Intelligent operation and maintenance system for platform door

Abstract

The invention discloses an intelligent operation and maintenance system for a platform door, and relates to the technical field of intelligent operation and maintenance of rail transit, which comprises the following steps of: acquiring real-time operation data and preprocessing, and extracting and storing the characteristics of the operation data; constructing a fault prediction model, training the fault prediction model by using the operation data features, and generating a trained fault prediction model; inputting the real-time operation data into the trained fault prediction model, generating early warning information, and sending the early warning information to the distributed intelligent diagnosis system; the distributed intelligent diagnosis system identifies an Internet of Things node needing to be diagnosed according to the early warning information, and the Internet of Things node performs preliminary diagnosis on the collected data according to a preset rule to generate a preliminary diagnosis result; according to the method, the model parameters are dynamically adjusted according to the actual fault processing result, the system performance is continuously optimized, the adaptability and stability of the system are enhanced, the fault response speed is increased, the fault prediction accuracy is improved, and the false alarm rate is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent operation and maintenance of rail transit, and in particular to an intelligent operation and maintenance system for platform doors. Background Art

[0002] With the rapid development of urban rail transit, platform door systems, as key equipment for ensuring passenger safety and train operation efficiency, have become increasingly important. In recent years, with the continuous development of the Internet of Things, big data, and artificial intelligence technologies, platform door operation and maintenance have gradually moved towards intelligence. Some intelligent operation and maintenance systems, by installing sensors to collect equipment operating data, enable real-time monitoring and fault alarms for platform door systems, aiming to reduce maintenance costs, improve system reliability, and extend equipment life.

[0003] Existing intelligent platform door operation and maintenance systems have significant shortcomings in terms of fault prediction accuracy and in-depth fault diagnosis. First, the existing system's fault prediction models are mostly based on simple statistical analysis, which fails to fully utilize the complex characteristics of equipment operating data, resulting in low fault prediction accuracy. Second, the existing system lacks a distributed intelligent diagnostic mechanism for fault diagnosis, making it unable to quickly locate and accurately analyze faults. This results in long fault resolution times and impacts the normal operation of equipment. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent operation and maintenance system for platform doors to solve the problems of inaccurate fault prediction and shallow fault diagnosis.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, the present invention provides an intelligent operation and maintenance system for platform doors, which includes a data acquisition and processing module: collecting real-time operation data and preprocessing it, extracting and storing operation data features; a fault prediction model construction module: constructing a fault prediction model, using operation data features to train the fault prediction model, and generating a trained fault prediction model; a fault warning module: inputting real-time operation data into the trained fault prediction model, generating warning information, and sending the warning information to a distributed intelligent diagnosis system; an intelligent diagnosis module: the distributed intelligent diagnosis system identifies the Internet of Things nodes that need to be diagnosed based on the warning information, and the Internet of Things nodes perform preliminary diagnosis on the collected data according to preset rules to generate preliminary diagnosis results; a fault decision module: performing a comprehensive analysis of the preliminary diagnosis results, and determining the location and cause of the fault based on the comprehensive analysis results, and generating fault handling suggestions; an optimization closed-loop module: the fault prediction model dynamically adjusts model parameters according to the fault handling suggestions, retrains the fault prediction model using the updated parameters, and continues to use it for fault prediction to form a complete closed loop.

[0008] As a preferred solution of the platform door intelligent operation and maintenance system of the present invention, wherein: the real-time operation data includes electrical operation data, environmental operation data, mechanical operation data and control operation data;

[0009] The preprocessing includes smoothing and denoising;

[0010] The operating data characteristics include statistical characteristics, time series characteristics and frequency domain characteristics;

[0011] Store operational data features in a relational database.

