Rail transit escalator monitoring system

Abstract

The invention discloses a rail transit escalator monitoring system, and belongs to the technical field of escalators, and the rail transit escalator monitoring system comprises a sensing layer which is composed of sensor networks deployed at key parts of each escalator, the sensors comprise a vibration sensor, a temperature sensor, a current and voltage sensor, a photoelectric sensor and a passenger flow counter; the network layer is used for carrying out data transmission in combination with 5G and an industrial Internet of Things private network; the platform layer is used for constructing a cloud platform based on a micro-service architecture, and the cloud platform comprises an equipment management module, a real-time monitoring module, a fault diagnosis module, a prediction maintenance module, a work order management module and a data analysis module; and the application layer is used for providing customized application interfaces for different users. According to the method, the response speed of the escalator can be guaranteed, full analysis of multiple data of the escalator is achieved, the maintenance efficiency and timeliness of the escalator are improved, and the equipment failure rate and the maintenance cost are greatly reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of escalators, and more particularly to a rail transit escalator monitoring system. Background Art

[0002] Rail transit escalators are composed of a specially constructed chain conveyor and two specially constructed belt conveyors, each with a circulating path. They are fixed, electrically driven devices used to transport passengers up or down between different floors of a building. With the rapid expansion of urban rail transit networks, rail transit escalators have become crucial passenger transportation equipment within stations, and their safety and reliability directly impact rail transit operational efficiency and service quality.

[0003] At present, in the actual use of traditional rail transit escalators, the monitoring systems used in traditional escalators have problems such as delayed response, insufficient data analysis, and low maintenance efficiency.

[0004] This paper proposes an intelligent rail transit escalator monitoring system based on the Internet of Things, big data analysis, and artificial intelligence technologies. Through innovations such as multi-dimensional data fusion, intelligent early warning, and predictive maintenance, it realizes the full life cycle management of escalators, significantly improving rail transit operation safety and maintenance efficiency.

[0005] Therefore, in view of this, the existing structure is studied and improved, and a rail transit escalator monitoring system is provided to achieve a more practical purpose. Summary of the Invention

[0006] 1. Technical problems to be solved

[0007] In response to the problems existing in the prior art, the purpose of the present invention is to provide a rail transit escalator monitoring system, which can ensure the response speed of the escalator, realize the full analysis of multiple data of the escalator, improve the maintenance efficiency and timeliness of the escalator, and significantly reduce the equipment failure rate and maintenance costs.

[0008] 2. Technical solution

[0009] To solve the above problems, the present invention adopts the following technical solutions.

[0010] A rail transit escalator monitoring system, the rail transit escalator monitoring system comprising:

[0011] Perception layer: It consists of a sensor network deployed at key locations on escalators. The sensors include vibration sensors, temperature sensors, current and voltage sensors, photoelectric sensors, and passenger flow counters.

[0012] Network layer: Combine 5G and industrial IoT private networks for data transmission;

[0013] Platform layer: Based on the microservice architecture, a cloud platform is built. The cloud platform includes equipment management module, real-time monitoring module, fault diagnosis module, predictive maintenance module, work order management module, and data analysis module;

[0014] Application layer: Provides customized application interfaces for different users, including operation and maintenance personnel, management personnel, and passenger service personnel.

[0015] Furthermore, in the perception layer:

[0016] Vibration sensors monitor the vibration frequency and amplitude of motors, gearboxes and other key components; temperature sensors collect real-time temperature data of bearings, motors and other heat-prone parts; current and voltage sensors monitor the electrical parameters of the motor during operation; photoelectric sensors detect missing steps, comb plates and other abnormal conditions; and passenger flow counters count real-time passenger flow and operating frequency.

[0017] Furthermore, in the network layer:

[0018] Key data is transmitted in real time through the 5G network, routine monitoring data is transmitted in batches through the industrial Internet of Things private network, and edge computing nodes pre-process the original data.

[0019] Furthermore, in the platform layer:

[0020] The equipment management module manages the entire life cycle of escalator assets, the real-time monitoring module visualizes the operating status, the fault diagnosis module detects anomalies based on machine learning, the predictive maintenance module predicts the remaining service life, the work order management module digitally manages the maintenance process, and the data analysis module conducts multi-dimensional operation performance analysis.

