Railway station elevator remote sensing service method and system based on internet of things

Abstract

The application provides a railway station elevator remote sensing service method and system based on the Internet of Things, which comprises the following steps: based on the positions of elevators and passenger areas, associating all elevators in a station with corresponding passenger areas, collecting and receiving real-time elevator operation and surrounding environment data, periodically receiving train operation and passenger flow statistical information of different passenger areas, and generating an elevator dispatching strategy according to real-time operation data, train operation and passenger flow statistical information of different passenger areas, and the association relationship; obtaining historical operation and surrounding environment data and historical fault data, performing fault prediction and warning according to the historical operation and surrounding environment data, the historical fault data, and the real-time operation and surrounding environment data by a long short-term memory network with an attention mechanism, and generating an elevator fault early warning result; and obtaining historical fault and maintenance data, generating an elevator maintenance plan according to the historical fault and maintenance data and the elevator fault early warning result by a convolutional neural network with an attention mechanism.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of Internet of Things, and in particular to a railway station elevator remote sensing service method and system based on Internet of Things. BACKGROUND

[0002] In public places such as railway passenger stations, elevators play a key role in passenger transportation, and are crucial to passenger safety and travel experience. The shutdown or problems of elevators can seriously interfere with passenger travel. At the same time, railway passenger stations usually face complex passenger flow situations, with a huge difference in passenger congestion in different time periods and areas, resulting in highly uneven demand for elevators.

[0003] The railway industry usually uses elevators produced by famous brand companies such as Thyssen, Mitsubishi, Hitachi, and Otis. These brand elevators have elevator monitoring systems for monitoring and managing elevator equipment, but these monitoring systems are only applicable to elevators of their own brand and cannot be used for elevators of other brands. Railway stations need to maintain multiple different brand monitoring systems, which increases the complexity of management and maintenance. In addition, the monitoring data obtained by the monitoring system is relatively limited and cannot provide comprehensive elevator status and environmental information, making it more difficult to discover potential problems and implement preventive maintenance in a timely manner. Most importantly, due to the failure to integrate business data in the railway field, the elevator system cannot intelligently schedule according to actual passenger demand and passenger flow, and cannot effectively alleviate the pressure during peak hours to improve elevator utilization. These problems limit the performance and availability of elevator systems in railway passenger stations, posing challenges to passenger travel experience and safety. SUMMARY

[0004] In view of this, the embodiments of the present application provide a railway station elevator remote sensing service method and system based on Internet of Things to eliminate or improve one or more defects in the prior art.

[0005] One aspect of the present application provides a railway station elevator remote sensing service method based on Internet of Things, comprising:

[0006] Based on the positions of the elevators and the passenger areas, all elevators in the station are associated with corresponding passenger areas, and the running data and surrounding environment data of all elevators in the station are collected in real time by a station-level sensor network;

[0007] The running data and surrounding environment data of all elevators from the station-level sensor network are received in real time by a comprehensive data platform, and train operation information and passenger flow statistical information of different passenger areas pre-configured from a passenger service and control platform are periodically received, and an elevator scheduling strategy is generated according to the real-time running data of the elevators, the train operation information and passenger flow statistical information of different passenger areas, and the association relationship between the elevators and the passenger areas.

[0008] The comprehensive data platform obtains historical operation data, historical surrounding environment data and historical fault data of all elevators, and a preset long short-term memory network model based on an attention mechanism performs fault prediction and warning according to the historical operation data, the historical surrounding environment data, the historical fault data and real-time operation data, real-time surrounding environment data of all elevators, and generates an elevator fault early warning result;

[0009] The comprehensive data platform obtains historical fault data and historical maintenance data of all elevators, and a preset convolutional neural network model based on an attention mechanism generates an elevator maintenance plan according to the historical fault data, the historical maintenance data and the elevator fault early warning result of all elevators;

[0010] The remote monitoring terminal displays the real-time operation data, the elevator scheduling strategy, the elevator fault early warning result and the elevator maintenance plan in real time.

[0011] In some embodiments of the application, the step of generating an elevator scheduling strategy according to real-time operation data of the elevator, train operation information and passenger flow statistical information of different passenger transport areas, and an association relationship between the elevator and the passenger transport area, comprises:

[0012] The comprehensive data platform determines available elevators and current operation states of the available elevators according to real-time operation data of the elevator, analyzes train operation information and passenger flow statistical information of different passenger transport areas received periodically, and obtains time periods of passenger flow peaks and passenger transport areas;

[0013] According to the time periods of passenger flow peaks and the passenger transport areas, the association relationship between the elevator and the passenger transport area, the scheduling sequence, the service time period, the service area, the operation speed and the group configuration of the available elevators are adjusted and optimized, and the use intensity of the available elevators is optimized according to the current operation states of the available elevators.