[0012] As a preferred solution of the platform door intelligent operation and maintenance system of the present invention, wherein: the fault prediction model is constructed, the fault prediction model is trained using the operation data features to generate a trained fault prediction model, and the specific steps are as follows:

[0013] Select the support vector machine algorithm to build a fault prediction model and initialize the fault prediction model parameters;

[0014] Divide the running data features into training set and test set;

[0015] The fault prediction model adjusts its internal parameters based on the training set data;

[0016] Use the test set to verify the trained fault prediction model and generate verification results;

[0017] According to the verification results, the grid search method is used to optimize the fault prediction model parameters to generate a trained fault prediction model.

[0018] As a preferred solution of the platform door intelligent operation and maintenance system described in the present invention, wherein: inputting the real-time operation data into the trained fault prediction model to generate early warning information and sending the early warning information to the distributed intelligent diagnosis system, the specific steps are as follows,

[0019] Load the trained fault prediction model, input the real-time operation data features into the fault prediction model, and calculate the probability P of fault occurrence;

[0020] Define the fault probability threshold Y. When P>Y, trigger a warning and generate early warning information;

[0021] When P<Y, it is considered that the operation state of the current device is stable;

[0022] Package the early warning information into JSON format and send the early warning information to the distributed diagnosis system through the MQTT protocol.

[0023] As a preferred solution of the platform door intelligent operation and maintenance system described in the present invention, wherein: the distributed intelligent diagnosis system identifies the Internet of Things nodes that need to be diagnosed according to the early warning information, the specific steps are as follows,

[0024] The early warning information includes the fault type, the expected occurrence time, the affected components, and the severity of the fault;

[0025] The distributed intelligent diagnosis system receives the early warning information through the MQTT protocol and analyzes the early warning information;

[0026] Based on the analyzed early warning information and combined with the pre-defined mapping relationship between components and nodes, the intelligent diagnosis system identifies the Internet of Things nodes related to the early warning information.

[0027] As a preferred solution of the platform door intelligent operation and maintenance system described in the present invention, wherein: the Internet of Things node conducts a preliminary diagnosis on the collected data according to the preset rules to generate a preliminary diagnosis result, the specific steps are as follows,

[0028] The preset rules include threshold rules, combination rules, pattern matching rules, time series rules, and anomaly detection rules;

[0029] The Internet of Things node collects the operation data of the platform door and key components in real time and extracts the operation data features;

[0030] Conduct a preliminary diagnosis on the operation data features according to the preset rules to generate a preliminary diagnosis result, and send the preliminary diagnosis result to the central diagnosis system.

[0031] As a preferred solution of the platform door intelligent operation and maintenance system described in the present invention, wherein: comprehensively analyze the preliminary diagnosis result, the specific steps are as follows,

[0032] The central diagnostic system collects the preliminary diagnostic results of each IoT node and analyzes the correlation between the preliminary diagnostic results;

[0033] Identify the fault mode based on the fault manifestations in the preliminary diagnosis results;

[0034] Through comparative analysis, real-time operating data is compared with historical normal operating data to identify data points that significantly deviate from the normal range;

[0035] Through correlation analysis, we explore whether the current anomaly between different types of data is accompanied by temperature rise and whether the change in vibration frequency is associated with a specific operation cycle.

[0036] As a preferred solution of the platform door intelligent operation and maintenance system of the present invention, wherein: the location and cause of the fault are determined based on the comprehensive analysis results, and fault handling suggestions are generated. The specific steps are as follows:

[0037] Based on the comprehensive analysis results, narrow down the source of the fault and identify the location and cause of the problem;

[0038] Infer the cause of the failure based on the equipment failure mode and preliminary diagnosis results;

[0039] According to the severity of the fault, determine the urgency of the fault, formulate a maintenance plan based on the cause of the fault, and generate fault handling suggestions.

