Method for predicting residual life of elevators in tropical and subtropical island regions

Abstract

The invention discloses a method for predicting the remaining life of an elevator in tropical and subtropical island regions. The method comprises the steps that environmental data and state data of key components in the operation process of the elevator in the tropical and subtropical island regions are obtained; wherein the state data comprises the electrical insulation performance and the corrosion degree of the metal part; preprocessing the environment data and the state data to obtain preprocessed data; an environment-equipment degradation model in the elevator running process is established; fault historical data in the elevator running process are introduced, and a fault prediction model is established; fusing the environment-equipment degradation model and the fault prediction model to construct a multivariate prediction model; predicting the preprocessed data through a multivariate prediction model to obtain a prediction result; and determining the elevator health state and the remaining life according to the prediction result. The rolling prediction of the remaining life of the elevator is realized through the multivariate prediction model, so that the method adapts to the change of an island extreme environment.

Description

Technical Field

[0001] The invention belongs to the technical field of elevator life prediction, and in particular relates to a method for predicting the remaining life of elevators in tropical and subtropical island areas. Background Art

[0002] In tropical and subtropical island regions, the normal operation of elevators is essential to ensure the daily travel of residents and tourists. Elevators in these areas are exposed to high temperature, high humidity and high salt environments for a long time, which pose severe challenges to the electrical components and mechanical structures of elevators. Existing elevator monitoring and maintenance technologies have been widely used in temperate regions. They mainly rely on regular inspections and fault response mechanisms to ensure the stable operation of equipment and the safety of passengers. These technologies can predict and diagnose potential problems of elevators to a certain extent, but their effectiveness may be limited under extreme climate conditions.

[0003] Although existing elevator prediction models have achieved certain results in temperate regions, they often fail to accurately reflect the actual situation when faced with the unique environmental conditions of islands. The combined effects of high humidity and salt spray lead to reduced insulation performance of elevator electrical components and accelerated corrosion of metal parts, which increase the uncertainty of failure. In addition, hot climate conditions also affect the stability of elevator operation, causing traditional fault diagnosis methods to lose reliability. Most existing prediction models are based on data from temperate regions and lack adaptability to the extreme environment of islands, making it difficult to accurately estimate the remaining life of elevators. Summary of the invention

[0004] To solve the above technical problems, the present invention proposes a method for predicting the remaining life of elevators in tropical and subtropical island areas, which comprehensively considers environmental factors and equipment status, and uses big data analysis and machine learning algorithms to accurately predict the remaining life of elevators in extreme environments, optimize maintenance strategies, extend equipment service life, and ensure passenger safety. This solution requires interdisciplinary cooperation and the application of innovative technologies to break through the limitations of traditional methods and provide an effective solution for elevator operation in extreme environments.

[0005] To achieve the above objectives, in a first aspect, the present invention provides a method for predicting the remaining life of an elevator in tropical and subtropical island areas, comprising:

[0006] Obtain environmental data and key component status data during elevator operation in tropical and subtropical island areas; wherein the status data includes: electrical insulation performance and degree of corrosion of metal components;

[0007] Preprocessing the environmental data and the state data to obtain preprocessed data;

[0008] Establish an environment-equipment degradation model during elevator operation;

[0009] Introduce the historical fault data during elevator operation and establish a fault prediction model;

[0010] The environment-equipment degradation model and the fault prediction model are integrated to construct a multivariate prediction model; the preprocessed data is predicted by the multivariate prediction model to obtain a prediction result; and the health status and remaining life of the elevator are determined according to the prediction result.

[0011] Prioritize obtaining environmental data and key component status data during elevator operation in tropical and subtropical island areas, including:

[0012] Collect environmental data in real time through sensors; wherein the environmental data includes: temperature, humidity and salt spray concentration;

[0013] The online monitoring system collects the status monitoring data of the elevator in real time during operation.

