapsulates and packages the multi-source sensing data set by means of wireless or wired communication protocols, such as Wi-Fi, Bluetooth, ZigBee or Ethernet protocol, etc. Then, according to the established communication rules, it is sent to the data fusion processing center in the form of data packets through the data communication network. During the transmission process, devices such as routers and switches in the network are used for data routing and forwarding to ensure that the data is transmitted along the optimal path and the transmission delay is reduced. At the same time, to ensure the accuracy and integrity of the data, a data verification and retransmission mechanism is also adopted. Once data transmission errors or losses are found, a retransmission request is made in a timely manner, and finally the multi-source sensing data set is transmitted to the data fusion processing center in real time and reliably for subsequent data fusion processing.

[0023] Step S300: At the data fusion processing center, a multi-source data fusion model is called to perform fusion processing on the multi-source sensing data set to generate a fused data set.

[0024] Specifically, after the data fusion processing center receives the multi-source sensing data set from the multi-source sensors, it first performs preprocessing on it. Through data cleaning, abnormal values and noises generated due to sensor failures, signal interferences, etc. in the data set are removed to ensure data quality; feature extraction technology is used to screen out key features valuable for the analysis of the escalator operation status from the data, such as extracting feature parameters reflecting the wear degree of key components of the escalator from a large amount of vibration data; at the same time, data association is carried out to establish a connection between the data collected by different sensors but actually interrelated, and the logical relationship between each data is determined. After the preprocessing is completed, a multi-source data fusion model constructed based on the Kalman filter algorithm or the neural network fusion algorithm is called. If the Kalman filter algorithm is used, this algorithm will perform an optimal estimation of the escalator operation status according to the statistical characteristics of the multi-source sensing data, predict the status at the next moment during the continuous update of the data, and combine the actual measurement data for correction, so as to fuse the data from different sensors. If it is based on the neural network fusion algorithm, the preprocessed multi-source sensing data is input into the trained neural network model. The neural network learns from a large amount of historical data, excavates the complex relationships between the data, automatically adjusts the network weights, and fuses the data from different sources, and finally generates a fused data set. This fused data set integrates the advantages of multi-source sensing data and more comprehensively and accurately reflects the operation status of the target escalator, providing high-quality data support for subsequent operation status monitoring and analysis.

[0025] Step S400: Conduct real-time analysis and feature extraction on the fused dataset, perform the operating status monitoring of the target escalator, and issue a warning signal according to the monitoring risk value.

[0026] Specifically, after the data fusion processing center receives the fused dataset, it initiates the real-time analysis and feature extraction process. Conduct high-frequency and uninterrupted dynamic monitoring on the fused data, closely monitor the real-time changes of the data, such as every fluctuation of parameters like component temperature and running speed. Use feature extraction algorithms to accurately screen out the key features closely related to the operating status of the escalator from the massive fused data. For example, extract specific frequency components from complex vibration signals, and these components can reflect the wear or looseness of the mechanical components of the escalator. Input the extracted feature data into a pre-trained operating status monitoring model, which is constructed based on a large amount of historical escalator operation risk monitoring data and has powerful pattern recognition and risk assessment capabilities. The model deeply analyzes the input features and outputs a monitoring risk value that can intuitively reflect the current operating risk level of the escalator. Continuously compare this monitoring risk value with the preset risk threshold. Once the monitoring risk value reaches or exceeds the preset threshold, quickly trigger the warning program and send a warning signal to the operation and maintenance personnel through various methods such as audible and visual alarms, SMS push, and system message pop-ups, so that the operation and maintenance personnel can timely know the potential safety hazards of the escalator and then take corresponding measures for processing to ensure the safe and stable operation of the escalator.

[0027] Step S500: Based on the warning signal, conduct performance evaluation and risk level classification on the target escalator, execute preventive maintenance decisions based on the evaluation results, and send them to the operation and maintenance management users.