[0040] As a preferred solution of the platform door intelligent operation and maintenance system of the present invention, the fault prediction model dynamically adjusts the model parameters according to the fault handling suggestions. The specific steps are as follows:

[0041] Collect fault handling suggestions and actual repair results from the operation and maintenance management system, and organize the collected data into a structured form;

[0042] Analyze the deviation between the prediction results of the fault prediction model and the actual fault, and identify the fault prediction model parameters that need to be adjusted based on the results of the deviation analysis.

[0043] As a preferred solution of the platform door intelligent operation and maintenance system of the present invention, wherein: the updated parameters are used to retrain the fault prediction model and continue to be used for fault prediction to form a complete closed loop. The specific steps are as follows:

[0044] The sorted fault handling suggestions and repair result data are merged with historical data to form a new training dataset. The fault prediction model is retrained using the new training dataset and updated parameters.

[0045] The retrained fault prediction model is updated to the fault prediction system to replace the old fault prediction model, and new fault handling suggestions and repair results are collected regularly.

[0046] The beneficial effects of the present invention are as follows: the present invention uses a distributed intelligent diagnosis and comprehensive analysis mechanism to quickly and accurately locate the fault location, analyze the fault cause, and generate targeted processing suggestions, thereby improving operation and maintenance efficiency, dynamically adjusting model parameters through actual fault processing results, continuously optimizing system performance, enhancing the system's adaptability and stability, accelerating fault response speed, improving the accuracy of fault prediction, reducing false alarm rate, and reducing dependence on manual inspections, reducing operation and maintenance costs and work intensity, and ensuring the operational safety and efficiency of urban rail transit. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 This is a schematic diagram of an intelligent operation and maintenance system for platform doors in Example 1.

[0049] Figure 2 This is a flow chart of data collection and fault prediction in Example 1.

[0050] Figure 3 This is the distributed intelligent diagnosis flow chart in Example 1.

[0051] Figure 4 This is the optimized closed-loop flow chart in Example 1. DETAILED DESCRIPTION

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0053] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0054] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0055] Example 1, reference Figures 1 to 4 , which is the first embodiment of the present invention, provides an intelligent operation and maintenance system for platform doors, including the following steps:

[0056] Data acquisition and processing module: collects real-time operation data and performs preprocessing, extracts operation data features and stores them.

[0057] Real-time operation data includes electrical operation data, environmental operation data, mechanical operation data and control operation data;

[0058] It should be noted that electrical operation data refers to the current value of the platform door motor, the voltage value of the platform door motor, and the power consumption of the platform door motor; environmental operation data refers to the temperature of the platform door and its key components, the humidity of the platform door operating environment, and the air pressure of the platform door operating environment; mechanical operation data refers to the vibration frequency and amplitude of the platform door, the displacement data of the platform door, and the opening and closing speed of the platform door; control operation data refers to the input and output signals of the platform door control unit, the fault codes generated by the platform door control unit, and the opening and closing operation records of the platform door;

[0059] Preprocessing includes smoothing and denoising;

[0060] Operational data characteristics include statistical characteristics, time series characteristics, and frequency domain characteristics;

[0061] It should be noted that statistical features refer to mean, variance, standard deviation, maximum value and minimum value; time series features refer to autocorrelation coefficient, partial autocorrelation coefficient, moving average and exponentially weighted moving average; frequency domain features refer to Fourier transform and power spectral density;

[0062] Storing operational data features in a relational database;

[0063] It should be noted that data in a relational database is stored in the form of tables, each table has a fixed column structure, and tables can be associated with each other.

[0064] Fault prediction model construction module: Build a fault prediction model, use the operating data features to train the fault prediction model, and generate a trained fault prediction model.

[0065] Select the support vector machine algorithm to build a fault prediction model and initialize the fault prediction model parameters;

[0066] It should be noted that the support vector machine algorithm is a supervised learning algorithm that is widely used in classification and regression tasks. In fault prediction, it is particularly suitable for processing high-dimensional data and can effectively handle nonlinear problems. The fault prediction model parameters refer to the kernel function type, regularization parameter C, and kernel function parameter γ.