[0014] Preferably, preprocessing the environment data and the status data includes:

[0015] Cleaning the environment data and the status data, removing noise and outliers, and obtaining a clean data set;

[0016] Extract key features from the clean data set through feature extraction algorithms to obtain feature vectors that reflect equipment degradation and environmental impacts;

[0017] The correlation between the environmental data and the equipment status is determined through correlation analysis to judge the influence of various environmental factors on equipment degradation.

[0018] Prioritize the establishment of an environment-equipment degradation model during elevator operation including:

[0019] Use machine learning algorithms to fit the nonlinear relationship between environmental factors and device performance degradation;

[0020] By analyzing the correlation between environmental factors and equipment performance degradation data, the input characteristic variables and output target variables of the environment-equipment degradation model are determined.

[0021] Prioritize the introduction of fault history data during elevator operation and establish a fault prediction model including:

[0022] Acquire historical fault data of the elevator equipment; wherein the historical fault data includes operating parameters, fault modes and fault causes when the fault occurs;

[0023] Cleaning and feature extraction of the historical fault data, removing noise data, and selecting features to represent the device status;

[0024] According to the characteristics, the equipment status is represented and a deep learning algorithm is selected to build a fault prediction model.

[0025] In a second aspect, the present invention further provides a system for predicting the remaining life of elevators in tropical and subtropical island regions, comprising:

[0026] The data acquisition module is used to acquire environmental data and status data of key components during the operation of elevators in tropical and subtropical island areas; wherein the status data includes: electrical insulation performance and corrosion degree of metal components;

[0027] A data preprocessing module, used for preprocessing the environment data and the state data to obtain preprocessed data;

[0028] The first model building module builds the environment-equipment degradation model during elevator operation;

[0029] The second model building module introduces the historical fault data during the operation of the elevator to establish a fault prediction model;

[0030] The multivariate prediction module is used to integrate the environment-equipment degradation model and the fault prediction model to construct a multivariate prediction model; predict the preprocessed data through the multivariate prediction model to obtain a prediction result; and determine the health status and remaining life of the elevator according to the prediction result.

[0031] In a third aspect, the present invention further discloses a computer device, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the first aspect.

[0032] In a fourth aspect, the present invention further discloses a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method described in the first aspect when executed by a processor.

[0033] In a fifth aspect, the present invention further discloses a computer program product, including a computer program, which implements the steps of the method described in the first aspect when executed by a processor.

[0034] Compared with the prior art, the present invention has the following advantages and technical effects:

[0035] The present invention provides a method for predicting the remaining life of elevators in tropical and subtropical island areas. First, environmental data and status data of key components during the operation of elevators in tropical and subtropical island areas are obtained; wherein the status data include: electrical insulation performance and corrosion degree of metal components; secondly, the environmental data and status data are preprocessed to obtain preprocessed data; then, an environment-equipment degradation model during the operation of the elevator is established; further, historical fault data during the operation of the elevator is introduced to establish a fault prediction model; finally, the environment-equipment degradation model and the fault prediction model are integrated to construct a multivariate prediction model; the preprocessed data is predicted by the multivariate prediction model to obtain a prediction result; and the health status and remaining life of the elevator are determined according to the prediction result.

[0036] The data collected by the present invention can reflect the unique environmental conditions of tropical and subtropical island areas, and provide input data for the model under specific environments. The present invention can describe the impact of high humidity and salt spray on the degradation of insulation performance of elevator electrical components and the rusting of metal parts, as well as the impact of hot climate on the stability of elevator operation through the environment-equipment degradation model. The present invention captures the uncertainty of fault occurrence and improves the accuracy of prediction by introducing historical fault data during elevator operation. The present invention realizes a rolling prediction of the remaining life of the elevator through a multivariate prediction model, thereby adapting to changes in the extreme environment of the island. In addition, the technical solution of the present invention solves the limitations of existing prediction models in island environments and improves the reliability and safety of elevators. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0038] Figure 1 is a flow chart of a method according to an embodiment of the present invention;