[0014] In some embodiments of the application, the step of generating an elevator fault early warning result by a preset long short-term memory network model based on an attention mechanism according to historical operation data, historical surrounding environment data, historical fault data and real-time operation data, real-time surrounding environment data of all elevators, comprises:

[0015] The historical operation data, the historical surrounding environment data, the historical fault data and the real-time operation data, the real-time surrounding environment data of all elevators are subjected to data cleaning and feature engineering processing;

[0016] The preset attention mechanism based long short-term memory network model is trained by the processed historical running data, historical surrounding environment data and historical fault data, so as to strengthen the attention of the long short-term memory network model to the relationship between the running state of the elevator, the equipment state and the possible fault;

[0017] The trained attention mechanism based long short-term memory network model is used to predict and alarm the elevator fault according to the processed real-time running data and real-time surrounding environment data, and an elevator fault early warning result is generated, the elevator fault early warning result at least including the elevator number, fault type, fault level, fault occurrence probability and influence degree of the fault on the elevator operation.

[0018] In some embodiments of the present application, the step of data cleaning and feature engineering processing of the historical running data, historical surrounding environment data, historical fault data and real-time running data, real-time surrounding environment data of all elevators comprises:

[0019] The historical running data, historical surrounding environment data, historical fault data and real-time running data, real-time surrounding environment data of all elevators include elevator non-vibration data, elevator vibration data and elevator image data, and the data cleaning of removing noise, filling missing values and abnormal values is performed on the elevator non-vibration data and the elevator vibration data.

[0020] The cleaned elevator non-vibration data is converted into statistical indicators and standardized, the cleaned elevator vibration data is identified and extracted by wavelet change to obtain wavelet components of different frequencies, the feature extraction and identification classification are performed on the elevator image data, and the feature engineering processing is realized.

[0021] In some embodiments of the present application, the step of generating an elevator maintenance plan by the preset attention mechanism based convolutional neural network model according to the historical fault data, historical maintenance data and elevator fault early warning result of all elevators comprises:

[0022] The historical fault data, historical maintenance data and elevator fault early warning result of all elevators are data cleaned, the cleaned data is vectorized by word embedding, and is standardized and normalized;

[0023] The preset attention mechanism based convolutional neural network model is trained by the historical fault data and historical maintenance data after the standardization and normalization, so as to strengthen the attention of the convolutional neural network model to the elevator maintenance information;

[0024] The elevator maintenance plan is generated by the trained attention mechanism based convolutional neural network model according to the standardized and normalized elevator fault early warning results, and the elevator maintenance plan at least includes elevator number needing maintenance, maintenance type, maintenance resource, maintenance frequency, maintenance time and priority.

[0025] In some embodiments of the present application, the method further comprises:

[0026] The operation data and surrounding environment data of all elevators from the station level sensor network are received by the communication gateway and forwarded to the integrated data platform, and the format and protocol of the operation data and surrounding environment data of all elevators are converted and unified during the forwarding process.

[0027] In some embodiments of the present application, the passenger area at least includes at least one of an entrance, a platform, an exit, a waiting room and a ticket gate.

[0028] In some embodiments of the present application, the operation data at least includes operation state, operation speed, elevator door switch state, operation position, temperature, vibration, pressure, load, operation times, start-stop times, elevator cumulative operation time and floor stay time;

[0029] The surrounding environment data at least includes passenger flow and non-standard passenger boarding behavior including elevator door opening and fighting;

[0030] The train operation information at least includes train number, and on-time status of trains of different train numbers, expected departure time, actual departure time, expected arrival time, actual arrival time, ticket checking time, platform, exit and ticket gate;

[0031] The passenger flow statistical information at least includes the number of people in the station in different time periods, the number of passengers getting on and off trains of different train numbers, and passenger flow distribution in different time periods in different passenger areas.

[0032] Another aspect of the present application provides a railway station elevator remote sensing service system based on Internet of Things, which comprises a computer device, the computer device comprising a processor and a memory, the memory storing computer instructions, and the processor being configured to execute the computer instructions stored in the memory, so that the system implements the steps of the foregoing method.

[0033] Another aspect of the present application provides a computer readable storage medium storing a computer program, which is executed by a processor to implement the steps of the foregoing method.

