A Neural Network Based Damage Detection Method for Urban Rail Vehicle Frame
An urban rail vehicle and neural network technology, applied in the field of neural network-based urban rail vehicle frame damage detection, can solve the problems of inaccurate frame damage and inability to accurately monitor stress concentration points, achieving high accuracy and difficult to solve Acquisition, the effect of good degradation performance
Active Publication Date: 2022-04-01
CRRC QINGDAO SIFANG CO LTD +1
View PDF14 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Since the stress concentration point of the vehicle may be different under different working conditions, this method cannot accurately monitor the stress concentration point, which leads to inaccurate frame damage calculated by using the detected stress value
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0053] Such as figure 1 , figure 2 As shown in the present invention, a neural network-based urban rail vehicle frame damage detection method calculates the stress value of each monitoring point corresponding to the theoretical force under each working condition by constructing a finite element model of the frame, and establishes the frame accordingly The neural network model of the relationship between force and stress, the actual monitoring stress value is input into the neural network model, and the actual force of the frame can be output; the actual force is loaded in the finite element model to obtain the frame stress, so as to calculate the equivalent of the stress concentration point The damage degree reflects the deterioration state of the frame. During implementation, the concrete process that the inventive method is applied in urban rail vehicle is as follows:
[0054] S1: Construct the finite element model of the frame, analyze the theoretical force of the urban ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for detecting the damage degree of urban rail vehicle frame based on neural network, including: S1: constructing the finite element model of the frame, analyzing the theoretical force of the urban rail vehicle frame under each working condition, and calculating the corresponding The stress value of each monitoring point; S2: Construct the neural network model of the relationship between the force and stress of the frame, and input the real monitoring stress value into the neural network model, and then the actual force of the frame can be output; S3: The finite element model of the frame Load the actual force on the frame output in step S2 to obtain the frame stress, calculate the equivalent damage degree of the stress concentration point; and judge the current deterioration state of the frame according to the equivalent damage degree. The invention combines the finite element model with the actual detection data, avoids the situation that the simple theoretical calculation is far from the actual working condition, can accurately find the stress concentration point, and the obtained equivalent damage degree is closer to the real state of the frame, thereby better The characterizes the degradation performance of the framework.
Description
technical field [0001] The invention relates to the technical field of vehicle frame damage, in particular to a neural network-based detection method for urban rail vehicle frame damage. Background technique [0002] The frame is the key main structural part of the bogie, which plays an important role in supporting the car body and transmitting force. The deterioration of the frame will affect the stability and safety of urban rail vehicles. The main form of frame degradation is fatigue damage, and the analysis methods of fatigue damage mainly include theoretical model calculation and field experiment detection. [0003] The theoretical model calculation determines the stress concentration point of the frame by loading the theoretical force of the frame. Because it uses the simulated force-driven finite element model instead of the actual force, the stress distribution of the frame obtained is quite different from the actual working condition , the calculation result cannot...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G01M17/10G06N3/04G06N3/08G06F30/23
CPCG01M17/10G06N3/04G06N3/08G06F30/23
Inventor 陈博胡林桥徐刚张志龙张恒志
Owner CRRC QINGDAO SIFANG CO LTD