[0039] Figure 2 Schematic diagram of a system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0041] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0042] Embodiment 1

[0043] like Figure 1 As shown, this embodiment provides a method for predicting the remaining life of elevators in tropical and subtropical island areas, including:

[0044] S1. Obtain environmental data and status data of key components during elevator operation in tropical and subtropical island areas; wherein the status data includes: electrical insulation performance and corrosion degree of metal components;

[0045] Furthermore, the environmental data and key component status data obtained during the operation of elevators in tropical and subtropical island areas include:

[0046] Collect environmental data in real time through sensors; wherein the environmental data includes: temperature, humidity and salt spray concentration;

[0047] The online monitoring system collects the status monitoring data of the elevator in real time during operation.

[0048] Specifically, according to the operating status of the elevator, the temperature data, humidity data and salt spray concentration data of the elevator operating environment are collected in real time through the temperature sensor, humidity sensor and salt spray concentration sensor.

[0049] For example, in an elevator deployed on an island, the temperature sensor can monitor the temperature of the machine room in real time. Assuming that the temperature detected at a certain moment is 35 degrees Celsius, which is slightly higher than the temperature range suitable for the elevator to operate, it can be inferred that the temperature at that moment is high and there is a risk of long-term high-temperature operation. The humidity sensor monitors the air humidity. For example, the reading is 85%, which is a typical manifestation of the humid environment on the island. The salt spray concentration sensor can monitor the salt content in the air. For example, the measured value is 50 mg per cubic meter. This high value indicates that the elevator has been in a high salt spray environment for a long time, and there is a risk of accelerated corrosion of elevator components. The monitoring of these three indicators together constitutes the basis for elevator monitoring in the island environment.

[0050] The sensor will collect data at a set frequency, for example, every 5 seconds, to ensure the real-time nature of the data. Through the built-in wireless transmission module, such as the narrowband Internet of Things module, it can provide stable and reliable data transmission in various environments with its advantages of wide coverage, multiple connections, low speed, low cost, low power consumption, and excellent architecture, and send the collected data to the remote data processing center. The data transmission frequency needs to be reasonably controlled. Too low a data frequency cannot detect data changes, which is not conducive to the rapid identification of abnormal data. Too high a transmission frequency will consume more power, which is not conducive to achieving low power consumption requirements.

[0051] Specifically, the status monitoring data of key elevator components, including electrical insulation performance, metal corrosion degree, etc., are collected in real time through the online monitoring system. For example, electrical insulation performance can be measured in real time by an insulation resistance monitor installed in the elevator circuit, and the metal corrosion degree can be detected by an electrochemical corrosion sensor installed on the metal component.

[0052] S2, preprocessing the environment data and the state data to obtain preprocessed data;

[0053] Further, preprocessing the environment data and the status data includes:

[0054] Cleaning the environment data and the status data, removing noise and outliers, and obtaining a clean data set;

[0055] Extract key features from the clean data set through feature extraction algorithms to obtain feature vectors that reflect equipment degradation and environmental impacts;

[0056] The correlation between the environmental data and the equipment status is determined through correlation analysis to judge the influence of various environmental factors on equipment degradation.

[0057] Specifically, data cleaning refers to detecting and correcting errors. For example, if the temperature sensor reading is 100 degrees Celsius at a certain moment, this is obviously beyond the normal range and may be a one-time error. It needs to be marked as invalid data or replaced with a normal value at a nearby moment.

[0058] Since the sensor range may not be uniform, data normalization is required for subsequent algorithm processing. For example, temperature data, humidity data, and salt spray concentration data can be normalized according to different algorithms, such as using the minimum and maximum values ​​in the data to process the data proportionally to the range of zero to one. For example, when normalizing temperature data, the minimum temperature is 20 degrees and the maximum temperature is 40 degrees, then the normalized value of 35 degrees is 0.75. After this step, the values ​​of all parameters are within the range of zero to one, which is convenient for subsequent processing. After preprocessing, the data has a unified format and no obvious errors.

