Railway vehicle safety intelligent early warning system

Abstract

The invention relates to the technical field of railway vehicle safety, and discloses a railway vehicle safety intelligent early warning system which comprises a sensor module, a data acquisition and transmission module, a data analysis and processing module, an early warning module, a user interface module, a storage module and a system management module. According to the railway vehicle safety intelligent early warning system, through the arrangement of the sensor module, the system can monitor and obtain various operation parameters such as railway vehicle axle temperature, wheel set tread damage, braking system performance and bogie state in real time, and processing and analysis are achieved through an algorithm arranged in the data analysis and processing module; when abnormal parameters are found, an early warning signal is sent out, maintenance personnel can take measures before a fault occurs, further deterioration of the fault is avoided, meanwhile, a sensor in the sensor module achieves uninterrupted real-time monitoring on a railway vehicle in a wired or wireless information transmission mode, and safety condition information of the vehicle can be obtained at any time.

Description

Technical Field

[0001] The present invention relates to the technical field of railway vehicle safety, and in particular to an intelligent early warning system for railway vehicle safety. Background Art

[0002] As a high-volume and high-efficiency mode of transportation, railway transportation plays an important role in the national economy. With the development of railway transportation, the operation safety of railway vehicles is of vital importance. In order to meet the growing transportation demand and improve the efficiency and quality of railway transportation, it is necessary to establish a more intelligent and automated railway vehicle safety monitoring and early warning system to reduce transportation delays and accidents caused by vehicle failures and ensure the safety, punctuality and efficiency of railway transportation. Traditional railway vehicle safety monitoring methods have limitations, such as:

[0003] Traditional railway vehicle safety inspections mainly rely on regular manual inspections. Inspectors need to conduct visual inspections and simple tool inspections on various vehicle components when the vehicle stops at a station or enters storage. The overall efficiency is low and it is easily affected by human factors. It is difficult to find some hidden faults. In addition, some railway vehicles are equipped with some independent sensors. The parameter detection between sensors is relatively independent and difficult to observe jointly, which increases the difficulty of safety detection and processing and reduces the timeliness of detection.

[0004] In view of the above problems, it is urgent to carry out innovative designs based on the original traditional railway vehicle safety monitoring methods. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent early warning system for railway vehicle safety to solve the problems mentioned in the above background technology, such as low efficiency of traditional railway vehicle safety monitoring means, partially independent sensors, relatively independent parameter detection between sensors, difficulty in joint observation and lack of real-time performance.

[0006] To achieve the above-mentioned object, the present invention provides the following technical solutions: a railway vehicle safety intelligent early warning system, comprising a sensor module, a data acquisition and transmission module, a data analysis and processing module, an early warning module, a user interface module, a storage module and a system management module;

[0007] The sensor module includes an axle temperature sensor installed at the end of the vehicle axle, a wheelset sensor installed on the surface of the wheelset, a brake system sensor installed on the automatic disc, and a bogie sensor installed on the bogie. The information collected by the sensor module is uploaded to the data acquisition and transmission module;

[0008] The data acquisition and transmission module is provided with a data acquisition unit and a wireless communication unit, and the wireless communication unit of the data acquisition and transmission module uploads the acquired data to the data analysis and processing module;

[0009] The data analysis and processing module is provided with a data preprocessing unit, a feature extraction unit, a fault diagnosis unit and a performance evaluation unit, the fault diagnosis unit is associated with the performance evaluation unit, and a fault diagnosis model is established in the fault diagnosis unit;

[0010] The early warning module receives data from the fault diagnosis model in the fault diagnosis unit, and the early warning module sends information to the indicator light and alarm connected to the system, the early warning module information is transmitted to the user interface module, and the user interface module sends instructions to the data analysis and processing module;

[0011] The storage module receives all information backups processed by the data acquisition and transmission module, the data analysis and processing module and the early warning module, and the storage module receives instructions from the data analysis and processing module, and the storage module is connected to the user interface module by signal;

[0012] The system management module is independently and interactively connected with the sensor module, the data acquisition and transmission module, the data analysis and processing module, the early warning module, the user interface module and the storage module.