[0067] Divide the running data features into training set and test set;

[0068] It should be noted that the operational data features are divided into training and test sets in a ratio of 8:2;

[0069] The fault prediction model adjusts its internal parameters based on the training set data;

[0070] It should be noted that the optimization algorithm (such as gradient descent and sequential minimum optimization (SMO)) will adjust the internal parameters of the model according to the training set data to find the optimal parameter combination, and the optimization algorithm will update the parameters of the model in each iteration;

[0071] Use the test set to verify the trained fault prediction model and generate verification results;

[0072] It should be noted that the test set is used to evaluate the performance of the fault prediction model on unseen data, thereby verifying the model's generalization ability. The fault prediction model will output the fault probability or fault category based on the feature data in the test set. The verification results usually include the model's accuracy, recall rate, and F1 score.

[0073] According to the verification results, the grid search method is used to optimize the fault prediction model parameters to generate a trained fault prediction model;

[0074] It should be noted that the grid search method is a commonly used parameter optimization method. By traversing the predefined parameter grid, the parameter combination that optimizes the model performance is found, and the fault prediction model is retrained using the optimal parameter combination. This training uses the entire training set to ensure that the fault prediction model fully utilizes all available data to generate the final fault prediction model.

[0075] Fault warning module: inputs real-time operation data into the trained fault prediction model, generates warning information, and sends the warning information to the distributed intelligent diagnosis system.

[0076] Load the trained fault prediction model and input the real-time operation data features into the fault prediction model. The fault prediction model calculates the fault occurrence probability P, which is expressed as:

[0077]

[0078] Among them, P is the failure probability, x represents the sample, f(x) is the decision function, which is used to represent the distance from the sample x to the decision boundary, α is the scaling parameter, which is used to adjust the sensitivity of the decision function output, usually α = 0.5, and β is the scaling parameter, which is used to adjust the offset of the probability curve;

[0079] f(x) = w·x + b;

[0080] Among them, w is the normal vector of the hyperplane, which is used to determine the direction of the hyperplane, and b is the bias term of the hyperplane, which is used to determine the position of the hyperplane;

[0081] It should be noted that the trained fault prediction model is usually saved as a file for loading and use in the subsequent prediction stage. The purpose of loading the fault prediction model is to restore the trained model parameters and structure to the current running environment so that it can perform fault prediction on new data;

[0082] Define the fault probability threshold Y. When P > Y, a warning is triggered and a warning message is generated;

[0083] When P < Y, it is considered that the current operating state of the device is stable;

[0084] It should be noted that the fault probability threshold is used to determine when to trigger a fault warning. The selection of this threshold needs to comprehensively consider factors such as the performance of the model, business requirements, and the costs of false alarms and missed alarms. By evaluating the performance of the model on the validation set, a threshold that can balance accuracy and recall is selected. A false alarm means that the model incorrectly predicts a fault, while a missed alarm means that the model fails to predict an actually occurring fault. If the cost of false alarms is high, a higher threshold can be selected to reduce false alarms; if the cost of missed alarms is high, a lower threshold can be selected to reduce missed alarms; when P > Y, it is considered that the device has a high fault risk and a warning needs to be triggered. When P < Y, it is considered that the current operating state of the device is stable and there is no obvious fault risk. In this case, the operating state of the device will continue to be monitored and the fault probability will be calculated regularly to ensure that any state changes can be captured in a timely manner;

[0085] The warning message is encapsulated in JSON format and sent to the distributed diagnostic system through the MQTT protocol;

[0086] It should be noted that JSON is a lightweight data exchange format that is easy to read and write, and is also easy for machines to parse and generate; MQTT is a lightweight message transmission protocol that is widely used in the field of Internet of Things. It supports message publishing and subscription between devices, and has the characteristics of low bandwidth, high reliability and easy implementation; when sending early warning information, it is necessary to first establish a connection with the MQTT proxy server, and then publish the early warning information in JSON format to the specified MQTT topic, and the distributed diagnostic system needs to subscribe to the relevant MQTT topic, so that it can receive and process these early warning information in real time, and finally confirm the delivery of the message.

