Escalator operation monitoring method and device, electronic equipment and storage medium

By setting up sensor arrays and edge computing equipment on the escalator to evaluate health index, combined with cloud analysis, the problem of difficulty in time discovering problems in traditional maintenance is solved, real-time monitoring and prediction of escalator is achieved, and safety and management efficiency are improved.

CN120482886APending Publication Date: 2025-08-15SHENZHEN EXCELLENCE INFORMATION TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202510823504.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-19
Publication Date
2025-08-15

AI Technical Summary

Technical Problem

Traditional escalators maintain rely on regular manual inspections, making it difficult to detect potential problems in a timely manner, resulting in equipment failure and safety risks.

Method used

By setting up sensor arrays on the escalator to collect key working status parameters, evaluating comprehensive health indexes using edge computing devices, and combining cloud analysis, real-time monitoring and prediction of fault trends.

Benefits of technology

It improves the operating safety and reliability of escalators, reduces the failure rate and maintenance costs, and supports intelligent equipment management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120482886A_ABST
    Figure CN120482886A_ABST
Patent Text Reader

Abstract

The invention provides an escalator operation monitoring method and device, electronic equipment and a storage medium, and the method comprises the steps: collecting various key working state parameters of a to-be-monitored escalator during working through a sensor array arranged on the to-be-monitored escalator, the working state parameters are uploaded to edge computing equipment beside the escalator to be monitored, and the edge computing equipment evaluates the comprehensive health index of the escalator to be monitored; the edge computing device uploads the monitored working state parameters of the escalator and the evaluated comprehensive health index to the cloud end, and the cloud end continues to monitor the operation condition of the escalator according to the indication condition of the comprehensive health index. By means of the method, comprehensive understanding of the state of the escalator is enhanced, and therefore the fault rate and the maintenance cost are reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention provides an escalator operation monitoring method, device, electronic equipment and storage medium, belonging to the technical field of escalator application safety. Background Art

[0002] In the process of modern urbanization, escalators have become an indispensable transportation facility in various public places such as shopping malls, subway stations, and airports. With their increasing frequency of use, the operational safety and reliability of escalators have become a major public concern. Traditional escalator maintenance typically relies on regular manual inspections, which is not only inefficient but also difficult to detect potential problems in a timely manner, potentially leading to equipment failure and posing a threat to passenger safety. Therefore, there is an urgent need for a technology that can accurately monitor the operating status of escalators in real time to ensure that abnormalities are detected and addressed promptly. Summary of the Invention

[0003] The present invention provides an escalator operation monitoring method, device, electronic device and storage medium to solve the above-mentioned problems:

[0004] The present invention provides an escalator operation monitoring method, the method comprising:

[0005] A sensor array disposed on the escalator to be monitored collects various key operating status parameters of the escalator to be monitored during operation, and the operating status parameters are uploaded to an edge computing device next to the escalator to be monitored. The edge computing device then evaluates the comprehensive health index of the escalator to be monitored.

[0006] The edge computing device uploads the monitored working status parameters of the escalator and the evaluated comprehensive health index to the cloud, and the cloud continues to monitor the operation of the escalator according to the indication of the comprehensive health index.

[0007] Furthermore, a sensor array provided on the escalator to be monitored collects various key operating status parameters of the escalator to be monitored during operation, and the operating status parameters are uploaded to an edge computing device next to the escalator to be monitored. The edge computing device evaluates the comprehensive health index of the escalator to be monitored, including:

[0008] By installing optical fiber strain gauges, optical fiber thermometers, optical fiber accelerometers, optical fiber noise meters, and optical fiber displacement meters on the escalator, the deformation of the truss, the temperature of the drive unit, the acceleration of the handrail, the vibration signal of the drive unit, and the displacement of the steps are measured respectively. The deformation of the truss, the temperature of the drive unit, the acceleration of the handrail, the vibration signal of the drive unit, and the displacement of the steps are the key working status parameters of the escalator.

[0009] The edge computing device evaluates the health index of the escalator to be monitored using a health index model. Specifically, the health index model is:

[0010]

[0011] Among them, H(t) represents the comprehensive health status index of the escalator at time t, w i represents the dynamic weight coefficient of the i-th working state parameter at time t, X i (t) represents the actual value of the escalator's i-th working state parameter at time t, μ i (t) represents the expected value of the i-th working state parameter at time t, τ′ i (t) represents the dynamic threshold of the i-th working state parameter of the escalator at time t.