[0028] Specifically, the monitoring risk value that triggers the warning signal is extracted and used as the key basis. Combining the equipment parameters, historical operation data, and industry standards of the target escalator, an evaluation algorithm is used to comprehensively evaluate the performance of the escalator. The evaluation process covers multiple aspects such as the mechanical transmission performance, electrical control performance, and safety protection performance of the escalator, comprehensively considering the operating conditions of each part to determine whether it meets the normal operation standard and the degree of performance degradation. According to the performance evaluation results, in accordance with the pre-set risk level classification rules, the risk status of the escalator is divided into different levels, such as low risk, medium risk, high risk, etc. Each risk level has a clear definition standard. High risk means that the escalator has serious safety hazards and may malfunction at any time; medium risk indicates that some performance indicators are abnormal and need to be closely monitored; low risk means that although there are some minor problems, it does not affect normal operation for the time being. Then, based on the risk level classification results, a preventive maintenance mechanism is used for decision-making analysis. For escalators with high risk, the decision is usually to immediately suspend operation to avoid serious accidents; for escalators with medium risk and where the scenario allows suspension, suspension of operation will also be arranged for a comprehensive overhaul; for medium-low risk or situations where suspension is not allowed, an adaptive degradation operation strategy is adopted to limit the running speed or load capacity of the escalator to reduce the likelihood of failure. Finally, the generated preventive maintenance decisions are sent to the operation and maintenance management users via text messages, emails, operation and maintenance management system messages, etc. The operation and maintenance personnel can maintain and manage the escalator in a timely manner according to these decisions to ensure the safe operation of the escalator.

[0029] In a possible implementation manner, step S100 further includes:

[0030] Step S110: The multi-source sensor includes a first type of sensor, a second type of sensor, and a third type of sensor. Among them, the first type of sensor is used to collect the equipment operation status parameters of the target escalator, the second type of sensor is used to collect the operation environment parameters of the target escalator, and the third type of sensor is used to collect the equipment structure health status parameters of the target escalator.

[0031] Specifically, the multi-source sensors are subdivided into the first type, the second type, and the third type of sensors. The first type of sensors includes temperature sensors, pressure sensors, vibration sensors, and flow sensors. The temperature sensors monitor the temperature of key components such as motors and transmission devices in real time. Once the temperature rises abnormally, potential overheating faults can be detected in a timely manner; the pressure sensors are distributed in hydraulic systems and mechanical connection parts to accurately measure pressure values and reflect the load and component working status of the equipment; the vibration sensors sensitively capture the vibration signals generated during the operation of the escalator to help determine whether there are abnormalities such as looseness and wear of components; the flow sensors are responsible for monitoring the flow of lubricating oil and hydraulic oil to ensure the stable operation of the equipment's lubrication and hydraulic systems. Through the data collected by these sensors, the equipment operation status parameters of the target escalator can be comprehensively grasped.

[0032] The second type of sensors consists of humidity sensors, gas concentration sensors, and electromagnetic field strength sensors. The humidity sensors are installed inside and around the escalator to constantly monitor the change of air humidity and avoid problems such as short circuits of electrical components and rust of metal parts caused by too high humidity; the gas concentration sensors are used to detect the content of harmful gases in the air to ensure the safety of passengers and equipment; the electromagnetic field strength sensors monitor the electromagnetic field strength of the environment where the escalator is located to prevent electromagnetic interference from affecting the normal operation of the escalator, thereby realizing the effective acquisition of the operation environment parameters of the target escalator.

[0033] The third type of sensors includes displacement sensors and strain sensors, which are installed at key structural parts of the escalator, such as trusses, support beams, and important moving joints. The displacement sensors accurately measure the displacement changes of components to evaluate the stability and accuracy of the escalator operation; the strain sensors monitor the strain conditions generated when the structure is stressed to timely detect whether there are potential fatigue damages or safety hazards in the structure, thereby obtaining the equipment structure health status parameters of the target escalator. These three types of sensors work together to collect data from different dimensions.

[0034] In a possible implementation manner, step S110 further includes:

[0035] Step S111: The first type of sensors includes temperature sensors, pressure sensors, vibration sensors, and flow sensors, the second type of sensors includes humidity sensors, gas concentration sensors, and electromagnetic field strength sensors, and the third type of sensors includes displacement sensors and strain sensors.