[0013] By adopting the above technical solution, the vehicle operation status can be monitored in real time, potential fault hazards can be discovered in time, and the occurrence of railway vehicle accidents can be effectively reduced.

[0014] Preferably, the shaft temperature sensor of the sensor module is a high-precision temperature sensor, and the shaft temperature sensor is connected to the data acquisition and transmission module through wireless data transmission technology.

[0015] The above technical solution is adopted to facilitate continuous temperature monitoring of the axle rod part of the railway vehicle.

[0016] Preferably, the wheelset sensor of the sensor module adopts a laser displacement sensor, and the wheelset sensor is connected to the data acquisition and transmission module via a signal cable.

[0017] The above technical solution is adopted to facilitate accurate inquiry of the working status of railway wheelsets.

[0018] Preferably, the brake system sensor of the sensor module adopts a pressure sensor and a temperature sensor, and the brake system sensor is connected to the data acquisition and transmission module through wireless data transmission technology.

[0019] The above technical solution is used to provide accurate detection of the pressure and temperature of the braking state of the railway vehicle.

[0020] Preferably, the bogie sensor of the sensor module adopts an acceleration sensor and a vibration sensor, and the bogie sensor is connected to the data acquisition and transmission module through wireless data transmission technology.

[0021] The above technical solution is adopted to facilitate fully monitoring the working status of the bogie.

[0022] Preferably, the data preprocessing unit receives the sensor data uploaded by the wireless communication unit, and the data processed by the data preprocessing unit is transmitted to the feature extraction unit.

[0023] By adopting the above technical solution, the wireless communication unit provides control over data transmission and reception for the sensor data.

[0024] Preferably, the data analysis and processing module receives instructions sent from the user interface module, and the user interface module provides a display platform in the form of user interaction.

[0025] By adopting the above technical solution, the data analysis and processing module assists in processing the instructions sent by the user interface.

[0026] Preferably, the user interface module is interactively connected to the early warning module, and the early warning module is connected to an alarm installed in a railway vehicle via a signal cable.

[0027] By adopting the above technical solution, the user interface module receives the warning signal of the warning module and can further set the warning module.

[0028] Preferably, the storage module adopts the Hadoop distributed file system, and the historical data in the storage module interacts with the fault diagnosis model in the fault diagnosis unit.

[0029] By adopting the above technical solution, the data in the system can be quickly backed up by adding nodes.

[0030] Preferably, the system management module manages and maintains the sensor module and the user interface module, and the system management module manages and controls the data acquisition and transmission module and the early warning module, and the system management module manages and supervises the data analysis and processing module.

[0031] The above technical solution is adopted to facilitate corresponding processing for all modules in the system.

[0032] Compared with the prior art, the invention has the following beneficial effects: the railway vehicle safety intelligent early warning system:

[0033] 1. Through the setting of the sensor module, the system can monitor and obtain various operating parameters such as axle temperature, wheel tread damage, brake system performance, bogie status, etc. of railway vehicles in real time. The algorithm set in the data analysis and processing module realizes processing and analysis, and issues a warning signal when abnormal parameters are found, so that maintenance personnel can take measures before the fault occurs to avoid further deterioration of the fault. At the same time, the sensors in the sensor module transmit information through wired or wireless means, so that the system can realize uninterrupted real-time monitoring of railway vehicles. Whether the vehicle is in operation or stationary, the safety status information of the vehicle can be obtained at any time, and the sudden safety problems can be responded to quickly, reducing the probability and impact range of safety accidents;

[0034] 2. The internal storage module cooperates with the performance evaluation unit in the data analysis and processing module to record each vehicle failure data and operating parameters, providing a large amount of data support for subsequent failure statistics and analysis. After in-depth analysis of the data, it can increase the understanding of the conditions in high-incidence areas of vehicle failure locations, provide important basis for vehicle design improvement, manufacturing process optimization and maintenance standard formulation, thereby continuously improving the overall quality and reliability of railway vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a schematic diagram of the working process of the early warning system of the present invention;

[0036] Figure 2 This is a schematic diagram of the system management module association module of the present invention;

[0037] Figure 3 It is a schematic diagram of the sensor module association module of the present invention;

[0038] Figure 4 It is a schematic diagram of the data analysis and processing module association module flow of the present invention. DETAILED DESCRIPTION

[0039] 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.