[0012] Furthermore, the dynamic weight coefficient is calculated by a dynamic weight model, and the specific dynamic weight model is:

[0013]

[0014] Among them, κ i Indicates the basic importance of parameters, f i (t) represents the dynamic sensitivity function, F i represents the total number of escalator failures caused by abnormalities in the i-th working state parameter in history, It represents the total number of faults caused by the escalator working state parameters, and n represents the total number of working state parameters.

[0015] Furthermore, the dynamic threshold is calculated by a dynamic threshold model. Specifically, the dynamic threshold model is:

[0016]

[0017] Among them, τ′ i (t) represents the threshold value of the i-th working state parameter at time t, τ i (0) represents the initial threshold of the i-th working state parameter, α represents the maximum degradation degree finally achieved, β represents the degradation rate coefficient, ΔX i represents the change of the i-th working state parameter, and ΔT represents the length of the time period in which the change occurs.

[0018] Furthermore, when it is detected that the working status parameter value of the escalator exceeds its dynamic threshold, the preliminary warning of the escalator is directly triggered and the relevant data is uploaded to the cloud.

[0019] Furthermore, the edge computing device uploads the monitored operating status parameters of the escalator and the evaluated comprehensive health index to the cloud, and the cloud continues to monitor the operation of the escalator according to the indication of the comprehensive health index, including:

[0020] The edge computing device uploads the monitored operating status parameters and the evaluated comprehensive health index of the escalator to the cloud. When the evaluated comprehensive health index is greater than or equal to 0.8, the cloud determines whether the escalator has a trend fault based on the current operating status parameters of the escalator, including:

[0021] Obtaining historical key operating status parameters of the escalator to be monitored, and integrating the operation log, fault record and maintenance log in the escalator control system;

[0022] Preprocessing the acquired historical key working status parameters includes: identifying and removing abnormal values in the historical key working status parameter data, such as jump data caused by sensor failure, and eliminating incomplete data fragments;

[0023] Extract key features from the raw data, including: maximum deformation, deformation rate, deformation mode, maximum temperature, average temperature, temperature fluctuation amplitude, temperature change rate, maximum acceleration value, acceleration oscillation frequency, acceleration direction change, vibration amplitude, spectrum analysis, kurtosis and skewness of vibration signals, maximum displacement, displacement period and phase, and displacement change rate. Associate the extracted key features with the fault type to form a historical data set.

[0024] Using the historical data set to train a long short-term memory network model, the input of the long short-term memory network model is the key feature, and the output is the fault type;

[0025] The data features of real-time detection are input into the trained long short-term memory network model to obtain the fault type. If the output prediction result of the long short-term memory network model is normal, no processing is required. If the output prediction result indicates a fault, the relevant staff will be notified to replace the components related to the fault type of the escalator to be monitored in advance.

[0026] Furthermore, the edge computing device uploads the monitored operating status parameters of the escalator and the evaluated comprehensive health index to the cloud, and the cloud continues to monitor the operation of the escalator according to the indication of the comprehensive health index, further comprising:

[0027] When the evaluated comprehensive health index is less than or equal to 0.8, the cloud sends the adjusted parameter threshold to the edge computing device.

[0028] τ i (t) = τ′ i(t)·H(t)·(X i (t)-μ i (t))

[0029] Among them, τ i (t) represents the adjusted parameter threshold, τ′ i (t) represents the dynamic threshold calculated by the dynamic threshold model, H(t) represents the comprehensive health status index of the escalator at time t, X i (t) represents the actual value of the escalator's i-th working state parameter at time t, μ i (t) represents the expected value of the i-th working state parameter at time t;

[0030] The edge computing device adjusts the real-time detection logic based on the feedback, and the edge computing device adjusts the dynamic threshold to avoid missed alarms or false alarms.

[0031] The present invention provides an escalator operation monitoring device, comprising:

[0032] A monitoring module is configured to collect key operating status parameters of the escalator to be monitored during operation through a sensor array provided on the escalator to be monitored, upload the operating status parameters to an edge computing device adjacent to the escalator to be monitored, and use the edge computing device to evaluate a comprehensive health index of the escalator to be monitored;

[0033] The fault trend prediction module is used for the edge computing device to upload the monitored working status parameters of the escalator and the evaluated comprehensive health index to the cloud, and the cloud continues to monitor the operation of the escalator according to the indication of the comprehensive health index.

[0034] The present invention proposes an electronic device, comprising a memory and a processor, characterized in that a computer program is stored in the memory, and the processor is configured to execute the escalator operation monitoring method through the computer program.