[0059] This embodiment also uses a clustering algorithm, such as a system clustering algorithm, to complete the automatic clustering processing of the data set by calculating the distance between different categories of data. Because each data has the attributes of these three dimensions, three typical modes may be identified after clustering: "high temperature, high humidity and high salt", "medium temperature, high humidity and high salt", and "low temperature, medium humidity and low salt". If the environment is changeable, the grouping type can be increased or decreased accordingly. Assume that the analysis obtains data groups of three typical environmental types, such as data of the "high temperature, high humidity and high salt" type. The characteristic values ​​of this type of data are concentrated in temperatures above 30 degrees Celsius, humidity above 80%, and salt spray concentration above 40 mg per cubic meter. The "high temperature, high humidity and high salt" data group can become the basis for identifying the typical hot and humid environment of the island. Then, at any subsequent moment, if the real-time data of these three dimensions collected meet the characteristics of "high temperature, high humidity and high salt", it can be classified as this type of environmental state. The formed data set can be stored in a database, using various mainstream database management systems.

[0060] Specifically, the state data transmitted to the data center is preprocessed to remove outliers and noise data to obtain a clean data set. For example, after receiving a set of data, the data center will first perform an outlier detection and find that a certain electrical insulation resistance value is abnormally low to 0.1 megohms, which is significantly lower than the normal range. It may be a sensor failure or temporary interference, and the system will remove it. Then, noise filtering is performed, and the data is smoothed using a sliding average or Kalman filter algorithm to finally obtain a clean data set.

[0061] S3. Establish an environment-equipment degradation model during elevator operation;

[0062] Furthermore, establishing the environment-equipment degradation model during elevator operation includes:

[0063] Use machine learning algorithms to fit the nonlinear relationship between environmental factors and device performance degradation;

[0064] By analyzing the correlation between environmental factors and equipment performance degradation data, the input characteristic variables and output target variables of the environment-equipment degradation model are determined.

[0065] Specifically, in the process of establishing a nonlinear mathematical model that describes the relationship between environmental factors and equipment performance degradation, it is first necessary to understand the basic principles and application scenarios of various machine learning algorithms. Taking the decision tree as an example, it recursively splits the data set to find the features that best distinguish different categories or values, thereby building a tree model. The support vector machine (SVM) finds an optimal hyperplane so that the intervals between data points of different categories on the plane are maximized. The neural network simulates the way the human brain processes information through a multi-layer neuron structure and nonlinear activation functions to capture complex nonlinear relationships.

[0066] In the specific implementation, it is assumed that there is a set of environmental parameter data, including temperature, humidity, vibration frequency, etc., as well as the corresponding equipment performance degradation data, such as equipment operating efficiency, wear degree, etc. First, through correlation analysis, it is found that temperature and humidity have a significant impact on equipment performance degradation, while vibration frequency has a smaller impact. Therefore, temperature and humidity are determined as the input characteristic variables of the model, and equipment operating efficiency is determined as the output target variable.

[0067] The data is normalized, for example, the temperature range from -20℃ to 50℃ is normalized to between 0 and 1, and the humidity range from 30% to 90% is normalized to between 0 and 1, to eliminate the influence of different dimensions on model training. Then, the cross-validation method is used to divide the data set into a training set and a test set, assuming that the training set accounts for 70% and the test set accounts for 30%.

[0068] In the model training phase, the decision tree algorithm was used, and the maximum depth was set to 5 to avoid overfitting. Through the training set data, the model learned the changing pattern of equipment operating efficiency under different temperature and humidity conditions. Similarly, the SVM algorithm was used, and the radial basis function (RBF) was selected as the kernel function. By optimizing the parameters, the error of the model on the training set was minimized.

