Elevator part aging state monitoring method and system
Through the combination of elevator component aging test and BP neural network model, real-time monitoring and evaluation of elevator component aging status is achieved, which solves the problems of inaccurate elevator risk prediction and insufficient intelligent monitoring in the existing technology, and improves the safety of elevators and maintenance efficiency.
Patent Information
- Application Number
- CN202411228714.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-11-26
AI Technical Summary
The existing technology lacks accurate and scientific prediction models in the early risk prediction of elevators, which leads to inaccurate prediction of prediction results and is unable to effectively guide elevator maintenance. In addition, the popularity and integration of intelligent monitoring systems are limited, making it difficult to achieve the operating status of various elevator components. Comprehensive, real-time monitoring and intelligent analysis.
The aging test of elevator components is designed, the characteristic parameters under different aging states are recorded, and the aging state evaluation model is constructed using BP neural network. The model is trained through forward propagation and backpropagation algorithms to realize real-time monitoring and evaluation of the aging state of elevator components.
By monitoring the aging status of elevator components in real time, discovering potential risks in advance, providing scientific decision-making basis, improving the safety and reliability of elevators, reducing maintenance costs, and improving maintenance efficiency and quality.
Smart Images

Figure CN119025897A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of elevator safety technology, and more particularly to a method and system for monitoring the aging status of elevator components. Background Art
[0002] In the field of early risk prediction for elevators, traditional elevators mostly adopt the method of regular inspection and post-failure maintenance, which is often lagging. That is, maintenance and replacement are only carried out when elevator components have obvious failures or performance degradation, making it difficult to detect and prevent potential risks in advance.
[0003] Existing technologies mostly rely on empirical judgment or simple statistical analysis in risk prediction, and lack accurate and scientific prediction models. This results in prediction results that are often not accurate enough and cannot provide effective guidance for the early maintenance of elevators. In addition, elevators generate a large amount of data during operation, and insufficient data collection, processing and analysis capabilities will lead to a large amount of valuable information being wasted. Although intelligent technology has been applied to a certain extent in the elevator industry, the overall degree of intelligence is still not high, and the popularity and integration of intelligent monitoring systems are limited, making it difficult to achieve comprehensive, real-time monitoring and intelligent analysis of the operating status of various elevator components.
[0004] In view of the above-mentioned defects of the prior art, how to monitor the aging status of various elevator components, prevent them in advance, reduce failures, and improve operation and maintenance efficiency and quality is an urgent problem that technical personnel in this field need to solve. Summary of the invention
[0005] In view of this, the present invention provides an elevator component aging status monitoring method and system, which are used to monitor and predict the operating status of various elevator components in real time, so as to promptly discover and deal with potential aging problems and ensure the safe operation of the elevator.
[0006] In order to achieve the above object, the present invention provides the following technical solutions:
[0007] A method for monitoring the aging status of elevator components comprises the following steps:
[0008] Step 1: Design and implement an aging test for elevator components, simulating long-term operation and wear. During the test, record the characteristic parameters of each component under different aging conditions;
[0009] Step 2: Using BP neural network, determine the number of layers, activation function, and optimization algorithm of the neural network, and construct a neural network model for monitoring the aging status of elevator components;
[0010] Step 3: Use the characteristic parameters as input features and the corresponding aging status as output labels to train the neural network model, calculate the network output through forward propagation, and then use the back propagation algorithm to adjust the network parameters to minimize the loss function and obtain the aging status assessment model;
[0011] Step 4: Deploy the trained aging status assessment model to the elevator monitoring system, monitor the operating status of each elevator component in real time, assess the aging status of the elevator components, and output the aging status level of the elevator components.
[0012] Optionally, in step 1, the aging test of elevator components includes the following process:
[0013] Construct a test bench that simulates the actual working environment of the elevator, including at least simulating the elevator shaft, car, guide rail, and traction system, and use a loading device to simulate the elevator load condition, use a heater and humidifier to simulate different temperature and humidity conditions, and use a vibration table to simulate the vibration and impact of the elevator during operation;
[0014] According to the actual frequency of use of the elevator, set the number of cycles of the aging test, including the number of operations per day and the distance of each operation; simulate the wear process by controlling the loading weight and running speed;
[0015] Install a data acquisition system to record the changes in these characteristic parameters, including at least temperature sensors, pressure sensors, vibration sensors, signal conditioning circuits, and data recorders; during the test, regularly record the characteristic parameter values under different aging conditions and any abnormal conditions.