[0034] The railway station elevator remote sensing service method and system based on the Internet of Things can improve the monitoring efficiency of all elevators, realize intelligent elevator fault early warning and operation and maintenance, integrate railway business, optimize intelligent scheduling and reasonable use of elevators, effectively reduce the elevator operation pressure during peak periods, and improve the utilization rate of elevators in the station.

[0035] Additional advantages, objects, and features of the application will be set forth in part in the description which follows, and will become apparent to those skilled in the art upon examination of the following or can be learned by practice of the application. The objects and other advantages of the application can be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

[0036] It will be understood by those skilled in the art that the objects and advantages of the present application can be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0037] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the principles of the application.

[0038] Figure 1 A flowchart of an embodiment of the railway station elevator remote sensing service method based on the Internet of Things of the present application;

[0039] Figure 2 A flowchart of another embodiment of the railway station elevator remote sensing service method based on the Internet of Things of the present application;

[0040] Figure 3 A flowchart of another embodiment of the railway station elevator remote sensing service method based on the Internet of Things of the present application;

[0041] Figure 4 A structural diagram of an embodiment of the railway station elevator remote sensing service system based on the Internet of Things of the present application. DETAILED DESCRIPTION

[0042] To make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in combination with embodiments and drawings. Herein, the illustrative embodiments of the present application and their descriptions are used to explain the present application, but are not limiting to the present application.

[0043] It is also necessary to point out that, in order not to obscure the application with unnecessary details, only the structures and / or processing steps closely related to the solution according to the application are shown in the attached drawings, while other details that are not relevant to the application are omitted.

[0044] It should be emphasized that the term "comprises / comprising" when used in this text refers to the presence of a feature, element, step or component, but does not exclude the presence or addition of one or more other features, elements, steps or components.

[0045] In the following, embodiments of the application will be described with reference to the attached drawings. In the drawings, the same reference numerals represent the same or similar parts or the same or similar steps.

[0046] In order to effectively deal with the complex passenger flow in the railway station, to make passengers in different time periods and different passenger areas reach the designated position they want to reach and travel safely and efficiently, while avoiding the problem of elevator downtime or failure, maintenance and interference with passenger travel, the embodiments of the application provide a railway station elevator remote sensing service method and system based on Internet of Things, which applies Internet of Things technology to railway station elevators, and all elevators in the railway station are included in a network that can realize interconnection within the scope of the railway station, which can improve the monitoring efficiency of all elevators, realize intelligent elevator fault warning and operation and maintenance, and can also integrate railway business, optimize intelligent scheduling and reasonable use of elevators, effectively reduce the elevator operation pressure during peak hours, and improve the utilization rate of elevators in the station.

[0047] Please refer to Figure 1 and Figure 3 The railway station elevator remote sensing service method based on Internet of Things of the embodiments of the application includes the following steps:

[0048] Step S110, based on the positions of the elevators and the passenger areas, all elevators in the station are associated with the corresponding passenger areas, and the running data and surrounding environment data of all elevators in the station are collected in real time by the station-level sensor network.

[0049] In an embodiment of the present application, the passenger area includes at least one of an entrance, a platform, an exit, a waiting room, and a ticket gate. One or more elevators, including escalators and moving walkways, are provided between these different passenger areas to enable passengers to smoothly move from one designated passenger area to another, for example, from the first waiting room to the sixth platform to take a train of a certain train number. According to the adjacent positional relationship between the elevators and the different passenger areas, whether the elevators are provided in a certain passenger area, and the passenger areas that the elevators can reach, the elevators are associated with the passenger areas that the elevators can reach, the passenger areas that are adjacent to the elevators, and the passenger areas in which the elevators are located, and the elevators are numbered.

[0050] In an embodiment of the present application, the station-level sensor network includes various types of physical sensors that are reasonably configured according to the characteristics of the elevator equipment and the monitoring requirements, specifically including switch sensors for monitoring elevator door switches, speed sensors for monitoring elevator running speeds, position sensors for monitoring the positions of elevators, temperature sensors for monitoring elevator environmental temperatures, human body sensors for monitoring whether there are people taking the elevator, vibration sensors for monitoring whether there are vibrations in the elevator, pressure sensors for monitoring elevator pressure conditions, load sensors for monitoring elevator loads, counting sensors for monitoring the number of times of elevator operation, up and down times, and start and stop times, time sensors for monitoring the time of elevator stay at each floor and the cumulative running time of the elevator, visual cameras for obtaining image data inside the elevator car or the environment of the elevator, and the like, which can monitor and perceive the real-time operation and environmental conditions of the elevator. The operation data of all elevators include but are not limited to running state, running speed, elevator door switch state, running position, temperature, vibration, pressure, load, number of times of operation, number of times of start and stop, cumulative running time of the elevator, and time of stay at each floor, wherein the running state can be determined according to the characteristics of the running speed and acceleration of the elevator whether the elevator is in a state of stop, operation, up, and down, the elevator door switch state includes normal and abnormal states of the switch door, and the surrounding environmental data include but are not limited to the number of people taking the elevator and non-standard taking behavior including the opening of the elevator door and the making of noise.