[0087] Intelligent diagnosis module: The distributed intelligent diagnosis system identifies the IoT nodes that need to be diagnosed based on the early warning information. The IoT nodes perform preliminary diagnosis on the collected data according to preset rules and generate preliminary diagnosis results.

[0088] Warning information includes fault type, expected occurrence time, affected components and fault severity;

[0089] It should be noted that the fault type refers to the specific manifestation of the fault, including abnormal current, temperature, vibration, and displacement. The expected time of occurrence refers to the specific time point when the fault is predicted to occur, including the time format and time range. The fault severity refers to the impact of the fault on the operation and stability of the equipment, which is usually divided into three ranges: "low", "medium", and "high". The affected equipment components include "motor", "controller", "sensor", etc.

[0090] The distributed intelligent diagnosis system receives warning information through the MQTT protocol and analyzes the warning information;

[0091] It should be noted that the received warning information is data encapsulated in JSON format. The distributed intelligent diagnosis system needs to use parsing tools to parse this data and extract fields such as fault type, expected occurrence time, and fault severity.

[0092] Based on the parsed warning information and the predefined mapping relationship between components and nodes, the intelligent diagnosis system identifies the IoT nodes related to the warning information;

[0093] It should be noted that in the distributed intelligent diagnosis system, a mapping relationship is pre-defined to associate device components with IoT nodes. This mapping relationship is usually a table or database that records the IoT node information corresponding to each component. This mapping relationship can quickly locate the IoT node related to the warning information. The distributed intelligent diagnosis system identifies the IoT node related to the warning information based on the "affected component" field in the parsed warning information and the pre-defined mapping relationship.

[0094] Preset rules include threshold rules, combination rules, pattern matching rules, time series rules and anomaly detection rules;

[0095] It should be noted that the threshold rule is to judge whether there is an anomaly based on the threshold of a specific feature. If the feature value exceeds the set threshold, it is considered that there may be a fault, including the current threshold, temperature change rate threshold and vibration frequency threshold; the combination rule is to combine multiple features for comprehensive judgment. If multiple features meet specific conditions at the same time, it is considered that there may be a fault. For example, if the current and temperature exceed the threshold at the same time, it is considered that there may be a serious overload; the pattern matching rule is to identify specific data patterns, such as periodic fluctuations, mutations, etc. If a specific pattern appears in the data, it is considered that there may be a fault, including periodic fluctuations and mutation detection; the time series rule is to analyze the time series trend of the data, such as continuous rise or fall. If the time series trend of the data is abnormal, it is considered that there may be a fault; the anomaly detection rule is to identify outliers in the data, such as sudden changes in current or temperature. If anomalies appear in the data, it is considered that there may be a fault;

[0096] The IoT nodes collect the operating data of platform doors and key components in real time and extract the operating data features;

[0097] Perform preliminary diagnosis on the operation data characteristics according to preset rules, generate preliminary diagnosis results, and send the preliminary diagnosis results to the central diagnosis system;

[0098] It should be noted that the preliminary diagnostic results usually include diagnostic status, such as "normal", "abnormal current", "abnormal temperature", "vibration problem", etc., and related data, such as the average current, the rate of change of temperature, the frequency of vibration, etc. The IoT node encapsulates the preliminary diagnostic results into JSON format and sends it to the central diagnostic system through the MQTT protocol.

[0099] Fault decision module: conducts a comprehensive analysis of the preliminary diagnosis results, determines the location and cause of the fault based on the comprehensive analysis results, and generates fault handling suggestions.

