Train health state monitoring system

Abstract

The invention relates to the technical field of train fault diagnosis, and discloses a train health state monitoring system. According to the train health state monitoring system, key data such as temperature, vibration, pressure and acceleration of a train can be acquired in real time through the data acquisition unit and transmitted to the data processing unit through the CAN bus to be analyzed and processed, and the health monitoring unit can recognize fault risks in time and generate early warning signals through real-time monitoring; in addition, the data communication and exchange unit ensures that fault information is uploaded to a train control center in real time, dispatching and decision making are facilitated, the operation and maintenance efficiency is greatly improved through the innovative monitoring mode, the safety and reliability of train operation are guaranteed, and the safety and reliability of train operation are improved. And powerful technical support is provided for modern railway transportation.

Description

Technical Field

[0001] The present invention relates to the technical field of train fault diagnosis, and specifically to a train health status monitoring system. Background Art

[0002] With the acceleration of the urbanization process and the continuous increase in transportation demand, railway transportation, as an efficient and safe transportation mode, is playing an increasingly important role. The safety and reliability of trains are directly related to the lives of passengers and transportation efficiency. Therefore, train health status monitoring has become an important part of railway operation. By obtaining and analyzing the operation data of trains in real time, train health monitoring can identify potential faults in a timely manner and significantly improve the safety of trains.

[0003] Traditional train operation and maintenance require train maintenance workers to check the train's operating components when the train stops running. This method has low maintenance efficiency and cannot achieve real-time monitoring of the train's operating status. Summary of the Invention

[0004] (1) Technical Problems to be Solved

[0005] Aiming at the deficiencies of the prior art, the present invention provides a train health status monitoring system. The data acquisition unit can obtain key data such as the temperature, vibration, pressure, and acceleration of the train in real time and transmit it to the data processing unit through the CAN bus for analysis and processing. This real-time monitoring enables the health monitoring unit to identify fault risks in a timely manner and generate warning signals, thereby realizing preventive maintenance and avoiding train stoppages and accidents caused by equipment failures. In addition, the data communication and exchange unit ensures that fault information is uploaded to the train control center in real time, facilitating dispatching and decision-making. This innovative monitoring method greatly improves the operation and maintenance efficiency, ensures the safety and reliability of train operation, and provides strong technical support for modern railway transportation.

[0006] (2) Technical Solutions

[0007] To achieve the above object, the present invention provides the following technical solution: A train health status monitoring system, including a data acquisition unit, a data processing unit, a health monitoring unit, a data communication and exchange unit, and a display unit;

[0008] The data acquisition unit is used to obtain the temperature data, vibration data, pressure data, and acceleration data of the train and transmit them to the data processing unit through the CAN bus;

[0009] The data processing unit is used to perform filtering and normalization operations on the data transmitted by the data acquisition unit, uniformly convert it into data in a standard format, and calculate the average train running temperature, the train running pressure change rate, the train acceleration change trend, the train vibration frequency, and analyze the train vibration amplitude;

[0010] The health monitoring unit, based on the data values processed and analyzed by the data processing unit, determines whether the train has a fault through a train fault diagnosis algorithm and generates a train fault warning signal;

[0011] The data communication and exchange unit is used to upload the train fault warning signal to the train control center in real time;

[0012] The display unit displays the health status of the train on a central control screen in the train control center.

[0013] Preferably, the formula for data filtering is as follows:

[0014] Y[n] = (1 - α)*X[n] + α*Y[n - 1]

[0015] In the formula, Y[n] represents the current output value after filtering, X[n] represents the current input data value, Y[n - 1] represents the previous output value, and α represents the smoothing factor, with a range of 0 - 1.

[0016] Preferably, the formula for data normalization is as follows:

[0017]

[0018] In the formula, Z norm represents the data value after normalization, Z represents the original data value to be normalized, Z min represents the minimum value of the original data in the dataset, Z max represents the maximum value of the original data in the dataset.

[0019] Preferably, the formula for calculating the average train running temperature is as follows:

[0020]

[0021] In the formula, T avg represents the average train running temperature, T i represents the i-th temperature measurement value, n represents the total number of temperature measurement values, and i represents the index subscript.