[0051] In step S130, the comprehensive data platform receives the operation data and surrounding environmental data of all elevators from the station-level sensor network in real time, and periodically receives train operation information and passenger flow statistical information of different passenger areas pre-configured from the passenger service and management platform, and generates an elevator dispatching strategy according to the real-time operation data of the elevators, the train operation information and passenger flow statistical information of different passenger areas, and the association relationship between the elevators and the passenger areas.

[0052] In an embodiment of the present application, the train operation information includes but is not limited to train number, and on-time or late-arrival status (including on-time arrival and late-arrival) of trains of different train numbers, estimated departure time, actual departure time, estimated arrival time, actual arrival time, ticket checking time, platform, exit and ticket checking gate. The passenger flow statistical information includes but is not limited to number of people in the station in different time periods, number of passengers getting on and off trains of different train numbers, passenger flow distribution in different time periods in different passenger transport areas and train numbers of trains taken by different passengers. The comprehensive data platform can receive and integrate multi-source data collected by various physical sensors in the station sensor network in real time and from the railway business data platform (passenger service and control platform).

[0053] In an embodiment of the present application, referring to Figure 3 , the step of generating the elevator dispatching strategy according to the real-time operation data of the elevator, the train operation information and the passenger flow statistical information of different passenger transport areas and the association between the elevator and the passenger transport area in step S130 includes: determining available elevators and current operation states of the available elevators according to the real-time operation data of the elevator by the comprehensive data platform, analyzing the train operation information and the passenger flow statistical information of different passenger transport areas received regularly to obtain time periods of passenger flow peaks and passenger transport areas; adjusting and optimizing the dispatching sequence, service time period, service area, operation speed and group configuration of the available elevators according to the time periods of passenger flow peaks and the passenger transport areas, the association between the elevator and the passenger transport area, and optimizing the use intensity of the available elevators according to the current operation states of the available elevators.

[0054] In the embodiment of the present application, the comprehensive data platform determines the available elevators and the number thereof according to the received data such as the elevator running speed and the elevator door switch state whether the door is normally opened or closed, and obtains the current running state (stopping or normal running) of the available elevators, analyzes the train running information and passenger flow statistical information of different waiting rooms, different ticket gates and different platforms received periodically, analyzes the predicted and actual departure and arrival running information of each train in different time periods, obtains the time period of passenger flow peak and the passenger transport area, for example, the two train of each platform corresponding to the first to sixth platform in the first waiting room are all in the same time period, and each train has more passengers, so the time period is the time period of passenger flow peak, the first waiting room in the time period, the ticket gate corresponding to the departure train and the first to sixth platform are the passenger transport area of passenger flow peak, and at least one of the following intelligent scheduling strategies is performed on the available elevators going to the first waiting room, the ticket gate corresponding to the departure train and the first to sixth platform or the available elevators in the adjacent position that can reach the passenger transport area. The use of the available elevators and the scheduling of the up and down running order can be preferentially scheduled, the available elevators are scheduled to serve the passengers in the passenger transport area in the peak time period, the running speed of the elevator is appropriately accelerated under the premise of safe running, multiple elevators located in the same passenger transport area or adjacent position that can reach the same passenger transport area are configured as an elevator group, the multiple elevators configured as an elevator group can respond to the same elevator request at the same time, and the use intensity of the available elevators is optimized according to the current running state of the available elevators, the use intensity (use frequency and passenger carrying rate) of the idle or low use intensity elevators is increased, the dynamic scheduling of the elevators is performed according to the passenger flow in the peak period of different passenger transport areas and different time periods, the utilization rate of idle elevators is improved to reduce the waiting time of passengers, ensure that each elevator reaches the designated passenger transport area in different time periods to meet the needs of passengers, significantly improve the one-stop travel experience of passengers entering the station, taking the train and leaving the station, and improve the working efficiency and rational utilization rate of the elevators.

[0055] In step S140, the comprehensive data platform obtains historical running data, historical surrounding environment data and historical fault data of all elevators, and the preset long short-term memory network model based on attention mechanism performs fault prediction and warning according to the historical running data, historical surrounding environment data, historical fault data and real-time running data, real-time surrounding environment data of all elevators, and generates an elevator fault warning result.