[0036] Specifically, among the first type of sensors, the temperature sensor is installed at easily heated parts such as the escalator drive motor and transmission components to monitor the temperature in real time and prevent the equipment from being damaged due to overheating; the pressure sensors are distributed at positions such as the hydraulic system and transmission chain to monitor the pressure changes and judge the load condition of the equipment and the working state of the components; the vibration sensors are attached to the key mechanical structures of the escalator to collect vibration data, thereby detecting problems such as looseness, wear or imbalance of the components; the flow sensors are used to monitor the flow of fluids such as lubricating oil and hydraulic oil to ensure the normal operation of the lubrication and hydraulic systems of the equipment.

[0037] Among the second type of sensors, the humidity sensor is arranged inside and around the escalator to monitor the air humidity and prevent electrical short circuits or corrosion of metal components caused by excessive humidity; the gas concentration sensor is responsible for detecting the concentration of harmful gases in the air to ensure the safety of passengers and equipment; the electromagnetic field strength sensor monitors the electromagnetic field strength in the operating environment of the escalator to avoid electromagnetic interference affecting the normal operation of the equipment.

[0038] Among the third type of sensors, the displacement sensor is installed at the key moving parts and supporting structures of the escalator to measure the displacement changes of the parts and evaluate their operating accuracy and stability; the strain sensor is attached to the load-bearing structure of the escalator to monitor the strain condition when the structure is stressed and timely detect potential structural safety hazards. These sensors work together to collect data in all directions and provide strong support for the monitoring and operation and maintenance of the escalator.

[0039] In a possible implementation manner, step S200 further includes:

[0040] Step S210: Using the Internet of Things technology to build a data communication network between the multi-source sensors and the data fusion processing center.

[0041] Step S220: Using the data communication network to transmit the multi-source sensor data set to the data fusion processing center in real time.

[0042] Specifically, a data communication network is constructed between multi-source sensors and a data fusion processing center with the help of Internet of Things technology. First, each multi-source sensor is equipped with a module with Internet of Things communication capabilities. These modules can digitally encode and encapsulate various types of data collected by the sensors to make them comply with the Internet of Things transmission protocol standard. According to the environmental conditions at the construction site and the distribution of sensors, a suitable communication method is selected. For example, for areas that are relatively close to the data fusion processing center and have little signal interference, wired Ethernet connection is preferred to ensure the stability and high speed of data transmission. For some sensors with difficult wiring or scattered locations, wireless communication technologies such as Wi-Fi, Bluetooth, and ZigBee are selected. By reasonably deploying network devices such as wireless access points and routers on-site, a wireless communication network covering all sensors is built. At the same time, a dedicated network interface and a data receiving server are set up for the data fusion processing center, and corresponding network parameters and security protection measures are configured to ensure the security and reliability of the network, thereby building a complete and efficient data communication network.

[0043] Based on the constructed data communication network, the multi-source sensor data set is transmitted. The multi-source sensors periodically send the collected data to their respective communication modules at set time intervals. The communication modules package these data and then send them out through wireless or wired network links. During the transmission process, devices such as routers and switches in the network forward the data accurately to the data receiving server of the data fusion processing center according to the destination address information in the data packets. To ensure the real-time nature of data transmission, the delay and packet loss rate of data transmission are monitored in real time. Once abnormal data transmission is detected, the retransmission mechanism is immediately activated or the network transmission strategy is adjusted. After receiving the data, the data receiving server of the data fusion processing center performs integrity verification and format conversion on the data to ensure that the data enters the subsequent data fusion processing link accurately, thus realizing the real-time transmission of the multi-source sensor data set from the sensors to the data fusion processing center.

[0044] In a possible implementation manner, step S300 further includes:

[0045] Step S310: Preprocess the multi-source sensor data set, including data cleaning, feature extraction, and data association.

[0046] Step S320: Invoke the multi-source data fusion model to perform fusion processing on the preprocessed multi-source sensor data set, where the multi-source data fusion model is constructed based on the Kalman filter algorithm or the neural network fusion algorithm.

[0047] Specifically, the multi-source sensing data set is preprocessed first. In the data cleaning stage, a comprehensive screening of the collected data is carried out. Since the sensors may be affected by factors such as noise interference and equipment failures during data collection, abnormal data may be generated. For example, when the temperature sensor fails, it will output a temperature value far beyond the normal range. At this time, data cleaning will identify and remove these outliers according to the preset reasonable data range, and fill in the missing data values at the same time to ensure the accuracy and integrity of the data. In the feature extraction link, data mining algorithms are used to extract key features from a large amount of raw data. Taking the data collected by the vibration sensor as an example, through Fourier transform technology, the time-domain vibration data is converted into the frequency domain, and specific frequency components are extracted. These frequency components can reflect the fault characteristics such as wear and looseness of the escalator mechanical components. Data association is to match and associate the data collected by different sensors according to their logical relationships and time series. For example, the motor temperature data collected by the temperature sensor is associated with the motor current data at the same moment to analyze the operating state of the motor more comprehensively.