[0069] Input the test set data into the trained model and compare the predicted value of equipment operating efficiency output by the model with the actual value. For example, the actual operating efficiency of a test sample is 0.85, the model predicted value is 0.83, and the calculated prediction error is 2%. By calculating the prediction error and determination coefficient (R 2 ), evaluate the model's fitting effect and generalization ability. Assume that R 2 The R of the optimized model on the test set is 0.92, which means that the model can explain 92% of the device performance degradation changes. According to the evaluation results, the model is optimized. For example, the maximum depth of the decision tree is adjusted to 7, or different SVM kernel functions, such as the polynomial kernel function, are tried to improve the fitting accuracy of the model. 2 The prediction error was reduced to 1.5% and the optimized model was applied to the actual scenario. When new environmental factors were input, such as temperature of 35°C and humidity of 70%, the model automatically output a predicted value of 0.82 for the equipment operating efficiency, indicating that the equipment may be slightly degraded and recommending preventive maintenance.

[0070] By continuously collecting online monitoring data and updating the model regularly, we can adapt to the dynamic changes in the relationship between environmental factors and equipment degradation. For example, after half a year of operation, we found that the impact of temperature on equipment degradation in the new data was weakened, while the impact of humidity was strengthened. We retrained the model and adjusted the feature weights to make the model R 2Maintaining above 0.95 ensures the stability and practical value of the prediction effect. Through the above steps, not only an accurate environment-equipment degradation prediction model is established, but also a quantitative basis is provided for equipment maintenance and fault prevention, which improves the reliability and operation efficiency of the equipment. The meticulous implementation and optimization of each step ensures the adaptability and prediction accuracy of the model under different environmental conditions, and provides strong technical support for the equipment management of enterprises.

[0071] S4. Introduce the fault history data during the operation of the elevator and establish a fault prediction model;

[0072] Furthermore, the fault history data during the operation of the elevator is introduced to establish a fault prediction model including:

[0073] Acquire historical fault data of the elevator equipment; wherein the historical fault data includes operating parameters, fault modes and fault causes when the fault occurs;

[0074] Cleaning and feature extraction of the historical fault data, removing noise data, and selecting features to represent the device status;

[0075] According to the characteristics, the equipment status is represented and a deep learning algorithm is selected to build a fault prediction model.

[0076] Specifically, the historical fault data of the equipment is obtained, including the operating parameters, fault mode and fault cause when the fault occurs, to form a fault history data set; data preprocessing technology is used to clean and extract features of the fault history data, remove noise data, and select appropriate features to represent the equipment status; a suitable deep learning algorithm, such as long short-term memory network (LSTM) or convolutional neural network (CNN), is selected to build a fault prediction model; the processed fault history data is divided into a training set and a test set, and the fault prediction model is trained using the training set data, and the model parameters are adjusted using the back propagation algorithm; the performance of the fault prediction model is evaluated on the test set, and the prediction effect of the model is measured using indicators such as accuracy, precision and recall, and the parameters are tuned; the trained fault prediction model is applied to online equipment monitoring, and equipment operation data is collected in real time to determine the health status of the equipment. When it is predicted that the equipment may fail, maintenance measures are taken in advance to avoid the occurrence of failures.

[0077] S5. Integrate the environment-equipment degradation model and the fault prediction model to construct a multivariate prediction model; predict the preprocessed data using the multivariate prediction model to obtain a prediction result; and determine the health status and remaining life of the elevator according to the prediction result.

[0078] Specifically, the environmental factor data and equipment status data during the operation of the elevator are obtained as the input data of the model; for example, the environmental factor data include temperature, humidity, vibration intensity, etc., and the equipment status data include motor current, car speed, door opening and closing times, etc. These data are collected in real time by sensors and transmitted to the data center for processing.

