Elevator intelligent management system based on edge computing and computing network integration

The elevator management system addresses latency and accuracy issues by using edge computing and network integration for real-time data processing and fault prediction, ensuring efficient and personalized maintenance.

CN119059385AInactive Publication Date: 2024-12-03JIANGSU IND INTERNET DEV RES CENT

Patent Information

Application Number
CN202411554799.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-04
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing elevator management systems rely heavily on centralized server computing, leading to increased latency, limited accuracy in fault warnings, and inability to predict equipment failures, with traditional maintenance plans lacking personalization and real-time adjustments.

Method used

An elevator intelligent management system utilizing edge computing and computing-network integration, including data acquisition, edge computing, cloud computing, and remote monitoring modules, to process data locally, generate fault warnings, and optimize maintenance plans in real-time.

Benefits of technology

The system enables timely detection of equipment abnormalities, improves fault prediction accuracy, reduces data transmission delays, and ensures efficient operation even in unstable networks, with personalized and dynamically optimized maintenance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119059385A_ABST
    Figure CN119059385A_ABST
Patent Text Reader

Abstract

The invention relates to an intelligent elevator management system based on edge computing and computing network fusion. The intelligent elevator management system comprises a data acquisition module, edge computing equipment, a cloud computing and data fusion module, a remote monitoring module, an intelligent maintenance module and a data analysis module. The data acquisition module is connected with an elevator system through industrial Internet of Things equipment, acquires operation state data of an elevator, and performs primary processing through the edge computing gateway. And the edge computing device receives and analyzes the data, generates a fault early warning signal and adjusts operation parameters. And the cloud computing and data fusion module receives data provided by the edge computing device, carries out deep analysis and generates a device health state evaluation and fault prediction result. The remote monitoring module displays the real-time state and historical data through a visual interface and provides elevator management optimization suggestions. And the intelligent maintenance module generates a maintenance plan based on the evaluation result and automatically allocates tasks to maintenance personnel. The safety, intelligence and maintenance efficiency of the elevator system can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of elevator intelligent management, and in particular to an elevator intelligent management system based on edge computing and computing-network integration. Background Art

[0002] In the prior art, the operation and maintenance management systems of elevators usually rely on traditional IoT technologies. These systems collect data such as temperature, vibration, and speed through various sensors installed on the elevators, and transmit the data to the server for analysis and processing. Based on the analysis results, the system generates fault warnings and maintenance plans to ensure the safe operation and timely maintenance of the elevators. However, the real-time and intelligent levels of such systems are limited, especially in terms of data processing speed and system response time.

[0003] The main problem in the existing technology is that these systems rely on servers for centralized computing when processing a large amount of real-time data from elevators, which easily leads to increased latency. In addition, the accuracy of fault warnings is limited, especially when a large amount of complex data needs to be processed, and the existing systems cannot effectively predict potential equipment failures. Due to the system's strong dependence on the server, once a network interruption occurs, the performance of the elevator management system will be significantly affected. In addition, traditional maintenance plans lack personalization and real-time adjustment capabilities, and cannot be dynamically optimized according to the specific operating status of the elevator.

[0004] Therefore, it is particularly important to develop an intelligent elevator management system based on edge computing and computing-network integration. Summary of the invention

[0005] The present application provides an elevator intelligent management system based on edge computing and computing-network integration to improve the safety, intelligence and maintenance efficiency of the elevator system.

[0006] This application provides an elevator intelligent management system based on edge computing and computing network integration, including: A data acquisition module is used to connect to the elevator system through the industrial Internet of Things device to collect the operating status data of the elevator equipment, wherein the operating status data includes the temperature, current, vibration, acceleration, operating speed and door status of the elevator equipment; the operating status data collected by the edge computing gateway is preliminarily processed, and the preliminarily processed data is transmitted to the edge computing device; The edge computing device is connected to the data acquisition module, and is used to receive and analyze the data after preliminary processing to obtain the elevator operation status data; adjust the operation parameters of the elevator according to the elevator operation status data; when the elevator operation status data shows that the elevator is in an abnormal state, generate a fault warning signal, and transmit the generated fault warning signal and the elevator operation status data to the cloud computing and data fusion module and the remote monitoring module; The cloud computing and data fusion module is connected to the edge computing processing device, and is used to receive the elevator operation status data and fault warning signals provided by the edge computing device, and perform in-depth analysis and data storage on them; the analysis results of the in-depth analysis are processed by the computing network fusion technology to generate equipment health status assessment results and fault prediction results, and the generated equipment health status assessment results and fault prediction results are transmitted to the remote monitoring module and the intelligent maintenance module; A remote monitoring module, connected to the cloud computing and data fusion module, is used to receive equipment health status assessment results, fault prediction results and fault warning signals of the elevator equipment; and to display the real-time status, historical data, fault statistics, maintenance records and elevator management optimization suggestions of the equipment to the user through a visual interface; The intelligent maintenance module is connected to the remote monitoring module and the cloud computing and integration module. Based on the received equipment health status assessment results and fault prediction results, it generates maintenance plans and maintenance reminders; according to the generated maintenance plan, it assigns maintenance tasks to maintenance personnel; and after the maintenance tasks are completed, it receives the maintenance records provided by the maintenance personnel; The data analysis module is connected to the intelligent maintenance module and the cloud computing and data fusion module, and is used to receive and analyze maintenance records, fault records and elevator equipment operation history data to obtain elevator management optimization suggestions; and feed back the elevator management optimization suggestions to the remote monitoring module.

[0007] The beneficial technical effects brought about by this application include: (1) By performing real-time analysis of the elevator's operating status data through edge computing devices, the system can detect abnormal conditions of the equipment in a timely manner and generate early warning signals before a fault occurs, thereby reducing the probability of a fault. At the same time, combined with the in-depth analysis of cloud computing, the accuracy of fault prediction is significantly improved, further ensuring the safety of elevator operation. (2) The present invention adopts edge computing technology to distribute the data processing part to edge computing devices close to the equipment, reducing the dependence of data transmission to the cloud and significantly reducing the delay of data transmission, thereby improving the response speed of the elevator management system, especially when the network connection is unstable, it can still ensure the efficient operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 It is a schematic diagram of an elevator intelligent management system based on edge computing and computing-network integration provided in the first embodiment of the present application. DETAILED DESCRIPTION

[0009] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0010] The first embodiment of the present application provides an elevator intelligent management system based on edge computing and computing network integration. Figure 1 , which is a schematic diagram of the first embodiment of the present application. Figure 1 The first embodiment of the present application provides an elevator intelligent management system based on edge computing and computing-network integration for detailed description.

[0011] like Figure 1 As shown, the elevator intelligent management system includes a data acquisition module 101, an edge computing device 102, an edge computing device 102, a cloud computing and data fusion module 103, a remote monitoring module 104, an intelligent maintenance module 105 and a data analysis module 106.

[0012] The data acquisition module 101 is used to connect to the elevator system through the industrial Internet of Things device to collect the operating status data of the elevator equipment, wherein the operating status data includes the temperature, current, vibration, acceleration, operating speed and door status of the elevator equipment; the operating status data collected by the edge computing gateway is preliminarily processed, and the preliminarily processed data is transmitted to the edge computing device.

[0013] In this embodiment, the industrial Internet of Things device refers to the hardware and software system used to interconnect the various sensors, edge computing devices and data acquisition module 101 of the elevator. These devices realize real-time monitoring, data acquisition and equipment management of the elevator through industrial-grade sensors, controllers, gateways, etc. Its core function is to ensure that various status data of the elevator can be accurately and stably transmitted to other parts of the system through a highly stable and anti-interference network connection, thereby realizing remote monitoring and intelligent management.

[0014] Specifically, industrial IoT devices include the following components: 1. Sensors: Industrial IoT devices are connected to key elevator components through multiple high-precision industrial sensors.

[0015] 2. Edge computing gateway: The core component of industrial IoT devices is the edge computing gateway. It is located at the elevator site and is responsible for receiving the raw data transmitted from various sensors, performing preliminary processing, and transmitting the processed data to the edge computing device or the cloud for further analysis. The gateway can handle large amounts of real-time data, reduce transmission delays, and support local data storage and processing to ensure that the system can still operate normally when there are network problems.

[0016] 3. Communication module: Industrial IoT devices communicate with data acquisition modules, edge computing devices, and cloud computing platforms through a variety of industrial-grade communication protocols (such as MQTT, Modbus, OPC UA, etc.). These communication modules support wired and wireless connections to meet network requirements in various industrial environments. Wireless connection methods may include Wi-Fi, Bluetooth, and 4G / 5G networks, which are particularly suitable for elevator installation environments where wiring is difficult.

[0017] 4. Controller: Some industrial IoT devices also include controllers, which are used to control the operating status of the elevator system in real time. For example, when the system detects that certain operating parameters of the elevator exceed the set threshold, the controller can directly take corresponding control measures (such as emergency stop of the elevator, speed limit operation, etc.) to ensure the safety of the elevator.