[0048] The data fusion processing center performs fusion processing on the preprocessed multi-source sensing data set. The multi-source data fusion model used is constructed based on the Kalman filter algorithm or the neural network fusion algorithm. If a model constructed based on the Kalman filter algorithm is adopted, it will make full use of the statistical characteristics of the multi-source sensing data. The model regards the data collected by each sensor as an observation of the escalator operating state. Through the system state equation and the observation equation, a recursive optimal estimation of the escalator operating state is carried out. In this process, the model will continuously predict and update the escalator state according to the estimated value at the previous moment and the measured value at the current moment, such as predicting the operating speed of the escalator and the temperature change trend of key components, and at the same time automatically adjusting the covariance of the estimation error to effectively reduce the influence of noise on the data, so as to fuse the data from different sensors into a more accurate data set that can better reflect the real operating state of the escalator. If a model constructed based on the neural network fusion algorithm is used, first, the preprocessed multi-source sensing data is input into the trained neural network. The neural network has mastered the complex non-linear relationships between different sensor data through learning a large amount of historical escalator data. When new multi-source sensing data is input, the neural network will process the data according to the learned pattern, and the neurons cooperate with each other to automatically extract the key features in the data and fuse them. For example, data of different types such as temperature sensors and vibration sensors are fused to comprehensively reflect the comprehensive operating state of the escalator, and finally a fused data set is output.

[0049] In a possible implementation manner, step S400 further includes:

[0050] Step S410: Construct a running state monitoring model, where the running state monitoring model is trained based on historical escalator running risk monitoring data.

[0051] Step S420: After performing real-time analysis and feature extraction on the fused data set, input the feature extraction results into the running state monitoring model for analysis, and output a monitoring risk value.

[0052] Step S430: If the monitoring risk value is greater than or equal to a preset risk threshold, generate the warning signal.

[0053] Specifically, use the long short-term memory network algorithm in deep learning to construct a running state monitoring model. The long short-term memory network is good at processing time series data and can effectively capture long-term dependencies in the data. First, collect a large amount of historical escalator running risk monitoring data, which includes multi-source information such as equipment running state parameters, running environment parameters, and equipment structure health state parameters at different time points. Organize these data into sequence samples in chronological order and divide them into training sets, validation sets, and test sets. During the training process, input the training set data into the long short-term memory network. The memory units in the network selectively save and update information through the gating mechanism, learning the complex relationship between different parameters and running risks over time. After multiple rounds of training, continuously adjust the network weights to minimize the error between the predicted risk value and the actual risk value. Use the validation set to evaluate and optimize the training process to avoid overfitting. Finally, use the test set to verify the generalization ability of the model, ensuring that the constructed running state monitoring model can accurately learn the rules based on historical data and then effectively monitor and risk assess the real-time running state of the escalator.

[0054] The data fusion processing center conducts real-time analysis and feature extraction on the generated fused data set. The real-time analysis continuously tracks the change trends of various data in the fused data set, such as real-time monitoring the temperature change curve of the escalator drive motor, the fluctuation of the running environment humidity, etc. In the feature extraction stage, for vibration data, use Fourier transform to convert the time-domain signal into a frequency-domain signal and extract the energy characteristics in a specific frequency band. These characteristics can effectively reflect potential faults such as wear and looseness of mechanical components; for temperature data, judge the thermal stability and potential fault risks of the equipment by calculating statistical characteristics such as the temperature change rate and the temperature average value; for environmental parameter data, use dimensionality reduction algorithms such as principal component analysis (PCA) to extract key environmental characteristics that have a greater impact on the running state of the escalator. Then, input the extracted feature results into the constructed running state monitoring model and output a quantified monitoring risk value to intuitively reflect the risk degree of the current escalator running state.