[0040] See also Figure 1-Figure 4 ,The present invention provides a technical solution: a railway vehicle safety intelligent early warning system, including a sensor module, a data acquisition and transmission module, a data analysis and processing module, an early warning module, a user interface module, a storage module and a system management module;

[0041] The sensor module includes an axle temperature sensor installed at the end of the vehicle axle, a wheelset sensor installed on the surface of the wheelset, a brake system sensor installed on the automatic disc, and a bogie sensor installed on the bogie. The information collected by the sensor module is uploaded to the data acquisition and transmission module;

[0042] The shaft temperature sensor of the sensor module adopts a high-precision temperature sensor, and the shaft temperature sensor is connected to the data acquisition and transmission module through wireless data transmission technology;

[0043] The wheel set sensor of the sensor module adopts a laser displacement sensor, and the wheel set sensor is connected to the data acquisition and transmission module through a signal cable;

[0044] The brake system sensor of the sensor module adopts a pressure sensor and a temperature sensor, and the brake system sensor is connected with the data acquisition and transmission module through wireless data transmission technology;

[0045] The bogie sensor of the sensor module adopts an acceleration sensor and a vibration sensor, and the bogie sensor is connected to the data acquisition and transmission module through wireless data transmission technology;

[0046] The data acquisition and transmission module is provided with a data acquisition unit and a wireless communication unit, and the wireless communication unit of the data acquisition and transmission module uploads the acquired data to the data analysis and processing module;

[0047] The data analysis and processing module is provided with a data preprocessing unit, a feature extraction unit, a fault diagnosis unit and a performance evaluation unit. The fault diagnosis unit is associated with the performance evaluation unit, and a fault diagnosis model is established in the fault diagnosis unit. The data preprocessing unit receives sensor data uploaded by the wireless communication unit, and the data processed by the data preprocessing unit is transmitted to the feature extraction unit. The data analysis and processing module receives instructions sent from the user interface module, and the user interface module provides a display platform in the form of user interaction;

[0048] The early warning module receives data of the fault diagnosis model in the fault diagnosis unit, and the early warning module sends information to the indicator light and the alarm connected to the system, the early warning module information is transmitted to the user interface module, and the user interface module sends instructions to the data analysis and processing module, the user interface module is interactively connected with the early warning module, and the early warning module is connected to the alarm installed in the railway vehicle through a signal cable;

[0049] The storage module receives all information backups processed by the data acquisition and transmission module, the data analysis and processing module and the early warning module, and the storage module receives instructions from the data analysis and processing module, and the storage module is connected to the user interface module by signal, the storage module adopts the Hadoop distributed file system, and the historical data in the storage module interacts with the fault diagnosis model in the fault diagnosis unit;

[0050] The system management module is independently and interactively connected with the sensor module, the data acquisition and transmission module, the data analysis and processing module, the early warning module, the user interface module and the storage module respectively. The system management module manages and maintains the sensor module and the user interface module, manages and controls the data acquisition and transmission module and the early warning module, and manages and supervises the data analysis and processing module.