[0016] Optionally, the elevator components that need to be subjected to aging tests include at least the traction machine, the door mechanism, and the control system.
[0017] Optionally, in step 1, the characteristic parameters include at least temperature, vibration, current, and voltage.
[0018] Optionally, in step 1, after obtaining the characteristic parameters, data preprocessing is also performed on the characteristic parameters, including data cleaning and data normalization, wherein data cleaning is used to remove outliers and process missing values, and data normalization is used to scale the characteristic parameters to the same scale to eliminate the influence of different dimensions on model training.
[0019] Optionally, in step 2, the structure of the BP neural network includes an input layer, a hidden layer and an output layer, wherein the input layer contains four neurons corresponding to the types of characteristic parameters, including temperature, vibration, current, and voltage, and the output layer contains the number of neurons corresponding to the output label, i.e., the aging state; the hidden layer adopts the ReLU activation function, and the output layer adopts the Softmax function; the optimization algorithm of the neural network adopts an adaptive learning rate algorithm.
[0020] Optionally, in step 3, the process of training the neural network model is:
[0021] Step 3.1, initialize the weights and biases in the BP neural network;
[0022] Step 3.2, using the aging status label as the classification label, it is divided into five labels: "Level 1 aging status", "Level 2 aging status", "Level 3 aging status", "Level 4 aging status" and "Level 5 aging status";
[0023] Step 3.3: The feature parameters in the preprocessed data are used as input and passed to the BP neural network; the data enters the hidden layer through the input layer, and the neurons in the hidden layer use the ReLU activation function to perform nonlinear transformation on the input; the output of the hidden layer is then passed to the output layer, and the output layer uses the Softmax function to calculate the probability of each aging state label; the loss between the probability distribution obtained by the output layer and the true label is calculated;
[0024] Step 3.4: Based on the gradient of the loss function, use the back propagation algorithm to calculate the gradient of each parameter in the network.
[0025] Step 3.5: Use the adaptive learning rate algorithm to update the weights and biases of the neural network according to the gradient;
[0026] Step 3.6: Repeat steps 3.3 to 3.5 until the preset training rounds are reached.
[0027] Optionally, the aging status levels of the various elevator components obtained in step 4 are divided into five levels, namely, "level 1 aging status", "level 2 aging status", "level 3 aging status", "level 4 aging status" and "level 5 aging status", with the aging degree increasing in ascending order.
[0028] Optionally, step 5 is also included, which is used to display information and provide graded warnings according to the aging status levels of various elevator components obtained in step 4, so as to remind maintenance personnel to handle the problem.
[0029] An elevator component aging status monitoring system, comprising:
[0030] The data acquisition module is used to design and implement the aging test of elevator components, simulate the long-term operation and wear process, and record the characteristic parameters of each component under different aging conditions during the test;
[0031] The initial model building module is used to use the BP neural network to determine the number of layers, activation function, and optimization algorithm of the neural network to build a neural network model for monitoring the aging status of elevator components;
[0032] The model training module is used to train the neural network model using the characteristic parameters as input features and the corresponding aging status as output labels, calculate the network output through forward propagation, and then adjust the network parameters using the back propagation algorithm to minimize the loss function and obtain the aging status assessment model;
[0033] The aging status assessment module is used to deploy the trained aging status assessment model into the elevator monitoring system, monitor the operating status of each elevator component in real time, assess the aging status of the elevator components, and output the aging status level of the elevator components.
[0034] It can be seen from the above technical solutions that the present invention provides a method and system for monitoring the aging status of elevator components, which have the following beneficial effects compared with the prior art:
[0035] (1) The present invention can detect potential aging risks in advance by real-time monitoring of the aging status of elevator components, and can display information and provide graded warnings, which helps staff to intervene in advance and take necessary maintenance measures to prevent failures and accidents caused by component aging, thereby improving the safety and reliability of the elevator.