[0022] Preferably, the formula for calculating the train running pressure change rate is as follows:

[0023]

[0024] In the formula, P change represents the relative change in pressure, P current represents the currently collected pressure value, P previous represents the pressure value collected at the previous moment.

[0025] Preferably, the calculation formula for the change trend of the train acceleration is as follows:

[0026]

[0027] In the formula, A trend represents the acceleration change trend, A cur represents the acceleration value at the current moment, A pre represents the acceleration value at the previous moment, and Δt represents the time interval between the current and the previous moment.

[0028] Preferably, the calculation formula for the vibration frequency of the train is as follows:

[0029]

[0030] In the formula, f represents the vibration frequency of the train, and Tr represents the period of the train vibration signal.

[0031] Preferably, the formula for analyzing the vibration amplitude of the train is as follows:

[0032]

[0033] In the formula, A rms represents the root mean square amplitude of the vibration signal, V j represents the vibration value at the j-th moment, m represents the number of samples of the vibration signal, and j represents the counting subscript.

[0034] Preferably, the train fault diagnosis algorithm is as follows:

[0035]

[0036] In the formula, Gini(t) represents the impurity for evaluating node t, and the smaller it is, the higher the purity of the node. C represents the total number of categories, which is used to indicate whether the train has a fault or is normal, p k represents the proportion of the k-th type of samples in node t, and k represents the subscript.

[0037] Preferably, the formula for generating the fault warning signal is as follows:

[0038] W = F * S

[0039] In the formula, W represents the fault warning signal, f represents the fault flag bit, which is 1 or 0, S represents the intensity of the fault signal, with value 1 indicating a minor fault, value 2 indicating a moderate fault, and value 3 indicating a severe fault.

[0040] Compared with the prior art, the present invention provides a train health status monitoring system, which has the following

[0041] Advantages:

[0042] Through the data acquisition unit, the present invention can obtain key data such as the temperature, vibration, pressure, and acceleration of the train in real time, and transmit it to the data processing unit through the CAN bus for analysis and processing. This real-time monitoring enables the health monitoring unit to identify fault risks in a timely manner and generate warning signals, thereby realizing preventive maintenance, avoiding outages and accidents caused by equipment failures. In addition, the data communication and exchange unit ensures that fault information is uploaded to the train control center in real time, facilitating dispatching and decision-making. This innovative monitoring method greatly improves the operation and maintenance efficiency, ensures the safety and reliability of train operation, and provides strong technical support for modern railway transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0045] Aiming at the problem that traditional train operation and maintenance requires train maintenance workers to check the train's operating components when the train stops running, which has low maintenance efficiency and cannot achieve real-time monitoring of the train's operating status, a train health status monitoring system is proposed. Please refer to Figure 1 , the system includes a data acquisition unit, a data processing unit, a health monitoring unit, a data communication and exchange unit, and a display unit;

[0046] As the core component of the train health monitoring system, the data acquisition unit is responsible for real-time acquisition and recording of various key parameters during train operation, including temperature, vibration, pressure, and acceleration data. This unit is equipped with a variety of sensors, such as thermocouples and piezoelectric sensors, etc., which can efficiently and accurately capture the working status of different components. The temperature sensor can monitor the operating temperature of the motor and braking system, the vibration sensor is used to detect the vibration frequency of the train body and axles, the pressure sensor can provide real-time feedback on the working status of the pneumatic and hydraulic systems, and the acceleration sensor measures the acceleration and deceleration processes of the train;

[0047] The collected data is connected to the CAN (Controller Area Network) bus system through an efficient controller. This multi-master network can ensure reliable data transmission in a high-noise environment. The CAN bus not only has good anti-interference ability but also can effectively manage and schedule multiple signals, while achieving low-latency data communication. This network structure enables the data transmitted by all sensors to reach the data processing unit in a real-time and continuous manner, providing a reliable basis for subsequent signal analysis;

[0048] The data processing unit is responsible for deeply processing the multi-dimensional health monitoring data transmitted from the data acquisition unit. First, this unit implements data filtering and normalization operations to improve data quality and eliminate noise interference. By using advanced technologies such as low-pass filters, it can effectively smooth the data curve and reduce the influence of high-frequency noise, making the subsequent analysis results more reliable and accurate. Subsequently, the data normalization process converts measurement values with different dimensions and ranges into a unified format through methods such as standardization or Min-Max normalization, ensuring that all data can be compared and analyzed under the same benchmark;