[0051] In conjunction with the accompanying drawings Figure 1-Figure 4 As shown, the axle temperature sensor of the sensor module is installed at the axle end of the vehicle to monitor the axle temperature in real time, the wheel set sensor of the sensor module is installed on the surface of the wheel set to monitor the wear condition of the wheel set in real time, the brake system sensor of the sensor module is installed in the key part of the brake system, the brake cylinder or the brake disc, to monitor the pressure and temperature of the brake system in real time, and the bogie sensor of the sensor module is installed on the surface of the bogie to monitor the vibration and displacement of the steering in real time;

[0052] The above-mentioned sensor data is collected and sorted by the data acquisition unit of the data acquisition and transmission module. The high-speed acquisition card and data collector set in the data acquisition unit are used to quickly convert the sensor data acquired by the wireless communication unit into digital signals. The wireless communication unit adopts Bluetooth, wireless LAN, 4G / 5G and other communication technologies to ensure the stability and reliability of data transmission;

[0053] The data received by the data analysis and processing module is further processed on the basis of the data processed by the data acquisition and transmission module. The data preprocessing unit of the data analysis and processing module cleans, filters and normalizes the sorted sensor data, and then uploads the data to the feature extraction unit. The feature extraction unit classifies the data according to time domain features and frequency domain features. The time domain features further calculate the mean, variance, maximum value, minimum value and other statistics of the shaft temperature by analyzing the characteristics of the data changing over time.

[0054] The mean value of the shaft temperature is: mean = sum (X) / n

[0055] Variance reflects the degree of dispersion of data. The formula is: variance = sum((X-mean) 2 ) / n

[0056] The peak index of the maximum and minimum values ​​is calculated as the peak value divided by the root mean square value, the formula is: PeakFactor = peak_value / RMS_value, which can be used to determine the impact situation in the vibration signal, so as to analyze the amplitude, frequency, phase and other characteristics of the wheelset vibration;

[0057] The frequency domain feature converts the time domain signal into the frequency domain signal and analyzes the frequency component of the signal through the Fourier transform method, that is,

[0058] X(k)=sum(x(n)×exp(-j×2×pi×k×n / N))

[0059] Used to analyze the frequency composition of vibration, noise and other signals. By analyzing the frequency characteristics of the wheelset vibration signal, it is determined whether there is an abnormal frequency. The frequency domain characteristics play an important role in identifying the fault mode and diagnosing the cause of the fault.

[0060] The fault diagnosis model in the fault diagnosis unit is established according to the fault type and characteristics of the vehicle, so as to establish a corresponding fault diagnosis model and construct a machine learning model, which includes:

[0061] Decision Tree Model:

[0062] ID3, C4.5, and CART algorithms are used to build a decision tree based on the characteristic attributes of the data. By learning the training data, branch decisions are made based on the threshold of the feature, and finally a classification result is formed. Based on the characteristics of axle temperature, wheelset wear, brake pressure, etc., it is judged whether the vehicle has a fault;

[0063] The model is easy to interpret and visualize, but may have overfitting problems and require optimization operations such as pruning;

[0064] Support Vector Machines:

[0065] By finding the optimal hyperplane, the normal and faulty data of different categories are separated. For linearly separable and nonlinearly separable data, the kernel function can be used to map the data into a high-dimensional space for classification;

[0066] Random Forest:

[0067] It is an integration of multiple decision trees. By randomly selecting samples and features to establish multiple decision trees, the results of multiple decision trees are integrated for classification or regression, which can effectively reduce overfitting and improve the robustness of the model.

[0068] Neural Networks:

[0069] Build a multi-layer perceptron, and use it with convolutional neural networks and recurrent neural networks to build a complete learning network. The multi-layer perceptron is suitable for general feature input and can be used for classification or regression tasks.

[0070] Convolutional neural networks are suitable for processing image data and can be used to analyze image data of vehicle parts;

[0071] Recurrent neural networks are suitable for processing sequence data. For vehicle time series data, they can capture the time dependency of data.

[0072] After confirming the model category, the historical data in the storage module is divided into training set, validation set and test set in a ratio of 70:15:15. The training set is used to train the model, the validation set is used to adjust the model's hyperparameters, and the test set is used to evaluate the performance of the final model.

[0073] Hyperparameter Tuning:

[0074] For decision trees, you can adjust data such as the depth of the tree and the minimum number of samples for node splitting;

[0075] For support vector machines, adjust the kernel function parameters and penalty coefficients;

[0076] For neural networks, adjust the number of network layers, the number of neurons in each layer, the learning rate and other data.