[0036] (2) The aging status assessment model constructed by the BP neural network in the present invention can accurately assess the aging status of elevator components. The model realizes quantitative assessment of the aging status of elevator components by automatically learning the complex relationship between characteristic parameters and aging status. This provides scientific decision-making basis for staff and helps to formulate more reasonable and effective maintenance plans.
[0037] In summary, the elevator component aging status monitoring method and system proposed in the present invention can detect potential aging risks in advance, and have significant beneficial effects in improving the safety, reliability, intelligence level of elevators and reducing maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.
[0039] Figure 1 It is a schematic diagram of the method steps of the present invention;
[0040] Figure 2 It is a schematic diagram of the system module of the present invention;
[0041] Figure 3 Schematic diagram of the training process of the BP neural network model. DETAILED DESCRIPTION
[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0043] The embodiment of the present invention discloses a method for monitoring the aging status of elevator components, comprising the following steps:
[0044] Step 1: Design and implement an aging test for elevator components, simulating long-term operation and wear. During the test, record the characteristic parameters of each component under different aging conditions.
[0045] Among them, the elevator components that need to be subjected to aging tests should include those that have an important impact on the safety, performance and life of the elevator. These components are usually subjected to large mechanical stress, electrical stress or environmental stress. Therefore, the elevator components that need to be subjected to aging tests include at least the following devices:
[0046] Traction machine: The traction machine is the power source of the elevator, responsible for driving the elevator up and down. It contains key components such as motors, reducers, brakes, etc. These components are prone to wear, heat, poor lubrication and other problems during long-term operation. The aging test of the traction machine should simulate its actual operating conditions, including performance changes under different loads, speeds, operating time and other conditions.
[0047] Door mechanism: The door mechanism includes the elevator door and the hall door, and is responsible for controlling the opening and closing of the elevator door. The normal operation of the door mechanism is crucial to the safety of passengers. In the aging test, the door mechanism should be simulated to simulate the frequent opening and closing, impact, vibration and other working conditions to evaluate its durability and reliability.
[0048] Control system: The control system is responsible for receiving instructions, controlling the elevator operation and monitoring the elevator status. Electronic components, circuit boards, sensors and other components in the control system are easily affected by factors such as temperature, humidity, and electromagnetic interference, and may age or fail. Therefore, the control system also needs to undergo aging tests to evaluate its stability and reliability under different environmental conditions.
[0049] Safety components: Safety components are important components of elevators, including speed limiters, safety clamps, buffers, etc. These components can respond quickly and protect passengers when abnormal situations occur in the elevator. Therefore, special attention should be paid to the performance changes of these components in the aging test to ensure that they can still work reliably after long-term operation.
[0050] Suspension system: The suspension system includes wire ropes, rope end assemblies, pulleys and other components, which are used to connect the car and counterweight. The suspension system needs to withstand stresses such as tension, bending and vibration, and is prone to wear or breakage after long-term operation. Therefore, the suspension system is also the focus of aging tests.
[0051] Guide rails: The guide rails provide guidance for the movement of the car and counterweight. The wear of the guide rails will directly affect the smoothness and safety of the elevator operation. Therefore, the guide rails also need to be monitored and evaluated during the aging test.
[0052] During the aging test of elevator components, the characteristic parameters that need to be collected include at least the following aspects, which can reflect the performance changes of elevator components under different aging conditions:
[0053] Temperature parameters: Temperature sensors are used to monitor the temperature changes of elevator components during operation, especially the surface temperature of heat-generating components such as traction machines and control systems. Abnormally high temperatures may indicate problems such as wear, poor lubrication or electrical failure inside the components.
[0054] Vibration parameters: Vibration sensors are used to monitor the vibration of elevator components during operation. Abnormal vibrations may indicate loose components, increased wear or imbalance. By measuring vibration acceleration, the smoothness and safety of component operation can be evaluated.
[0055] Electrical parameters: Monitor changes in electrical parameters of elevator components, including current and voltage, through ammeters and voltmeters. Abnormal fluctuations in current and voltage may indicate problems such as aging of electrical components, poor contact or short circuits. These parameters are critical to evaluating the performance of electrical components such as control systems and traction machines.