[0035] The present invention proposes a computer-readable storage medium, characterized in that the computer-readable storage medium includes a stored program, and the escalator operation monitoring method is executed when the program is run.

[0036] The beneficial effects of the present invention are as follows: through real-time feedback from sensors and edge computing devices, any abnormal situation of the escalator can be quickly detected and responded to, reducing the risk of accidents; the comprehensive health index evaluated by the edge device in real time reflects the current status of the escalator, providing data support for maintenance and decision-making; through further analysis in the cloud, the system can predict potential problems in advance based on long-term data trends and implement preventive maintenance, rather than relying solely on regular inspections; improving system reliability, the use of the comprehensive health index can significantly enhance the sensitivity to the health status of the equipment and enhance the comprehensive understanding of the status of the escalator, thereby reducing the failure rate and maintenance costs; automatically integrating edge computing and cloud monitoring, supporting intelligent and automated equipment management strategies, and enabling managers to take measures based on real-time and accurate data; this solution not only realizes comprehensive monitoring of the escalator status, but also improves the safety and operation efficiency of the escalator through intelligent data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a schematic diagram of an escalator operation monitoring method according to the present invention. DETAILED DESCRIPTION

[0038] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein may be combined with each other.

[0039] The following description sets forth numerous specific details to facilitate a thorough understanding of the present invention. The embodiments described are merely a portion of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are intended to fall within the scope of protection of the present invention.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0041] One embodiment of the present invention provides a method for monitoring escalator operation, the method comprising:

[0042] A sensor array disposed on the escalator to be monitored collects various key operating status parameters of the escalator to be monitored during operation, and the operating status parameters are uploaded to an edge computing device next to the escalator to be monitored. The edge computing device then evaluates the comprehensive health index of the escalator to be monitored.

[0043] The edge computing device uploads the monitored working status parameters of the escalator and the evaluated comprehensive health index to the cloud, and the cloud continues to monitor the operation of the escalator according to the indication of the comprehensive health index.

[0044] The working principle and effect of the above technical solution are as follows: multiple sensors are installed on the entire escalator to monitor its key working status parameters. These sensors collect data in real time and capture various working status information when the escalator is in operation; the data collected by the sensors is uploaded to the edge computing device nearby. The edge computing device processes this batch of data and evaluates the comprehensive health index (CHI) of the escalator in real time. The comprehensive health index is calculated according to a preset algorithm or model, usually combining multiple working status parameters, and is used to measure the overall status and performance of the escalator; the edge computing device uploads the processed working status parameters and comprehensive health index to the cloud for further analysis. The cloud can perform long-term storage, analysis and trend prediction of these data for more in-depth monitoring and evaluation. The cloud platform continuously analyzes and monitors the uploaded escalator data, and observes the operation of the escalator through the comprehensive health index. Based on historical trends and prediction models, the cloud can make more accurate predictions on the changing trends of the comprehensive health index and provide early warnings when necessary. Real-time feedback from sensors and edge computing devices ensures that any abnormal conditions in the escalator can be quickly detected and responded to, reducing the risk of accidents. The comprehensive health index assessed in real time by edge devices reflects the current status of the escalator and provides data support for maintenance and decision-making. Through further analysis in the cloud, the system can predict potential problems in advance based on long-term data trends and implement preventive maintenance, rather than relying solely on regular inspections. The use of the comprehensive health index improves system reliability and significantly enhances sensitivity to equipment health status and a comprehensive understanding of the escalator's status, thereby reducing failure rates and maintenance costs. The automatic integration of edge computing and cloud monitoring supports intelligent and automated equipment management strategies, enabling managers to take measures based on real-time and accurate data. This solution not only achieves comprehensive monitoring of the escalator's status, but also improves the safety and operational efficiency of the escalator through intelligent data analysis.

[0045] In one embodiment of the present invention, a sensor array disposed on an escalator to be monitored collects key operating status parameters of the escalator during operation, uploads the operating status parameters to an edge computing device adjacent to the escalator to be monitored, and evaluates the comprehensive health index of the escalator to be monitored by the edge computing device, including:

[0046] By installing optical fiber strain gauges, optical fiber thermometers, optical fiber accelerometers, optical fiber noise meters, and optical fiber displacement meters on the escalator, the deformation of the truss, the temperature of the drive unit, the acceleration of the handrail, the vibration signal of the drive unit, and the displacement of the steps are measured respectively. The deformation of the truss, the temperature of the drive unit, the acceleration of the handrail, the vibration signal of the drive unit, and the displacement of the steps are the key working status parameters of the escalator.