[0049] After completing the preliminary data processing, the data processing unit calculates multiple important operation indicators, including the average train operation temperature, pressure change rate, acceleration change trend, and vibration frequency, etc. The calculation of these indicators provides an intuitive understanding of the train health status. For example, the calculation of the average train operation temperature not only reflects the thermal condition of the equipment during operation but also can warn of potential overheating risks and prevent equipment damage. The real-time monitoring of the pressure change rate enables maintenance personnel to quickly identify abnormal situations in the system and take timely measures to avoid accidents. The analysis of the acceleration change trend provides a quantitative basis for the acceleration and deceleration behavior of the train, helping to evaluate its operation safety. At the same time, the measurement and analysis of the vibration frequency can determine whether there are mechanical failures or unbalanced states during train operation, and the systematic evaluation of the vibration amplitude provides a scientific basis for vibration monitoring, helping to take maintenance actions in a timely manner before major equipment failures occur;

[0050] Among them, the formula for the data filtering application is as follows:

[0051] Y[n] = (1 - α) * X[n] + α * Y[n - 1]

[0052] By eliminating noise, data filtering can significantly improve the accuracy of data, ensure that subsequent processing is based on real signals, remove unnecessary interference before the data is transmitted to the next stage, and provide a data basis for the monitoring of the health state. In the formula, Y[n] represents the current output value after filtering, X[n] represents the current input data value, Y[n - 1] represents the previous output value, and α represents the smoothing factor, with a range of 0 - 1. Clear and clean data can make data normalization, mean calculation, and other analysis steps more effective, reduce the uncertainty and potential errors introduced by noise, and thus ensure that the obtained diagnostic results are more reliable;

[0053] The formula for data normalization is as follows:

[0054]

[0055] By standardizing indicators such as temperature, pressure, and vibration, all data is placed on the same basis, facilitating comparison and analysis. This step ensures that the influence of various data on the results is consistent, and helps the subsequent analysis to draw more reasonable conclusions. In the formula, Z norm represents the normalized data value, Z represents the original data value to be normalized, Z min represents the minimum value of the original data in the dataset, Z max represents the maximum value of the original data in the dataset. The normalized data is convenient for model application and calculation, and can effectively improve the efficiency and accuracy of subsequent calculations such as mean and rate of change analysis, making the evaluation of the health state by the monitoring system more comprehensive and accurate;

[0056] The calculation formula for the average temperature of train operation is as follows:

[0057]

[0058] The mean provides information on the overall operating temperature of the equipment and helps to identify the performance of the equipment under different working conditions. If the average temperature rises abnormally, it may mean that the equipment is overloaded or there is a risk of failure. In the formula, T avg represents the average temperature of train operation, T i represents the i-th temperature measurement value, n represents the total number of temperature measurement values, and i represents the index subscript. By monitoring the average temperature, the operation and maintenance personnel can take timely measures to prevent equipment damage caused by excessive temperature, thereby further reducing the maintenance cost and the failure rate;

[0059] The calculation formula for the rate of change of train operation pressure is as follows:

[0060]

[0061] Monitoring the pressure change rate can quickly capture the changes between normal operation and abnormal states, providing early warnings for maintenance personnel to facilitate timely fault troubleshooting and repair. In the formula, P change represents the relative change in pressure, P current represents the currently collected pressure value, P previous represents the pressure value collected at the previous moment. By controlling the system pressure, ensuring operation within a safe range, and thereby reducing the risk of faults caused by pressure fluctuations, combined with the calculation of the temperature average, it jointly improves the overall safety of the train;

[0062] The calculation formula for the change trend of train acceleration is as follows:

[0063]

[0064] Analyzing the trend of acceleration can reveal the performance of the train during acceleration and deceleration. The maintenance team can adjust the operation strategy based on this to improve the overall operation efficiency and passenger comfort. In the formula, A trend represents the acceleration change trend, A cur represents the acceleration value at the current moment, A pre represents the acceleration value at the previous moment, Δt represents the time interval between the current and the previous moment. Real-time monitoring of the acceleration change can help identify potential abnormal states, such as sudden acceleration or deceleration, and feedback the risks to the maintenance team in a timely manner, working synergistically with temperature and pressure analysis to form an all-round monitoring system;