[0021] Furthermore, in the application layer:

[0022] The applications for operation and maintenance personnel include mobile APP and PC management background, the applications for managers include data dashboards and decision support, and the applications for passenger service personnel include real-time push and guidance of abnormal status.

[0023] Furthermore, the data analysis module and the fault diagnosis module are combined to perform escalator fault analysis and pre-testing. A fault prediction model is established based on deep learning to improve prediction accuracy. Deep learning methods include multimodal data fusion analysis, transfer learning application, and adaptive threshold adjustment.

[0024] Furthermore, the real-time monitoring module is combined with the application layer to monitor and display the escalator. Specifically, based on the digital twin drive, visual monitoring is carried out to form intelligent monitoring that integrates virtual and real, and then displayed at the application layer in the form of three-dimensional visual display. The digital twin drive method includes virtual reality maintenance training and fault backtracking analysis.

[0025] Furthermore, the predictive maintenance module is combined with the work order management module to apply knowledge graph technology to maintenance work order management. The forms of work order management include intelligent work order allocation, maintenance knowledge graph and AR-assisted maintenance.

[0026] In the maintenance work order management process, the specific steps are:

[0027] Work order generation: When a fault occurs and is reported to the platform, the maintenance management system automatically triggers and pushes a repair work order to the maintenance personnel;

[0028] Maintenance personnel accept tasks on the app, record the authenticity of the event, and for real faults, record the handling process and the cause of the fault;

[0029] Work order processing: On the mobile side, maintenance personnel can view the maintenance work orders pushed from the background, and verify and handle them on site. The verified actual situation can be filled in the "On-site situation description" text box.

[0030] Furthermore, the fault diagnosis module and the work order management module are combined to conduct maintenance quality traceability based on blockchain. Specific operations include uploading maintenance records to the chain, automatic execution of smart contracts, and supply chain collaboration.

[0031] Furthermore, the application layer display tool also includes a rail transit board, which is equipped with a rail transit route map and board statistics, including:

[0032] The operation steps of the rail transit line map are:

[0033] If an escalator in the station is in an abnormal state, the station will be highlighted;

[0034] Click on a station to display the list of escalators in the station and the basic operating status of the escalators;

[0035] Click the escalator icon to enter the monitoring details;

[0036] Dashboard statistics: includes statistics on escalator types within the site, escalator work order quantity, operating time, operating times, and scrolling display of escalator lists.

[0037] 3. Beneficial effects

[0038] Compared with the prior art, the advantages of the present invention are:

[0039] In this solution, the system consists of perception layer, network layer, platform layer and application layer.

[0040] Through Internet of Things technology, big data analysis and artificial intelligence algorithms, intelligent management of the entire life cycle of escalators has been achieved, transforming from passive response maintenance to active preventive maintenance, ensuring the response speed of escalators, realizing full analysis of multiple escalator data, improving the maintenance efficiency and timeliness of escalators, and significantly reducing equipment failure rate and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 Schematic diagram of the structure of the rail transit escalator monitoring system of the present invention;

[0042] Figure 2 This is a schematic diagram of the system used in Suzhou Rail Transit Escalator Monitoring System. Figure 1 ;

[0043] Figure 3 This is a schematic diagram of the system used in Suzhou Rail Transit Escalator Monitoring System. Figure 2 . DETAILED DESCRIPTION

[0044] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention; it is obvious that the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0045] Example 1:

[0046] See also Figure 1 , a rail transit escalator monitoring system, the rail transit escalator monitoring system comprising:

[0047] Perception layer: It consists of a sensor network deployed at key locations on escalators. The sensors include vibration sensors, temperature sensors, current and voltage sensors, photoelectric sensors, and passenger flow counters.

[0048] Specifically, vibration sensors monitor the vibration frequency and amplitude of motors, gearboxes and other key components; temperature sensors collect temperature data of bearings, motors and other heat-prone parts in real time; current and voltage sensors monitor the electrical parameters of the motor during operation; photoelectric sensors detect missing steps, comb plates and other abnormal conditions; and passenger flow counters count real-time passenger flow and operating frequency.

[0049] Network layer: Combine 5G and industrial IoT private networks for data transmission;

[0050] Specifically, the key data is transmitted in real time through the 5G network, ensuring low-latency transmission, and the conventional monitoring data is transmitted in batches through the industrial Internet of Things private network, which can reduce costs. The edge computing node preprocesses the raw data, which can reduce the burden on the cloud.