[0056] In an embodiment of the present application, please refer to Figure 3, the step S140 of generating the elevator fault early warning result by the preset attention mechanism based long short-term memory network model according to the historical running data, the historical surrounding environment data, the historical fault data and the real-time running data, the real-time surrounding environment data of all elevators, the step of fault prediction and alarm, comprising: data cleaning and feature engineering processing are performed on the historical running data, the historical surrounding environment data, the historical fault data and the real-time running data, the real-time surrounding environment data of all elevators; the historical running data, the historical surrounding environment data and the historical fault data are processed, and the preset attention mechanism based long short-term memory network model is trained, so that the long short-term memory network model pays more attention to the relationship between the running state, the equipment state of the elevator and the possible fault; the trained attention mechanism based long short-term memory network model is used to predict and alarm the elevator fault according to the processed real-time running data and real-time surrounding environment data, and an elevator fault early warning result is generated, wherein the elevator fault early warning result at least includes the elevator number, the fault type, the fault level, the fault probability and the influence degree of the fault on the elevator operation.

[0057] The step of data cleaning and feature engineering processing on the historical running data, the historical surrounding environment data, the historical fault data and the real-time running data, the real-time surrounding environment data of all elevators comprises: the historical running data, the historical surrounding environment data, the historical fault data and the real-time running data, the real-time surrounding environment data of all elevators include elevator non-vibration data, elevator vibration data and elevator image data, the data cleaning of removing noise, filling missing values and abnormal values is performed on the elevator non-vibration data and the elevator vibration data; the cleaned elevator non-vibration data is converted into statistical indicators and standardized, the wavelet components of different frequencies are identified and extracted from the cleaned elevator vibration data through wavelet change, the feature extraction and identification classification are performed on the elevator image data, and the feature engineering processing is realized. The above preprocessing process can improve the accuracy and consistency of the data, and on the other hand, the feature engineering processing of different types of data in a specific way can accurately extract corresponding data features from a large amount of various data, and improve the performance of the deep learning model in accurately identifying the data.

[0058] In the embodiment of the application, the historical fault data at least includes the fault type, the fault level and the influence degree of the fault on the elevator operation of the elevator occurred in a past time period, for example, in the past two years or several years.

[0059] In step S150, the historical fault data and the historical maintenance data of all elevators are acquired by the comprehensive data platform, and the preset attention mechanism based convolutional neural network model is used to generate an elevator maintenance plan according to the historical fault data, the historical maintenance data and the elevator fault early warning result of all elevators.

[0060] In an embodiment of the present application, please refer to Figure 3 In step S150, the step of generating the elevator maintenance plan from the historical failure data, the historical maintenance data and the elevator failure warning result of all elevators by the preset attention mechanism-based convolutional neural network model includes: performing data cleaning on the historical failure data, the historical maintenance data and the elevator failure warning result of all elevators, vectorizing the cleaned data through word embedding, and performing standardization and normalization processing; training the preset attention mechanism-based convolutional neural network model from the historical failure data and the historical maintenance data after standardization and normalization processing, and strengthening the attention of the convolutional neural network model to the elevator maintenance information; generating the elevator maintenance plan from the elevator failure warning result after standardization and normalization processing by the trained attention mechanism-based convolutional neural network model, wherein the elevator maintenance plan at least includes the elevator number to be maintained, the maintenance type, the maintenance resource, the maintenance frequency, the maintenance time and the priority.

[0061] In an embodiment of the present application, the historical maintenance data at least includes the maintenance type (including routine maintenance, maintenance of the elevator failure with a large impact on the elevator operation, and emergency maintenance), the required maintenance resource (maintenance personnel and equipment), the maintenance frequency, the maintenance time and the priority of the elevator failure maintenance occurred in the past time period, for example, in the past two years or several years.

[0062] In step S160, the remote monitoring terminal displays the real-time running data, the elevator scheduling strategy, the elevator failure warning result and the elevator maintenance plan in real time.

[0063] In an embodiment of the present application, the remote monitoring terminal displays the real-time running data of the elevator and the generated scheduling strategy, failure warning result and maintenance plan in real time, which can timely understand the actual operation of the elevator in the station, and make the station master the situation, and macro-control and auxiliary decision of the dynamic scheduling of the elevator, so as to make up for the deficiency of the generated scheduling strategy, and at the same time, the abnormal information (elevator number that may fail, failure type, failure level, failure probability and impact on elevator operation) of the predicted elevator failure and the corresponding elevator maintenance plan can be sent or notified to the corresponding maintenance personnel in time to maintain the corresponding elevator, so as to avoid the generation of elevator major failure and serious impact or interference on passenger travel. The sending or notification forms include but are not limited to the forms of mobile phone short message, email, push notification and sound alarm.

