Digital signal processing and analyzing device for high-speed motor train unit

Through modular signal processing and analysis devices, combined with machine learning and hardware acceleration technology, the problem of large data volume and real-time requirements of high-speed EMUs is solved, high-precision fault diagnosis and performance optimization are achieved, and the safe operation of the train is ensured.

CN118964848APending Publication Date: 2024-11-15DALIAN DATIE TONGYI S&T CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411041850.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The data volume of high-speed EMUs is large, complex, and requires real-time monitoring of train status, requiring high accuracy and reliability to ensure safety and operational efficiency.

Method used

A modular signal processing and analysis device including data acquisition, signal preprocessing, feature extraction and selection, fault diagnosis and prediction, real-time guarantee, system integration and optimization was designed, using machine learning, deep learning, parallel computing, and distribution. Format calculation and hardware acceleration technology, combining wavelet transformation, principal component analysis, support vector machine and neural network algorithms, data preprocessing, feature extraction and fault diagnosis.

Benefits of technology

Real-time monitoring and fault diagnosis of the status of high-speed EMUs is realized, the accuracy and performance optimization of fault diagnosis are improved, and the safe operation and processing efficiency of the train are ensured.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118964848A_ABST
    Figure CN118964848A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of signal processing and analyzing devices, and discloses a digital signal processing and analyzing device for a high-speed motor train unit, comprising a data acquisition module which is responsible for acquiring data from a sensor of each part of the train and transmitting the data to a processing unit; the signal preprocessing module is used for carrying out filtering, noise reduction and abnormal value removal preprocessing operation on the collected original data so as to improve the accuracy and stability of subsequent analysis; the feature extraction and selection module is used for extracting effective features from the preprocessed data and performing screening according to a feature selection method so as to reduce data dimensions and improve analysis efficiency; and the fault diagnosis and prediction module analyzes the extracted features by adopting a machine learning or deep learning algorithm to realize real-time monitoring, fault diagnosis and performance prediction of the train state. The train state can be monitored in real time in the train running process, the fault diagnosis accuracy is improved, the train performance is optimized, and safe running of the train is ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the field of signal processing and analysis devices, and in particular to a high-speed train set digital signal processing and analysis device. Background Art

[0002] In the operation of high-speed EMUs, digital signal processing and analysis devices play a key role. They are mainly used to process sensor data from various components of the train, such as speed, temperature, vibration, etc., and analyze these data to achieve functions such as train status monitoring, fault diagnosis, and performance optimization. However, when processing and analyzing these data, the following problems are often encountered:

[0003] Large amount of data and high complexity: The amount of data generated by the various components of the high-speed EMU is huge, diverse and complex, requiring effective processing and analysis methods.

[0004] Real-time requirements: The train status needs to be monitored timely and accurately during train operation, so the signal processing and analysis device needs to have high real-time performance.

[0005] Accuracy and reliability: The accuracy and reliability of processing and analysis results directly affect the safety and operating efficiency of trains. Therefore, effective algorithms and technologies are required to ensure the accuracy and credibility of the results.

[0006] In order to solve the above problems, the present application proposes a high-speed train digital signal processing and analysis device. Summary of the invention

[0007] (I) Purpose of the invention

[0008] In order to solve the technical problems existing in the background technology, the present invention proposes a high-speed EMU digital signal processing and analysis device, which can monitor the train status in real time during the train operation, improve the accuracy of fault diagnosis, optimize the train performance, and ensure the safe operation of the train.

[0009] (II) Technical solution

[0010] In order to solve the above problems, the present invention provides a high-speed train digital signal processing and analysis device, comprising:

[0011] The data acquisition module is responsible for collecting data from sensors of various components of the train and transmitting it to the processing unit;

[0012] The signal preprocessing module performs filtering, noise reduction, and outlier removal preprocessing operations on the collected raw data to improve the accuracy and stability of subsequent analysis;

[0013] Feature extraction and selection module, used to extract effective features from preprocessed data and screen them according to feature selection methods to reduce data dimensions and improve analysis efficiency;

[0014] The fault diagnosis and prediction module uses machine learning or deep learning algorithms to analyze the extracted features to achieve real-time monitoring of train status, fault diagnosis, and performance prediction;

[0015] The real-time guarantee module optimizes the algorithm design and adopts efficient parallel computing and distributed computing technologies to ensure the real-time and efficiency of processing and analysis.

[0016] The system integration and optimization module is used to integrate the above modules and perform system optimization to ensure the stability and performance of the entire system.