[0047] The edge computing device evaluates the health index of the escalator to be monitored using a health index model. Specifically, the health index model is:

[0048]

[0049] Among them, H(t) represents the comprehensive health status index of the escalator at time t, w i represents the dynamic weight coefficient of the i-th working state parameter at time t, X i (t) represents the actual value of the escalator's i-th working state parameter at time t, μ i (t) represents the expected value of the i-th working state parameter at time t, τ′ i (t) represents the dynamic threshold of the i-th working state parameter of the escalator at time t.

[0050] The working principle and effect of the above technical solution are as follows: The comprehensive health status index is used to characterize the overall health status of the escalator at a specific time t. If H(t) is close to 1, it means that the system is in a healthy state; if it is close to 0, it means that there is an abnormality or potential fault. Different operating status parameters may contribute differently to the overall health status of the escalator, and therefore are assigned different weights. The weights are dynamic, meaning that under certain conditions or periods, a certain parameter is more important for judging the health status. By comparing the difference between the actual value and the expected value, it is possible to identify which parameters deviate from the normal state. The dynamic threshold provides a flexible standard for judging the severity of deviations. It relies on real-time parameters and can adapt to the changes of each parameter in different environments and operating conditions. The model integrates information from multiple operating status parameters and synthesizes them into an index to comprehensively evaluate the overall health status of the escalator, thus avoiding misjudgments that may occur when analyzing based on only a single parameter. Because the weights and thresholds are dynamic, they can be adaptively adjusted according to the actual operating environment and equipment status, improving the robustness and adaptability of the system. This means that the monitoring system can be adjusted to different environments and operating conditions to ensure monitoring accuracy.

[0051] It has high sensitivity and uses the square of the deviation to calculate, making it more sensitive to outliers. If a parameter deviates seriously, it will have a greater impact on the health index, which helps to quickly identify problems. By accurately identifying the deviation of parameters from normal, the system can issue a warning before the equipment fails completely or a serious fault occurs, thereby having the opportunity to perform preventive maintenance and reduce downtime and repair costs. The health index model realizes real-time monitoring and intelligent evaluation of the operating status of the escalator through dynamic adjustment and comprehensive consideration, thereby improving the efficiency and safety of equipment management. The health index model can intuitively evaluate the health status of the system by limiting the index value between 0 and 1. The closer H(t) is to 1, the better the health status of the equipment and the lower the risk of failure. The closer H(t) is to 0, the worse the health status of the equipment and the higher the risk of failure.

[0052] In one embodiment of the present invention, the dynamic weight coefficient is calculated by a dynamic weight model. Specifically, the dynamic weight model is:

[0053]

[0054] Among them, f i (t) represents the dynamic sensitivity function, F i represents the total number of escalator failures caused by abnormalities in the i-th working state parameter in history, It represents the total number of faults caused by the escalator working state parameters, and n represents the total number of working state parameters.

[0055] The working principle and effect of the above technical solution are as follows: dynamic weighting is designed to assign different weights to each indicator. New escalators are more sensitive to "vibration" faults, while old escalators are more sensitive to "temperature" or "current" faults. That is, the weight of vibration acceleration is higher when the escalator is just in use and gradually decreases as the equipment ages; the weight of temperature parameters increases after the escalator ages because temperature rise is a key indicator of later faults; the impact of historical faults, F i Indicates the total number of failures caused by parameter i in history, through Calculate the contribution of the parameter to the total number of faults. This part reflects the importance of the parameter in the historical fault data. The importance weight of each parameter is set based on the historical data. This is a dynamically changing function that may adjust the sensitivity at the current point in time based on real-time data or the current environment. This allows the system to respond quickly to changes in the environment or operating conditions and improve sensitivity to abnormal situations. Normalization processing: The calculation of the entire weight is done through the overall normalization process, that is, the denominator in Ensure that the sum of the weights of all parameters is 1. This process ensures that the proportional relationship of the weights remains consistent. Regardless of how the values change, the stability of the overall evaluation system is maintained. Utilization of historical data: By combining historical failure data, the model can consider which parameters have shown a higher failure risk in the past during the design and initialization phase. This enables the model to learn and apply accumulated data; Dynamic adaptability: Dynamic sensitivity function f i (t) Provides sensitive adjustments to the current situation. For example, changes in certain parameters under certain environmental conditions may indicate higher risks. Dynamically adjusting the weights of these parameters helps improve the sensitivity of the model. Enhanced predictive capabilities. By integrating historical data and dynamic real-time data, the model can more accurately predict the future state of the equipment, thereby achieving more efficient preventive maintenance in real operations. i (t) = a·e -b·t , where a represents the initial sensitivity, which is a baseline value set at the beginning of equipment monitoring. It represents the sensitivity to a certain parameter in the initial stage. When the escalator is first put into use, the initial sensitivity of parameters such as vibration or noise may be high because abnormal changes in these parameters in new equipment are more likely to indicate fault problems. b represents the decay rate, which determines the speed at which the sensitivity decreases over time. This parameter reflects the rate at which the importance of the parameter is adjusted during the continuous operation of the escalator. In an escalator, if a parameter such as vibration or noise is a high priority in the early stage of the escalator's service but gradually becomes a low priority as it is used, then a b value lower than the original value can be set to slowly reduce the sensitivity. The b value can be adjusted based on historical fault records and equipment life prediction to optimize the monitoring of potential problems. t represents the operating time of the escalator from the start of monitoring to the current time. In an escalator, as time t increases, deviations in certain parameters are gradually no longer considered major problems, which reflects the adaptation to the longer-term operating behavior of the equipment.

