A method for predicting fatigue life and health management of key components of a motor train unit bogie

Abstract

This invention discloses a method for predicting the fatigue life and health management of key components of EMU bogies, belonging to the field of EMU bogie operation and maintenance monitoring technology. The method includes the following steps: S1, synchronous acquisition of multi-source operating data; S2, load characteristic inversion and working condition analysis; S3, phased fatigue life assessment: based on the material fatigue performance, structural welding characteristics, and actual alternating loads of each key component, a fatigue damage accumulation analysis method is used to assess and predict the fatigue damage initiation stage and crack propagation stage in two phases; S4, comprehensive health status analysis of multiple indicators; S5, dynamic correction of health and lifespan: enabling the remaining fatigue life to be adaptively updated according to the actual aging and degradation process of the components; S6, multi-component coupled linkage decision-making; S7, visualization and hierarchical early warning. This invention possesses the technical effects of comprehensive assessment, fitting real working conditions, accurate dynamic correction, scientific operation and maintenance decision-making, and timely early warning.

Description

Technical Field

[0001] This invention belongs to the field of EMU bogie operation and maintenance monitoring technology, and particularly relates to a method for predicting the fatigue life and health management of key components of EMU bogies. Background Technology

[0002] As the core running gear component of high-speed trains, the bogie plays a crucial role in transmitting loads, mitigating shocks, and ensuring smooth and safe operation. Its key components, such as the bogie frame, axle box bearings, wheel treads, and primary and secondary suspensions, are subjected to alternating loads, impact loads, and vibration loads over long periods. This makes them susceptible to fatigue damage accumulation, performance degradation with increasing operating mileage, and the initiation and propagation of microcracks. In severe cases, this can lead to component failure and traffic accidents. With the increasing operating speed and mileage of high-speed trains, higher demands are placed on the fatigue life prediction and health management of key bogie components. While existing technologies have been applied, some shortcomings remain, making it difficult to meet actual operational needs.

[0003] Existing technologies mostly focus on monitoring or estimating the lifespan of a single component, lacking a holistic assessment of multiple components. Fatigue life prediction often relies on offline fixed load spectra, which is not conducive to inverting the actual load under actual working conditions, resulting in insufficient prediction accuracy. Lifespan prediction and health assessment are independent of each other, lacking a dynamic closed-loop correction mechanism, and cannot achieve integrated management of simultaneous monitoring, accurate prediction, scientific classification, and coordinated operation and maintenance of multiple components. Summary of the Invention

[0004] To address the problems existing in the prior art, this invention provides a method for predicting the fatigue life and health management of key components of EMU bogies. It has the advantages of comprehensive assessment, fitting real working conditions, accurate dynamic correction, scientific operation and maintenance decision-making, and timely early warning. It solves the problems of single component assessment, low prediction accuracy, separation of life and health, and isolated operation and maintenance strategies in the prior art.

[0005] This invention is implemented as follows: a method for predicting the fatigue life and managing the health of key components of a high-speed train bogie, comprising the following steps: S1. Synchronous acquisition of multi-source operation data: Real-time acquisition of operation monitoring data and basic maintenance data of key components of EMU bogies; S2. Load characteristic inversion and working condition analysis: Based on the collected multi-source data and combined with the mechanical transmission relationship of the bogie multi-body structure, the load inversion analysis approach is adopted to analyze the alternating load and load fluctuation law of each key component under different operating speeds and different track conditions, so as to obtain load time series data that fits the actual operating conditions. S3. Staged fatigue life assessment: Based on the material fatigue performance, structural welding characteristics and actual alternating load of each key component, the fatigue damage accumulation analysis method is used to assess and predict the fatigue damage initiation stage and crack propagation stage in two stages. S4. Multi-indicator comprehensive health status analysis: Select core assessment indicators, adopt a multi-indicator comprehensive evaluation mechanism, allocate corresponding weights according to the degree of influence of each indicator on driving safety, and divide the health status of each key component into five levels: normal, slight degradation, moderate degradation, severe degradation, and fault warning. S5. Health-Life Dynamic Correction: Based on the health level degradation of each key component, the baseline conditions for fatigue life assessment and the damage accumulation judgment scale are dynamically adjusted in real time. The life prediction results are corrected in reverse by using the health status evolution trend, so that the remaining fatigue life can be adaptively updated as the component actually ages and degrades. S6. Multi-component coupling and linkage decision-making: Considering the correlation between load coupling and damage transmission among key components of the bogie, and combining the health level, remaining life, maintenance cost and driving safety constraints of each component, the flaw detection cycle, life replacement threshold and maintenance operation priority of each component are formulated in a coordinated manner. S7. Visualization and Hierarchical Early Warning: Visualize the fatigue life change trend, health status distribution, maintenance schedule, and process sequence of each component. When the remaining life or health level of a component reaches the preset warning threshold, the corresponding level of warning will be automatically triggered and a prompt message will be pushed to the operation and maintenance terminal.