[0077] Find the optimal hyperparameters through grid search, random search, or more advanced Bayesian optimization methods;

[0078] For machine learning models, use the training set for training, and update the model parameters according to the selected optimization algorithm to minimize the loss function of the model on the training set;

[0079] For deep learning models, use the deep learning framework for training, set two functions: cross entropy loss and mean square error loss. During training, use any appropriate loss function and optimizer to perform multiple rounds of training.

[0080] The trained model is input into the performance evaluation unit, which uses the test set to evaluate the trained model and evaluates the performance of the model by using indicators such as accuracy, recall, precision, and F1 score.

[0081] Accuracy = (number of samples predicted correctly) / (total number of samples);

[0082] Recall = (true positives) / (true positives + false negatives), which reflects the model's ability to detect faults;

[0083] Precision = (true positives) / (true positives + false positives), which reflects the proportion of samples predicted as faults by the model that are actually faulty.

[0084] The F1 score is the harmonic mean of recall and precision, taking both into account;

[0085] Regression task: Use mean square error: MSE = sum((y_pred-y_true) 2 ) / n,

[0086] Mean absolute error: MAE = sum(abs(y_pred-y_true)) / n, where y_pred is the predicted value and y_true is the true value;

[0087] Calculate the above evaluation indicators, observe the performance of the model, use the cross-validation method, and divide the data into K parts after K-fold cross-validation. Use K-1 parts for training and 1 part for testing each time. Repeat multiple times and take the average value as the evaluation result to improve the reliability of the evaluation.

[0088] The trained model is deployed to the railway vehicle safety intelligent early warning system and integrated with the data acquisition and processing module and the early warning module. The model is updated regularly and retrained and adjusted based on the newly collected data to adapt to new vehicle conditions, new failure modes and performance changes.

[0089] The early warning module receives the diagnosis result of the fault diagnosis model and sends out an early warning signal, which is directly displayed on the display device connected to the user interface module. At the same time, the user interface module realizes the interaction between the user and the system, and is used to query historical data and set the early warning parameters in the early warning module. At the same time, the user interface module sends instructions to the data analysis and processing module, and the data analysis and processing module performs corresponding processing according to the user instructions and feeds back the processing results to the user interface module. The setting of the instructions facilitates the retrieval of the historical data of the storage module. The user can view the vehicle's operating status, fault diagnosis results and other information through the user interface module, and can also set and adjust the data analysis and processing module;

[0090] At the same time, the user interface module cooperates with the system management module to modify and adjust the data of other modules. The system management module manages and maintains the sensor module, including the installation, debugging, calibration and other operations of the sensor to ensure the normal operation of the sensor. At the same time, the system management module will also adjust and optimize the sensor according to the working conditions of the sensor;

[0091] The system management module manages and controls the data acquisition and transmission module, sets the parameters and protocols for data transmission, and ensures the stability and security of data transmission. At the same time, the system management module also monitors and manages the data acquisition and transmission module, and promptly discovers and solves problems that arise during data transmission;

[0092] The system management module manages and supervises the data analysis and processing module, sets the parameters and algorithms of the data analysis and processing module, ensures the normal operation of the system, and guarantees the processing capacity and efficiency of the system. At the same time, the system management module will also maintain and update the data analysis and processing module to improve the performance and functions of the system;

[0093] The system management module manages and controls the early warning module, sets the early warning rules and thresholds of the early warning module, and ensures the normal operation of the early warning system. At the same time, the system management module also maintains and updates the early warning module to improve the performance and functions of the system;

[0094] This early warning system has accumulated a large amount of vehicle operation data and fault diagnosis information, providing maintenance managers with rich data resources. By analyzing and mining these data, the failure patterns and life cycles of various vehicle components can be understood, so as to formulate more scientific and reasonable maintenance plans and repair strategies, and realize the transformation from traditional periodic maintenance to precise maintenance based on the actual status of the vehicle, thereby improving the scientificity and effectiveness of maintenance management. At the same time, the information connectivity of the wireless network enables railway vehicles equipped with the early warning system to have remote monitoring functions. Maintenance managers can view the vehicle's operating status and early warning information in real time through the network in a control center or office far away from the vehicle, so that managers can evaluate and make decisions on the safety status of the vehicle in a timely manner, improving the convenience and timeliness of maintenance management.