[0018] The data acquisition module 101 is one of the core components. Its main function is to connect with the elevator system through the industrial Internet of Things device and collect various operating status data of the elevator in real time. In order to achieve this function, the data acquisition module 101 is equipped with a variety of sensors and communication interfaces to ensure the comprehensiveness, real-time and accuracy of the data.

[0019] First, the data acquisition module 101 obtains the key operating parameters of the elevator equipment by connecting with multiple sensors. These parameters include but are not limited to the temperature, current, vibration, acceleration, running speed and door opening and closing status of the elevator. For example, the temperature sensor is used to detect the temperature of the elevator interior or key components (such as motors and brakes) in real time; the current sensor is used to monitor the current load of the elevator motor and other electrical equipment; the vibration sensor is used to capture the vibration of the elevator during operation, especially the vibration changes that may indicate equipment wear or abnormality; the acceleration sensor is used to monitor the acceleration of the elevator in real time to ensure the smoothness of the acceleration and deceleration of the elevator during operation; the door status sensor is used to determine whether the elevator door is closed and opened correctly to prevent abnormal door control.

[0020] After collecting these data, the data acquisition module 101 uses the internal edge computing gateway to perform preliminary processing on the data. Specifically, the preliminary processing includes data format conversion, noise filtering, and elimination of invalid or abnormal data. In order to improve the efficiency and accuracy of data transmission, the module 101 can use a data compression algorithm to reduce the volume of data while ensuring the integrity of the data. The preprocessing function of the edge computing gateway ensures that only necessary and meaningful data is further transmitted to the edge computing device 102, reducing data redundancy and bandwidth occupancy.

[0021] During the data transmission process, the data acquisition module 101 interacts with the edge computing device through a standard communication protocol (such as MQTT, HTTP or other protocols suitable for the industrial Internet of Things). The built-in communication interface of the edge computing gateway ensures that data can be transmitted quickly and stably from the elevator sensor to the edge computing device, avoiding the impact of transmission delays or data loss on the real-time monitoring and management of the elevator. The design of module 101 not only supports wired connection, but also can interact with other devices through wireless methods (such as Wi-Fi, Bluetooth, LoRa, etc.) to adapt to different installation environments and needs.

[0022] In short, the data acquisition module 101 can not only accurately collect the multi-dimensional operation data of the elevator, but also ensure the efficiency and reliability of the elevator management system through the preprocessing function of the edge computing gateway, the mechanism of dynamically adjusting the acquisition frequency, and the support of multiple communication methods. In the present invention, the data acquisition module 101, as the basis of the entire elevator intelligent management system, provides real-time and reliable operation data, providing a solid foundation for subsequent fault warning, equipment health assessment and intelligent maintenance.

[0023] Furthermore, the data acquisition module is specifically used for: Establish real-time connection between industrial IoT devices and sensors in the elevator system to collect multi-dimensional operating status data of elevator equipment, ensuring that the temperature, current, vibration, acceleration and door status of the elevator are obtained regularly at each preset time interval; Use edge computing gateways to pre-process the collected data, including cleaning, filtering, and formatting abnormal data, and organize the data into a predefined format to reduce the transmission load.

[0024] After preprocessing is completed, the preprocessed data is transmitted to the edge computing device.

[0025] The data acquisition module plays a key role in the intelligent management system of elevators. It is used to connect to multiple sensors in the elevator system in real time through industrial Internet of Things devices to collect multi-dimensional operating status data of elevator equipment. These sensors are installed in key parts of the elevator, such as the elevator motor, control panel, door control device, etc., to detect the temperature, current, vibration, acceleration and door opening and closing status of the elevator. Through this real-time connection, the data acquisition module can regularly obtain these key data at preset time intervals to ensure that the system has accurate monitoring of each key state of the elevator.

[0026] The data acquisition module can ensure that the acquired data is highly accurate and real-time by connecting to industrial IoT devices. These data change dynamically during the operation of the elevator. The data acquisition module relies on the stable connection of sensors to continuously collect data. For example, the elevator's temperature sensor can detect the temperature change of the motor in real time, the current sensor monitors the current of the elevator circuit, the vibration sensor is used to detect the mechanical vibration of the elevator during operation, and the acceleration sensor can accurately record the acceleration and deceleration process of the elevator to ensure the smooth operation of the elevator. The door status sensor can determine the opening and closing status of the elevator door in real time to ensure that the elevator door operates safely under normal conditions.

[0027] After the data collection is completed, the data collection module does not simply transmit the data, but also needs to pre-process the data through the edge computing gateway. The pre-processing process mainly includes three parts: first, the abnormal data is cleaned to eliminate noise or erroneous data that may be caused by sensor failure. Secondly, the data is filtered to screen out key data that has a direct impact on the health status of the elevator and remove redundant or irrelevant information. Finally, the data is formatted. This process organizes the data according to the standard format predefined by the system to ensure that different types of data can be processed uniformly in subsequent analysis. This pre-processing greatly reduces the computing load of subsequent processing equipment, while improving the efficiency and accuracy of data transmission.

[0028] After completing all the preprocessing steps, the data acquisition module transmits the processed elevator status data to the edge computing device. This transmission process is achieved through an efficient data communication protocol to ensure that the data can be transmitted quickly and stably. After receiving this data, the edge computing device will continue to conduct more in-depth analysis and processing. As an important part of the elevator intelligent management system, the data acquisition module provides a solid data foundation for the normal operation of the entire system through accurate data collection and processing.

[0029] Furthermore, the data acquisition module is specifically used for: Dynamically adjust data collection frequency and parameter priority according to real-time changes in elevator operating status; Dynamically optimize data collection strategies based on the environment and equipment operation through adaptive algorithms; When it is detected that the sensor value exceeds the safety threshold, the real-time data transmission mode is triggered; the relevant abnormal data is marked as high priority and uploaded to the cloud computing and data fusion module through the edge computing gateway.

[0030] The data acquisition module has highly intelligent and flexible operation capabilities, and can dynamically adjust the frequency and parameter priority of data acquisition according to the real-time changes in the elevator's operating status. In actual applications, elevators have different data requirements at different operating stages. For example, when the elevator is operating normally, the data acquisition frequency can be maintained at a relatively stable level, but when starting, accelerating or decelerating, due to the heavy load on the equipment at these moments, the data acquisition module will automatically increase the acquisition frequency to ensure that the most accurate operating status information is captured. This ability to dynamically adjust the data acquisition frequency enables the system to obtain more detailed data feedback at critical moments, and when the equipment is running smoothly, it reduces unnecessary data collection, thereby improving the overall efficiency of the system.

[0031] The data acquisition module also has the ability to dynamically optimize data acquisition strategies based on the environment and equipment operation. This is achieved through a built-in adaptive algorithm, and the system can optimize and adjust the data acquisition strategy based on real-time detected environmental factors (such as temperature, humidity, etc.) and the elevator's own operating status (such as operating speed, load, etc.). For example, when the system detects that the elevator equipment is operating in a high temperature environment, the data acquisition module may prioritize increasing temperature-related parameter monitoring and reduce attention to other relatively stable parameters (such as door status), thereby concentrating system resources on more risky areas. Through such dynamic adjustments, the data acquisition module can effectively improve collection efficiency while ensuring the quality of key data collection.

[0032] In addition, the data acquisition module is also equipped with an intelligent safety monitoring mechanism. When the sensor detects that a parameter of the elevator equipment exceeds the preset safety threshold, such as a sharp rise in the temperature of the elevator or abnormal current fluctuations, the module will automatically trigger the real-time data transmission mode. In this mode, the system will not only immediately increase the acquisition frequency of the parameter, but also mark the collected abnormal data as high priority. These priority-marked abnormal data are quickly transmitted to the cloud computing and data fusion module through the edge computing gateway for in-depth processing and analysis. This design ensures that the elevator can transmit key information in real time when potential danger occurs, quickly issue fault warnings or initiate protective measures.

[0033] In general, this dynamic adjustment and optimization mechanism makes the data acquisition module more flexible, intelligent and efficient in the entire elevator intelligent management system.

[0034] The edge computing device 102 is connected to the data acquisition module, and is used to receive and analyze the data after preliminary processing to obtain the elevator operation status data; adjust the operation parameters of the elevator according to the elevator operation status data; when the elevator operation status data shows that the elevator is in an abnormal state, generate a fault warning signal, and transmit the generated fault warning signal and the elevator operation status data to the cloud computing and data fusion module and the remote monitoring module.

[0035] The edge computing device 102 plays a vital role in this embodiment, and is mainly used to receive and process the elevator operation status data after preliminary processing from the data acquisition module 101, and further analyze and calculate these data. Its key feature is that it can perform complex data processing tasks in real time at a physical location close to the elevator equipment, reduce the cloud load, and improve the system's response speed and data processing efficiency.

