Fatigue life prediction method and system for rail vehicle cantilever structure

Abstract

The present invention provides a fatigue life prediction method and system for a rail vehicle cantilever structure. The method comprises the following steps: building a test bench to test the cantilever structure, obtaining acceleration and stress data of the cantilever structure, and establishing a BP neural network training system to obtain an acceleration-stress function; obtaining a stress prediction value of the cantilever structure based on the acceleration-stress function according to the measured acceleration of the rail vehicle; compiling a stress spectrum by a rain flow counting method based on the stress prediction value; obtaining a stress probability density function according to the stress spectrum, solving and obtaining a stress maximum value, compiling an extended stress spectrum, and determining a critical size of a defect of the cantilever structure based on the stress maximum value; and using a cumulative damage method or a fracture mechanics method to perform life prediction based on a comparison between an actual defect size of the cantilever structure and the critical defect size, so as to truly reflect the stress level of the cantilever structure of the rail vehicle in service, thereby accurately predicting the remaining life of the cantilever structure.

Description

Technical Field

[0001] The present invention relates to the technical field of rail vehicles, and in particular to a fatigue life prediction method and system for a rail vehicle cantilever structure. Background Art

[0002] With the rapid development of rail transit, the operating speed of rail vehicles is also constantly improving. However, as rail transit is operated in a more severe environment, the conditions of rail transit lines are also deteriorating. This will cause the vibration load on the cantilever structure of the rail vehicle to continue to increase, especially the vibration load on the bogie will continue to increase, especially the impact on the primary unsprung components is more serious.

[0003] However, during the operation of rail vehicles, they are mainly subjected to non-stationary vibration loads generated by wheel-rail excitation. The current random vibration fatigue assessment method for rail vehicle cantilever structures is still in the research stage. Therefore, there is an urgent need for a fatigue life prediction method and system for rail vehicle cantilever structures to predict and evaluate the fatigue life of rail vehicle cantilever structures. Summary of the invention

[0004] The present invention provides a method and system for predicting the fatigue life of a rail vehicle cantilever structure, which are used to solve the technical problem that the fatigue life of a rail vehicle cantilever structure is difficult to evaluate in the prior art, and realize the prediction of the rail vehicle cantilever structure.

[0005] The present invention provides a method for predicting fatigue life of a rail vehicle cantilever structure, comprising:

[0006] A test bench was built to test the cantilever structure, to obtain the acceleration and stress data of the cantilever structure, and a BP neural network training system was established to obtain the acceleration-stress function;

[0007] According to the measured acceleration of the rail vehicle, the stress prediction value of the cantilever structure is obtained based on the acceleration-stress function;

[0008] Compile stress spectra using the rainflow counting method based on stress prediction values;

[0009] The stress probability density function is obtained from the stress spectrum, the maximum stress value is obtained and the extended stress spectrum is compiled, and the critical size of the defect of the cantilever structure is determined based on the maximum stress value;

[0010] Based on the comparison between the actual defect size and the critical defect size of the cantilever structure, the life prediction is carried out using the cumulative damage method or the fracture mechanics method.

[0011] According to a fatigue life prediction method for a rail vehicle cantilever structure provided by the present invention, the steps of building a test bench to test the cantilever structure and obtaining acceleration and stress data of the cantilever structure include:

[0012] A vibration test bench is built to perform stress testing on the cantilever structure of the rail vehicle. An acceleration time domain signal is input into the vibration test bench to collect the stress response of the cantilever structure and obtain first data of the acceleration time domain signal-stress response.

[0013] According to a fatigue life prediction method for a rail vehicle cantilever structure provided by the present invention, the step of building a test bench to test the cantilever structure and obtaining acceleration and stress data of the cantilever structure further comprises:

[0014] A rolling vibration test bench was built to collect the acceleration and stress signals of the cantilever structure and obtain the second acceleration-stress data.

[0015] According to a fatigue life prediction method for a rail vehicle cantilever structure provided by the present invention, the BP neural network training system is built in combination with the first data and the second data.