[0056] In one embodiment of the present invention, the dynamic threshold is calculated by a dynamic threshold model. Specifically, the dynamic threshold model is:

[0057]

[0058] Among them, τ′ i (t) represents the threshold value of the i-th working state parameter at time t, τ i (0) represents the initial threshold of the i-th working state parameter, α represents the maximum degradation degree finally achieved, β represents the degradation rate coefficient, ΔX i represents the change of the i-th working state parameter, and ΔT represents the length of the time period in which the change occurs.

[0059] The working principle and effect of the above technical solution are: the initial threshold τ′i (t) is the baseline value set during the escalator commissioning phase, reflecting the expected value under normal working conditions; the change in value affects It reflects the rate of parameter change. When a parameter changes rapidly, it will make the dynamic threshold value more actively adjusted. This helps to adapt to rapidly changing environments or operating conditions. The maximum degradation degree α represents the maximum possible change of the parameter during escalator operation. This constant sets the upper limit of the dynamic adjustment range to ensure that in extreme cases, the threshold adjustment will not exceed the reasonable range. The exponential decay function (1-e -βt ) is used to simulate parameter changes or degradation that gradually stabilize over time. It ensures that the dynamic adjustment rate is faster in the early stages and more stable in the later stages of equipment operation, avoiding over-adjustment. Dynamic adaptability enables the threshold to be dynamically adjusted as the actual operating conditions change, enhancing the model's adaptability to parameter fluctuations. This is because the parameter change characteristics of different escalators vary under different usage periods and environmental conditions. Enhanced flexibility: escalators face different operating environments and stress conditions in different states or usage phases. The dynamic model improves flexibility by adapting to the current equipment state as the operating time t changes. Preventing false alarms: By adjusting the threshold, the system can prevent false alarms when parameter fluctuations are still within reasonable expectations, reducing unnecessary maintenance and downtime. Reflecting equipment aging and wear: By using degradation rate coefficients and maximum degradation levels, the model can effectively represent the natural performance degradation of equipment or components due to wear or aging. Supporting condition monitoring and maintenance decision-making, dynamic thresholds enable maintenance personnel to better understand equipment status differences and when maintenance operations are required, identifying potential faults early and improving overall equipment reliability. The model provides a responsive method for managing operating equipment parameters, ensuring that the system can quickly respond to environmental changes while avoiding unnecessary and complex adjustment processes. Through such a dynamic mechanism, maintenance and operations can be carried out in a safer and more efficient framework.

[0060] In one embodiment of the present invention, when it is detected that the value of the working status parameter of the escalator exceeds its dynamic threshold, a preliminary warning of the escalator is directly triggered and relevant data is uploaded to the cloud.