[0064] The elevator remote sensing service method and system based on the Internet of Things for railway passenger stations disclosed by the embodiments of the present application can realize real-time state monitoring, intelligent scheduling, fault prediction, abnormal alarm and preventive maintenance of elevators in stations, can discover potential faults and risks of elevators in stations in advance, and timely and targeted maintenance can be performed in advance to eliminate potential faults and risks, thereby building a safer and more reliable elevator operation environment for railway passenger stations, ensuring the safety of passengers and improving the travel experience.

[0065] In another embodiment of the present application, referring to Figure 2 and Figure 3 The elevator remote sensing service method based on the Internet of Things for railway passenger stations further comprises the following steps: step S120, receiving running data and surrounding environment data of all elevators from the station-level sensor network by the communication gateway and forwarding to the integrated data platform, and converting and unifying the format and protocol of the running data and surrounding environment data of all elevators in the forwarding process.

[0066] In the embodiments of the present application, according to step S120, step S130 receives the multi-source data collected by various physical sensors in the station-level sensor network from the communication gateway by the integrated data platform, in order to uniformly manage the multi-source data of different protocols and different formats, make the multi-source data reliably transmitted to the Internet of Things platform-integrated data platform for efficient analysis and use, and in the process of forwarding and transmitting by the communication gateway through wired or wireless communication, the multi-source data also needs to be converted in format and protocol, and the data of different types of sensors is converted into a high compatibility format, including converting the data protocols of different sensors, such as Modbus, CAN, BACnet, OPC-UA, etc. into a unified MQTT protocol, realizing the unified transmission and processing of different sensor data, and interacting with the Internet of Things platform. The wired communication technology includes but is not limited to Ethernet, RS485, RS232, CAN bus, etc., and the wireless communication technology includes but is not limited to Wi-Fi, Bluetooth, LoRa, Zigbee, mobile communication network (such as 3G, 4G, 5G), NB-IoT, etc.

[0067] Corresponding to the above method, the elevator remote sensing service system based on the Internet of Things for railway passenger stations in the embodiments of the present application comprises a computer device, the computer device comprises a processor and a memory, the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system realizes the steps of the elevator remote sensing service method based on the Internet of Things for railway passenger stations.

[0068] Referring to Figure 4The Internet of Things-based railway station elevator remote sensing service system comprises a station-level sensor network, a communication gateway, a comprehensive data platform and a remote monitoring terminal, and constitutes a complete railway station elevator Internet of Things monitoring service system. The station-level sensor network is used to collect the running data and surrounding environment data of all elevators in the station in real time. The station-level sensor network comprises various physical sensors reasonably configured according to the characteristics of the elevator equipment and the monitoring requirements, specifically comprising a switch sensor for monitoring the elevator door switch, a speed sensor for monitoring the elevator running speed, a position sensor for monitoring the position of the elevator, a temperature sensor for monitoring the environment temperature of the elevator, a human body sensor for monitoring whether there is a person taking the elevator, a vibration sensor for monitoring whether the elevator has vibration, a pressure sensor for monitoring the pressure condition of the elevator, a load sensor for monitoring the load of the elevator, a counting sensor for monitoring the running times, up and down times and start and stop times of the elevator, a time sensor for monitoring the staying time of the elevator at each floor and the cumulative running time of the elevator, a visual camera for acquiring image data in the elevator car or the environment of the elevator, etc., so as to realize real-time monitoring and sensing of the running condition and environment condition of the elevator. The communication gateway is used to receive and forward the running data and surrounding environment data of all elevators from the station-level sensor network, and to convert and unify the format and protocol of the running data and surrounding environment data of all elevators in the process of forwarding and transmission. The comprehensive data platform is used to receive the running data and surrounding environment data of all elevators forwarded and transmitted from the communication gateway in real time, and to receive train running information and passenger flow statistical information of different passenger transport areas from the passenger service and control platform pre-configured regularly, to generate an elevator dispatching strategy according to the real-time running data of the elevator, the train running information and passenger flow statistical information of different passenger transport areas, and the association relationship between the elevator and the passenger transport area. The comprehensive data platform is also used to acquire historical running data, historical surrounding environment data and historical fault data of all elevators, to perform fault prediction and warning by a preset long short-term memory network model based on attention mechanism according to the historical running data, historical surrounding environment data, historical fault data and real-time running data, real-time surrounding environment data of all elevators, and to generate an elevator fault warning result. The comprehensive data platform is also used to acquire historical fault data and historical maintenance data of all elevators, to generate an elevator maintenance plan by a preset convolutional neural network model based on attention mechanism according to the historical fault data, historical maintenance data and elevator fault warning result of all elevators. The remote monitoring terminal is used to display the real-time running data, the elevator dispatching strategy, the elevator fault warning result and the elevator maintenance plan in real time.