[0055] Compare the monitored risk value with a pre-set risk threshold, which is determined based on comprehensive factors such as the safety standards of the escalator, historical failure data, and industry experience. Once the monitored risk value is greater than or equal to the pre-set risk threshold, it means that the current operating state of the escalator has a relatively high risk, and an early warning signal is generated quickly. The early warning signal will be presented in various forms, such as popping up a prominent warning window on the monitoring system interface, emitting a loud audible and visual alarm, and sending a text message notification to the mobile phones of relevant maintenance personnel, etc., so that the maintenance personnel can take measures in time to ensure the safe operation of the escalator.

[0056] In a possible implementation manner, step S500 further includes:

[0057] Step S510: Extract the monitored risk value that triggers the early warning signal, perform performance evaluation and risk level classification, and generate the evaluation result.

[0058] Step S520: According to the evaluation result, use a preventive maintenance mechanism to conduct decision-making analysis, generate a maintenance decision and send it to the operation and maintenance management user.

[0059] Step S530: Among them, the preventive maintenance mechanism includes a risk classification range for adaptive degradation and a risk classification range for suspension of operation of the target escalator.

[0060] Specifically, extract the monitored risk value that triggers the early warning signal from the monitoring data, and use the Analytic Hierarchy Process (AHP) for performance evaluation. First, construct a hierarchical structure model that includes criterion layers such as the operating state of the equipment, the operating environment, and the structural health status of the equipment. Assign corresponding sub-indicators to each criterion layer. For example, the operating state of the equipment can be broken down into motor temperature, speed, vibration, etc. Determine the relative importance of each indicator with respect to the upper-level criterion through the expert scoring method, construct a judgment matrix, calculate the eigenvector and the largest eigenvalue of the matrix, and conduct a consistency test to ensure reasonable weight allocation. According to the monitored risk value and the actual measured values of each indicator, calculate the score of each indicator. Multiply the score of each indicator by its corresponding weight and sum them to obtain the performance scores of the target escalator in terms of the operating state of the equipment, the operating environment, and the structural health status of the equipment. Then, use the fuzzy comprehensive evaluation method for risk level classification. Determine the domain of the risk level, such as low risk, medium risk, and high risk, construct an evaluation factor set, that is, the previous performance indicators. Calculate the membership degree of each indicator belonging to different risk levels through the membership function, form a membership degree matrix, combine the previously determined indicator weights, conduct a fuzzy transformation, obtain a comprehensive membership degree vector, and determine the current risk level of the target escalator according to the maximum membership degree principle. Finally, integrate the score situation of the performance evaluation and the result of the risk level classification to generate a comprehensive evaluation result.

[0061] Based on the obtained evaluation results, the preventive maintenance mechanism is initiated for decision-making analysis. According to the different risk levels of the escalator and combined with the actual on-site operation scenarios, such as the size of passenger flow and the operation hours of the venue, the most appropriate maintenance decision is formulated. If the escalator is at a medium or low risk level and on-site suspension of operation is not allowed, such as during the business hours of a shopping mall, the decision is to let the escalator adaptively degrade its operation, restricting its running speed or load capacity, reducing the probability of failures, ensuring basic operation while waiting for an appropriate time for maintenance; if the escalator is at a high risk level, or at a medium-high risk level and on-site suspension of operation is allowed, such as at a subway station during non-business hours, the decision is to immediately suspend the operation of the escalator to avoid serious accidents. Finally, the generated maintenance decision is sent to the operation and maintenance management users through various means such as text messages, emails, and operation and maintenance management system messages to ensure that information can be obtained in a timely manner and corresponding actions can be taken.

[0062] A clear regulation is made on the risk division scope of adaptive degradation and suspension of operation. This mechanism comprehensively determines different risk division scopes based on a large amount of historical failure data, the design parameters of the escalator, and industry safety standards. When the monitored risk value is within a specific interval, for example, at a medium risk level and not reaching the level of seriously threatening the safety of passengers, it falls into the risk division scope of adaptive degradation. At this time, to avoid further deterioration of the failure while maintaining the basic operation function of the escalator, the operation parameters of the escalator are automatically adjusted, reducing its running speed, restricting the number of passengers carried, and reducing the load pressure on the equipment, so as to ensure that the possibility of failure is reduced without interrupting the service. And when the monitored risk value exceeds the pre-set high-risk threshold, indicating that the escalator has serious potential safety hazards and is extremely likely to cause major accidents, this enters the risk division scope of suspension of operation. In this case, the emergency braking device is immediately triggered to stop the operation of the escalator and prohibit passengers from using it to prevent danger from occurring. The escalator can resume normal operation only after professional maintenance personnel complete the inspection and confirm safety. This clear risk division scope effectively ensures the safe and stable operation of the escalator.