[0051] Platform layer: based on micro-service architecture, build cloud platform, cloud platform includes device management module, real-time monitoring module, fault diagnosis module, predictive maintenance module, work order management module, data analysis module;

[0052] Specifically, the device management module manages the escalator asset throughout its life cycle, the real-time monitoring module visually displays the running state, the fault diagnosis module detects abnormalities based on machine learning, the predictive maintenance module predicts the remaining useful life, the work order management module digitally manages the maintenance process, and the data analysis module performs multi-dimensional performance analysis.

[0053] Application layer: provide customized application interfaces for different users, including operation and maintenance personnel, management personnel, and passenger service personnel.

[0054] Specifically, the application of operation and maintenance personnel includes mobile APP and PC management background, the application of management personnel includes data dashboard and decision support, and the application of passenger service personnel includes real-time push and guidance of abnormal state.

[0055] Then, combine the perception layer, network layer, platform layer and application layer:

[0056] Specifically, the data analysis module and the fault diagnosis module are combined to analyze and test the escalator faults, wherein a fault prediction model is established based on deep learning to improve prediction accuracy, and the deep learning method includes multi-modal data fusion analysis, transfer learning application and adaptive threshold adjustment.

[0057] In multi-modal data fusion analysis:

[0058] Align the time and space of multi-dimensional sensor data such as vibration signals, temperature curves and current waveforms, dynamically allocate the weights of different sensor data using attention mechanism, and construct deep convolutional neural network to extract time and frequency domain features;

[0059] In transfer learning application:

[0060] Pre-train the base model based on a large amount of historical fault data, fine-tune it for different brands and models of escalators, and realize knowledge transfer across devices and scenarios;

[0061] Adaptive threshold adjustment: Automatically adjust the alarm threshold according to the equipment age and operating environment, taking into account the impact of seasonal factors and passenger flow changes on equipment status, and dynamically optimize the balance point between false alarm rate and missed detection rate.

[0062] Specifically, the real-time monitoring module and the application layer are combined to monitor and display escalators. Specifically, based on the digital twin drive, visual monitoring is carried out to form intelligent monitoring that integrates virtual and real, and then displayed at the application layer in the form of three-dimensional visual display. The digital twin drive method includes virtual reality maintenance training and fault backtracking analysis.

[0063] 3D visualization display: Based on BIM technology, a high-fidelity escalator 3D model is constructed, which maps the operating status and health indicators of the physical equipment in real time, and supports interactive viewing from multiple perspectives and multiple levels of detail.

[0064] In virtual reality maintenance training, various fault scenarios are simulated in a digital twin environment, providing maintenance personnel with an immersive training experience and supporting standard process drills for maintenance operations.

[0065] In fault retrospective analysis, the complete device status before and after the fault occurs is recorded, supporting timeline playback and key parameter comparison, assisting in fault root cause analysis and disposal plan optimization.

[0066] Specifically, the predictive maintenance module is combined with the work order management module to apply knowledge graph technology to maintenance work order management. The forms of work order management include intelligent work order allocation, maintenance knowledge graph and AR-assisted maintenance.

[0067] In intelligent work order allocation, optimal matching is performed based on the maintenance personnel's location, skill tags, and historical performance, taking into account constraints such as spare parts inventory and traffic conditions, to achieve dynamic scheduling and load balancing of maintenance resources;

[0068] In the maintenance knowledge graph, a domain knowledge base including fault phenomena, possible causes, and solutions is constructed, supporting natural language queries and case similarity retrieval to provide intelligent decision support for on-site maintenance;

[0069] In AR-assisted maintenance, augmented reality technology is used to superimpose maintenance instructions and key parameters, support remote expert collaborative consultation, and record the maintenance process to form standardized cases.

[0070] In the maintenance work order management process, the specific steps are:

[0071] Work order generation: When a fault occurs and is reported to the platform, the maintenance management system automatically triggers and pushes a repair work order to the maintenance personnel;

[0072] Maintenance personnel accept tasks on the APP and record the authenticity of the event (including real, test, false alarm, etc.). For real faults, they record the handling process and the cause of the fault.