[0036] The edge computing device 102 is closely connected to the data acquisition module 101. Through the edge computing gateway, the edge computing device 102 can receive the elevator operation status data that has been preliminarily processed, including the elevator's temperature, current, vibration, acceleration, operating speed, and elevator door status. The first task of the edge computing device 102 is to further analyze these data. The device is embedded with multiple analysis algorithms for real-time processing of data to detect whether there are abnormalities or potential faults. For example, based on the current acceleration and vibration data of the elevator, the edge computing device can determine whether the elevator is in a stable operating state; based on the temperature and current data, the device can also determine whether the elevator motor has overload or heating problems. Through these analyses, the edge computing device can quickly adjust the elevator's operating parameters to ensure that it is in the best working condition.

[0037] When the elevator's operating status data shows that certain parameters exceed the preset safety threshold, the edge computing device 102 will generate a fault warning signal. This warning signal is not only based on the current real-time data, but also combined with the comparative analysis of historical data. For example, the device can analyze the aging trend of elevator components and past maintenance records to more accurately determine the possibility of a fault. After the fault warning signal is generated, the edge computing device packages the signal with the relevant elevator operating status data and transmits it to the cloud computing and data fusion module 103 and the remote monitoring module 104 through the network. In order to ensure the security and integrity of data transmission, the edge computing device 102 supports a variety of encryption and security protocols to ensure that it is not interfered with or tampered with during the data transmission process.

[0038] The edge computing device 102 also has local data storage and caching capabilities. This means that when the network connection is interrupted or cloud computing resources are unavailable, the device can still analyze the data locally and synchronize the data to the cloud after the network is restored. This local storage capability makes the system more fault-tolerant and stable, ensuring that the elevator management system can still maintain efficient operation under various extreme conditions.

[0039] In addition, the edge computing device 102 has the ability of adaptive adjustment. Based on the analysis results of real-time data, it can automatically optimize the operating parameters of the elevator. For example, when an abnormal acceleration is detected during the operation of the elevator, the device will actively adjust the acceleration or deceleration curve of the elevator to reduce mechanical wear and improve riding comfort. When the current or temperature data indicates that the elevator motor is overloaded, the edge computing device can also automatically reduce the operating speed of the elevator or even trigger an emergency shutdown procedure to ensure the safety of the equipment.

[0040] The design of the edge computing device 102 enables it to process a large number of parallel data computing tasks, which not only allows it to adjust the operating status of the elevator in real time, but also reduces the reliance on cloud computing resources and improves the response speed and stability of the entire system. At the same time, the device can support modular upgrades, and in the future, more intelligent algorithms and functions can be integrated as needed to further improve the intelligent management level of the elevator system.

[0041] In summary, the edge computing device 102 significantly improves the safety, stability and intelligence of the elevator system through functions such as efficient data processing, fault warning, automatic adjustment of operating parameters and local storage.

[0042] Furthermore, the edge computing device is specifically used for: Receive the elevator operation status data after preliminary processing transmitted from the data acquisition module, and perform further data filtering and verification processing, including eliminating duplicate data and correcting data deviations to improve the accuracy of data processing; Analyze the processed elevator operation status data and determine whether the equipment is in an abnormal state according to the preset threshold; if the operation status data exceeds the safety threshold, generate a fault warning signal; When the fault warning signal is generated, the fault warning signal is packaged with the corresponding operating status data and transmitted to the cloud computing and data fusion module and the remote monitoring module.

[0043] Edge computing devices play an important role in further processing and analyzing elevator operation status data in the elevator intelligent management system. First, the edge computing device receives the elevator operation data after preliminary processing transmitted from the data acquisition module. These data have been preliminarily cleaned and formatted, but may still contain some duplicate data or deviations. In order to improve the accuracy of data processing, the edge computing device will further filter and verify these data to ensure that the system only processes high-quality and reliable data. The specific processing process includes eliminating the redundant part of the data, that is, invalid data that is repeatedly collected or transmitted, and correcting the data with deviations to ensure that all operation status data can accurately reflect the actual operation of the elevator. This process not only helps to improve the overall processing efficiency of the system, but also greatly enhances the accuracy of fault warning and status monitoring.

[0044] After completing data filtering and verification, the edge computing device will conduct an in-depth analysis of the processed elevator operation status data. Through the system's built-in algorithm, the device can monitor and evaluate real-time operation data, and determine whether the elevator equipment is in an abnormal state based on the preset threshold standards. The preset thresholds are set according to the parameter ranges for normal elevator operation, such as temperature, vibration, acceleration, etc. When one or more parameters exceed these safe ranges, the edge computing device can quickly identify the anomaly and immediately generate a fault warning signal. This signal means that a component of the elevator may be malfunctioning or at risk of malfunctioning.

[0045] Once a fault warning signal is generated, the edge computing device not only marks the signal as high priority, but also packages it together with the corresponding operating status data for processing. The packaged data includes detailed operating parameters when the fault occurs, ensuring that the fault information is complete and useful when it is transmitted to the cloud computing and data fusion module and the remote monitoring module. This correlation between fault signals and data is crucial, as it provides a comprehensive information basis for subsequent analysis, troubleshooting, and maintenance work. In this way, the system can ensure that when potential faults occur, managers and cloud computing modules can obtain sufficient contextual information to make accurate judgments and respond quickly.

[0046] Through this series of operations, edge computing devices have greatly improved the intelligence and safety of elevator management systems. Its ability to filter, verify, analyze, and package transmission enables the system to process large amounts of real-time data more efficiently and ensure that the equipment can quickly issue an alarm when an abnormality occurs, providing users with timely feedback and protection.

[0047] The cloud computing and data fusion module 103 is connected to the edge computing processing device, and is used to receive the elevator operation status data and fault warning signals provided by the edge computing device, and perform in-depth analysis and data storage on them; the analysis results of the in-depth analysis are processed through the computing network fusion technology to generate equipment health status assessment results and fault prediction results, and the generated equipment health status assessment results and fault prediction results are transmitted to the remote monitoring module and the intelligent maintenance module.

[0048] The cloud computing and data fusion module 103 plays a core data processing and storage role in this system. This module is mainly used to receive the elevator operation status data and fault warning signals transmitted from the edge computing device 102, and perform in-depth analysis, fusion processing and long-term storage on these data. Through the computing network fusion technology, the cloud computing and data fusion module can make full use of the computing resources in the cloud to perform large-scale data analysis in real time, and at the same time combine the computing power of the network to improve the overall intelligence level of the system.

[0049] After the edge computing device 102 completes the preliminary analysis of the elevator operation data and generates a fault warning signal, the data is transmitted to the cloud computing and data fusion module 103. Here, module 103 is first responsible for receiving and storing data. The module can classify and store the received data, and store different types of data (such as temperature, current, vibration, etc.) in the corresponding database. Module 103 has elastically scalable cloud storage capabilities, and can dynamically adjust the storage capacity according to the amount of data in the elevator equipment to ensure that no matter how large the amount of data is, it can be stored safely and efficiently. In addition, the module's built-in security encryption mechanism ensures the integrity and security of the data during storage and transmission, preventing data loss or unauthorized access.

[0050] After the data is received and stored, the cloud computing and data fusion module 103 performs in-depth analysis. This analysis is based on computing-network fusion technology, combining the capabilities of cloud computing and network computing to perform large-scale and complex processing of the elevator's operating data. Specifically, the module will comprehensively analyze the operating data from different elevators, identify possible trends or anomalies, and compare them with historical data. This process can effectively identify potential hidden faults or performance degradation trends. Through big data analysis technology, the cloud computing and data fusion module can not only evaluate the health status of the current equipment, but also predict future failures of elevator equipment. This prediction is based on in-depth mining and learning of the current operating status of the equipment, historical maintenance records, and long-term data, and ultimately generates equipment health status assessment results and fault prediction results.

[0051] The generated equipment health status assessment results and fault prediction results are the key outputs of the entire elevator management system. After further processing, these results will be transmitted to the remote monitoring module 104 and the intelligent maintenance module 105. Through the remote monitoring module, system managers can view the current health status of the elevator equipment and predicted fault information in a visual interface. The intelligent maintenance module uses these results to automatically generate a maintenance plan and optimize the equipment maintenance strategy.

[0052] The cloud computing and data fusion module 103 also has a powerful data fusion capability. By performing correlation analysis on multi-dimensional data from different elevators, the module can identify common problems or potential systemic failures between different devices. For example, the module can find similar operating anomalies and infer possible common causes by comparing the acceleration and vibration data of multiple elevators. This data fusion and analysis between multiple devices not only improves the fault prediction accuracy of a single device, but also provides more comprehensive support for the intelligent management of the entire elevator system.

[0053] The cloud computing and data fusion module 103 can also achieve modular upgrades and expansions. As the system operation data accumulates and the equipment ages, the module's analysis algorithm and processing capabilities can be dynamically upgraded as needed to ensure that it can always adapt to the needs of the system. By regularly updating the module's analysis model, the system can continue to optimize over time, further improving the operational safety and management efficiency of the equipment.

[0054] In summary, the cloud computing and data fusion module 103 realizes the health assessment and fault prediction of elevator equipment through powerful cloud computing capabilities, data storage and security protection mechanisms, and in-depth data analysis and fusion capabilities, providing important support for the efficient operation of the entire system.