[0095] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A railway vehicle safety intelligent early warning system, characterized in that: include: Sensor module, data acquisition and transmission module, data analysis and processing module, early warning module, user interface module, storage module and system management module; The sensor module includes an axle temperature sensor installed at the vehicle axle end, a wheelset sensor installed on the surface of the wheelset, a brake system sensor installed on the automatic disc, and a bogie sensor installed on the bogie. The information collected by the sensor module is uploaded to the data acquisition and transmission module; The data acquisition and transmission module is provided with a data acquisition unit and a wireless communication unit, and the wireless communication unit of the data acquisition and transmission module uploads the acquired data to the data analysis and processing module; The data analysis and processing module is provided with a data preprocessing unit, a feature extraction unit, a fault diagnosis unit and a performance evaluation unit, the fault diagnosis unit is associated with the performance evaluation unit, and a fault diagnosis model is established in the fault diagnosis unit; The early warning module receives data from the fault diagnosis model in the fault diagnosis unit, and the early warning module sends information to the indicator light and alarm connected to the system, the early warning module information is transmitted to the user interface module, and the user interface module sends instructions to the data analysis and processing module; The storage module receives all information backups processed by the data acquisition and transmission module, the data analysis and processing module and the early warning module, and the storage module receives instructions from the data analysis and processing module, and the storage module is connected to the user interface module by signal; The system management module is independently and interactively connected with the sensor module, the data acquisition and transmission module, the data analysis and processing module, the early warning module, the user interface module and the storage module.

2. The intelligent early warning system for railway vehicle safety according to claim 1, characterized in that: The shaft temperature sensor of the sensor module adopts a high-precision temperature sensor, and the shaft temperature sensor is connected to the data acquisition and transmission module through wireless data transmission technology.

3. The intelligent early warning system for railway vehicle safety according to claim 1 is characterized in that: The wheel set sensor of the sensor module adopts a laser displacement sensor, and the wheel set sensor is connected to the data acquisition and transmission module through a signal cable.

4. The intelligent early warning system for railway vehicle safety according to claim 1, characterized in that: The brake system sensor of the sensor module adopts a pressure sensor and a temperature sensor, and the brake system sensor is connected with the data acquisition and transmission module through wireless data transmission technology.

5. The intelligent early warning system for railway vehicle safety according to claim 1 is characterized in that: The bogie sensor of the sensor module adopts an acceleration sensor and a vibration sensor, and the bogie sensor is connected with the data acquisition and transmission module through wireless data transmission technology.

6. The intelligent early warning system for railway vehicle safety according to claim 1, characterized in that: The data preprocessing unit receives the sensor data uploaded by the wireless communication unit, and the data processed by the data preprocessing unit is transmitted to the feature extraction unit.

7. The intelligent early warning system for railway vehicle safety according to claim 1 is characterized in that: The data analysis and processing module receives instructions sent from the user interface module, and the user interface module provides a display platform in the form of user interaction.

8. The intelligent early warning system for railway vehicle safety according to claim 1 is characterized in that: The user interface module is interactively connected to the early warning module, and the early warning module is connected to an alarm installed in a railway vehicle via a signal cable.

9. The intelligent early warning system for railway vehicle safety according to claim 1, characterized in that: The storage module adopts the Hadoop distributed file system, and the historical data in the storage module interacts with the fault diagnosis model in the fault diagnosis unit.

10. The intelligent early warning system for railway vehicle safety according to claim 1, characterized in that: The system management module manages and maintains the sensor module and the user interface module, manages and controls the data acquisition and transmission module and the early warning module, and manages and supervises the data analysis and processing module.

Images