[0073] Work order processing: On the mobile side, maintenance personnel can view the maintenance work orders pushed from the background, and verify and handle them on site. The verified actual situation can be filled in the "On-site situation description" text box.

[0074] Specifically, the fault diagnosis module and the work order management module are combined to conduct maintenance quality traceability based on blockchain. At this time, blockchain technology is introduced to ensure the credibility and transparency of the maintenance process. Specific operations include uploading maintenance records to the chain, automatic execution of smart contracts, and supply chain collaboration.

[0075] Maintenance records are being uploaded to the chain: key maintenance operations, replacement parts, quality inspection and other information are uploaded to the chain to ensure that the data cannot be tampered with and is fully traceable, and a complete digital archive of equipment maintenance is established

[0076] Smart contracts are automatically executed: preset repair quality standards and acceptance conditions automatically trigger subsequent processes such as payment and evaluation, reducing human intervention and disputes.

[0077] Supply chain collaboration: connecting equipment manufacturers, maintenance units, and parts suppliers to achieve intelligent forecasting of spare parts demand and automatic replenishment, optimizing inventory turnover and capital utilization.

[0078] See also Figure 2 、 Figure 3 Specifically, the display tools of the application layer also include rail transit boards, which are equipped with rail transit route maps and board statistics, including:

[0079] The operation steps of the rail transit line map are:

[0080] If an escalator in the station is in an abnormal state (maintenance / fault), the station will be highlighted;

[0081] Click on a station to display the list of escalators in the station and the basic operating status of the escalators;

[0082] Click the escalator icon to enter the monitoring details.

[0083] Dashboard statistics: includes statistics on escalator types within the site, escalator work order quantity, operating time, operating times, and scrolling display of escalator lists.

[0084] Example 2:

[0085] Based on the above embodiment 1, further description is given.

[0086] Based on this rail transit escalator monitoring system, its application in pilot implementation has the following implementation benefits:

[0087] (1) Safety benefits

[0088] The failure warning time advance rate is more than 85%;

[0089] The incidence of major safety accidents decreased by 90%;

[0090] Passenger complaint rates dropped by 70%;

[0091] (2) Economic benefits

[0092] Maintenance costs reduced by 40% to 50%;

[0093] Equipment service life is extended by 30%;

[0094] Spare parts inventory turnover rate increased by 60%.

[0095] (3) Management benefits

[0096] Maintenance response time is shortened to less than 30 minutes;

[0097] Work order processing efficiency increased by 3 times;

[0098] Systematization of knowledge accumulation and inheritance;

[0099] (4) Social benefits

[0100] Improve rail transit service quality and passenger satisfaction;

[0101] Reduce passenger congestion caused by equipment failure;

[0102] Promote the digital transformation of rail transit operation and maintenance.

[0103] Example 3:

[0104] Based on the above-mentioned embodiment 1 and embodiment 2, further description is given.

[0105] The future development and application directions of this rail transit escalator monitoring system include:

[0106] Deep integration with the urban rail transit brain: Incorporate escalator monitoring data into the overall rail transit scheduling decision-making system to achieve more intelligent passenger flow guidance and equipment coordination.

[0107] Expand to full equipment health management: Expand the existing technical framework to other key equipment such as vertical elevators and platform shield doors to build a unified equipment health management platform.

[0108] Carbon neutrality and energy efficiency optimization: Optimize equipment start-stop strategies and speed adjustment based on operating data, reduce energy consumption, and contribute to the green operation of rail transit.

[0109] A new paradigm for metaverse operation and maintenance: Explore a remote collaborative maintenance model based on the concept of the metaverse, break the limitations of time and space, and improve the utilization of expert resources.

[0110] In summary, this system has achieved the transformation and upgrading of the rail transit escalator operation and maintenance mode, which not only solves the pain points in the current operation and maintenance work, but also lays a solid foundation for the future construction of smart rail transit. With the continuous iteration of technology and the continuous expansion of application scenarios, the system will play a greater role in ensuring operational safety, improving service quality, and reducing operation and maintenance costs.

[0111] The above description is merely a preferred embodiment of the present invention; however, the scope of protection of the present invention is not limited thereto. Any person skilled in the art who, within the technical scope disclosed by the present invention, makes equivalent substitutions or modifications based on the technical solutions and improved concepts of the present invention shall be covered by the scope of protection of the present invention.