[0016] According to a fatigue life prediction method for a rail vehicle cantilever structure provided by the present invention, the steps of using a cumulative damage method or a fracture mechanics method to predict the life based on the comparison between the actual defect size of the cantilever structure and the critical defect size include:

[0017] During the inspection and flaw detection process or the factory sampling inspection of the cantilever structure, the actual size of the defect of the cantilever structure is compared with the critical size of the defect;

[0018] If the actual size of the defect is larger than the critical size of the defect, the cumulative damage method is used for life prediction;

[0019] If the actual size of the defect is smaller than the critical size of the defect, the fracture mechanics method is used to predict the life.

[0020] The present invention also provides a fatigue life prediction system for a rail vehicle cantilever structure, comprising:

[0021] A vibration test bench is used to perform stress testing on a cantilever structure of a rail vehicle, and based on an input acceleration time domain signal, collect a stress response of the cantilever structure to obtain first data of the acceleration time domain signal-stress response;

[0022] The rolling vibration test bench is used to collect the acceleration and stress signals of the cantilever structure and obtain the second data of acceleration-stress;

[0023] A BP neural network training system is connected to the vibration test bench and the rolling vibration test bench signals to obtain an acceleration-stress function according to the first data and the second data;

[0024] Sensors for measuring the acceleration of rail vehicles;

[0025] A stress prediction value calculation module is connected to the BP neural network training system and the sensor signal, and is used to obtain a stress prediction value of the cantilever structure according to the acceleration-stress function and the measured acceleration of the rail vehicle;

[0026] A stress spectrum compilation module, connected to the stress prediction value calculation module by signal, for compiling a stress spectrum by rain flow counting method according to the stress prediction value;

[0027] a defect critical size calculation module, connected to the stress spectrum compilation module by signal, for obtaining a stress probability density function according to the stress spectrum, solving and obtaining a stress maximum value and compiling an extended stress spectrum, and determining a defect critical size of the cantilever structure based on the stress maximum value; and

[0028] The comparison calculation module is connected to the defect critical size calculation module and the stress spectrum compilation module for inputting the actual size of the defect of the cantilever structure, and based on the comparison between the actual size of the defect and the critical size of the defect, the cumulative damage method or the fracture mechanics method is selected for life prediction calculation, and the remaining life of the cantilever structure is output according to the calculation method combined with the stress spectrum.

[0029] The fatigue life prediction system of the rail vehicle cantilever structure provided by the present invention further includes a health monitoring system of the rail vehicle, and the health monitoring system is signal-connected to the stress prediction value calculation module for real-time monitoring of the stress state of the rail vehicle cantilever structure.

[0030] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the aforementioned methods for predicting fatigue life of a rail vehicle cantilever structure when executing the program.

[0031] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any of the aforementioned methods for predicting fatigue life of a rail vehicle cantilever structure are implemented.

[0032] The present invention also provides a computer program product, which implements the steps of any of the aforementioned methods for predicting fatigue life of a rail vehicle cantilever structure when the computer program product is run on an electronic device.

[0033] The fatigue life prediction method of the rail vehicle cantilever structure provided by the embodiment of the present invention has at least one of the following beneficial effects:

[0034] 1. Using the measured acceleration of the rail vehicle as the input load can effectively reflect the actual service environment and load conditions of the cantilever structure, and can truly reflect the stress level of the rail vehicle cantilever structure under service, so as to accurately predict the remaining life of the cantilever structure;

[0035] 2. Use the BP neural network training system to establish the acceleration-stress function, and combine the measured acceleration as the input load to obtain the stress response of the rail vehicle cantilever structure, which can accurately reflect the actual stress level of the structure;

[0036] 3. The rain flow counting method is used to sort out statistics and compile stress spectra, so that the predicted stress distribution characteristics are basically consistent with the measured stress, and the relative fatigue damage deviation of the cantilever structure is small, so that the remaining life error of the subsequent calculation results is small and the accuracy is high;