[0065] The calculation formula for the train vibration frequency is as follows:

[0066]

[0067] Different vibration frequencies can reveal the health status of the equipment, identifying problems such as wear, looseness, or imbalance. The frequency analysis combined with the monitoring of temperature and pressure forms a comprehensive assessment of the equipment status, improving the comprehensiveness of fault detection. In the formula, f represents the train vibration frequency, Tr represents the period of the train vibration signal. Keeping the vibration frequency within the normal range can not only ensure the normal operation of the equipment but also reduce accidental faults, thereby extending the service life of the equipment, forming a virtuous cycle with the analysis of operating temperature and pressure;

[0068] The formula for analyzing the train vibration amplitude is as follows:

[0069]

[0070] Through the change in vibration amplitude, operation and maintenance personnel can accurately evaluate the wear condition of equipment, such as the wear of wheels, bearings, and motors. Such quantitative feedback is crucial for timely problem detection, preventing small faults from evolving into major problems, and thus ensuring the safe operation of the train. In the formula, A rms represents the root mean square amplitude of the vibration signal, and V j represents the vibration value at the j-th moment, m represents the number of samples of the vibration signal, and j represents the counting subscript. By combining the vibration amplitude data with other operation data (such as temperature and pressure), high-risk components can be identified, enabling targeted preventive maintenance. Such a maintenance strategy can significantly reduce unexpected downtime, save maintenance costs, and improve equipment usage efficiency;

[0071] Through these comprehensive processing and calculations, the data processing unit not only provides accurate and reliable data support for train health monitoring but also lays a foundation for realizing intelligent fault diagnosis and proactive maintenance, significantly enhancing the safety and efficiency of train operation;

[0072] The core function of the health monitoring unit is to use the train fault diagnosis algorithm to determine whether the train has a fault based on the data values processed and analyzed by the data processing unit and generate timely fault warning signals. To achieve this function, the system adopts a variety of advanced technical means to ensure the accuracy and efficiency of fault detection;

[0073] During the fault diagnosis process, it is first necessary to evaluate the distribution of monitoring indicators to identify the differences between the normal state and the fault state. For this purpose, the health monitoring unit provides the Gini coefficient as an indicator to measure the degree of inequality. The specific formula is:

[0074]

[0075] Here, C represents the category of monitored data (such as different sensor data), and p k is the proportion of the k-th type of data in the total data. By calculating the Gini coefficient, the system can quantitatively evaluate the distribution balance of each monitoring indicator. When the Gini coefficient is high, it indicates that some indicators are abnormally prominent, possibly indicating the risk of potential faults;

[0076] Secondly, the fault diagnosis process also relies on a weight evaluation model to integrate the influence of multiple indicators in a combined manner. After comprehensively considering multiple judgment indicators, the generation of the fault signal can be calculated using the following formula:

[0077] W = F * S

[0078] Among them, F represents the result of fault diagnosis (usually 0 or 1, indicating a fault or normal condition), while S represents the intensity of the fault signal. A value of 1 indicates a minor fault, a value of 2 indicates a moderate fault, and a value of 3 indicates a severe fault;

[0079] When S exceeds the set threshold, the system will immediately issue a train fault warning signal to inform the operation and maintenance personnel to take necessary preventive measures, thereby ensuring the safe and stable operation of the train. Combining the above technical means, the health monitoring unit not only has efficient fault detection capabilities but also provides a scientific basis for subsequent maintenance decisions, helping to achieve effective resource allocation and risk management, and minimizing economic losses and operation interruptions caused by faults;

[0080] The main function of the data communication and exchange unit is to upload the train fault warning signal generated by the health monitoring unit to the train control center in real time. This process is achieved through efficient wireless communication technologies, such as using 4G / 5G networks or other dedicated communication protocols (such as LoRa, Zigbee, etc.), to ensure fast and reliable information transmission. The data communication unit is not only responsible for the transmission of fault warning signals but also capable of collecting real-time monitoring data from different trains and integrating them into an effective information flow for subsequent centralized management and analysis;