[0017] Preferably, the data acquisition module includes:

[0018] Speed ​​sensor, used to collect speed data of high-speed EMU;

[0019] Temperature sensor, used to collect temperature data of each component;

[0020] Vibration sensors, used to monitor the vibration of the EMU;

[0021] Current sensors, used to monitor the current in the power system;

[0022] Wired communication module, used for wired data transmission;

[0023] Wireless communication module, used for wireless data transmission.

[0024] Preferably, the signal preprocessing module includes:

[0025] A digital filter is used to filter the collected data;

[0026] Wavelet denoising algorithm, used to remove noise from the signal;

[0027] Anomaly detection algorithms are used to detect anomalies in data.

[0028] Preferably, the feature extraction and selection module includes:

[0029] Wavelet transform algorithm is used to extract the time-frequency characteristics of the signal;

[0030] Principal component analysis algorithm is used to select the main features in the data.

[0031] Preferably, the fault diagnosis and prediction module includes:

[0032] Support vector machine algorithm to classify the data into faults;

[0033] Neural network algorithms for predicting system performance.

[0034] Preferably, the real-time guarantee module includes:

[0035] Multi-threaded processing unit to increase data processing speed;

[0036] Distributed computing units, used to share computing tasks;

[0037] GPU acceleration unit, which uses GPU to accelerate parallel computing.

[0038] Preferably, the system integration and optimization module includes:

[0039] FPGA acceleration unit, used for hardware acceleration;

[0040] ASIC acceleration unit, used to customize ASIC chips to improve computing performance;

[0041] The algorithm optimization unit is used to optimize the algorithm to improve efficiency and performance.

[0042] The above technical solution of the present invention has the following beneficial technical effects:

[0043] Sensors are used to collect data from various components of the train and transmitted to the processing unit. The collected raw data is preprocessed by filtering, denoising, and outlier processing to obtain clean data; time-frequency analysis and wavelet transform methods are used to extract frequency domain and time domain characteristics of the data; correlation analysis, principal component analysis and other methods are used to select the most representative features to reduce redundant information; based on the selected features, support vector machines, neural networks and other algorithms are used for fault diagnosis and performance prediction; parallel computing, GPU acceleration and other technologies are used to improve the efficiency of algorithm operation and ensure real-time requirements; various modules are integrated and system-level optimization is performed, including hardware acceleration and algorithm optimization; the algorithm is verified through actual train data, and the system is tuned and improved to improve accuracy and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 The present invention is a schematic structural diagram of a high-speed train digital signal processing and analysis device proposed by the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0046] like Figure 1 As shown, the present invention proposes a high-speed train digital signal processing and analysis device, comprising:

[0047] The data acquisition module is responsible for collecting data from sensors of various components of the train and transmitting it to the processing unit;

[0048] The data acquisition module includes:

[0049] Speed ​​sensor, used to collect speed data of high-speed EMU;

[0050] Temperature sensor, used to collect temperature data of each component;

[0051] Vibration sensors, used to monitor the vibration of the EMU;

[0052] Current sensors, used to monitor the current in the power system;

[0053] Wired communication module, used for wired data transmission;

[0054] Wireless communication module, used for wireless data transmission.

[0055] The signal preprocessing module performs filtering, noise reduction, and outlier removal preprocessing operations on the collected raw data to improve the accuracy and stability of subsequent analysis;

[0056] The signal preprocessing module includes:

[0057] A digital filter is used to filter the collected data;

[0058] Wavelet denoising algorithm, used to remove noise from the signal;

[0059] Anomaly detection algorithms are used to detect anomalies in data.

[0060] Feature extraction and selection module, used to extract effective features from preprocessed data and screen them according to feature selection methods to reduce data dimensions and improve analysis efficiency;

[0061] Feature extraction algorithm: The wavelet transform algorithm is used to decompose the original signal into wavelet coefficients of different frequencies to obtain the time-frequency feature representation.

[0062] formula:

[0063] W(a,b): wavelet coefficients;

[0064] x(t): original signal;

[0065] ψa,b(t)dt: wavelet function.

[0066] The feature extraction and selection module includes:

[0067] Wavelet transform algorithm is used to extract the time-frequency characteristics of the signal;

[0068] Principal component analysis algorithm is used to select the main features in the data.

[0069] The fault diagnosis and prediction module uses machine learning or deep learning algorithms to analyze the extracted features to achieve real-time monitoring of train status, fault diagnosis, and performance prediction;

[0070] Feature selection algorithm: The principal component analysis (PCA) algorithm is used to select the most representative features through the maximum variance principle.

[0071] Formula Y = X·V;

[0072] Y: feature vector after dimensionality reduction;

[0073] X: original feature matrix;

[0074] V : eigenvector matrix.