Claims

1. A rail transit escalator monitoring system, characterized by: The rail transit escalator monitoring system includes: Perception layer: It consists of a sensor network deployed at key locations on escalators. The sensors include vibration sensors, temperature sensors, current and voltage sensors, photoelectric sensors, and passenger flow counters. Network layer: Combine 5G and industrial IoT private networks for data transmission; Platform layer: Based on the microservice architecture, a cloud platform is built. The cloud platform includes equipment management module, real-time monitoring module, fault diagnosis module, predictive maintenance module, work order management module, and data analysis module; Application layer: Provides customized application interfaces for different users, including operation and maintenance personnel, management personnel, and passenger service personnel.

2. A rail transit escalator monitoring system according to claim 1, characterized in that: In the perception layer: Vibration sensors monitor the vibration frequency and amplitude of motors, gearboxes and other key components; temperature sensors collect real-time temperature data of bearings, motors and other heat-prone parts; current and voltage sensors monitor the electrical parameters of the motor during operation; photoelectric sensors detect missing steps, comb plates and other abnormal conditions; and passenger flow counters count real-time passenger flow and operating frequency.

3. A rail transit escalator monitoring system according to claim 1, characterized in that: In the network layer: Key data is transmitted in real time through the 5G network, routine monitoring data is transmitted in batches through the industrial Internet of Things private network, and edge computing nodes pre-process the original data.

4. A rail transit escalator monitoring system according to claim 1, characterized in that: In the platform layer: The equipment management module manages the entire life cycle of escalator assets, the real-time monitoring module visualizes the operating status, the fault diagnosis module detects anomalies based on machine learning, the predictive maintenance module predicts the remaining service life, the work order management module digitally manages the maintenance process, and the data analysis module conducts multi-dimensional operation performance analysis.

5. The rail transit escalator monitoring system according to claim 1, characterized in that: In the application layer: The applications for operation and maintenance personnel include mobile APP and PC management background, the applications for managers include data dashboards and decision support, and the applications for passenger service personnel include real-time push and guidance of abnormal status.

6. A rail transit escalator monitoring system according to claim 1, characterized in that: The data analysis module and the fault diagnosis module are combined to perform escalator fault analysis and pre-testing. A fault prediction model is established based on deep learning to improve prediction accuracy. Deep learning methods include multimodal data fusion analysis, transfer learning application, and adaptive threshold adjustment.

7. A rail transit escalator monitoring system according to claim 1, characterized in that: The real-time monitoring module is combined with the application layer to monitor and display the escalator. Specifically, based on the digital twin drive, visual monitoring is carried out to form intelligent monitoring that integrates virtual and real, and then displayed at the application layer in the form of three-dimensional visual display. The digital twin drive method includes virtual reality maintenance training and fault backtracking analysis.

8. The rail transit escalator monitoring system according to claim 1, characterized in that: The predictive maintenance module is combined with the work order management module to apply knowledge graph technology to maintenance work order management. The forms of work order management include intelligent work order allocation, maintenance knowledge graph and AR-assisted maintenance. In the maintenance work order management process, the specific steps are: Work order generation: When a fault occurs and is reported to the platform, the maintenance management system automatically triggers and pushes a repair work order to the maintenance personnel; Maintenance personnel accept tasks on the app, record the authenticity of the event, and for real faults, record the handling process and the cause of the fault; Work order processing: On the mobile terminal, maintenance personnel can view the maintenance work orders pushed from the background, and conduct on-site verification and processing. The verified actual situation can be filled in the "On-site situation description" text box.

9. The rail transit escalator monitoring system according to claim 1, characterized in that: The fault diagnosis module and the work order management module are combined to conduct maintenance quality traceability based on blockchain. Specific operations include uploading maintenance records to the chain, automatic execution of smart contracts, and supply chain collaboration.

10. The rail transit escalator monitoring system according to claim 1, characterized in that: The application layer display tools also include rail transit dashboards, which include rail transit route maps and dashboard statistics. The operation steps of the rail transit line map are: If an escalator in the station is in an abnormal state, the station will be highlighted; Click on a station to display the list of escalators in the station and the basic operating status of the escalators; Click the escalator icon to enter the monitoring details; Dashboard statistics: includes statistics on escalator types within the site, escalator work order quantity, operating time, operating times, and scrolling display of escalator lists.

Images