[0037] 4. Based on the comparison between the actual defect size and the critical defect size of the cantilever structure, the cumulative damage method or fracture mechanics method is used for life prediction. Different algorithms can be used according to different conditions to make the cantilever structure life calculation more reasonable. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 This is one of the flow diagrams of the fatigue life prediction method of the rail vehicle cantilever structure provided by the present invention;

[0040] Figure 2 This is the second flow chart of the fatigue life prediction method of the rail vehicle cantilever structure provided by the present invention;

[0041] Figure 3 It is a time-stress comparison diagram of the predicted value and the measured value of the stress response of the frame end of the bogie on the Guangzhou-Shenzhen Line;

[0042] Figure 4 It is a time-stress comparison diagram of the predicted value and the measured value of the stress response of the frame end of the bogie on the Yichang-Qianhong line;

[0043] Figure 5 It is a comparison curve between the predicted value and the measured value of the stress spectrum of the frame end of the bogie on the Guangzhou-Shenzhen Line;

[0044] Figure 6 This is a comparison curve between the predicted and measured values ​​of the stress spectrum at the frame end of the bogie on the Yichang-Qianhong Line. DETAILED DESCRIPTION

[0045] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0046] In the description of the embodiments of the present invention, it should be noted that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limitations on the embodiments of the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0047] In the description of the embodiments of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "connected" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific circumstances.

[0048] In the embodiments of the present invention, unless otherwise clearly specified and limited, the first feature being "above" or "below" the second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, the first feature being "above", "above" and "above" the second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. The first feature being "below", "below" and "below" the second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0049] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0050] Combine the following Figure 1-Figure 6 The fatigue life prediction method of the rail vehicle cantilever structure of the present invention comprises:

[0051] A test bench was built to test the cantilever structure, to obtain the acceleration and stress data of the cantilever structure, and a BP (Back Propagation) neural network training system was established to obtain the acceleration-stress function;

[0052] According to the measured acceleration of the rail vehicle, the stress prediction value of the cantilever structure is obtained based on the acceleration-stress function;

[0053] Compile stress spectra using the rainflow counting method based on stress prediction values;

[0054] The stress probability density function is obtained from the stress spectrum, the maximum stress value is obtained and the extended stress spectrum is compiled, and the critical size of the defect of the cantilever structure is determined based on the maximum stress value;

[0055] Based on the comparison between the actual defect size and the critical defect size of the cantilever structure, the life prediction is carried out using the cumulative damage method or the fracture mechanics method.

[0056] By building a test bench to test the cantilever structure, we can obtain the data on the relationship between the acceleration and stress of the cantilever structure. Based on these data, a BP neural network training system can be established to form an acceleration-stress function. The acceleration-stress function is the corresponding relationship between acceleration and stress under a large number of data, that is, the stress value of the cantilever structure at this time can be obtained based on the input acceleration.

[0057] By using the measured acceleration of the rail vehicle as the input load, the actual service environment and load conditions of the cantilever structure can be effectively reflected, and the stress level of the rail vehicle cantilever structure under service can be truly reflected, thereby accurately predicting the remaining life of the cantilever structure.

[0058] The acceleration-stress function is established using the BP neural network training system, and the measured acceleration is used as the input load to obtain the stress response of the rail vehicle cantilever structure, which can accurately reflect the actual stress level of the structure.

[0059] The rain flow counting method is used to sort out statistics and compile stress spectra, so that the predicted stress distribution characteristics are basically consistent with the measured stress. The relative fatigue damage deviation of the cantilever structure is small (within 15%), so that the remaining life error of the subsequent calculation results is small and the accuracy is high.

[0060] The stress probability density function is obtained according to the stress spectrum, and the maximum stress value is obtained by solving it. The maximum stress value of the cantilever structure within the fatigue life mileage is determined, and then the critical size of the defect is determined, which can provide a theoretical basis for the formulation of the welding process requirements of the cantilever structure.