[0055] Furthermore, the cloud computing and data fusion module is specifically used for: The comprehensive performance index of the elevator is calculated according to the following formula 1: In formula 1, the upper and lower limits 0 and t of the definite integral operation represent the starting point of time and the current moment respectively. The specific meanings are as follows: 0: represents the starting point of time, that is, a reference time point. Usually, this reference point can be the time when the elevator system starts or the equipment monitoring starts. For example, if the monitoring system starts recording the running status of the elevator from a certain moment, this moment is the lower limit of the integral 0. It is the time point when the equipment starts running or the data collection starts.

[0056] : represents the current time, indicating the time point at this moment. In the actual operation of the system, This can be the time when the device status is currently being evaluated. Calculate the current comprehensive performance indicators based on the operation data at all times .

[0057] in, for Comprehensive performance indicators at all times, used to reflect the overall operating status of the elevator; for The equipment health status index at all times, which reflects the operating health of each key component of the elevator; for The moment The reliability of the prediction of a certain type of fault, which reflects the possibility of a certain type of fault occurring in the elevator; For the The weight of the class fault; The total number of fault types, which may include motor fault, door fault, transmission fault, etc.; for Energy efficiency index at the moment; is the weight coefficient; is the time attenuation coefficient; is the energy efficiency attenuation coefficient; The time of the most recent energy efficiency calibration; The equipment health status index is calculated by the following formula 2: in, is the total number of elevator operating status parameters, wherein the elevator equipment operating status parameters include temperature, current, vibration, acceleration, operating speed and door status; Indicates The maximum permissible value of the elevator operation status parameter; For the current Elevator-like operating status parameters; For the The weight coefficients of the elevator operation status parameters can be determined by experimental data or directly set by expert knowledge; For the The adjustment parameters of the elevator operation status parameters can be determined by experimental data or directly set by expert knowledge; For the The normalization coefficient of the elevator operation status parameters can be determined by experimental data or directly set by expert knowledge; is the current time; The time of the most recent elevator maintenance; is the time decay constant; Failure prediction reliability It is calculated by the following formula 3: in, For the The sensitivity coefficient of the class fault can be determined by experimental data or directly set by expert knowledge; For the Real-time monitoring value of class faults; For the The prediction threshold of class faults can be determined through experimental data or directly set through expert knowledge; In the elevator intelligent management system, different types of faults involve different monitoring parameters. It is updated in real time based on the actual operating status of the elevator. These parameters may include vibration, temperature, current, acceleration, etc.

[0058] The following examples illustrate some typical elevator faults and their corresponding real-time monitoring values: Example 1: Motor overheating fault No. Class Fault: Motor overheating.

[0059] is the real-time temperature of the elevator motor. For example, if the temperature range of the elevator motor during normal operation is 60°C to 80°C, and exceeding 90°C may cause the motor to overheat and eventually damage. The system monitors the temperature of the motor in real time through the temperature sensor and uses this temperature value as .

[0060] Real-time monitoring value: Assuming the current motor temperature is 85°C, then That is 85°C. As time goes by, the temperature changes (such as rising to 88°C or falling to 82°C) will continue to update .

[0061] Example 2: Elevator door failure No. Type of fault: The elevator door closes abnormally.

[0062] It is the monitoring value of the elevator door's open and closed state. For example, the normal open and closed state of the elevator door will be completed within the specified time range. If the door fails to close within the predetermined time, it may indicate that the door is stuck, the track is blocked, or the sensor is faulty.

[0063] Real-time monitoring value: The system monitors the opening and closing time of the elevator door or the opening and closing angle of the door. Assuming that the elevator door usually completes the closing operation within 3 seconds, but the current monitoring shows that the elevator door has been running for 5 seconds and is still not completely closed, then this timeout monitoring value becomes , for example, 5 seconds as the real-time value in an abnormal state.

[0064] Example 3: Elevator vibration failure No. Type of fault: Abnormal vibration during elevator operation.

[0065] It represents the vibration amplitude measured by the elevator acceleration sensor. For example, the vibration frequency of the elevator should be maintained within a certain range during normal operation, such as 0.2g to 0.5g (g is the unit of gravity acceleration). Vibration exceeding this range may indicate problems in the mechanical system, such as bearing wear or unstable suspension system.

[0066] Real-time monitoring value: Assuming that the vibration amplitude of the elevator increases to 0.7g during acceleration, That is the currently measured vibration amplitude of 0.7g.

[0067] Example 4: Abnormal current fluctuation fault No. Type of fault: abnormal current fluctuation.

[0068] It is the current value when the elevator is running. For example, the current consumption of the elevator's drive system should be within the preset range under different load conditions. If the current is out of range, it may indicate a motor problem or circuit failure.

[0069] Real-time monitoring value: Assume that the system detects that the current is 150A, and the normal operating current range is 100A to 120A, then 150A is the current value at this time. , indicating that the current consumption is too high.

[0070] Energy efficiency index Use the following formula 4 for calculation: in, is the theoretical optimal energy consumption value, which is the standard energy consumption of the elevator under the best operating conditions; For elevator Actual energy consumption at the moment; When the calculated comprehensive performance index Less than the preset threshold , perform the following steps: P101: Sending a feature extraction instruction to the edge computing device; the feature extraction instruction is used to control the edge computing device to extract feature parameters related to the elevator operation status, including temperature, acceleration and current data; P102: Obtain relevant feature parameters of feature transmission extracted by edge computing devices; P103: Use the pre-trained deep learning model to perform fault mode recognition on the obtained relevant characteristic parameters to identify whether the current state of the elevator meets the characteristics of the historical fault mode; P104: If yes, the identified fault mode is transmitted to the edge computing device for result verification; P105: If the edge computing device passes the verification, an accurate fault location report is generated; if the verification fails, steps P101 to P104 are repeated until the verification passes or the preset maximum number of iterations is reached.

[0071] When the calculated comprehensive performance index Less than the preset threshold When the system enters the automatic fault detection and handling process, it will ensure that potential elevator faults are identified and resolved in a timely manner. This process consists of multiple steps, as follows: First, in The indicator is below the threshold When the system automatically sends a feature extraction instruction to the edge computing device (step P101), the system automatically sends a feature extraction instruction to the edge computing device. The purpose of this instruction is to control the edge computing device to extract feature parameters related to the elevator operation status from the elevator's sensors. These feature parameters include but are not limited to the elevator's temperature, acceleration, and current data. These data can reflect the real-time operation status of the elevator and help the system evaluate whether the equipment is in the early stages of abnormality or failure. The edge computing device is responsible for obtaining these key operating parameters from multiple sensors on the elevator in real time to ensure that the system can capture any abnormalities in the elevator operation in a timely manner.

[0072] After the edge computing device extracts these characteristic parameters (step P102), they are transmitted to the central system or cloud for further analysis and processing. These transmitted characteristic parameters can fully reflect the status of the elevator at the current operation stage, such as whether there is overheating, whether the acceleration is too large, or whether the current fluctuates abnormally. By transmitting and processing this data in real time, the system ensures that even if potential problems occur during the operation of the equipment, it can respond quickly.

[0073] Next, the system uses a pre-trained deep learning model to analyze these acquired feature parameters (step P103). The deep learning model is trained based on historical data and can identify the differences in the modes of elevator equipment in normal and faulty states. By comparing the features with the historical fault modes, the system can determine whether the current state of the elevator conforms to any known fault mode. If the identified feature parameters are highly consistent with a known fault mode, it indicates that the elevator may be in a fault or is about to fail.

[0074] If the deep learning model confirms that the current state of the elevator matches the historical fault pattern (step P104), the system transmits the identified fault pattern back to the edge computing device for verification of the result. This verification process is critical, as it ensures the accuracy of fault identification by comparing the current data and pattern again. The edge computing device can quickly verify the fault pattern transmitted back to determine whether there is indeed a potential problem. If the verification is successful, the system will generate an accurate fault location report. This report describes in detail the location of the fault, possible causes, and recommended solutions, helping maintenance personnel quickly locate and repair the fault.

[0075] If during the verification process, the edge computing device finds that the identified fault mode does not fully conform to the current feature data, or there is data inconsistency, the system will automatically re-execute the feature extraction and pattern recognition steps (step P105). The system will re-extract features based on the latest data and analyze them until the verification passes or the preset maximum number of iterations is reached. In this case, the system can continuously adjust and optimize itself to ensure that the final fault report is accurate and reliable, and minimize the possibility of false positives or false negatives.

[0076] The deep learning model can be a deep learning model structure based on a long short-term memory network (LSTM). LSTM is a neural network that is particularly suitable for processing time series data. It can effectively capture the time correlation in the elevator operation status and help predict equipment failures.

[0077] This model is trained and predicts faults based on the historical operating data of the elevator equipment (such as temperature, acceleration, current, etc.). When the elevator is running, these data are input into the model as a time series. The structure of the model includes the following levels: Input layer: The input received by the model is a multi-dimensional time series containing data from multiple sensors (such as temperature, vibration, current, etc.). Each time step contains the value read by a different sensor. For example, the input data can be of shape (T, N), where T represents the time step (such as the sampled data for the past 10 seconds) and N represents the number of sensors (for example, 3 sensors: temperature, vibration, and current).