[0006] As a preferred embodiment of the present invention, in step S1, edge computing + 5G transmission is used to achieve millisecond-level synchronous acquisition and preprocessing of multi-source data, and outliers are removed for data alignment. The key components include bogie frame, axle box bearing, wheelset tread, primary and secondary suspension components. The data includes vibration data, structural strain data, operating temperature data, train operating condition data, track environment data, and historical maintenance and operation records data.

[0007] This setup enables high-precision and timely synchronous acquisition of multiple types of monitoring data, completes raw data preprocessing and anomaly removal, and aligns and normalizes the time axis, ensuring the data foundation for subsequent load inversion and life assessment is authentic and reliable, while fully covering all core and critical components of the bogie and multi-dimensional operation and maintenance data dimensions.

[0008] As a preferred embodiment of the present invention, in step S2, the load transmission deviation of a single component is corrected by utilizing the structural mechanical correlation characteristics of the bogie, the interference of vehicle speed, track curve, and slope conditions on the load is eliminated, and stable and effective alternating load characteristics are extracted.

[0009] This setting can correct load estimation deviations caused by structural transmission, eliminate interference factors from external operating conditions, accurately extract the real alternating load variation characteristics of each key component, and make subsequent life assessments fit the actual operating stress state of the train.

[0010] As a preferred embodiment of the present invention, in step S3, a comprehensive evaluation is conducted based on the fatigue damage accumulation analysis method and the crack propagation evolution law. Combined with the fatigue characteristic evaluation logic, the current fatigue damage level of each key component is comprehensively determined, and the remaining fatigue life and long-term decay trend are estimated.

[0011] This setup comprehensively covers the entire fatigue evolution process of a component from both the damage initiation and crack propagation levels, accurately assesses the current degree of damage accumulation, and predicts the remaining lifespan and long-term degradation pattern of the component. The assessment dimensions are complete and the judgment basis is sufficient.

[0012] As a preferred embodiment of the present invention, in step S4, the core evaluation indicators include structural stress level, temperature anomaly degree, vibration characteristic amplitude, fatigue damage degree, and remaining life margin. A weighted comprehensive evaluation approach is adopted to complete the multi-indicator fusion rating, taking into account objective data characteristics and operation and maintenance experience, so as to ensure that the health classification results are consistent with the actual on-site operation and maintenance standards.

[0013] This setup enables the construction of a comprehensive multi-dimensional evaluation indicator system. Through weighted comprehensive evaluation, quantitative grading is achieved, taking into account both objective monitoring data and actual operation and maintenance experience, so that the health level classification results are reasonable and in line with on-site operation and maintenance management requirements.

[0014] As a preferred embodiment of the present invention, in step S5, a long short-term memory network (LSTM) is used to capture the health degradation trend, predict the health level evolution 30-90 days in advance, track the continuous change trend of the health level, predict the degradation development trend of the component, and correct the medium and long-term fatigue life prediction results in advance.

[0015] This setting enables precise capture of the continuous degradation pattern of component health status, long-term prediction of health level evolution, and reverse correction of fatigue life assessment results, so that the remaining life is no longer a fixed static value, but can be dynamically updated according to the actual degradation process of the component.

[0016] As a preferred embodiment of the present invention, in step S6, the effects of fault transmission and load coupling between components are incorporated to avoid maintenance waste or safety oversights caused by independently formulating maintenance plans for each component. The visualization is presented in the form of statistical charts, timelines, and Gantt charts.

[0017] This design fully considers the load correlation and damage transmission characteristics between various bogie components, abandons the isolated operation and maintenance mode of single components, and realizes coordinated decision-making of multiple components, thereby improving the economic efficiency of operation and maintenance while ensuring operational safety.

[0018] As a preferred embodiment of the present invention, in step S7, customizable lifespan warning thresholds and health level classification thresholds are supported, and the warning methods include interface pop-ups, background log recording, and mobile terminal message push.