[0061] Based on the comparison between the actual defect size and the critical defect size of the cantilever structure, the cumulative damage method or the fracture mechanics method can be used to predict the life span. Different algorithms can be used according to different conditions to make the cantilever structure life calculation more reasonable.

[0062] At the same time, this method obtains the test samples required by the BP neural network training system by building a test bench. The method is simple and has a fast calculation speed, and can quickly predict the fatigue life of the cantilever structure.

[0063] According to the fatigue life prediction method of the rail vehicle cantilever structure provided by the present invention, the step of building a test bench to test the cantilever structure and obtaining acceleration and stress data of the cantilever structure comprises:

[0064] A vibration test bench is built to perform stress testing on the cantilever structure of the rail vehicle. An acceleration time domain signal is input into the vibration test bench to collect the stress response of the cantilever structure and obtain first data of the acceleration time domain signal-stress response.

[0065] The step of building a test bench to test the cantilever structure and obtaining acceleration and stress data of the cantilever structure also includes:

[0066] A rolling vibration test bench was built to collect the acceleration and stress signals of the cantilever structure and obtain the second acceleration-stress data.

[0067] The BP neural network training system is built by combining the first data and the second data.

[0068] The BP neural network training system derives the acceleration-stress function based on the acceleration-stress relationship given by the two tests. The acceleration time domain signal input to the vibration test bench can be an electronic input, and tens of thousands of acceleration values ​​can be input per second, and the input time is less than 20 minutes. In this way, sufficient data can be input in the early stage to form a relatively complete acceleration-stress function. This can improve the utilization rate of test data, reduce line test content, and save test costs.

[0069] Based on relatively complete data, for newly designed cantilever structures that have not undergone relevant line tests in the early stage, the vibration acceleration can be tested separately, and the dynamic stress test points can be deleted to reduce the test cost.

[0070] According to the fatigue life prediction method of the rail vehicle cantilever structure provided by the present invention, the step of using the cumulative damage method or the fracture mechanics method to predict the life based on the comparison between the actual defect size of the cantilever structure and the critical defect size comprises:

[0071] During the inspection and flaw detection process or the factory sampling inspection of the cantilever structure, the actual size of the defect of the cantilever structure is compared with the critical size of the defect;

[0072] If the actual size of the defect is larger than the critical size of the defect, the cumulative damage method is used for life prediction;

[0073] If the actual size of the defect is smaller than the critical size of the defect, the fracture mechanics method is used to predict the life.

[0074] According to the actual defect depth of the cantilever structure, the cumulative damage method or the fracture mechanics method is selected for life prediction, which makes the life prediction of the cantilever structure more reasonable and specifies a reasonable maintenance cycle based on the calculated remaining life.

[0075] Taking the rail vehicle bogie and its actual operation as an example for in-depth explanation, the frame end of the bogie is taken as the research object, and the measured acceleration of the Wuhan-Guangzhou line can be selected as the input data of the acceleration time domain signal. The output stress information is combined with the acceleration time domain signal data as a learning sample. The acceleration-stress transfer relationship of the bogie is obtained based on the acceleration and stress information of this sample. The acceleration signal obtained by the Guangzhou-Shenzhen Line and Yichang-Qianhong Line test is used as input, and the stress response curve of the frame end of the bogie can be calculated. Compared with the actual stress response curve, it has good consistency.

[0076] Then the rain flow counting method is used to calculate the data in the Guangshen line and Yichang-Qianhong line to obtain the stress spectrum, such as Figure 3-Figure 6 As shown in the figure, the predicted value and the measured value have the same distribution characteristics. At the same time, the relative fatigue damage is calculated on this basis and normalized. It is found that when the train is operating on the Guangzhou-Shenzhen line, the relative fatigue damage of the predicted value and the measured value of the frame end of the bogie are 1 and 0.92 respectively. When the train is operating on the Yichang-Qianjiang line, the relative fatigue damage of the predicted value and the measured value of the frame end of the bogie are 1 and 0.86 respectively. It can be seen that the fatigue damage caused by the stress prediction value is slightly different from the measured value, and the predicted value damage is slightly higher than the measured value. The comparison result further verifies the effectiveness and accuracy of the fatigue life prediction method proposed in the present invention.