[0078] LSTM layer: This is the core part. The LSTM layer can capture the temporal dependencies in the data, especially the trends or patterns over a long period of time. The model inputs a series of sensor data into the LSTM network, which learns the temporal relationships between these data and identifies abnormal patterns, such as the data change trends when the elevator is in a normal state and when it is about to fail.

[0079] Fully connected layer (Dense layer): After LSTM processing, the output data is passed to a fully connected layer for further feature extraction and classification. This layer reduces the dimensionality of high-dimensional features and prepares to output the final prediction results.

[0080] Output layer: The output layer is usually a node with an activation function for fault classification. For example, it outputs a binary classification result (0 for normal, 1 for fault), or a multi-classification result (for example, 0 for normal, 1 for motor fault, 2 for abnormal vibration, 3 for door fault, etc.).

[0081] The training process of deep learning models usually adopts supervised learning. Specifically, historical data is divided into training sets and validation sets. The training set is used to let the model "learn" the elevator operation mode under different conditions, and the validation set is used to test the prediction accuracy of the model. In each training iteration, the model analyzes the input data, adjusts the internal weights and parameters, and gradually optimizes its ability to classify normal and faulty states. Through continuous training, the model can more and more accurately identify the characteristic patterns of elevators when they are close to failure.

[0082] The remote monitoring module 104 is connected to the cloud computing and data fusion module, and is used to receive the equipment health status assessment results, fault prediction results and fault warning signals of the elevator equipment; and display the real-time status, historical data, fault statistics, maintenance records and elevator management optimization suggestions of the equipment to the user through a visual interface.

[0083] The remote monitoring module 104 is an important component of the elevator intelligent management system. Its main function is to receive the equipment health status assessment results, fault prediction results and fault warning signals from the cloud computing and data fusion module 103, and display these key information to the user through a visual interface so that the user can understand the operating status of the elevator in real time and make corresponding management decisions.

[0084] The remote monitoring module 104 first synchronizes data with the cloud computing and data fusion module, and receives the operating status, historical data, fault statistics, and fault prediction signals of all elevator equipment through a reliable network communication interface. When these data enter the remote monitoring module, the module will classify and process the data, and display the real-time operating status and historical data separately, thereby providing users with a clear view to facilitate their analysis of the health status of the elevator. The design of the module ensures that the data can be updated in real time to avoid information lag, thereby ensuring that users can respond quickly and accurately during operation.

[0085] The visualization interface is one of the important functions of the remote monitoring module 104. It provides users with an intuitive way to monitor the status of elevator equipment. Through graphical display, users can view key operating parameters of the elevator, such as temperature, current, acceleration, and vibration, in the form of bar graphs, line graphs, heat maps, etc. This visual display method not only improves the readability of the data, but also allows users to perform multi-dimensional queries on the interface. For example, users can choose to view the operating status trend within a certain time period, or view the detailed historical fault records of a specific elevator. This flexibility ensures that users can have a deep understanding of the operating status of the elevator system.

[0086] The remote monitoring module 104 not only provides data display function, but also has a real-time alarm function. When the system receives a fault warning signal from the cloud computing and data fusion module, the remote monitoring module will immediately pop up an alarm on the interface and attract the user's attention through sound or visual prompts. The alarm system is triggered based on a preset threshold, which means that when certain parameters of the elevator (such as temperature or current) exceed the safe range, the system will automatically generate a warning signal, and the remote monitoring module will immediately notify the operator. The content of the alarm includes detailed information on the warning signal, such as the specific device that triggered the alarm, the cause of the trigger, and the real-time operating status of the device. With this information, users can quickly identify potential problems and take timely countermeasures.

[0087] In addition, the remote monitoring module 104 also has the function of generating management optimization suggestions. This function automatically generates targeted operation suggestions based on the management optimization suggestions received from the data analysis module 106, combined with the historical data, fault records and health status assessment of the elevator. These suggestions include how to optimize the operating parameters of the elevator, how to allocate maintenance resources, and how to formulate future maintenance plans. Managers can view these suggestions on the interface and make adjustment decisions based on the specific equipment conditions. The remote monitoring module also allows users to convert these optimization suggestions into actual operations, such as automatically generating maintenance tasks and passing them to the intelligent maintenance module 105 to execute the corresponding maintenance plan.

[0088] The remote monitoring module 104 also has a historical data archiving and retrieval function. The module can save all received operating status data and fault records, and allow users to retrieve these data for analysis at any time. Users can filter data by time, equipment or fault type to find specific faults or maintenance records. This function greatly facilitates system managers to track the entire cycle of elevator operation and analyze faults, ensuring the continuity and traceability of equipment maintenance and management.

[0089] Through the remote monitoring module 104, the system manager can monitor the operating status of the elevator in real time, respond quickly to fault warnings, and reasonably allocate resources according to the optimization suggestions provided by the system to ensure the safe and stable operation of the elevator equipment.

[0090] Furthermore, the remote monitoring module is specifically used for: Receive the elevator equipment health status assessment results, fault prediction results and fault warning signals from the cloud computing and data fusion module, and generate equipment operation status reports based on the received data, including real-time status and historical operation trends of the equipment; The real-time status, fault statistics and maintenance records of the equipment are displayed to users in the form of charts, graphics and text through a visual interface; users are allowed to remotely monitor and manage the equipment according to the interactive functions provided by the interface, including pausing the equipment, adjusting the elevator operation mode or setting monitoring strategies for a specific time period; When there is a significant change in the elevator's operating status or a fault warning signal is triggered, the remote monitoring module sends a notification to the relevant maintenance personnel or managers via SMS, email or mobile application.

[0091] The remote monitoring module is mainly responsible for receiving, displaying and processing various elevator operation status information from the cloud computing and data fusion module in the elevator intelligent management system. First, the remote monitoring module receives the health status assessment results, fault prediction results and fault warning signals of the elevator equipment. These data are transmitted through the cloud computing and data fusion module, covering the real-time status of the elevator equipment and the prediction of possible future faults. The remote monitoring module processes the received data and generates a detailed equipment operation status report. This report includes the real-time monitoring of the elevator operation status and the equipment operation trend obtained based on historical data analysis. These historical trends can help users judge the long-term performance of the equipment and identify potential performance degradation problems.

[0092] The remote monitoring module displays data to users not only through text but also through visualization. Through the interface, users can view the real-time status of elevator equipment, including key parameters such as temperature, current, and vibration. Fault statistics are displayed in the form of charts or graphs to help users understand the frequency and type of faults during elevator operation. At the same time, maintenance records will also be displayed through the interface, and users can view the maintenance history of the elevator to ensure that the equipment is maintained normally according to the established maintenance plan. The design of the remote monitoring module focuses on intuitiveness. Through graphical display, users can easily understand complex data and equipment status, thereby improving the operating efficiency of the system.

[0093] The remote monitoring module also provides users with interactive functions, allowing them to remotely operate and manage the equipment directly through the interface. For example, users can pause the elevator equipment according to the current operating status for emergency maintenance or inspection. The module also allows users to adjust the operation mode of the elevator, change its operating speed or adjust its operating time. At the same time, users can also set monitoring strategies for specific time periods according to different monitoring needs. For example, during peak usage time periods, users can choose more frequent monitoring to ensure that the equipment operates safely under high load.

[0094] When the operating status of the elevator equipment changes significantly or the system detects a fault warning signal, the remote monitoring module has the function of real-time notification. It will send an alarm to the relevant maintenance personnel or managers via SMS, email or mobile application. This function ensures that the relevant personnel can understand the abnormal situation of the equipment in time and respond quickly, thereby minimizing the downtime or safety risks caused by the fault.

[0095] The remote monitoring module greatly improves the monitorability and operational convenience of elevator equipment through its powerful data reception, display and interaction functions.

[0096] Furthermore, the visualization interface of the remote monitoring module adopts a multi-level interface based on dynamic data interaction to display the operating status of the elevator equipment; and displays the temperature, current, acceleration, vibration and operating speed of the elevator through hierarchical status charts, allowing users to view data at different zoom levels, including from a global operating status overview to detailed trend charts of single parameters.

[0097] The visual interface of the remote monitoring module adopts a multi-level interface design based on dynamic data interaction to display the operating status of the elevator equipment. This design allows users to flexibly view various types of data in the elevator system and obtain a comprehensive view from the overall to the details at different levels and zoom levels.

[0098] First, the visual interface of the remote monitoring module displays the overall operating status of the elevator equipment in a clear and intuitive way. When users enter the system, they will first see a global view in which the key operating parameters of the elevator, such as temperature, current, acceleration, vibration and running speed, are presented in the form of charts. Such charts are usually presented in the form of colorful trend lines, bar charts or other forms of graphical displays, allowing users to quickly browse the overall performance of the elevator and identify potential anomalies or problems.

[0099] In order to facilitate users to deeply analyze the operation of the equipment, the interface also provides a multi-level zoom function. Users can select specific parameters from the global view to zoom in and view. For example, users can click on the temperature chart to enter a special temperature monitoring view, in which they can view the temperature trend of different parts of the elevator in detail. This zoom and layered display function allows users to switch from the global status of the equipment to the details of specific parameters, so as to more accurately monitor and analyze the operation of the elevator.