[0069] The remote monitoring terminal and the comprehensive data platform establish a data interface, and through a standardized mqtt communication protocol, bidirectional transmission and interaction of data are realized. The remote monitoring terminal can send data requests for obtaining various operation data of the elevator, train operation and passenger flow statistical information and various plan data (dispatching strategy, fault prediction and early warning result and maintenance plan, etc.) to the comprehensive data platform. Meanwhile, the comprehensive data platform can also transmit the elevator operation data and train operation and passenger flow information processed and analyzed by the comprehensive data platform to the remote monitoring terminal, and also transmit the elevator dispatching strategy, fault prediction and early warning result and maintenance plan, etc. generated by the comprehensive data platform to the remote monitoring terminal for visual display, so that relevant maintenance and support personnel can timely discover potential risks and faults of the entire system and timely solve them, so that passengers can smoothly travel in each passenger transport area in the station, and the experience of getting on and off the vehicle is more safe and reliable.

[0070] The embodiment of the present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the steps of the aforementioned railway station elevator remote sensing service method based on Internet of Things. The computer readable storage medium can be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0071] Those of ordinary skill in the art should understand that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software, or a combination of both. Whether the implementation is in hardware or software depends on the specific application and design constraints imposed on the overall system. Skilled persons can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, etc. When implemented in software, the elements of the present application are program or code segments used to perform the required tasks. The program or code segments can be stored in a machine readable medium or transmitted through a data signal carried in a carrier wave on a transmission medium or communication link.

[0072] It is to be expressly understood that the invention is not limited to the specific configurations and process described above and illustrated in the accompanying drawings. For the sake of clarity, detailed descriptions of known methods are omitted. In the above-described embodiments, several specific steps are described and illustrated as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and various changes, modifications and additions can be made thereto by one of ordinary skill in the art without departing from the spirit of the present invention, and the order of the steps can be changed.

[0073] In the present invention, features described and / or illustrated with respect to one embodiment can be used in the same or a similar way in one or more other embodiments, and / or in combination with or instead of features of other embodiments.

[0074] The above description is only preferred embodiments of the present invention, and is not intended to limit the present invention. The embodiments of the present invention can be variously changed and modified by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the scope of the present invention.

Claims

1. A method for remote sensing services of railway passenger station elevators based on the Internet of Things, characterized in that, The method includes: Based on the location relationship between elevators and passenger areas, all elevators in the station are associated with their corresponding passenger areas, and the station-level sensor network collects the operating data of all elevators in the station and the surrounding environment data in real time. The integrated data platform receives real-time operation data and surrounding environment data of all elevators from the station-level sensor network, and periodically receives train operation information and passenger flow statistics from different passenger areas pre-configured by the passenger service and control platform. Based on the real-time operation data of the elevators, the train operation information and passenger flow statistics of different passenger areas, and the relationship between the elevators and passenger areas, the platform generates elevator scheduling strategies. The system acquires historical operating data, historical surrounding environment data, and historical fault data of all elevators from the integrated data platform. A pre-set attention-based long short-term memory network model then performs fault prediction and alarm based on the historical operating data, historical surrounding environment data, historical fault data, real-time operating data, and real-time surrounding environment data of all elevators, generating elevator fault warning results. The system acquires historical fault data and historical maintenance data of all elevators from the integrated data platform, and generates an elevator maintenance plan based on the historical fault data, historical maintenance data and elevator fault warning results of the pre-set attention-based convolutional neural network model. The remote monitoring terminal displays the real-time operating data, the elevator scheduling strategy, the elevator fault early warning results, and the elevator maintenance plan in real time. The step of generating an elevator scheduling strategy based on real-time elevator operation data, train operation information and passenger flow statistics for different passenger areas, and the correlation between elevators and passenger areas includes: The integrated data platform determines the available elevators and their current operating status based on real-time elevator operation data. It also analyzes the train operation information and passenger flow statistics received periodically from different passenger transport areas to obtain the peak passenger flow time periods and passenger transport areas. Based on the peak passenger flow time periods and the relationship between passenger areas, elevators and passenger areas, the scheduling order, service time periods, service areas, operating speeds and group configurations of available elevators are adjusted and optimized. The utilization intensity of available elevators is optimized based on the current operating status of available elevators. Multiple elevators that are adjacent to the same passenger area, located in the same passenger area, or can reach the same passenger area are configured into an elevator group. Multiple elevators configured into an elevator group respond simultaneously based on the same passenger request. The utilization intensity of available elevators is optimized based on the current operating status of available elevators, and the utilization intensity of idle or low-utilization elevators is increased. Dynamic scheduling of elevators is performed based on the peak passenger flow of different passenger areas and different time periods. The steps involved in generating an elevator maintenance plan using a pre-defined attention-based convolutional neural network model based on all historical elevator fault data, historical maintenance data, and elevator fault warning results include: Data cleaning is performed on all historical elevator fault data, historical maintenance data, and elevator fault warning results. The cleaned data is then vectorized through word embedding and standardized and normalized. The pre-set attention-based convolutional neural network model is trained using standardized and normalized historical fault data and historical maintenance data to enhance the model's attention to elevator maintenance information. An elevator maintenance plan is generated by a pre-trained attention-based convolutional neural network model based on the standardized and normalized elevator fault warning results. The elevator maintenance plan includes at least the elevator number that needs maintenance, maintenance type, maintenance resources, maintenance frequency, maintenance time, and priority.