[0081] In the train control center, the data display unit visually presents the health status of the train through a high-level central control screen. This display unit uses high-resolution multi-touch screen technology and combines a graphical user interface (GUI) design to display various key indicators, including dynamic changes in operating temperature, pressure, vibration frequency, acceleration, etc. This visualization technology enables operation and maintenance personnel to monitor the status of various train health indicators at a glance and quickly identify potential fault risks. In addition, a fault alarm system is provided in the interface. Once an abnormal situation is detected, the fault warning information will be presented in a red warning box and accompanied by audible and visual alarms to ensure that operation and maintenance personnel can respond in a timely manner;

[0082] The entire system not only improves the safety and stability of train operation but also realizes the efficient allocation of resources and the reduction of operation costs through the effective management of data. This integrated monitoring and feedback mechanism is an important part of modern intelligent transportation systems and lays a solid foundation for the intelligent development of future railways.

[0083] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A train health status monitoring system, characterized in that: It includes a data acquisition unit, a data processing unit, a health monitoring unit, a data communication and exchange unit, and a display unit; The data acquisition unit is used to obtain temperature data, vibration data, pressure data and acceleration data of the train, and transmit them to the data processing unit via the CAN bus; The data processing unit is used to filter and normalize the data transmitted by the data acquisition unit, convert it into data in a standard format, calculate the mean value of train running temperature, train running pressure change rate, train acceleration change trend, train vibration frequency, and perform train vibration amplitude analysis; The health monitoring unit determines whether a train fault occurs based on the data value processed and analyzed by the data processing unit through a train fault diagnosis algorithm, and generates a train fault warning signal; The data communication and exchange unit is used to upload the train fault warning signal to the train control center in real time; The display unit displays the health status of the train at the train control center through a central control screen.

2. A train health status monitoring system according to claim 1, characterized in that: The formula used for the data filtering is as follows: Y[n]=(1-α)*X[n]+α*Y[n-1] In the formula, Y[n] represents the current output value after filtering, X[n] represents the current input data value, Y[n-1] represents the previous output value, and α represents the smoothing factor, which ranges from 0 to 1.

3. A train health status monitoring system according to claim 2, characterized in that: The formula for data normalization is as follows: In the formula, Z norm represents the normalized data value, Z represents the original data value to be normalized, and Z min Represents the minimum value of the original data in the data set, Z max Indicates the maximum value of the original data in the data set.

4. A train health status monitoring system according to claim 3, characterized in that: The formula for calculating the mean train operating temperature is as follows: In the formula, T avg represents the mean temperature of the train operation, T i represents the i-th temperature measurement value, n represents the total number of temperature measurements, and i represents the index subscript.

5. A train health status monitoring system according to claim 4, characterized in that: The formula for calculating the train operating pressure change rate is as follows: In the formula, P change Indicates the relative change in pressure, P current Indicates the currently collected pressure value, P previous Indicates the pressure value collected at the last moment.

6. A train health status monitoring system according to claim 5, characterized in that: The calculation formula of the train acceleration change trend is as follows: In the formula, A trend Indicates the acceleration change trend, A cur Indicates the acceleration value at the current moment, A pre It represents the acceleration value at the previous moment, and Δt represents the time interval between the current moment and the previous moment.

7. A train health status monitoring system according to claim 6, characterized in that: The calculation formula of the train vibration frequency is as follows: In the formula, f represents the train vibration frequency, and Tr represents the period of the train vibration signal.

8. A train health status monitoring system according to claim 7, characterized in that: The formula for train vibration amplitude analysis is as follows: In the formula, A rms Represents the root mean square amplitude of the vibration signal, V j represents the vibration value at the jth moment, m represents the number of samples of the vibration signal, and j represents the count subscript.

9. A train health status monitoring system according to claim 8, characterized in that: The train fault diagnosis algorithm is as follows: In the formula, Gini(t) represents the impurity used to evaluate node t. The smaller it is, the higher the purity of the node. C represents the total number of categories, which is used to indicate whether the train is faulty or normal. k It represents the proportion of samples of the kth category in node t, where k represents the subscript.

10. A train health status monitoring system according to claim 9, characterized in that: The generation formula of the fault warning signal is as follows: W=F*S In the formula, W represents the fault warning signal, F represents the fault flag, which is 1 or 0, and S represents the strength of the fault signal. A value of 1 represents a minor fault, a value of 2 represents a moderate fault, and a value of 3 represents a severe fault.

Images