[0100] In each level of the interface, data display is based on real-time updates. The remote monitoring module can dynamically receive and process various real-time data in the operation of the elevator, so the charts displayed in the interface will also be updated in real time. This means that users can obtain the latest operating status at any time without manually refreshing the page, ensuring real-time control of the equipment status.

[0101] In addition, the visualization interface also uses status charts to intuitively display the operating status of the elevator in a hierarchical manner. For example, when the user views the vibration data, the interface can show the trend of the elevator's vibration amplitude over time, while providing vibration data for different components. Users can view the specific vibration conditions of components such as elevator doors and elevator motors. Similarly, for current and acceleration, the interface can display parameter changes in different operating stages, such as current fluctuations and acceleration changes during acceleration and deceleration. These data are displayed in charts to help users understand the performance of the equipment under different working conditions.

[0102] This multi-level visual interface design not only provides a flexible interactive experience, but also ensures that users can view all information from the overall to the details as needed when monitoring the elevator system. In this way, users can quickly obtain the overall health of the equipment in a global view, and then analyze the detailed data of specific parameters in depth when necessary. This design greatly improves the practicality and user experience of the system, making the elevator management system more efficient and intelligent.

[0103] The intelligent maintenance module 105 is connected to the remote monitoring module and the cloud computing and fusion module, and generates a maintenance plan and maintenance reminder based on the received equipment health status assessment results and fault prediction results; according to the generated maintenance plan, it assigns maintenance tasks to maintenance personnel; and after the maintenance task is completed, it receives the maintenance record provided by the maintenance personnel.

[0104] The intelligent maintenance module 105 is the core module responsible for automatically generating and managing elevator maintenance plans. It is closely connected with the cloud computing and data fusion module 103 and the remote monitoring module 104, and intelligently formulates personalized maintenance plans based on the health status assessment results and fault prediction results of the elevator equipment. This module is designed to improve maintenance efficiency, reduce operating risks, and ensure that the elevator equipment always maintains the best operating status during its life cycle.

[0105] When the intelligent maintenance module 105 receives the equipment health status assessment results and fault prediction results, it first conducts a comprehensive analysis of these data. The health status assessment results reflect the current operating conditions of the various components of the elevator, including the health of mechanical components, electrical systems, and safety devices, while the fault prediction results are based on historical data and current status to make advance predictions of possible faults. The intelligent maintenance module uses this information to dynamically adjust the maintenance needs of the elevator. Specifically, the module automatically calculates the priority and schedule of the maintenance plan based on the health status of each component. For example, for those components with low health status scores or high risks in fault predictions, the module will mark them as priority maintenance objects to ensure that these components can be inspected and repaired in a timely manner.

[0106] In the process of formulating the maintenance plan, the intelligent maintenance module 105 not only relies on the current status of the equipment, but also combines historical maintenance records, operating hours, and the environment in which the elevator is used. The module will make a detailed plan for each maintenance task, including the required maintenance time, the required tools and equipment, and the appropriate maintenance personnel. In addition, the module can automatically generate maintenance reminders to ensure that the system can promptly notify relevant personnel to perform maintenance as planned to prevent equipment failure or unsafe operation due to negligence.

[0107] The intelligent maintenance module also has a task allocation function. Based on the generated maintenance plan, the module automatically assigns each task to the appropriate maintenance personnel. In this process, the module takes into account the maintenance personnel's skills, geographical location and current workload to optimize resource allocation. After the task is assigned, the relevant maintenance tasks will be sent to the maintenance personnel in real time via mobile terminals or other communication devices. The maintenance personnel can immediately obtain detailed information on the task, including the status report of the parts to be repaired, the specific maintenance steps, and the required tools and materials.

[0108] After the maintenance task is completed, the intelligent maintenance module 105 is also responsible for receiving and recording the maintenance reports submitted by the maintenance personnel. These reports include information such as the specific implementation of the maintenance, whether additional problems are found, the replaced parts and the materials used. After the maintenance report is submitted, the intelligent maintenance module will upload this data to the cloud computing and data fusion module and save it as a historical record for further analysis and optimization in the future. Through the accumulation of maintenance records, the system can continuously improve the maintenance plan to make it more accurate and efficient.

[0109] In addition, the intelligent maintenance module can continuously optimize itself. By analyzing the execution of the maintenance plan and the long-term health status of the equipment, the module can dynamically adjust the frequency of future maintenance. For example, if a certain type of equipment component performs well in multiple maintenance tasks and its health status remains at a high level, the intelligent maintenance module may appropriately extend the next maintenance cycle of the component to reduce unnecessary maintenance resource investment. For those components that still frequently have problems after maintenance, the system will shorten the maintenance cycle and put forward more detailed maintenance requirements to ensure that the problem can be completely resolved.

[0110] The advantages of the intelligent maintenance module 105 are not only reflected in its automated and intelligent task generation and allocation functions, but also in its ability to further optimize the operational efficiency of the entire elevator system by analyzing historical maintenance records and equipment operation data, reduce operational interruptions caused by sudden failures, reduce maintenance costs, and improve the safety and reliability of elevators.

[0111] Furthermore, the intelligent maintenance module is specifically used for: Generate a maintenance plan based on the received equipment health status assessment results and fault prediction results; the maintenance plan is prioritized according to the current status of the equipment, historical fault frequency, and component life, ensuring that high-risk equipment or components that are about to reach the end of their service life are given priority for maintenance; According to the generated maintenance plan, tasks are assigned to corresponding maintenance personnel, and the task assignment is performed based on the maintenance personnel's skill level, current workload, and geographical location.

[0112] The intelligent maintenance module is mainly used in the elevator intelligent management system to generate a maintenance plan based on the equipment health status assessment results and fault prediction results. The design of this module ensures that the maintenance plan is not just based on a static schedule, but is dynamically adjusted and optimized based on the current status of the equipment, historical fault frequency, and service life of the components.

[0113] When the intelligent maintenance module receives the health status assessment results of the elevator equipment, it first analyzes the current status of the equipment and compares it with historical data. If certain components are marked as high risk in the fault prediction, or their health status assessment scores are low, the intelligent maintenance module will prioritize the maintenance tasks of these components and add them to the maintenance plan. The module will also dynamically adjust the priority of the maintenance plan based on the service life of each component of the elevator equipment to ensure that components that are about to reach the end of their service life can be maintained or replaced in time. This function combines the current actual operating status of the equipment with historical records to ensure that the system's predictions are more accurate, thereby reducing the risk of sudden failures.

[0114] Another core function of the intelligent maintenance module is task allocation. After the maintenance plan is generated, the system allocates the maintenance tasks to the appropriate maintenance personnel according to the priority of the tasks. This allocation process is not random, but is based on a combination of factors. First, the system selects the most suitable personnel based on the skill level of each maintenance personnel. For example, if a task involves the complex electrical system of the elevator, the intelligent maintenance module will give priority to technicians with corresponding electrical maintenance skills to perform the task. Secondly, the module will consider the current workload of each maintenance personnel to ensure that too many tasks are not assigned to a technician, thereby avoiding a decrease in work efficiency. Finally, the module will also combine the geographical location of the maintenance personnel and give priority to personnel who are closer to the faulty elevator for task allocation. This approach not only improves the response speed, but also greatly reduces the travel time of maintenance personnel, improving the overall maintenance efficiency.

[0115] The entire intelligent maintenance module achieves more accurate and efficient maintenance management by combining equipment status, historical fault data and dynamic matching of maintenance resources.

[0116] Furthermore, the intelligent maintenance module is specifically used for: Dynamically adjust the maintenance plan based on the acquired equipment operation status and health assessment results; the dynamic adjustment of the maintenance plan includes adjusting the maintenance frequency and notifying relevant personnel for equipment with significant status changes; if the equipment status continues to remain good, the maintenance cycle will be extended; Generate maintenance optimization suggestions by analyzing various fault records and maintenance history; the maintenance optimization suggestions include the best maintenance time and maintenance warnings for the most vulnerable parts; Generate emergency maintenance reminders when the equipment is in a critical state or during a high-prone period of failure.

[0117] The intelligent maintenance module is mainly used in the elevator intelligent management system to dynamically adjust the maintenance plan according to the real-time operating status and health assessment results of the elevator equipment. The design of this module ensures that the maintenance plan can be flexibly adjusted as the equipment status changes, thereby effectively reducing unnecessary maintenance and improving the efficiency of the system.

[0118] The intelligent maintenance module continuously monitors the operating status of the equipment. When the system detects a large fluctuation in the status of a certain device, such as a significant change in key parameters such as vibration, temperature or current, the module will immediately adjust the maintenance frequency of the device. Specifically, for equipment with large status changes, the intelligent maintenance module will shorten its maintenance cycle to ensure that the equipment can maintain normal operation with more frequent maintenance. At the same time, the system will automatically generate notifications to remind relevant maintenance personnel or managers to conduct inspections or maintenance in a timely manner to prevent equipment failures under high load. This dynamic adjustment mechanism greatly enhances the system's responsiveness to equipment health, allowing the system to proactively prevent failures rather than relying on passive regular maintenance.