[0079] Based on the environmental factor data obtained, the environment-equipment degradation model is used to obtain the degradation of the equipment in the current environment; assuming that an elevator is operating in a high temperature and high humidity environment, the environment-equipment degradation model will evaluate the degradation rate of key elevator components such as motors and bearings based on historical data and empirical formulas. For example, the model may show that at 30°C and 80% humidity, the motor degradation rate is 15% faster than in a standard environment.

[0080] Based on the acquired equipment status data, a fault prediction model is used to determine the fault risk of the equipment in the current state; for example, by analyzing the fluctuation of the motor current through the long short-term memory network (LSTM) model, it is found that the current fluctuation amplitude is abnormally increased, and the model predicts that the probability of motor failure is 20%. At the same time, the abnormal fluctuation of the car speed may also be captured by the convolutional neural network (CNN) model to further confirm the fault risk.

[0081] The output of the environment-equipment degradation model and the output of the fault prediction model are integrated to build a multivariate prediction model that comprehensively considers environmental factors and equipment status; for example, the fusion model may use a weighted average method to combine the environmental degradation rate and the fault risk probability to obtain a comprehensive equipment health score. Assuming the environmental degradation score is 0.7 and the fault risk score is 0.3, the comprehensive score may be 0.5, indicating that the equipment is in a medium health state.

[0082] The parameters of the multivariate prediction model are adjusted and optimized in a dynamic update manner according to the real-time operation data of the elevator. For example, the model initially sets the temperature weight to 0.4 and the humidity weight to 0.3. However, through real-time data analysis, it is found that humidity has a greater impact on equipment degradation. Therefore, the humidity weight is adjusted to 0.4 and the temperature weight to 0.3, so that the model can more accurately reflect the actual situation.

[0083] The optimized multivariate prediction model is used to predict the remaining life of the elevator and obtain the remaining service time of the elevator in the current state. For example, based on the current comprehensive health score and historical data, the model predicts that the elevator can still operate normally for 8,000 hours in the current state. This prediction result can help property companies formulate maintenance plans and avoid sudden failures.

[0084] According to the predicted remaining life of the elevator, the rolling prediction method is adopted to regularly update the remaining life prediction results of the elevator, providing a decision-making basis for the maintenance and update of the elevator. For example, the prediction is updated once a quarter, and the remaining life of the elevator is re-evaluated based on the latest operating data and model parameters. Assuming that the remaining life was predicted to be 8,000 hours last time, after one quarter of operation, the new prediction result shows that the remaining life is 7,500 hours. This change prompts the maintenance personnel to strengthen inspection and maintenance. In this way, the maintenance and update decisions of the elevator are no longer based on experience and intuition, but on the analysis results of data and models, which greatly improves the scientificity and accuracy of the decision. The comprehensive consideration of environmental factors and equipment status enables the prediction model to more comprehensively reflect the actual operation of the elevator, and the dynamic update and rolling prediction ensure the timeliness and reliability of the prediction results. In the end, the application of this multivariate prediction model not only extends the service life of the elevator, but also reduces maintenance costs and improves the reliability and safety of elevator operation.

[0085] In this embodiment, it is determined whether the predicted remaining life is lower than a preset threshold. If so, an early warning message is triggered and pushed to maintenance personnel. The maintenance personnel formulate a targeted maintenance plan based on the early warning information and health status assessment results, combined with the elevator's service life and historical maintenance records. The elevator is maintained and repaired according to the maintenance plan to eliminate potential fault hazards, improve equipment reliability, and extend the elevator's service life.

[0086] Embodiment 2

[0087] like Figure 2 As shown, based on the same inventive concept, this embodiment provides a system for predicting the remaining life of elevators in tropical and subtropical island areas, including:

[0088] The data acquisition module is used to acquire environmental data and status data of key components during the operation of elevators in tropical and subtropical island areas; wherein the status data includes: electrical insulation performance and corrosion degree of metal components;

[0089] A data preprocessing module, used for preprocessing the environment data and the state data to obtain preprocessed data;

[0090] The first model building module builds the environment-equipment degradation model during elevator operation;

[0091] The second model building module introduces the historical fault data during the elevator operation process to establish a fault prediction model;

[0092] The multivariate prediction module is used to integrate the environment-equipment degradation model and the fault prediction model to construct a multivariate prediction model; predict the preprocessed data through the multivariate prediction model to obtain a prediction result; and determine the health status and remaining life of the elevator according to the prediction result.