[0056] Environmental parameters: The temperature and humidity changes of the test environment are monitored by a thermometer and hygrometer. Environmental parameters have an important influence on the aging process of elevator components, so they need to be strictly controlled during the test.
[0057] The aging test of elevator components includes the following processes:
[0058] Construct a test bench that simulates the actual working environment of the elevator, including at least simulating the elevator shaft, car, guide rail, and traction system, and use a loading device to simulate the elevator load condition, use a heater and humidifier to simulate different temperature and humidity conditions, and use a vibration table to simulate the vibration and impact of the elevator during operation;
[0059] According to the actual frequency of use of the elevator, set the number of cycles of the aging test, including the number of operations per day and the distance of each operation; simulate the wear process by controlling the loading weight and running speed;
[0060] Install a data acquisition system to record the changes in these characteristic parameters, including at least temperature sensors, pressure sensors, vibration sensors, signal conditioning circuits, and data recorders; during the test, regularly record the characteristic parameter values under different aging conditions and any abnormal conditions.
[0061] After obtaining the characteristic parameters, data preprocessing is also performed on the characteristic parameters, including data cleaning and data normalization, wherein data cleaning is used to remove outliers and process missing values, and data normalization is used to scale the characteristic parameters to the same scale to eliminate the influence of different dimensions on model training.
[0062] Step 2: Use BP neural network to determine the number of neural network layers, activation function, and optimization algorithm, and build a neural network model for monitoring the aging status of elevator components.
[0063] Specifically, the structure of the BP neural network includes an input layer, a hidden layer, and an output layer. The input layer contains four neurons, corresponding to the types of characteristic parameters, including temperature, vibration, current, and voltage; the number of hidden layers needs to be determined through experiments to determine the best configuration. At the beginning, you can start with one or two hidden layers, each containing a certain number of neurons, and then gradually adjust according to the performance of the model; the output layer contains the number of neurons corresponding to the output label, that is, the aging state (that is, the degree of aging); the hidden layer uses the ReLU activation function, and the output layer uses the Softmax function; the optimization algorithm of the neural network uses an adaptive learning rate algorithm.
[0064] Step 3: Use the characteristic parameters as input features and the corresponding aging status as output labels to train the neural network model, calculate the network output through forward propagation, and then use the back propagation algorithm to adjust the network parameters to minimize the loss function and obtain the aging status assessment model.
[0065] The process of training the neural network model can be found in Figure 3 As shown:
[0066] Step 3.1, model initialization: initialize the weights and biases in the BP neural network;
[0067] Step 3.2, label classification: take the aging status label as the classification label, and divide it into five labels: "Level 1 aging status", "Level 2 aging status", "Level 3 aging status", "Level 4 aging status" and "Level 5 aging status";
[0068] Step 3.3, forward propagation: The feature parameters in the preprocessed data are used as input and passed to the BP neural network; the data enters the hidden layer through the input layer, and the hidden layer neurons use the ReLU activation function to perform nonlinear transformation on the input; the output of the hidden layer is then passed to the output layer, and the output layer uses the Softmax function to calculate the probability of each aging state label; the loss between the probability distribution obtained by the output layer and the true label is calculated;
[0069] Step 3.4, back propagation: According to the gradient of the loss function, use the back propagation algorithm to calculate the gradient of each parameter in the network;
[0070] Step 3.5, parameter update: Use the adaptive learning rate algorithm to update the weights and biases of the neural network according to the gradient;
[0071] Step 3.6, iterative optimization: Repeat steps 3.3 to 3.5 until the preset training rounds are reached.
[0072] Step 4. Deploy the trained aging status assessment model to the elevator monitoring system, monitor the operating status of each elevator component in real time, assess the aging status of the elevator components, and output the aging status level of the elevator components. The aging status level is divided into five levels: "Level 1 aging status", "Level 2 aging status", "Level 3 aging status", "Level 4 aging status" and "Level 5 aging status", and the aging degree increases in ascending order.
[0073] The elevator monitoring system collects real-time operation data through sensors installed on various elevator components, including the above-mentioned characteristic parameters such as temperature, vibration, current, and voltage, and cleans and normalizes the collected raw data to eliminate the influence of noise, outliers, and different dimensions on model evaluation. The preprocessed data is input into the aging status evaluation model, and the model calculates and outputs the aging status evaluation results of each component based on the input characteristics.