[0075] The fault diagnosis and prediction module includes:

[0076] Support vector machine algorithm to classify the data into faults;

[0077] Neural network algorithms for predicting system performance.

[0078] The real-time guarantee module optimizes the algorithm design and adopts efficient parallel computing and distributed computing technologies to ensure the real-time and efficiency of processing and analysis.

[0079] Fault diagnosis algorithm: Support vector machine (SVM) algorithm is used for fault classification, and kernel function is used to map nonlinear problems into high-dimensional space.

[0080] formula:

[0081] f(x): decision function;

[0082] a i Support vector weights;

[0083] y i : Category label;

[0084] K(x i ,x);

[0085] The real-time guarantee module includes:

[0086] Multi-threaded processing unit to increase data processing speed;

[0087] Distributed computing units, used to share computing tasks;

[0088] GPU acceleration unit, which uses GPU to accelerate parallel computing.

[0089] The system integration and optimization module is used to integrate the above modules and perform system optimization to ensure the stability and performance of the entire system.

[0090] System integration and optimization modules include:

[0091] FPGA acceleration unit, used for hardware acceleration;

[0092] ASIC acceleration unit, used to customize ASIC chips to improve computing performance;

[0093] The algorithm optimization unit is used to optimize the algorithm to improve efficiency and performance.

[0094] It should be understood that the above specific embodiments of the present invention are only used to illustrate or explain the principles of the present invention, and do not constitute a limitation of the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modifications that fall within the scope and boundaries of the appended claims, or the equivalent forms of such scope and boundaries.

Claims

1. A high-speed train digital signal processing and analysis device, characterized in that: include: The data acquisition module is responsible for collecting data from sensors of various components of the train and transmitting it to the processing unit; The signal preprocessing module performs filtering, noise reduction, and outlier removal preprocessing operations on the collected raw data; Feature extraction and selection module, used to extract effective features from preprocessed data and screen them according to feature selection methods; The fault diagnosis and prediction module uses machine learning or deep learning algorithms to analyze the extracted features to achieve real-time monitoring of train status, fault diagnosis, and performance prediction; The real-time guarantee module optimizes the algorithm design and adopts efficient parallel computing and distributed computing technologies to ensure the real-time and efficiency of processing and analysis. The system integration and optimization module is used to integrate the above modules and perform system optimization to ensure the stability and performance of the entire system.

2. A high-speed train digital signal processing and analysis device according to claim 1, characterized in that: The data acquisition module includes: Speed ​​sensor, used to collect speed data of high-speed EMU; Temperature sensor, used to collect temperature data of each component; Vibration sensors, used to monitor the vibration of the EMU; Current sensors, used to monitor the current in the power system; Wired communication module, used for wired data transmission; Wireless communication module, used for wireless data transmission.

3. A high-speed train digital signal processing and analysis device according to claim 2, characterized in that: The signal preprocessing module includes: A digital filter is used to filter the collected data; Wavelet denoising algorithm, used to remove noise from the signal; Anomaly detection algorithms are used to detect anomalies in data.

4. A high-speed train digital signal processing and analysis device according to claim 3, characterized in that: The feature extraction and selection module includes: Wavelet transform algorithm is used to extract the time-frequency characteristics of the signal; Principal component analysis algorithm is used to select the main features in the data.

5. A high-speed train digital signal processing and analysis device according to claim 4, characterized in that: The fault diagnosis and prediction module includes: Support vector machine algorithm to classify the data into faults; Neural network algorithms for predicting system performance.

6. A high-speed train digital signal processing and analysis device according to claim 5, characterized in that: The real-time guarantee module includes: Multi-threaded processing unit to increase data processing speed; Distributed computing units, used to share computing tasks; GPU acceleration unit, which uses GPU to accelerate parallel computing.

7. A high-speed train digital signal processing and analysis device according to claim 6, characterized in that: System integration and optimization modules include: FPGA acceleration unit, used for hardware acceleration; ASIC acceleration unit, used to customize ASIC chips to improve computing performance; The algorithm optimization unit is used to optimize the algorithm to improve efficiency and performance.

Citation Information

Patent Citations

  • Online monitoring fault diagnosis system and method of train power system

    CN103901882A

  • Data recording device of network control and monitoring system of train

    CN104361652A

  • Diagnosis method for sensor faults of motor train unit braking system

    CN104596780A

  • Safety monitoring method and device for running gear of motor train unit

    CN111516711A

  • Rail transit vehicle state real-time monitoring and predicting system and method and vehicle

    CN116573022A