[0119] On the other hand, if the health status of the equipment remains good for a long time and the operating parameters are stable, the intelligent maintenance module will extend the maintenance cycle of the equipment based on this information. This strategy helps to reduce unnecessary maintenance tasks, thereby saving resources and reducing operating costs. This adaptive adjustment function of the module makes the entire maintenance plan more efficient and can be flexibly optimized according to the actual operating status of the equipment.

[0120] The intelligent maintenance module also generates maintenance optimization suggestions by analyzing fault records and maintenance history data. By deeply analyzing past fault data, the system can identify the most vulnerable parts of the elevator equipment and generate early warnings for these parts. These optimization suggestions not only point out the parts of the equipment that are most prone to failure, but also give the best maintenance time, helping managers to perform preventive maintenance before the equipment has problems. This fault analysis based on historical data greatly improves the intelligence of the system and ensures that the equipment can be maintained in time before a serious failure occurs.

[0121] In addition, the intelligent maintenance module also has the function of emergency maintenance reminder. When the system detects that the equipment is in a critical state or enters a high-incidence period of failure, such as when the equipment frequently fails or some components enter a high-load operation stage, the module will automatically generate an emergency maintenance reminder. This reminder can be sent immediately to the relevant maintenance personnel to ensure that they can deal with the problem as soon as possible to prevent small problems from evolving into major failures. This real-time reminder mechanism greatly improves the system's response speed to equipment anomalies and effectively reduces the risk of equipment downtime.

[0122] In summary, the intelligent maintenance module provides strong support for the efficient maintenance of elevator equipment by dynamically adjusting maintenance plans, generating optimization suggestions and real-time emergency reminders.

[0123] The data analysis module 106 is connected to the intelligent maintenance module and the cloud computing and data fusion module, and is used to receive and analyze maintenance records, fault records and elevator equipment operation history data to obtain elevator management optimization suggestions; and feed back the elevator management optimization suggestions to the remote monitoring module.

[0124] The data analysis module 106 plays a core analysis and optimization decision-making role in this system. Its function is to conduct in-depth analysis of the maintenance records, fault records and operation history data from the elevator system to obtain optimization suggestions for elevator management, and feed these suggestions back to the remote monitoring module and the intelligent maintenance module, thereby improving the intelligence and efficiency of elevator management.

[0125] The data analysis module 106 first receives and summarizes data from multiple sources, including the maintenance records of the intelligent maintenance module 105, the fault records of the equipment, and the operation history data of the elevator equipment. The maintenance records cover the detailed information of each maintenance, such as the content of the maintenance, the components involved, the tools and materials used, etc.; the fault records include all the fault events detected during the operation of the elevator and their corresponding repair conditions; the operation history data involves various operating status parameters of the elevator within a specific time period, such as temperature, current, vibration and acceleration, etc. These data are transmitted to the data analysis module 106 through the cloud computing and data fusion module 103, and are formatted for further analysis.

[0126] The key to the data analysis module 106 is its powerful data processing and analysis capabilities. The module has built-in analysis algorithms that can compare historical data with current data to identify potential operating trends or hidden faults in elevator equipment. For example, by analyzing the changing trends of temperature and vibration, the data analysis module can determine whether a component is at risk of aging or about to fail. The module can also identify frequently occurring failure modes in the system by comparing fault records and predict when these failures may occur again in the future. This predictive analysis helps plan maintenance work in advance to avoid downtime or safety hazards caused by failures.

[0127] In addition, the data analysis module 106 continuously optimizes its analysis model through machine learning technology. As more operating data and maintenance records are accumulated, the module can automatically adjust and update its analysis algorithm to make its assessment of equipment health status and fault prediction more accurate. For example, when a certain elevator component has the same fault multiple times, the data analysis module will identify this trend and prioritize the inspection or replacement of this component in future maintenance plans. This intelligent learning and optimization process ensures that the system can continuously adapt to changes in the operation of elevator equipment and improve the accuracy of predictions.

[0128] Based on the results of data analysis, the module generates optimization suggestions for elevator management. These suggestions may include adjusting the operating parameters of the elevator, optimizing the maintenance frequency, or replacing certain key components. For example, the data analysis module may find that the acceleration data of a certain elevator fluctuates greatly within a specific time period, which may cause increased equipment wear. Therefore, the module will recommend adjusting the acceleration parameters or speeding up the maintenance cycle of related components. The optimization suggestions can also be combined with the use of maintenance resources to propose how to efficiently use maintenance resources and reduce redundant inspections, thereby reducing overall operating costs.

[0129] Once these management optimization suggestions are generated, the data analysis module 106 will feed them back to the remote monitoring module 104 and the intelligent maintenance module 105. The remote monitoring module 104 presents these suggestions to the management personnel in a visual form, and the management personnel can make real-time adjustments and optimizations to the elevator system based on these suggestions. The intelligent maintenance module 105 will automatically update the maintenance plan based on these suggestions, and assign the optimized plan to the corresponding maintenance personnel to ensure that the execution of each maintenance task can reflect the latest management optimization strategy.

[0130] The design of the data analysis module 106 not only enables it to have powerful data processing capabilities, but also improve the operating efficiency and safety of the elevator equipment through continuous learning and optimization.

[0131] Furthermore, the data analysis module is specifically used for: Receive and integrate maintenance records, fault records and elevator equipment operation history data to generate a preliminary diagnostic report; the preliminary diagnostic report includes historical trends of key parameters of the equipment, as well as the frequency and causes of faults; Based on the preliminary diagnostic report, using a fault prediction model based on historical data to analyze the health status of key components of the elevator; Generate elevator management optimization suggestions based on the health status of key components obtained through analysis, combined with elevator operating efficiency, maintenance cost and energy consumption performance.

[0132] The data analysis module in the elevator intelligent management system first generates a preliminary diagnostic report by receiving and integrating maintenance records, fault records, and historical operation data of the elevator equipment. The core of this diagnostic report is to analyze the key parameters of the elevator equipment, including historical trends such as the temperature, vibration, and acceleration of the equipment. At the same time, the system analyzes the fault records of the equipment to derive the frequency and cause of each fault. This preliminary diagnostic report provides elevator managers with a panoramic view, helping them understand the past performance of the equipment and find potential causes of equipment failures. For example, if the vibration data of a component gradually increases and matches the data in the historical fault record, the system may indicate that the component may be at risk of failure again.

[0133] After generating the preliminary diagnosis report, the data analysis module will further use the fault prediction model based on historical data to analyze the health status of each key component of the elevator. The fault prediction model can identify the typical operating characteristics of the component before the failure occurs by learning and pattern recognition from a large amount of historical data. For example, if an elevator motor has experienced a sharp rise in temperature and caused failures many times in history, the model will compare this pattern with the current data. When the model finds that the temperature curve of the current motor matches the historical failure data, the system will evaluate the health status of the motor as "high risk" and make corresponding annotations in the preliminary diagnosis report.

[0134] After evaluating the health of key components, the data analysis module will generate elevator management optimization suggestions based on these results and other factors such as the elevator's operating efficiency, maintenance costs and energy consumption performance. These optimization suggestions are designed to help managers make informed decisions to improve the elevator's operating efficiency and reduce the possibility of failure. For example, if a component is in poor health but its replacement cost is high, the system may recommend optimizing its operating conditions and extending its service life before it fails. In addition, if a component consumes a lot of power, the system may recommend that users adjust the elevator's operating mode to reduce energy consumption while ensuring that performance is not affected.

[0135] Optimization recommendations can also involve adjustments to maintenance plans. For example, the system may recommend increasing the maintenance frequency based on the health of the equipment to reduce the risk of failure of key components, or reducing the maintenance frequency of certain components in good health, thereby saving resources and costs. Through these optimization strategies, the elevator management system can achieve higher operating efficiency and lower maintenance costs, ensuring that the equipment is always in the best condition.

[0136] In short, the data analysis module receives data from multiple sources, conducts in-depth analysis and generates optimization suggestions to ensure the long-term healthy operation of elevator equipment.