[0077] The fatigue life prediction system of the rail vehicle cantilever structure provided by the present invention is described below. The fatigue life prediction system of the rail vehicle cantilever structure described below and the fatigue life prediction method of the rail vehicle cantilever structure described above can correspond to each other.

[0078] The fatigue life prediction system of rail vehicle cantilever structure includes:

[0079] A vibration test bench is used to perform stress testing on a cantilever structure of a rail vehicle, and based on an input acceleration time domain signal, collect a stress response of the cantilever structure to obtain first data of the acceleration time domain signal-stress response;

[0080] The rolling vibration test bench is used to collect the acceleration and stress signals of the cantilever structure and obtain the second data of acceleration-stress;

[0081] A BP neural network training system is connected to the vibration test bench and the rolling vibration test bench signals to obtain an acceleration-stress function according to the first data and the second data;

[0082] A sensor, used for measuring the acceleration of the rail vehicle, and the sensor may be a sensor for detecting acceleration provided by the rail vehicle;

[0083] A stress prediction value calculation module is connected to the BP neural network training system and the sensor signal, and is used to obtain a stress prediction value of the cantilever structure according to the acceleration-stress function and the measured acceleration of the rail vehicle;

[0084] A stress spectrum compilation module, connected to the stress prediction value calculation module by signal, for compiling a stress spectrum by rain flow counting method according to the stress prediction value;

[0085] a defect critical size calculation module, connected to the stress spectrum compilation module by signal, for obtaining a stress probability density function according to the stress spectrum, solving and obtaining a stress maximum value and compiling an extended stress spectrum, and determining a defect critical size of the cantilever structure based on the stress maximum value; and

[0086] The comparison calculation module is connected to the defect critical size calculation module and the stress spectrum compilation module for inputting the actual size of the defect of the cantilever structure, and based on the comparison between the actual size of the defect and the critical size of the defect, the cumulative damage method or the fracture mechanics method is selected for life prediction calculation, and the remaining life of the cantilever structure is output according to the calculation method combined with the stress spectrum.

[0087] By building a test bench to test the cantilever structure, we can obtain the data on the relationship between the acceleration and stress of the cantilever structure. Based on these data, a BP neural network training system can be established to form an acceleration-stress function. The acceleration-stress function is the corresponding relationship between acceleration and stress under a large number of data, that is, the stress value of the cantilever structure at this time can be obtained based on the input acceleration.

[0088] By using the measured acceleration of the rail vehicle as the input load, the actual service environment and load conditions of the cantilever structure can be effectively reflected, and the stress level of the rail vehicle cantilever structure under service can be truly reflected, thereby accurately predicting the remaining life of the cantilever structure.

[0089] The acceleration-stress function is established using the BP neural network training system, and the measured acceleration is used as the input load to obtain the stress response of the rail vehicle cantilever structure, which can accurately reflect the actual stress level of the structure.

[0090] The rain flow counting method is used to sort out statistics and compile stress spectra, so that the predicted stress distribution characteristics are basically consistent with the measured stress. The relative fatigue damage deviation of the cantilever structure is small (within 15%), so that the remaining life error of the subsequent calculation results is small and the accuracy is high.

[0091] The stress probability density function is obtained according to the stress spectrum, and the maximum stress value is obtained by solving it. The maximum stress value of the cantilever structure within the fatigue life mileage is determined, and then the critical size of the defect is determined, which can provide a theoretical basis for the formulation of the welding process requirements of the cantilever structure.

[0092] Based on the comparison between the actual defect size and the critical defect size of the cantilever structure, the cumulative damage method or the fracture mechanics method can be used to predict the life span. Different algorithms can be used according to different conditions to make the cantilever structure life calculation more reasonable.

[0093] At the same time, this method obtains the test samples required by the BP neural network training system by building a test bench. The method is simple and has a fast calculation speed, and can quickly predict the fatigue life of the cantilever structure.