[0100] The central diagnostic system collects the preliminary diagnostic results of each IoT node and analyzes the correlation between the preliminary diagnostic results;

[0101] Identify the fault mode based on the fault manifestations in the preliminary diagnosis results;

[0102] It should be noted that the fault manifestation refers to the specific description of the potential problem determined by the IoT node based on preset rules, including abnormal current, abnormal temperature, abnormal vibration, and abnormal displacement. The fault manifestation is extracted from the preliminary diagnosis results and matched with the known fault mode. If the preliminary diagnosis results mention "abnormal current", the matched fault mode may be "excessive current" or "current fluctuation". Based on the matching results, a specific fault mode description is generated. If multiple nodes report "abnormal current", the generated fault mode description may be "power supply system failure"; if a node reports "abnormal temperature" and "vibration problem", the generated fault mode description may be "mechanical component overload";

[0103] Through comparative analysis, real-time operating data is compared with historical normal operating data to identify data points that significantly deviate from the normal range;

[0104] It should be noted that real-time operation data refers to the device operation status data collected from the IoT node at the current moment, and historical normal operation data refers to the historical data accumulated when the device was in normal operation. Comparative analysis usually includes data alignment to ensure that the real-time operation data and historical normal operation data are aligned in time, sampling frequency and data format; calculating the difference, for each data point, calculating the difference between the real-time operation data and the historical normal operation data; setting a threshold, based on the statistical characteristics of the historical data; identifying abnormal point data, if the difference of a data point exceeds the set threshold, the data point is considered to have significantly deviated from the normal range;

[0105] Through correlation analysis, we explore whether current anomalies between different types of data are accompanied by temperature increases, and whether changes in vibration frequency are associated with specific operating cycles;

[0106] It should be noted that correlation analysis is a data analysis method used to explore the relationship between different variables. In intelligent operation and maintenance systems, correlation analysis can help identify potential connections between different operating data features, thereby more comprehensively understanding the operating status and potential faults of the equipment. During equipment operation, excessive current or current fluctuations may affect the temperature of the equipment. By collecting current and temperature data and calculating the correlation between them, it can be determined whether the current anomaly is accompanied by a temperature rise. The vibration frequency of the equipment may be related to a specific operating cycle (such as the start, stop, acceleration, deceleration, etc. of the equipment). By collecting vibration frequency data and operating cycle data and using time series analysis methods, it can be determined whether the change in vibration frequency is associated with a specific operating cycle.

[0107] Based on the comprehensive analysis results, narrow down the source of the fault and identify the location and cause of the problem;

[0108] Infer the cause of the failure based on the equipment failure mode and preliminary diagnosis results;

[0109] It should be noted that if "abnormal current" occurs and the device has a history of overload, it is because the load is too large, resulting in excessive current. If "abnormal temperature" is accompanied by "vibration problems", it is because the mechanical components are loose or worn, resulting in poor heat dissipation. If voltage fluctuations occur at multiple nodes at the same time, it is a power supply problem.

[0110] Determine the urgency of the fault based on its severity, formulate a maintenance plan based on the cause of the fault, and generate fault handling suggestions;

[0111] It should be noted that troubleshooting recommendations include maintenance time, components that need to be checked, parts that need to be replaced, parameter adjustments, and cleaning. If the fault involves multiple components, the repair sequence needs to be coordinated to ensure that the repair process is efficient and orderly.

[0112] Optimization closed-loop module: The fault prediction model dynamically adjusts model parameters based on fault handling suggestions, uses the updated parameters to retrain the fault prediction model, and continues to use it for fault prediction, forming a complete closed loop.

[0113] Collect fault handling suggestions and actual repair results from the operation and maintenance management system, and organize the collected data into a structured form;

[0114] It should be noted that the operation and maintenance management system is a system used to record and manage equipment operation and maintenance information. Actual maintenance results include actual maintenance time, replaced parts, and equipment status after maintenance. Structured data is usually stored in a table format, with each row representing a record and each column representing an attribute, to facilitate subsequent data analysis and model optimization.