[0061] In one embodiment of the present invention, the edge computing device uploads the monitored operating status parameters and the evaluated comprehensive health index of the escalator to the cloud, and the cloud continues to monitor the operation of the escalator according to the indication of the comprehensive health index, including:

[0062] The edge computing device uploads the monitored operating status parameters and the evaluated comprehensive health index of the escalator to the cloud. When the evaluated comprehensive health index is greater than or equal to 0.8, the cloud determines whether the escalator has a trend fault based on the current operating status parameters of the escalator, including:

[0063] Obtaining historical key operating status parameters of the escalator to be monitored, and integrating the operation log, fault record and maintenance log in the escalator control system;

[0064] Preprocessing the acquired historical key working status parameters includes: identifying and removing abnormal values in the historical key working status parameter data, such as jump data caused by sensor failure, and eliminating incomplete data fragments;

[0065] Extract key features from the raw data, including: maximum deformation, deformation rate, deformation mode, maximum temperature, average temperature, temperature fluctuation amplitude, temperature change rate, maximum acceleration value, acceleration oscillation frequency, acceleration direction change, vibration amplitude, spectrum analysis, kurtosis and skewness of vibration signals, maximum displacement, displacement period and phase, and displacement change rate. Associate the extracted key features with the fault type to form a historical data set.

[0066] Using the historical data set to train a long short-term memory network model, the input of the long short-term memory network model is the key feature, and the output is the fault type;

[0067] The data features of real-time detection are input into the trained long short-term memory network model to obtain the fault type. If the output prediction result of the long short-term memory network model is normal, no processing is required. If the output prediction result indicates a fault, the relevant staff will be notified to replace the components related to the fault type of the escalator to be monitored in advance.

[0068] The working principle and effectiveness of the above technical solution are as follows: real-time monitoring and dynamic thresholds. Edge computing devices monitor the escalator's operating parameters in real time. When these parameters exceed the set dynamic thresholds, a preliminary warning is triggered, and the warning signal and related data are uploaded to the cloud for further analysis. The escalator's operating parameters and a comprehensive health index calculated by the edge computing device are uploaded to the cloud. The cloud further monitors and analyzes the escalator's operating parameters based on the comprehensive health index (if it is below 0.8, it indicates potential risk). In the cloud, the system integrates and preprocesses historical data of key operating parameters to remove outliers and organizes operation logs, fault records, and maintenance logs to form the basis for analysis. Key features such as deformation, temperature, and vibration are extracted to establish a historical database. This historical data is used to train a long short-term memory (LSTM) network model to learn the relationship between parameter features and fault types. The real-time monitored parameter features are input into the trained LSTM model, which determines whether a fault exists in the current operating state based on its training patterns. Based on the fault type output by the model, if the predicted result indicates an abnormality, the system notifies maintenance personnel to perform preventive maintenance or replace the relevant component. Improve early warning accuracy, use dynamic thresholds to ensure that the system is more sensitive to parameter changes under different states, and reduce the chances of false alarms and missed alarms; timely maintenance and prevention, through the calculation and analysis of the comprehensive health index, can predict and prevent potential failures in advance, reducing unnecessary downtime and operational risks; the LSTM model can learn and extract complex time series feature relationships from historical data, and then accurately predict the possibility of future failures, thereby improving the intelligence level of escalator management; efficient data processing and decision support, combining edge computing with cloud analysis, so that on-site real-time response and remote deep processing can be carried out in parallel, improving decision-making efficiency; optimize maintenance and reduce costs, through fault prediction, maintenance activities can be carried out more accurately, reducing the waste of resources caused by traditional regular maintenance; not only is the technology advanced but also has high practical application value, enabling operations and maintenance teams to grasp the real-time health status of equipment and improve service reliability and safety through intelligent means.

[0069] In one embodiment of the present invention, the edge computing device uploads the monitored operating status parameters and the evaluated comprehensive health index of the escalator to the cloud, and the cloud continues to monitor the operation of the escalator according to the indication of the comprehensive health index, further comprising:

[0070] When the evaluated comprehensive health index is less than or equal to 0.8, the cloud sends the adjusted parameter threshold to the edge computing device.

[0071] τ i (t) = τ′ i (t)·H(t)·(X i (t)-μ i(t))

[0072] Among them, τ i (t) represents the adjusted parameter threshold, τ′ i (t) represents the dynamic threshold calculated by the dynamic threshold model, H(t) represents the comprehensive health status index of the escalator at time t, X i (t) represents the actual value of the escalator's i-th working state parameter at time t, μ i (t) represents the expected value of the i-th working state parameter at time t;

[0073] The edge computing device adjusts the real-time detection logic based on the feedback, and the edge computing device adjusts the dynamic threshold to avoid missed alarms or false alarms.