[0094] The fatigue life prediction system of the rail vehicle cantilever structure also includes a health monitoring system of the rail vehicle, which is connected to the stress prediction value calculation module signal and is used to monitor the stress state of the rail vehicle cantilever structure in real time. Therefore, the stress state of the cantilever structure can be monitored in real time on the rail vehicle.

[0095] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above-mentioned fatigue life prediction methods for rail vehicle cantilever structures when executing the program. The fatigue life prediction method for rail vehicle cantilever structures includes building a test bench to test the cantilever structure, obtaining acceleration and stress data of the cantilever structure, and establishing a BP neural network training system to obtain an acceleration-stress function; obtaining a stress prediction value of the cantilever structure based on the acceleration-stress function according to the measured acceleration of the rail vehicle; compiling a stress spectrum using a rain flow counting method based on the stress prediction value; obtaining a stress probability density function based on the stress spectrum, solving for a stress maximum value and compiling an extended stress spectrum, and determining the critical size of defects in the cantilever structure based on the stress maximum value; and using a cumulative damage method or a fracture mechanics method to predict life based on a comparison between the actual size of defects in the cantilever structure and the critical size of defects.

[0096] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the fatigue life prediction method of a rail vehicle cantilever structure as described in any of the above are implemented. The fatigue life prediction method of the rail vehicle cantilever structure includes building a test bench to test the cantilever structure, obtaining acceleration and stress data of the cantilever structure, and establishing a BP neural network training system to obtain an acceleration-stress function; obtaining a stress prediction value of the cantilever structure based on the acceleration-stress function according to the measured acceleration of the rail vehicle; compiling a stress spectrum based on the stress prediction value by using the rainflow counting method; deriving a stress probability density function based on the stress spectrum, solving the stress maximum value and compiling an extended stress spectrum, and determining the critical size of defects in the cantilever structure based on the stress maximum value; and using a cumulative damage method or a fracture mechanics method to predict the life based on the actual size of the defect of the cantilever structure compared with the critical size of the defect.

[0097] On the other hand, the present invention also provides a computer program product, which implements the steps of any of the above-mentioned fatigue life prediction methods for rail vehicle cantilever structures when the computer program product is run on an electronic device. The fatigue life prediction method for rail vehicle cantilever structures includes building a test bench to test the cantilever structure, obtaining acceleration and stress data of the cantilever structure, and establishing a BP neural network training system to obtain an acceleration-stress function; obtaining a stress prediction value of the cantilever structure based on the acceleration-stress function according to the measured acceleration of the rail vehicle; compiling a stress spectrum based on the stress prediction value by using the rainflow counting method; obtaining a stress probability density function based on the stress spectrum, solving the stress maximum value and compiling an extended stress spectrum, and determining the critical size of defects in the cantilever structure based on the stress maximum value; and using a cumulative damage method or a fracture mechanics method to predict the life based on the actual size of the defect of the cantilever structure and the critical size of the defect.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A fatigue life prediction method for a rail vehicle cantilever structure, characterized in that: include: A test bench is built to test the cantilever structure, to obtain acceleration and stress data of the cantilever structure, and a BP neural network training system is established to obtain an acceleration-stress function; According to the measured acceleration of the rail vehicle, a stress prediction value of the cantilever structure is obtained based on the acceleration-stress function; Based on the stress prediction value, a stress spectrum is compiled by using a rain flow counting method; A stress probability density function is obtained according to the stress spectrum, a maximum stress value is obtained by solving the stress spectrum, and an extended stress spectrum is compiled, and a critical defect size of the cantilever structure is determined based on the maximum stress value; Based on the comparison between the actual size of the defect of the cantilever structure and the critical size of the defect, a cumulative damage method or a fracture mechanics method is used to predict the life span; The step of comparing the actual defect size of the cantilever structure with the critical defect size and using the cumulative damage method or the fracture mechanics method to predict the lifespan includes: During the inspection and flaw detection process or the factory sampling inspection of the cantilever structure, the actual size of the defect of the cantilever structure is compared with the critical size of the defect; If the actual size of the defect is larger than the critical size of the defect, the cumulative damage method is used for life prediction; If the actual size of the defect is smaller than the critical size of the defect, the fracture mechanics method is used to predict the life.