[0115] Analyze the deviation between the prediction results of the fault prediction model and the actual fault, and identify the fault prediction model parameters that need to be adjusted based on the results of the deviation analysis;

[0116] It should be noted that the accuracy of the fault prediction model is identified by comparing its prediction results with the actual fault conditions. The grid search method is used to adjust the parameters. The grid search method is a commonly used parameter optimization method that traverses a predefined parameter grid to find the parameter combination that optimizes the performance of the fault prediction model.

[0117] The sorted fault handling suggestions and repair result data are merged with historical data to form a new training dataset. The fault prediction model is retrained using the new training dataset and updated parameters.

[0118] It should be noted that historical data refers to data that has been previously used to train fault prediction models. This data includes past fault records, maintenance records, and related operational data features. Merging the collated fault handling suggestions and maintenance results data with historical data can increase the quantity and diversity of training data, improve the generalization ability of the fault prediction model, ensure that the fault prediction model can adapt to new data distributions, and improve prediction performance.

[0119] Update the retrained fault prediction model to the fault prediction system to replace the old one, and regularly collect new fault handling suggestions and repair results;

[0120] It should be noted that the retrained model is saved to a file for subsequent loading and use. In order to continuously optimize the fault prediction model, new fault handling suggestions and repair results need to be collected regularly. These data will be used for subsequent fault prediction model training and optimization. The time interval for data collection is defined, such as collecting new fault handling suggestions and repair results once a week or a month.

[0121] In summary, the present invention uses: distributed intelligent diagnosis and comprehensive analysis mechanism to quickly and accurately locate the fault location, analyze the cause of the fault, and generate targeted processing suggestions, thereby improving operation and maintenance efficiency, dynamically adjusting model parameters through actual fault processing results, continuously optimizing system performance, enhancing the system's adaptability and stability, accelerating fault response speed, improving the accuracy of fault prediction, reducing false alarm rate, and reducing dependence on manual inspections, reducing operation and maintenance costs and work intensity, and ensuring the operational safety and efficiency of urban rail transit.

[0122] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent operation and maintenance system for platform doors, characterized by: including Data acquisition and processing module: Collect real-time operation data, perform preprocessing, extract operation data features, and store them; Fault prediction model construction module: Construct a fault prediction model, use operation data features to train the fault prediction model, and generate a trained fault prediction model; Fault warning module: Input real-time operation data into the trained fault prediction model, generate warning information, and send the warning information to the distributed intelligent diagnosis system; Intelligent diagnosis module: The distributed intelligent diagnosis system identifies the IoT nodes that need to be diagnosed according to the warning information. The IoT nodes perform preliminary diagnosis on the collected data according to preset rules and generate preliminary diagnosis results; Fault decision-making module: Comprehensively analyze the preliminary diagnosis results, determine the location and cause of the fault according to the comprehensive analysis results, and generate fault handling suggestions; Optimization closed-loop module: The fault prediction model dynamically adjusts the model parameters according to the fault handling suggestions, retrains the fault prediction model with the updated parameters, and continues to be used for fault prediction to form a complete closed-loop.

2. The platform door intelligent operation and maintenance system according to claim 1, wherein: The real-time operation data includes electrical operation data, environmental operation data, mechanical operation data, and control operation data; The preprocessing includes smoothing processing and denoising processing; The operation data features include statistical features, time series features, and frequency domain features; Store the operation data features in a relational database.

3. The platform door intelligent operation and maintenance system according to claim 2, characterized in that: The steps of constructing the fault prediction model, using the operation data features to train the fault prediction model, and generating a trained fault prediction model are as follows: Select the support vector machine algorithm to construct the fault prediction model and initialize the fault prediction model parameters; Divide the operation data features into a training set and a test set; The fault prediction model adjusts the internal parameters according to the training set data; Use the test set to verify the trained fault prediction model and generate verification results; According to the verification results, use the grid search method to optimize the fault prediction model parameters and generate a trained fault prediction model.