[0074] The working principle and effect of the above technical solution are as follows: by coordinating between the edge computing device and the cloud, dynamic monitoring and adjustment of the escalator operating parameters are achieved, which not only improves the accuracy of monitoring, but also enhances the responsiveness and reliability of the system; the edge computing device continuously monitors the working status parameters of the escalator and calculates a comprehensive health index. When the index is lower than or equal to 0.8, it indicates that the device may be in poor condition and requires stricter monitoring; threshold adjustment and feedback, after the cloud receives the parameters and comprehensive health index uploaded by the edge device, in order to more accurately reflect the current device status, the adjustment threshold is recalculated, and the edge computing device responds in real time. After receiving the adjusted parameter threshold returned by the cloud, the edge device recalibrates the detection logic according to the new threshold; on this basis, the monitoring conditions and alarm mechanism are adjusted to reduce missed reports and false alarms, and improve the pertinence and effectiveness of monitoring. Improve monitoring accuracy, dynamically adjust thresholds to make monitoring sensitivity more precise, and be able to adjust according to real-time conditions to reduce the incidence of false alarms and missed alarms; enhance system stability, when the comprehensive health index is low, through refined control of work and numbers, the system's fault prediction and early warning response capabilities can be effectively improved; dynamic adaptability, through continuous learning and adaptation of the system, it can flexibly respond to equipment requirements under different operating conditions, adapt to environmental changes and equipment wear; optimize resource utilization, dynamic adjustment avoids waste of resources due to too frequent maintenance and inspection, and enhances the accuracy of maintenance plans and the rationality of resource allocation; improved decision support, providing a centralized monitoring and management platform, from which the data and analysis results obtained can be used to further improve equipment management and decision-making; through precise control of thresholds and collaboration between edge and cloud, the scientific nature and operability of escalator monitoring are improved, thereby extending the service life of the equipment and improving its operational safety and reliability.

[0075] One embodiment of the present invention provides an escalator operation monitoring device, comprising:

[0076] A monitoring module is configured to collect key operating status parameters of the escalator to be monitored during operation through a sensor array provided on the escalator to be monitored, upload the operating status parameters to an edge computing device adjacent to the escalator to be monitored, and use the edge computing device to evaluate a comprehensive health index of the escalator to be monitored;

[0077] The fault trend prediction module is used for the edge computing device to upload the monitored working status parameters of the escalator and the evaluated comprehensive health index to the cloud, and the cloud continues to monitor the operation of the escalator according to the indication of the comprehensive health index.

[0078] One embodiment of the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the escalator operation monitoring method through the computer program.

[0079] One embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, and the escalator operation monitoring method is executed when the program is run.

[0080] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for monitoring escalator operation, characterized in that: The method comprises: A sensor array disposed on the escalator to be monitored collects various key operating status parameters of the escalator to be monitored during operation, and the operating status parameters are uploaded to an edge computing device next to the escalator to be monitored. The edge computing device then evaluates the comprehensive health index of the escalator to be monitored. The edge computing device uploads the monitored working status parameters of the escalator and the evaluated comprehensive health index to the cloud, and the cloud continues to monitor the operation of the escalator according to the indication of the comprehensive health index.

2. The escalator operation monitoring method according to claim 1, characterized in that: The sensor array set on the escalator to be monitored collects various key working status parameters of the escalator to be monitored during operation, and uploads the working status parameters to the edge computing device next to the escalator to be monitored. The edge computing device evaluates the comprehensive health index of the escalator to be monitored, including: By installing optical fiber strain gauges, optical fiber thermometers, optical fiber accelerometers, optical fiber noise meters, and optical fiber displacement meters on the escalator, the deformation of the truss, the temperature of the drive unit, the acceleration of the handrail, the vibration signal of the drive unit, and the displacement of the steps are measured respectively. The deformation of the truss, the temperature of the drive unit, the acceleration of the handrail, the vibration signal of the drive unit, and the displacement of the steps are the key working status parameters of the escalator. The edge computing device evaluates the health index of the escalator to be monitored using a health index model. Specifically, the health index model is: Among them, H(t) represents the comprehensive health status index of the escalator at time t, w i represents the dynamic weight coefficient of the i-th working state parameter at time t, X i (t) represents the actual value of the escalator's i-th working state parameter at time t, μ i (t) represents the expected value of the i-th working state parameter at time t, τ′ i (t) represents the dynamic threshold of the i-th working state parameter of the escalator at time t.