[0019] This setting allows for flexible configuration of early warning judgment criteria based on operation and maintenance management needs, enabling simultaneous status visualization and tiered early warning pushes through multiple channels, facilitating timely understanding of component status and enabling maintenance personnel to carry out repairs and maintenance.

[0020] Compared with the prior art, the beneficial effects of the present invention are as follows: Simultaneously covering multiple core and critical components of the bogie, it achieves unified collection and preprocessing of multi-source operation and maintenance data; through load inversion analysis, it obtains alternating load characteristics that conform to actual working conditions, overcoming the limitations of traditional offline fixed load spectra; it adopts fatigue damage accumulation and crack propagation laws to assess fatigue life in stages, with complete assessment dimensions; it constructs a multi-index comprehensive health grading system, with grading standards that conform to actual on-site operation and maintenance; it introduces a long short-term memory network to capture health degradation trends, achieving dynamic closed-loop correction of health status and fatigue life; it also considers the load coupling and fault propagation relationship between components, forming multi-component coupled linkage operation and maintenance decision-making; and it is equipped with multi-form visualization display and multi-channel graded early warning mechanism.

[0021] The overall solution integrates data acquisition, load analysis, life prediction, health classification, closed-loop correction, coordinated operation and maintenance, and visualized early warning. It has high assessment accuracy, wide coverage, scientific operation and maintenance decision-making, and more timely early warning response, effectively meeting the actual needs of safe and healthy operation and maintenance of EMU bogies throughout the entire life cycle. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of the method flow provided in an embodiment of the present invention. Detailed Implementation

[0023] To further understand the invention's content, features, and effects, the following embodiments are provided, and detailed descriptions are given in conjunction with the accompanying drawings.

[0024] The structure of the present invention will now be described in detail with reference to the accompanying drawings.

[0025] refer to Figure 1 As shown in the figure, an embodiment of the present invention provides a method for predicting the fatigue life and managing the health of key components of a high-speed train bogie, comprising the following steps: S1. Synchronous acquisition of multi-source operation data: Real-time acquisition of operation monitoring data and basic maintenance data of key components of EMU bogies; S2. Load characteristic inversion and working condition analysis: Based on the collected multi-source data and combined with the mechanical transmission relationship of the bogie multi-body structure, the load inversion analysis approach is adopted to analyze the alternating load and load fluctuation law of each key component under different operating speeds and different track conditions, so as to obtain load time series data that fits the actual operating conditions. S3. Staged fatigue life assessment: Based on the material fatigue performance, structural welding characteristics and actual alternating load of each key component, the fatigue damage accumulation analysis method is used to assess and predict the fatigue damage initiation stage and crack propagation stage in two stages. S4. Multi-indicator comprehensive health status analysis: Select core assessment indicators, adopt a multi-indicator comprehensive evaluation mechanism, allocate corresponding weights according to the degree of influence of each indicator on driving safety, and divide the health status of each key component into five levels: normal, slight degradation, moderate degradation, severe degradation, and fault warning. S5. Health-Life Dynamic Correction: Based on the health level degradation of each key component, the baseline conditions for fatigue life assessment and the damage accumulation judgment scale are dynamically adjusted in real time. The life prediction results are corrected in reverse by using the health status evolution trend, so that the remaining fatigue life can be adaptively updated as the component actually ages and degrades. S6. Multi-component coupling and linkage decision-making: Considering the correlation between load coupling and damage transmission among key components of the bogie, and combining the health level, remaining life, maintenance cost and driving safety constraints of each component, the flaw detection cycle, life replacement threshold and maintenance operation priority of each component are formulated in a coordinated manner. S7. Visualization and Hierarchical Early Warning: Visualize the fatigue life change trend, health status distribution, maintenance schedule, and process sequence of each component. When the remaining life or health level of a component reaches the preset warning threshold, the corresponding level of warning will be automatically triggered and a prompt message will be pushed to the operation and maintenance terminal.

[0026] Specifically, in step S1, edge computing + 5G transmission is used to achieve millisecond-level synchronous acquisition and preprocessing of multi-source data, and outliers are removed for data alignment. The key components include bogie frame, axle box bearing, wheelset tread, primary and secondary suspension components. The data includes vibration data, structural strain data, operating temperature data, train operating condition data, track environment data, and historical maintenance and operation records data.