[0063] Embodiment 2, based on the same inventive concept as the method for monitoring and operation and maintenance of an escalator based on multi-source data fusion in the foregoing embodiment, as Figure 2 shown, this application provides a system for monitoring and operation and maintenance of an escalator based on multi-source data fusion. The system in the embodiment of this application and the method embodiment are based on the same inventive concept. Among them, the system includes:

[0064] A multi-source data acquisition module 10, configured to collect multi-source parameters of a target escalator through multi-source sensors and generate a multi-source sensing data set.

[0065] A data transmission module 20, configured to transmit the multi-source sensing data set to a data fusion processing center in real time.

[0066] The data fusion and processing module 30 is used to call a multi-source data fusion model in the data fusion processing center to fuse and process the multi-source sensing data set to generate a fused data set.

[0067] The intelligent monitoring and warning module 40 is used to perform real-time analysis and feature extraction on the fused data set, monitor the operating status of the target escalator, and send a warning signal according to the monitoring risk value.

[0068] The equipment management and intelligent evaluation module 50 is used to perform performance evaluation and risk level classification on the target escalator based on the warning signal, execute preventive maintenance decisions based on the evaluation results, and send them to the operation and maintenance management user.

[0069] Furthermore, the system is also used to implement the following functions:

[0070] The multi-source sensors include the first type of sensors, the second type of sensors, and the third type of sensors. Among them, the first type of sensors is used to collect the equipment operating status parameters of the target escalator, the second type of sensors is used to collect the operating environment parameters of the target escalator, and the third type of sensors is used to collect the equipment structure health status parameters of the target escalator.

[0071] Furthermore, the system is also used to implement the following functions:

[0072] The first type of sensors includes temperature sensors, pressure sensors, vibration sensors, and flow sensors. The second type of sensors includes humidity sensors, gas concentration sensors, and electromagnetic field strength sensors. The third type of sensors includes displacement sensors and strain sensors.

[0073] Furthermore, the system is also used to implement the following functions:

[0074] Adopt Internet of Things technology to build a data communication network between the multi-source sensors and the data fusion processing center; use the data communication network to transmit the multi-source sensing data set to the data fusion processing center in real time.

[0075] Furthermore, the system is also used to implement the following functions:

[0076] Preprocess the multi-source sensing data set, including data cleaning, feature extraction, and data association; call the multi-source data fusion model to fuse and process the preprocessed multi-source sensing data set, where the multi-source data fusion model is constructed based on the Kalman filter algorithm or the neural network fusion algorithm.

[0077] Furthermore, the system is also used to implement the following functions:

[0078] Build an operating status monitoring model, where the operating status monitoring model is trained based on historical escalator operation risk monitoring data; perform real-time analysis and feature extraction on the fusion dataset, and then input the feature extraction results into the operating status monitoring model for analysis to output a monitoring risk value; if the monitoring risk value is greater than or equal to a preset risk threshold, generate the warning signal.

[0079] Further, the system is also used to implement the following functions:

[0080] Extract the monitoring risk value that triggers the warning signal, perform performance evaluation and risk level classification to generate the evaluation result; according to the evaluation result, use a preventive maintenance mechanism to perform decision analysis, generate a maintenance decision and send it to the operation and maintenance management user; where the preventive maintenance mechanism includes the risk division range for adaptive degradation of the target escalator and the risk division range for suspension of operation.

[0081] It should be noted that the above sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above specific embodiments of the present specification have been described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0082] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

[0083] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. An escalator monitoring and operation and maintenance method based on multi-source data fusion, characterized in that Including: Collecting multi-source parameters of the target escalator through multi-source sensors to generate a multi-source sensing data set; Transmitting the multi-source sensing data set to the data fusion processing center in real time; In the data fusion processing center, calling a multi-source data fusion model to perform fusion processing on the multi-source sensing data set to generate a fusion data set; Performing real-time analysis and feature extraction on the fusion data set, monitoring the operating status of the target escalator, and sending out a warning signal according to the monitoring risk value; Performing performance evaluation and risk level classification on the target escalator based on the warning signal, making a preventive maintenance decision based on the evaluation result, and sending it to the operation and maintenance management user.