3. The escalator operation monitoring method according to claim 2, characterized in that: The dynamic weight coefficient is calculated by a dynamic weight model. Specifically, the dynamic weight model is: Among them, f i (t) represents the dynamic sensitivity function, F i represents the total number of escalator failures caused by abnormalities in the i-th working state parameter in history, It represents the total number of faults caused by the escalator working state parameters, and n represents the total number of working state parameters.

4. The escalator operation monitoring method according to claim 2, characterized in that: The dynamic threshold is calculated by a dynamic threshold model. Specifically, the dynamic threshold model is: Among them, τ′ i (t) represents the threshold value of the i-th working state parameter at time t, τ i (0) represents the initial threshold of the i-th working state parameter, α represents the maximum degradation degree finally achieved, β represents the degradation rate coefficient, ΔX i It represents the change of the i-th working state parameter, ΔT represents the length of the time period in which the change occurs, and t represents the running time of the escalator from the initial monitoring to the current time.

5. The escalator operation monitoring method according to claim 4, characterized in that: When it is detected that the working status parameter value of the escalator exceeds its dynamic threshold, the escalator's preliminary warning is directly triggered and the relevant data is uploaded to the cloud.

6. The escalator operation monitoring method according to claim 1, characterized in that: The edge computing device uploads the monitored operating status parameters of the escalator and the evaluated comprehensive health index to the cloud, and the cloud continues to monitor the operation of the escalator according to the indication of the comprehensive health index, including: The edge computing device uploads the monitored operating status parameters and the evaluated comprehensive health index of the escalator to the cloud. When the evaluated comprehensive health index is greater than or equal to 0.8, the cloud determines whether the escalator has a trend fault based on the current operating status parameters of the escalator, including: Obtaining historical key operating status parameters of the escalator to be monitored, and integrating the operation log, fault record and maintenance log in the escalator control system; Preprocessing the acquired historical key working status parameters includes: identifying and removing abnormal values in the historical key working status parameter data, such as jump data caused by sensor failure, and eliminating incomplete data fragments; Extract key features from the raw data, including: maximum deformation, deformation rate, deformation mode, maximum temperature, average temperature, temperature fluctuation amplitude, temperature change rate, maximum acceleration value, acceleration oscillation frequency, acceleration direction change, vibration amplitude, spectrum analysis, kurtosis and skewness of vibration signals, maximum displacement, displacement period and phase, and displacement change rate. Associate the extracted key features with the fault type to form a historical data set. Using the historical data set to train a long short-term memory network model, the input of the long short-term memory network model is the key feature, and the output is the fault type; The data features of real-time detection are input into the trained long short-term memory network model to obtain the fault type. If the output prediction result of the long short-term memory network model is normal, no processing is required. If the output prediction result indicates a fault, the relevant staff will be notified to replace the components related to the fault type of the escalator to be monitored in advance.

7. The escalator operation monitoring method according to claim 1, characterized in that: The edge computing device uploads the monitored operating status parameters of the escalator and the evaluated comprehensive health index to the cloud, and the cloud continues to monitor the operation of the escalator according to the indication of the comprehensive health index, and further includes: When the evaluated comprehensive health index is less than or equal to 0.8, the cloud sends the adjusted parameter threshold to the edge computing device. t i (t)=τ′ i (t)·H(t)·(X i (t)-m i (t)); Among them, τ i (t) represents the adjusted parameter threshold, τ′ i (t) represents the dynamic threshold calculated by the dynamic threshold model, H(t) represents the comprehensive health status index of the escalator at time t, X i (t) represents the actual value of the escalator's i-th working state parameter at time t, μ i (t) represents the expected value of the i-th working state parameter at time t; The edge computing device adjusts the real-time detection logic based on the feedback, and the edge computing device adjusts the dynamic threshold to avoid missed alarms or false alarms.

8. An escalator operation monitoring device, characterized in that: The device comprises: A monitoring module is configured to collect key operating status parameters of the escalator to be monitored during operation through a sensor array provided on the escalator to be monitored, upload the operating status parameters to an edge computing device adjacent to the escalator to be monitored, and use the edge computing device to evaluate a comprehensive health index of the escalator to be monitored; The fault trend prediction module is used for the edge computing device to upload the monitored working status parameters of the escalator and the evaluated comprehensive health index to the cloud, and the cloud continues to monitor the operation of the escalator according to the indication of the comprehensive health index.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 7 through the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, and when the program is executed, the method according to any one of claims 1 to 7 is executed.

Citation Information

Cited By

  • Apparatus and method for determining anomaly probability of escalator based on artificial intelligence

    KR103019335B1