2. The fatigue life prediction method of a rail vehicle cantilever structure according to claim 1, characterized in that: The steps of building a test bench to test the cantilever structure and obtaining acceleration and stress data of the cantilever structure include: A vibration test bench is built to perform stress testing on the cantilever structure of the rail vehicle. An acceleration time domain signal is input into the vibration test bench to collect the stress response of the cantilever structure and obtain first data of the acceleration time domain signal-stress response.

3. The fatigue life prediction method of a rail vehicle cantilever structure according to claim 2, characterized in that: The step of building a test bench to test the cantilever structure and obtaining acceleration and stress data of the cantilever structure also includes: A rolling vibration test bench was built to collect the acceleration and stress signals of the cantilever structure and obtain the second acceleration-stress data.

4. The fatigue life prediction method of a rail vehicle cantilever structure according to claim 3, characterized in that: The BP neural network training system is constructed by combining the first data and the second data.

5. A fatigue life prediction system for a rail vehicle cantilever structure, characterized in that: include: A vibration test bench is used to perform a stress test on the cantilever structure of the rail vehicle, and based on the input acceleration time domain signal, collect the stress response of the cantilever structure to obtain first data of the acceleration time domain signal-stress response; A rolling vibration test bench, used for collecting acceleration and stress signals of the cantilever structure to obtain second acceleration-stress data; A BP neural network training system is connected to the vibration test bench and the rolling vibration test bench signals to obtain an acceleration-stress function according to the first data and the second data; A sensor, used for measuring the acceleration of the rail vehicle; A stress prediction value calculation module is connected to the BP neural network training system and the sensor signal, and is used to obtain the stress prediction value of the cantilever structure according to the acceleration-stress function and the measured acceleration of the rail vehicle; A stress spectrum compilation module, connected to the stress prediction value calculation module by signal, for compiling a stress spectrum according to the stress prediction value by using a rain flow counting method; A defect critical size calculation module is connected to the stress spectrum compilation module by signal, and is used to obtain a stress probability density function according to the stress spectrum, solve and obtain the maximum stress value and compile an extended stress spectrum, and determine the defect critical size of the cantilever structure based on the maximum stress value; as well as A comparison calculation module is connected to the defect critical size calculation module and the stress spectrum compilation module by signal, and is used to input the actual size of the defect of the cantilever structure, and based on the comparison between the actual size of the defect and the critical size of the defect, select the cumulative damage method or the fracture mechanics method to perform life prediction calculation, and output the remaining life of the cantilever structure according to the calculation method combined with the stress spectrum; The step of comparing the actual defect size of the cantilever structure with the critical defect size and using the cumulative damage method or the fracture mechanics method to predict the lifespan includes: During the inspection and flaw detection process or the factory sampling inspection of the cantilever structure, the actual size of the defect of the cantilever structure is compared with the critical size of the defect; If the actual size of the defect is larger than the critical size of the defect, the cumulative damage method is used for life prediction; If the actual size of the defect is smaller than the critical size of the defect, the fracture mechanics method is used to predict the life.

6. The fatigue life prediction system for a rail vehicle cantilever structure according to claim 5, characterized in that: It also includes a health monitoring system for the rail vehicle, which is signal-connected to the stress prediction value calculation module and is used to monitor the stress state of the rail vehicle cantilever structure in real time.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the fatigue life prediction method for a rail vehicle cantilever structure as claimed in any one of claims 1 to 4 are implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the fatigue life prediction method of a rail vehicle cantilever structure as claimed in any one of claims 1 to 4 are implemented.

9. A computer program product, characterized in that When the computer program product is run on an electronic device, the steps of the fatigue life prediction method for a rail vehicle cantilever structure as claimed in any one of claims 1 to 4 are implemented.

Images