[0027] By adopting the above scheme, high-precision and high-time synchronous acquisition of multiple types of monitoring data can be achieved, and raw data preprocessing, anomaly removal, and time axis alignment and regularization can be completed to ensure that the data foundation for subsequent load inversion and life assessment is true and reliable. At the same time, it fully covers all core and key components of the bogie and multi-dimensional operation and maintenance data dimensions.

[0028] Specifically, in step S2, the load transmission deviation of a single component is corrected by utilizing the structural mechanical correlation characteristics of the bogie, the interference of vehicle speed, track curve, and slope conditions on the load is eliminated, and stable and effective alternating load characteristics are extracted.

[0029] By adopting the above scheme, the load estimation deviation caused by structural transmission can be corrected, the interference factors of external operating conditions can be eliminated, and the real alternating load change characteristics of each key component can be accurately extracted, so that the subsequent life assessment can be consistent with the actual operating stress state of the train.

[0030] Specifically, in step S3, a comprehensive assessment is conducted based on the fatigue damage accumulation analysis method and the crack propagation evolution law. Combined with the fatigue characteristic evaluation logic, the current fatigue damage level of each key component is comprehensively determined, and the remaining fatigue life and long-term decay trend are estimated.

[0031] The above scheme comprehensively covers the entire fatigue evolution process of a component from two levels: damage initiation and crack propagation. It accurately assesses the current degree of damage accumulation and predicts the remaining lifespan and long-term decay pattern of the component. The assessment dimensions are complete and the judgment basis is sufficient.

[0032] Specifically, in step S4, the core evaluation indicators include structural stress level, temperature anomaly degree, vibration characteristic amplitude, fatigue damage degree, and remaining life margin. A weighted comprehensive evaluation approach is adopted to complete the multi-indicator fusion rating, taking into account objective data characteristics and operation and maintenance experience, to ensure that the health classification results are consistent with the actual on-site operation and maintenance standards.

[0033] By adopting the above scheme, a multi-dimensional and complete evaluation index system is constructed. Quantitative grading is achieved through weighted comprehensive evaluation, taking into account both objective monitoring data and actual operation and maintenance experience, so that the health level classification results are reasonable and in line with on-site operation and maintenance management requirements.

[0034] Specifically, in step S5, a Long Short-Term Memory (LSTM) network is used to capture the trend of health degradation, predict the evolution of health level 30-90 days in advance, track the continuous change trend of health level, predict the development trend of component degradation, and correct the medium and long-term fatigue life prediction results in advance.

[0035] By adopting the above scheme, we can accurately capture the continuous degradation pattern of component health status, realize the prediction of medium and long-term evolution of health level, and reverse the fatigue life assessment results, so that the remaining life is no longer a fixed static value, but can be dynamically updated with the actual degradation process of the component.

[0036] Specifically, in step S6, the effects of fault propagation and load coupling between components are incorporated to avoid maintenance waste or safety oversights caused by developing maintenance plans independently for each component. The visualization is presented in the form of statistical charts, timelines, and Gantt charts.

[0037] By adopting the above scheme, the load correlation and damage transmission characteristics between various bogie components are fully considered, the isolated operation and maintenance mode of single components is abandoned, and the coordinated decision-making of multiple components is realized, thereby improving the operation and maintenance economy while ensuring operational safety.

[0038] Specifically, in step S7, customizable lifespan warning thresholds and health level classification thresholds are supported, and the warning methods include interface pop-ups, background log recording, and mobile message push.

[0039] By adopting the above solution, early warning judgment criteria can be flexibly configured according to operation and maintenance management needs, and status visualization and hierarchical early warning push can be realized through multiple channels simultaneously, which makes it easier for operation and maintenance personnel to grasp the status of components in a timely manner and carry out maintenance and disposal.

[0040] This invention forms a systematic solution that integrates data acquisition, load analysis, life prediction, health classification, closed-loop correction, coordinated operation and maintenance, and visual early warning. It has high assessment accuracy, wide coverage, scientific operation and maintenance decision-making, and more timely early warning response, effectively meeting the actual needs of safe and healthy operation and maintenance of EMU bogies throughout the entire life cycle.