[0093] The remaining life prediction system for elevators in tropical and subtropical island regions provided by this embodiment has all the advantages of the remaining life prediction method for elevators in tropical and subtropical island regions provided by the first embodiment.

[0094] Embodiment 3

[0095] This embodiment further discloses a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the first embodiment.

[0096] Embodiment 4

[0097] This embodiment further discloses a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in the first embodiment are implemented.

[0098] Embodiment 5

[0099] This embodiment also discloses a computer program product, including a computer program, which implements the steps of the method described in the first embodiment when executed by a processor.

[0100] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for predicting the remaining life of elevators in tropical and subtropical island areas, characterized in that: The following steps are involved: Obtain environmental data and key component status data during elevator operation in tropical and subtropical island areas; wherein the status data includes: electrical insulation performance and degree of corrosion of metal components; Preprocessing the environmental data and the state data to obtain preprocessed data; Establish an environment-equipment degradation model during elevator operation; Introduce the historical fault data during elevator operation and establish a fault prediction model; The environment-equipment degradation model and the fault prediction model are integrated to construct a multivariate prediction model; the preprocessed data is predicted by the multivariate prediction model to obtain a prediction result; and the health status and remaining life of the elevator are determined according to the prediction result.

2. The method according to claim 1, characterized in that Obtaining environmental data and key component status data during elevator operation in tropical and subtropical island areas includes: Collect environmental data in real time through sensors; wherein the environmental data includes: temperature, humidity and salt spray concentration; The online monitoring system collects the status monitoring data of the elevator in real time during operation.

3. The method according to claim 1, characterized in that Preprocessing the environment data and the status data includes: Cleaning the environment data and the status data, removing noise and outliers, and obtaining a clean data set; Extract key features from the clean data set through feature extraction algorithms to obtain feature vectors that reflect equipment degradation and environmental impacts; The correlation between the environmental data and the equipment status is determined through correlation analysis to judge the influence of various environmental factors on equipment degradation.

4. The method according to claim 1, characterized in that: Establishing the environment-equipment degradation model during elevator operation includes: Use machine learning algorithms to fit the nonlinear relationship between environmental factors and device performance degradation; By analyzing the correlation between environmental factors and equipment performance degradation data, the input characteristic variables and output target variables of the environment-equipment degradation model are determined.

5. The method according to claim 1, characterized in that Introducing the fault history data during elevator operation and establishing a fault prediction model include: Acquire historical fault data of the elevator equipment; wherein the historical fault data includes operating parameters, fault modes and fault causes when the fault occurs; Cleaning and feature extraction of the historical fault data, removing noise data, and selecting features to represent the device status; According to the characteristics, the equipment status is represented and a deep learning algorithm is selected to build a fault prediction model.

6. A system for predicting the remaining life of elevators in tropical and subtropical island areas, characterized in that: include: The data acquisition module is used to acquire environmental data and status data of key components during the operation of elevators in tropical and subtropical island areas; wherein the status data includes: electrical insulation performance and corrosion degree of metal components; A data preprocessing module, used for preprocessing the environment data and the state data to obtain preprocessed data; The first model building module builds the environment-equipment degradation model during elevator operation; The second model building module introduces the historical fault data during the operation of the elevator to establish a fault prediction model; The multivariate prediction module is used to integrate the environment-equipment degradation model and the fault prediction model to construct a multivariate prediction model; predict the preprocessed data through the multivariate prediction model to obtain a prediction result; and determine the health status and remaining life of the elevator according to the prediction result.

7. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images