[0074] Furthermore, the method of this embodiment further includes step 5, which is used to display information and provide graded warnings according to the aging status levels of each elevator component obtained in step 4, and remind maintenance personnel to handle the problem. Specifically, the following implementation methods are adopted:
[0075] The elevator monitoring system continuously monitors the operating status of each elevator component in real time, and uses the aging status assessment model to evaluate the collected data. According to the model assessment results, the aging status level of each component is determined, and information is displayed and graded warnings are given. Among them, the information display can display the aging status level of each elevator component through the human-computer interaction interface of the elevator monitoring system. The interface can use charts, color coding, etc. to intuitively display the aging status of each component to intuitively reflect the aging degree and potential risks of the elevator components.
[0076] Different aging status levels correspond to different warning methods:
[0077] Level 1 aging state: Although in good condition, the system can record data and analyze it to provide a reference for preventive maintenance. No special warning is required at this time.
[0078] Level II aging status: The system issues a slight warning through the human-computer interaction interface, prompting staff to pay attention to the status of the component and recommends regular inspection or maintenance.
[0079] Level 3 aging status: The system issues a yellow warning to remind maintenance personnel that the component is close to the threshold that requires repair or replacement, and it is recommended to arrange a maintenance plan as soon as possible.
[0080] Level 4 aging status: The system issues an orange emergency warning, indicating that the component has entered a high-risk area and immediate measures are required, such as suspending the elevator operation for emergency repair or replacement.
[0081] Level 5 aging status: The system issues a red serious warning, indicating that the component has been seriously aged and may cause a failure or accident. The elevator must be stopped immediately and repaired or replaced immediately. At the same time, relevant personnel must be notified to ensure on-site safety.
[0082] In addition, the warning information can be sent to designated staff and managers via SMS, email, etc. to ensure timely communication and processing of the information. At the same time, the system can record the details of each warning and processing, providing a basis for subsequent maintenance management and data analysis.
[0083] The embodiment of the present invention further discloses an elevator component aging status monitoring system, comprising:
[0084] The data acquisition module is used to design and implement the aging test of elevator components, simulate the long-term operation and wear process, and record the characteristic parameters of each component under different aging conditions during the test;
[0085] The initial model building module is used to use the BP neural network to determine the number of layers, activation function, and optimization algorithm of the neural network to build a neural network model for monitoring the aging status of elevator components;
[0086] The model training module is used to train the neural network model using the characteristic parameters as input features and the corresponding aging status as output labels, calculate the network output through forward propagation, and then adjust the network parameters using the back propagation algorithm to minimize the loss function and obtain the aging status assessment model;
[0087] The aging status assessment module is used to deploy the trained aging status assessment model into the elevator monitoring system, monitor the operating status of each elevator component in real time, assess the aging status of the elevator components, and output the aging status level of the elevator components.
[0088] As for the system device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.
[0089] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0090] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for monitoring the aging status of elevator components, characterized in that: The following steps are involved: Step 1: Design and implement an aging test for elevator components, simulating long-term operation and wear. During the test, record the characteristic parameters of each component under different aging conditions; Step 2: Using BP neural network, determine the number of layers, activation function, and optimization algorithm of the neural network, and construct a neural network model for monitoring the aging status of elevator components; Step 3: Use the characteristic parameters as input features and the corresponding aging status as output labels to train the neural network model, calculate the network output through forward propagation, and then use the back propagation algorithm to adjust the network parameters to minimize the loss function and obtain the aging status assessment model; Step 4: Deploy the trained aging status assessment model to the elevator monitoring system, monitor the operating status of each elevator component in real time, assess the aging status of the elevator components, and output the aging status level of the elevator components.