[0041] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0042] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for predicting the fatigue life and managing the health of key components of a high-speed train bogie, characterized in that, Includes the following steps: S1. Synchronous acquisition of multi-source operation data: Real-time acquisition of operation monitoring data and basic maintenance data of key components of EMU bogies; S2. Load characteristic inversion and working condition analysis: Based on the collected multi-source data and combined with the mechanical transmission relationship of the bogie multi-body structure, the load inversion analysis approach is adopted to analyze the alternating load and load fluctuation law of each key component under different operating speeds and different track conditions, so as to obtain load time series data that fits the actual operating conditions. S3. Staged fatigue life assessment: Based on the material fatigue performance, structural welding characteristics and actual alternating load of each key component, the fatigue damage accumulation analysis method is used to assess and predict the fatigue damage initiation stage and crack propagation stage in two stages. S4. Multi-indicator comprehensive health status analysis: Select core assessment indicators, adopt a multi-indicator comprehensive evaluation mechanism, allocate corresponding weights according to the degree of influence of each indicator on driving safety, and divide the health status of each key component into five levels: normal, slight degradation, moderate degradation, severe degradation, and fault warning. S5. Health-Life Dynamic Correction: Based on the health level degradation of each key component, the baseline conditions for fatigue life assessment and the damage accumulation judgment scale are dynamically adjusted in real time. The life prediction results are corrected in reverse by using the health status evolution trend, so that the remaining fatigue life can be adaptively updated as the component actually ages and degrades. S6. Multi-component coupling and linkage decision-making: Considering the correlation between load coupling and damage transmission among key components of the bogie, and combining the health level, remaining life, maintenance cost and driving safety constraints of each component, the flaw detection cycle, life replacement threshold and maintenance operation priority of each component are formulated in a coordinated manner. S7. Visualization and Hierarchical Early Warning: Visualize the fatigue life change trend, health status distribution, maintenance schedule, and process sequence of each component. When the remaining life or health level of a component reaches the preset warning threshold, the corresponding level of warning will be automatically triggered and a prompt message will be pushed to the operation and maintenance terminal.

2. The method for predicting the fatigue life and managing the health of key components of a high-speed train bogie as described in claim 1, characterized in that: In step S1, edge computing + 5G transmission is used to achieve millisecond-level synchronous acquisition and preprocessing of multi-source data, and outliers are removed for data alignment. The key components include bogie frame, axle box bearing, wheelset tread, primary and secondary suspension components. The data includes vibration data, structural strain data, operating temperature data, train operating condition data, track environment data, and historical maintenance and operation records data.

3. The method for predicting the fatigue life and managing the health of key components of a high-speed train bogie as described in claim 1, characterized in that: In step S2, the load transmission deviation of a single component is corrected by utilizing the structural mechanical correlation characteristics of the bogie, the interference of vehicle speed, track curve, and slope conditions on the load is eliminated, and stable and effective alternating load characteristics are extracted.

4. The method for predicting the fatigue life and managing the health of key components of a high-speed train bogie as described in claim 1, characterized in that: In step S3, a comprehensive evaluation is conducted based on the fatigue damage accumulation analysis method and the crack propagation evolution law. Combined with the fatigue characteristic evaluation logic, the current fatigue damage level of each key component is determined, and the remaining fatigue life and long-term decay trend are estimated.

5. The method for predicting the fatigue life and managing the health of key components of a high-speed train bogie as described in claim 1, characterized in that: In step S4, the core evaluation indicators include structural stress level, temperature anomaly degree, vibration characteristic amplitude, fatigue damage degree, and remaining life margin. A weighted comprehensive evaluation approach is adopted to complete the multi-indicator fusion rating, taking into account objective data characteristics and operation and maintenance experience, so as to ensure that the health classification results are consistent with the actual on-site operation and maintenance standards.

6. The method for predicting the fatigue life and managing the health of key components of a high-speed train bogie as described in claim 1, characterized in that: In step S5, a Long Short-Term Memory (LSTM) network is used to capture the health degradation trend, predict the health level evolution 30-90 days in advance, track the continuous change trend of the health level, predict the degradation development of components, and correct the medium and long-term fatigue life prediction results in advance.

7. The method for predicting the fatigue life and managing the health of key components of a high-speed train bogie as described in claim 1, characterized in that: In step S6, the effects of fault propagation and load coupling between components are taken into account to avoid maintenance waste or safety oversights caused by developing maintenance plans for individual components. The visualization is presented in the form of statistical charts, timelines, and Gantt charts.

8. The method for predicting the fatigue life and managing the health of key components of a high-speed train bogie as described in claim 1, characterized in that: In step S7, customizable lifespan warning thresholds and health level classification thresholds are supported. The warning methods include interface pop-ups, background log recording, and mobile message push.

Images