4. The platform door intelligent operation and maintenance system according to claim 3, characterized in that: The steps of inputting the real-time operation data into the trained fault prediction model, generating warning information, and sending the warning information to the distributed intelligent diagnosis system are as follows: Load the trained fault prediction model, input the real-time operation data features into the fault prediction model, and calculate the probability of fault occurrence P; Define a fault probability threshold Y. When P>Y, trigger a warning and generate warning information; When P<Y, it is considered that the operation state of the current device is stable; Package the warning information in JSON format and send the warning information to the distributed diagnosis system through the MQTT protocol.

5. The platform door intelligent operation and maintenance system according to claim 4, characterized in that: The steps for the distributed intelligent diagnosis system to identify the IoT nodes that need to be diagnosed according to the warning information are as follows: The warning information includes the fault type, the expected occurrence time, the affected components, and the severity of the fault; The distributed intelligent diagnosis system receives the warning information through the MQTT protocol and analyzes the warning information; Based on the parsed warning information, combined with the pre-defined mapping relationship between components and nodes, the intelligent diagnosis system identifies the IoT nodes related to the warning information.

6. The platform door intelligent operation and maintenance system according to claim 5, characterized in that: The IoT node performs preliminary diagnosis on the collected data according to preset rules and generates preliminary diagnosis results. The specific steps are as follows: The preset rules include threshold rules, combination rules, pattern matching rules, time series rules and anomaly detection rules; The IoT nodes collect the operating data of platform doors and key components in real time and extract the operating data features; Perform preliminary diagnosis on the operating data characteristics according to preset rules, generate preliminary diagnosis results, and send the preliminary diagnosis results to the central diagnosis system.

7. The platform door intelligent operation and maintenance system according to claim 6, characterized in that: The specific steps for conducting a comprehensive analysis of the preliminary diagnostic results are as follows: The central diagnostic system collects the preliminary diagnostic results of each IoT node and analyzes the correlation between the preliminary diagnostic results; Identify the fault mode based on the fault manifestations in the preliminary diagnosis results; Through comparative analysis, real-time operating data is compared with historical normal operating data to identify data points that significantly deviate from the normal range; Through correlation analysis, we explore whether the current anomaly between different types of data is accompanied by temperature rise and whether the change in vibration frequency is associated with a specific operation cycle.

8. The platform door intelligent operation and maintenance system according to claim 7, characterized in that: The location and cause of the fault are determined based on the comprehensive analysis results, and fault handling suggestions are generated. The specific steps are as follows: Based on the comprehensive analysis results, narrow down the source of the fault and identify the location and cause of the problem; Infer the cause of the failure based on the equipment failure mode and preliminary diagnosis results; According to the severity of the fault, determine the urgency of the fault, formulate a maintenance plan based on the cause of the fault, and generate fault handling suggestions.

9. The platform door intelligent operation and maintenance system according to claim 8, characterized in that: The fault prediction model dynamically adjusts model parameters according to the fault handling suggestions. The specific steps are as follows: Collect fault handling suggestions and actual repair results from the operation and maintenance management system, and organize the collected data into a structured form; Analyze the deviation between the prediction results of the fault prediction model and the actual fault, and identify the fault prediction model parameters that need to be adjusted based on the results of the deviation analysis.

10. The platform door intelligent operation and maintenance system according to claim 9, characterized in that: The updated parameters are used to retrain the fault prediction model and continue to be used for fault prediction to form a complete closed loop. The specific steps are as follows: Merge the organized fault handling suggestions and repair result data with historical data to form a new training dataset, and retrain the fault prediction model using the new training dataset and updated parameters; The retrained fault prediction model is updated to the fault prediction system to replace the old fault prediction model, and new fault handling suggestions and repair results are collected regularly.

Images