2. The elevator component aging status monitoring method according to claim 1, characterized in that: In step 1, the aging test of elevator components includes the following processes: Construct a test bench that simulates the actual working environment of the elevator, including at least simulating the elevator shaft, car, guide rail, and traction system, and use a loading device to simulate the elevator load condition, use a heater and humidifier to simulate different temperature and humidity conditions, and use a vibration table to simulate the vibration and impact of the elevator during operation; According to the actual frequency of use of the elevator, set the number of cycles of the aging test, including the number of operations per day and the distance of each operation; simulate the wear process by controlling the loading weight and running speed; Install a data acquisition system to record the changes in these characteristic parameters, including at least temperature sensors, pressure sensors, vibration sensors, signal conditioning circuits, and data recorders; during the test, regularly record the characteristic parameter values under different aging conditions and any abnormal conditions.
3. The elevator component aging status monitoring method according to claim 1, characterized in that: The elevator components that need to undergo aging tests include at least the traction machine, door mechanism, and control system.
4. The elevator component aging status monitoring method according to claim 1, characterized in that: In step 1, the characteristic parameters include at least temperature, vibration, current, and voltage.
5. The elevator component aging status monitoring method according to claim 1, characterized in that: In the step 1, after obtaining the characteristic parameters, data preprocessing is also performed on the characteristic parameters, including data cleaning and data normalization, wherein data cleaning is used to remove outliers and process missing values, and data normalization is used to scale the characteristic parameters to the same scale to eliminate the influence of different dimensions on model training.
6. The elevator component aging status monitoring method according to claim 1, characterized in that: In step 2, the structure of the BP neural network includes an input layer, a hidden layer and an output layer, wherein the input layer contains four neurons corresponding to the types of characteristic parameters, including temperature, vibration, current, and voltage, and the output layer contains the number of neurons corresponding to the output label, i.e., the aging state; the hidden layer uses the ReLU activation function, and the output layer uses the Softmax function; the optimization algorithm of the neural network uses an adaptive learning rate algorithm.
7. The elevator component aging status monitoring method according to claim 6, characterized in that: In step 3, the process of training the neural network model is as follows: Step 3.1, initialize the weights and biases in the BP neural network; Step 3.2, using the aging status label as the classification label, it is divided into five labels: "Level 1 aging status", "Level 2 aging status", "Level 3 aging status", "Level 4 aging status" and "Level 5 aging status"; Step 3.3, the characteristic parameters in the preprocessed data are passed as input to the BP neural network; The data enters the hidden layer through the input layer, and the neurons in the hidden layer use the ReLU activation function to perform nonlinear transformation on the input; the output of the hidden layer is then passed to the output layer, and the output layer uses the Softmax function to calculate the probability of each aging state label; the loss between the probability distribution obtained by the output layer and the true label is calculated; Step 3.4: Based on the gradient of the loss function, use the back propagation algorithm to calculate the gradient of each parameter in the network. Step 3.5: Use the adaptive learning rate algorithm to update the weights and biases of the neural network according to the gradient; Step 3.6: Repeat steps 3.3 to 3.5 until the preset training rounds are reached.
8. The elevator component aging status monitoring method according to claim 1, characterized in that: The aging status levels of the various elevator components obtained in step 4 are divided into five levels, namely, "level 1 aging status", "level 2 aging status", "level 3 aging status", "level 4 aging status" and "level 5 aging status", with the aging degrees increasing in ascending order.
9. The elevator component aging status monitoring method according to claim 8, characterized in that: The method further includes step 5, which is used to display information and provide graded warnings according to the aging status levels of various elevator components obtained in step 4, so as to remind maintenance personnel to handle the problem.
10. An elevator component aging status monitoring system, characterized in that: include: The data acquisition module is used to design and implement the aging test of elevator components, simulate the long-term operation and wear process, and record the characteristic parameters of each component under different aging conditions during the test; The initial model building module is used to use the BP neural network to determine the number of layers, activation function, and optimization algorithm of the neural network to build a neural network model for monitoring the aging status of elevator components; The model training module is used to train the neural network model using the characteristic parameters as input features and the corresponding aging status as output labels, calculate the network output through forward propagation, and then adjust the network parameters using the back propagation algorithm to minimize the loss function and obtain the aging status assessment model; The aging status assessment module is used to deploy the trained aging status assessment model into the elevator monitoring system, monitor the operating status of each elevator component in real time, assess the aging status of the elevator components, and output the aging status level of the elevator components.