2. The method according to claim 1, characterized in that, The step of generating elevator fault warning results by using a preset attention-based long short-term memory network model to predict and alarm faults based on all elevator historical operating data, historical surrounding environment data, historical fault data, and real-time operating data and real-time surrounding environment data includes: Data cleaning and feature engineering processing are performed on all elevator historical operation data, historical surrounding environment data, historical fault data, and real-time operation data and real-time surrounding environment data. The pre-set attention-based long short-term memory network model is trained using processed historical operating data, historical surrounding environment data, and historical fault data to enhance the long short-term memory network model's attention to the relationship between the elevator's operating status, equipment status, and potential faults. The trained attention-based long short-term memory network model predicts and alerts elevator malfunctions based on processed real-time operating data and real-time surrounding environment data, generating elevator malfunction warning results. The elevator malfunction warning results include at least the elevator number that may malfunction, the malfunction type, the malfunction level, the probability of malfunction occurrence, and the degree of impact of the malfunction on elevator operation.

3. The method according to claim 2, characterized in that, The steps of data cleaning and feature engineering processing for all elevator historical operation data, historical surrounding environment data, historical fault data, and real-time operation data and real-time surrounding environment data include: All historical operation data, historical surrounding environment data, historical fault data, and real-time operation data and real-time surrounding environment data of elevators include elevator non-vibration data, elevator vibration data, and elevator image data. Data cleaning is performed on the elevator non-vibration data and elevator vibration data to remove noise, fill in missing values, and process outliers. The non-vibration data of the cleaned elevator is converted into statistical indicators and standardized. Wavelet transformation is used to identify and extract wavelet components of different frequencies from the vibration data of the cleaned elevator. Feature extraction and classification of elevator image data are performed to achieve feature engineering processing.

4. The method according to claim 1, characterized in that, The method further includes: The communication gateway receives all elevator operation data and surrounding environment data from the station-level sensor network and forwards them to the integrated data platform. During the forwarding process, the format and protocol of all elevator operation data and surrounding environment data are converted and unified.

5. The method according to any one of claims 1 to 4, characterized in that, The passenger transport area includes at least one entrance, platform, exit, waiting room, and ticket gate.

6. The method according to any one of claims 1 to 4, characterized in that, The operational data includes at least the following: operational status, operational speed, elevator door open / close status, operational position, temperature, vibration, pressure, load, number of operations, number of starts and stops, cumulative elevator operation time, and dwell time on each floor. The surrounding environment data includes at least the elevator passenger flow and non-standard elevator riding behaviors such as prying open elevator doors and fighting inside the elevator. The train operation information includes at least the train number, as well as the on-time / delay status of different train numbers, estimated departure time, actual departure time, estimated arrival time, actual arrival time, boarding time, platform, exit, and boarding gate; The passenger flow statistics include at least the number of people in the station at different time periods, the number of people getting on and off different trains, and the passenger flow distributed in different passenger areas at different time periods.

7. A remote sensing service system for railway passenger station elevators based on the Internet of Things, comprising a processor and a memory, characterized in that, The memory stores computer instructions, and the processor executes the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps of the method as described in any one of claims 1 to 6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 1 to 6.

Images