[0137] Although the present application is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

Claims

1. An elevator intelligent management system based on edge computing and computing network integration, characterized in that: include: A data acquisition module is used to connect to the elevator system through the industrial Internet of Things device to collect the operating status data of the elevator equipment, wherein the operating status data includes the temperature, current, vibration, acceleration, operating speed and door status of the elevator equipment; the operating status data collected by the edge computing gateway is preliminarily processed, and the preliminarily processed data is transmitted to the edge computing device; The edge computing device is connected to the data acquisition module, and is used to receive and analyze the data after preliminary processing to obtain the elevator operation status data; adjust the operation parameters of the elevator according to the elevator operation status data; when the elevator operation status data shows that the elevator is in an abnormal state, generate a fault warning signal, and transmit the generated fault warning signal and the elevator operation status data to the cloud computing and data fusion module and the remote monitoring module; The cloud computing and data fusion module is connected to the edge computing processing device, and is used to receive the elevator operation status data and fault warning signals provided by the edge computing device, and perform in-depth analysis and data storage on them; the analysis results of the in-depth analysis are processed by the computing network fusion technology to generate equipment health status assessment results and fault prediction results, and the generated equipment health status assessment results and fault prediction results are transmitted to the remote monitoring module and the intelligent maintenance module; A remote monitoring module, connected to the cloud computing and data fusion module, is used to receive equipment health status assessment results, fault prediction results and fault warning signals of the elevator equipment; and to display the real-time status, historical data, fault statistics, maintenance records and elevator management optimization suggestions of the equipment to the user through a visual interface; The intelligent maintenance module is connected to the remote monitoring module and the cloud computing and integration module. Based on the received equipment health status assessment results and fault prediction results, it generates maintenance plans and maintenance reminders; according to the generated maintenance plan, it assigns maintenance tasks to maintenance personnel; and after the maintenance tasks are completed, it receives the maintenance records provided by the maintenance personnel; The data analysis module is connected to the intelligent maintenance module and the cloud computing and data fusion module, and is used to receive and analyze maintenance records, fault records and elevator equipment operation history data to obtain elevator management optimization suggestions; and feed back the elevator management optimization suggestions to the remote monitoring module.

2. The elevator intelligent management system based on edge computing and computing network integration according to claim 1 is characterized in that: The data acquisition module is specifically used for: Establish real-time connection between industrial IoT devices and sensors in the elevator system to collect multi-dimensional operating status data of elevator equipment, ensuring that the temperature, current, vibration, acceleration and door status of the elevator are obtained regularly at each preset time interval; Use edge computing gateways to pre-process the collected data, including cleaning, filtering, and formatting abnormal data, while arranging the data in a predefined format to reduce the transmission load; After preprocessing is completed, the preprocessed data is transmitted to the edge computing device.

3. The elevator intelligent management system based on edge computing and computing network integration according to claim 2 is characterized in that: The data acquisition module is specifically used for: Dynamically adjust data collection frequency and parameter priority according to real-time changes in elevator operating status; Dynamically optimize data collection strategies based on the environment and equipment operation through adaptive algorithms; When the sensor value is detected to exceed the safety threshold, the real-time data transmission mode is triggered; The relevant abnormal data is marked as high priority and uploaded to the cloud computing and data fusion module through the edge computing gateway.

4. The elevator intelligent management system based on edge computing and computing network integration according to claim 1 is characterized in that: The edge computing device is specifically used for: Receive the elevator operation status data after preliminary processing transmitted from the data acquisition module, and perform further data filtering and verification processing, including eliminating duplicate data and correcting data deviations to improve the accuracy of data processing; Analyze the processed elevator operation status data and determine whether the equipment is in an abnormal state based on the preset threshold; If the operating status data exceeds the safety threshold, a fault warning signal is generated; When the fault warning signal is generated, the fault warning signal is packaged with the corresponding operating status data and transmitted to the cloud computing and data fusion module and the remote monitoring module.

5. The elevator intelligent management system based on edge computing and computing network integration according to claim 1 is characterized in that: The remote monitoring module is specifically used for: Receive the elevator equipment health status assessment results, fault prediction results and fault warning signals from the cloud computing and data fusion module, and generate equipment operation status reports based on the received data, including real-time status and historical operation trends of the equipment; The real-time status, fault statistics and maintenance records of the equipment are displayed to users in the form of charts, graphics and text through the visual interface; Allow users to remotely monitor and manage equipment based on the interactive functions provided by the interface, including pausing equipment, adjusting elevator operation modes, or setting monitoring strategies for specific time periods; When there is a significant change in the elevator's operating status or a fault warning signal is triggered, the remote monitoring module sends a notification to the relevant maintenance personnel or managers via SMS, email or mobile application.

6. The elevator intelligent management system based on edge computing and computing network integration according to claim 1 is characterized in that: The visualization interface of the remote monitoring module adopts a multi-level interface based on dynamic data interaction to display the operating status of the elevator equipment; and displays the temperature, current, acceleration, vibration and operating speed of the elevator through hierarchical status charts, allowing users to view data at different zoom levels, including from a global operating status overview to detailed trend charts of single parameters.

7. The elevator intelligent management system based on edge computing and computing network integration according to claim 1 is characterized in that: The intelligent maintenance module is specifically used for: Generate a maintenance plan based on the received equipment health status assessment results and fault prediction results; the maintenance plan is prioritized according to the current status of the equipment, historical fault frequency, and component life, ensuring that high-risk equipment or components that are about to reach the end of their service life are given priority for maintenance; According to the generated maintenance plan, tasks are assigned to corresponding maintenance personnel, and the task assignment is performed based on the maintenance personnel's skill level, current workload, and geographical location.

8. The elevator intelligent management system based on edge computing and computing network integration according to claim 1 is characterized in that: The intelligent maintenance module is specifically used for: Dynamically adjust the maintenance plan based on the acquired equipment operation status and health assessment results; the dynamic adjustment of the maintenance plan includes adjusting the maintenance frequency for equipment with significant status changes and notifying relevant personnel; If the equipment continues to be in good condition, the maintenance cycle will be extended; Generate maintenance optimization suggestions by analyzing various fault records and maintenance history; the maintenance optimization suggestions include the best maintenance time and maintenance warnings for the most vulnerable parts; Generate emergency maintenance reminders when the equipment is in a critical state or during a high-prone period of failure.

9. The elevator intelligent management system based on edge computing and computing network integration according to claim 1 is characterized in that: The data analysis module is specifically used for: Receive and integrate maintenance records, fault records and elevator equipment operation history data to generate a preliminary diagnostic report; the preliminary diagnostic report includes historical trends of key parameters of the equipment, as well as the frequency and causes of faults; Based on the preliminary diagnostic report, using a fault prediction model based on historical data to analyze the health status of key components of the elevator; Based on the health status of key components obtained through analysis, optimization algorithms are used to combine elevator operating efficiency, maintenance costs and energy consumption performance to generate elevator management optimization suggestions.

10. The elevator intelligent management system based on edge computing and computing network integration according to claim 1 is characterized in that: The cloud computing and data fusion module is specifically used for: The comprehensive performance index of the elevator is calculated according to the following formula 1: ; in, for Comprehensive performance indicators at all times; for The equipment health status index at the moment; for The moment Class fault prediction credibility; For the The weight of the class fault; is the total number of fault types; for Energy efficiency index at the moment; is the weight coefficient; is the time attenuation coefficient; is the energy efficiency attenuation coefficient; The time of the most recent energy efficiency calibration; The equipment health status index is calculated by the following formula 2: ; in, is the total number of elevator operating status parameters, wherein the elevator equipment operating status parameters include temperature, current, vibration, acceleration, operating speed and door status; Indicates The maximum permissible value of the elevator operation status parameter; For the current Elevator-like operating status parameters; For the Weight coefficient of elevator operation status parameters; For the Adjustment parameters of elevator operation status parameters; For the Normalization coefficient of elevator-like operating state parameters; is the current time; The time of the most recent elevator maintenance; is the time decay constant; Failure prediction reliability It is calculated by the following formula 3: ; in, For the Sensitivity coefficient of class fault; For the Real-time monitoring value of class faults; For the Prediction threshold of class fault; Energy efficiency index Use the following formula 4 for calculation: ; in, is the theoretical optimal energy consumption value; For elevator Actual energy consumption at the moment; When the calculated comprehensive performance index Less than the preset threshold , perform the following steps: P101: Sending a feature extraction instruction to the edge computing device; the feature extraction instruction is used to control the edge computing device to extract feature parameters related to the elevator operation status, including temperature, acceleration and current data; P102: Obtain relevant feature parameters of feature transmission extracted by edge computing devices; P103: Use the pre-trained deep learning model to perform fault mode recognition on the obtained relevant characteristic parameters to identify whether the current state of the elevator meets the characteristics of the historical fault mode; P104: If yes, the identified fault mode is transmitted to the edge computing device for result verification; P105: If the edge computing device passes the verification, an accurate fault location report is generated; if the verification fails, steps P101 to P104 are repeated until the verification passes or the preset maximum number of iterations is reached.

Citation Information

Patent Citations

  • Escalator full-life-cycle health management system based on predictive maintenance

    CN111401583A

  • Elevator intelligent supervision and on-demand repair and maintenance system and method based on PHM technology

    CN111994749A

  • Elevator maintenance early warning system and method based on deep learning

    CN113697623A

  • Intelligent equipment monitoring and early warning system

    CN117826715A

  • Graphical-based cloud elevator monitoring management background early warning system and method

    CN118495283A

Cited By

  • Intelligent equipment data interaction system based on industrial internet

    CN119299489A

  • Edge side total detection method and system based on industrial internet

    CN119402302A

  • Safety management method and device for elevator operation

    CN119450175A

  • Anti-abrasion and anti-explosion intelligent real-time monitoring system and method for boiler

    CN119472508A

  • Real-time monitoring system for electron accelerator

    CN119511924A