2. The method for monitoring and operation and maintenance of an escalator based on multi-source data fusion according to claim 1, wherein The multi-source sensors include a first type of sensor, a second type of sensor, and a third type of sensor. Among them, the first type of sensor is used to collect the equipment operating status parameters of the target escalator, the second type of sensor is used to collect the operating environment parameters of the target escalator, and the third type of sensor is used to collect the equipment structure health status parameters of the target escalator.

3. The method for monitoring and maintaining the escalator based on multi-source data fusion according to claim 2, wherein, The first type of sensor includes a temperature sensor, a pressure sensor, a vibration sensor, and a flow sensor. The second type of sensor includes a humidity sensor, a gas concentration sensor, and an electromagnetic field intensity sensor. The third type of sensor includes a displacement sensor and a strain sensor.

4. The method for monitoring and operation and maintenance of escalators based on multi-source data fusion according to claim 1, characterized in that, Transmitting the multi-source sensing data set to the data fusion processing center in real time includes: Using Internet of Things technology to build a data communication network between the multi-source sensors and the data fusion processing center; Using the data communication network to transmit the multi-source sensing data set to the data fusion processing center in real time.

5. The method for monitoring and maintaining an escalator based on multi-source data fusion according to claim 1, wherein Calling a multi-source data fusion model to perform fusion processing on the multi-source sensing data set to generate a fusion data set includes: Performing preprocessing on the multi-source sensing data set, including data cleaning, feature extraction, and data association; Calling the multi-source data fusion model to perform fusion processing on the preprocessed multi-source sensing data set, where the multi-source data fusion model is built based on the Kalman filter algorithm or the neural network fusion algorithm.

6. The method for monitoring and maintaining an escalator based on multi-source data fusion according to claim 1, wherein Performing real-time analysis and feature extraction on the fusion data set, monitoring the operating status of the target escalator, and sending out a warning signal according to the monitoring risk value includes: Building an operating status monitoring model, where the operating status monitoring model is trained based on historical escalator operation risk monitoring data; Performing real-time analysis and feature extraction on the fusion data set, inputting the feature extraction result into the operating status monitoring model for analysis, and outputting the monitoring risk value; If the monitoring risk value is greater than or equal to the preset risk threshold, generating the warning signal.

7. The method for monitoring and operation and maintenance of an escalator based on multi-source data fusion according to claim 1, characterized in that Performing performance evaluation and risk level classification on the target escalator based on the warning signal, making a preventive maintenance decision based on the evaluation result, and sending it to the operation and maintenance management user includes: Extracting the monitoring risk value that triggers the warning signal, performing performance evaluation and risk level classification, and generating the evaluation result; According to the evaluation result, using a preventive maintenance mechanism to perform decision analysis, generating a maintenance decision and sending it to the operation and maintenance management user; Among them, the preventive maintenance mechanism includes a risk division range for adaptively degrading the target escalator and a risk division range for suspending operation.

8. An escalator monitoring and operation and maintenance system based on multi-source data fusion, characterized in that, The system is used to implement the escalator monitoring and operation and maintenance method based on multi-source data fusion according to any one of claims 1-7. The system includes: A multi-source data acquisition module, configured to collect multi-source parameters of a target escalator through multi-source sensors and generate a multi-source sensing data set; A data transmission module, configured to transmit the multi-source sensing data set to a data fusion processing center in real time; A data fusion and processing module, configured to call a multi-source data fusion model in the data fusion processing center to perform fusion processing on the multi-source sensing data set and generate a fusion data set; An intelligent monitoring and warning module, configured to perform real-time analysis and feature extraction on the fusion data set, monitor the operation state of the target escalator, and issue a warning signal according to the monitoring risk value; An equipment management and intelligent evaluation module, configured to perform performance evaluation and risk level division on the target escalator based on the warning signal, execute preventive maintenance decisions based on the evaluation results, and send them to operation and maintenance management users.

Images