Reliability Evaluation of Flat Car Underframe based on GSA-BP Neural Network and Probability Box

doi:10.23940/ijpe.24.06.p7.400411

Abstract

Abstract: In order to improve the calculation efficiency and reduce the uncertainty in the reliability evaluation process of flat car underframe, a new method based on an improved genetic simulated annealing algorithm-back propagation neural network (GSA-BP) and probability box is proposed. Firstly, a certain type of flat car underframe is taken as the research object, genetic evolution algorithm (GA) and simulated annealing algorithm (SA) are utilized to optimize the weights and thresholds of the GSA-BP neural network and obtain the best initial parameter values. Applying the values, the BP neural network is trained, and the improved GSA-BP neural network is established which is verified by test functions. Secondly, the central plate sub-model of the flat car underframe is obtained by sub-model technology and the correctness of its boundary conditions is tested. On this basis, the static strength analysis of the sub-model is carried out. Finally, the improved GSA-BP neural network and probability box are utilized to evaluate the reliability of the sub-model of flat car underframe, and the Monte Carlo method is utilized to verify it. The results show that the proposed method not only improves the accuracy of reliability evaluation but also shortens the calculation time from 10 hours to 6 hours. The calculation efficiency is increased by 40%, which further verifies its superiority and feasibility in structural reliability evaluation.

Key words: BP neural network, genetic simulated annealing algorithm, probability box, reliability evaluation, flat car underframe

Zhiyang Zhang, Yonghua Li, Dongxu Zhang, Yuhan Tang, and Qing Xia. Reliability Evaluation of Flat Car Underframe based on GSA-BP Neural Network and Probability Box [J]. Int J Performability Eng, 2024, 20(6): 400-411.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References

[1] Pei B., Li Z., Li X., Chen Z., He P. and Huang X., 2023. Research on time-varying reliability of subway gearbox housing based on response surface method. Journal of Mechanical Transmission, 47(2), pp.142-148.
[2] Liu Z., Lin H., Li L., Li D., Gao Y., Xu L. and Hu J., 2022. Analysis on the Reliability of Tunnel System Based on Multiple Response Surface Methodology and Monte Carlo Method. Modern Tunnelling Technology, 59(3), pp.78-87.
[3] Zhang C.Y., Song L.K., Fei C.W., Hao G.P. and Li X.Q., 2017. Intelligent Dual Response Surface Method for Reliability Sensitivity Analysis of Turbine Blisk. Journal of Propulsion Technology, 38(5), pp.1155-1164.
[4] Hao D., Qi C., Yongfa Z. and Lizhi J., 2018. Reliability Analysis of Passive System Based on PSO Optimized Neural Network Response Surface Method. Nuclear Power Engineering, 39(4), pp.101-106.
[5] LI Y., LIANG X. and GONG Q., 2019. Improved kriging response surface reliability calculation method based on two-point addition strategy. China Mechanical Engineering, 30(17), pp.2051.
[6] Chen, S.K. and Wang, D.Y., 2018. An Improved Monte Carlo Reliability Analysis Method Based on Neural Network. Journal of Shanghai Jiaotong University, 52(6), pp.687-692.
[7] Zhao L., Zhao M. and Liu X., 2017. Research on reliability of shearer' rocker shell based on VP and BP neural network, Journal of Mechanical Strength, 39(6), pp.1379-1384.
[8] Li J., Cheng X., Qin Y., Zhang Y. and Xing Z., 2013. Reliability prediction of urban rail transit vehicle based on BP neural network. Journal of Central South University (Science and Technology), 44(1), pp.42-46.
[9] Guo X.Y., Wang J.G., Fan B., Zhang C. and Yu H., 2023. Gearbox wear condition monitoring based on oil-vibration multi-dimensional features and PSO-LSTM. Lubrication and Sealing, 48(12), pp.117-123.
[10] Liu, H.J. and Shao, H.B., 2023. Prediction of clamping deformation of aviation panel based on SSA-PSO-BP neural network. Machine tools and hydraulics, 51(23), pp.114-120.
[11] Wen K., He L., Liu J. and Gong J., 2019. An optimization of artificial neural network modeling methodology for the reliability assessment of corroding natural gas pipelines. Journal of Loss Prevention in the Process Industries, 60, pp.1-8.
[12] Xiangwen Z., Chenguang F., An H., Chuang W. and Yujing Y., 2023. Performance Prediction and Structural Parameter Optimization of Control Rod Hydraulic Buffer Based on GA-BP Neural Network. Nuclear power engineering, 44(6), pp.162-169.
[13] Lin J., Shi G. and Tang S., 2020. Forward Kinematics Solution Analysis of 3-UPS-RCR Parallel Mechanism Based on Improved BP Neural Network, Machine design and research, 36(3), pp.30-34+49.
[14] Deng L., Mei H., Zhou W. and Jing E., 2021. B-spline fitting method of optimal running-time-energy function in an urban rail section, Journal of Railway Science and Engineering, 18(9), pp.2461-2468.
[15] Sha Y., Guan S., Zhao H., Liu Y. and Liu W., 2023. Prediction of Cutting Force in Internal Spiral Groove Machining by Support Vector Regression Machine Based on Simulated Annealing Optimization, Tool Engineering, 57(1), pp.100-105.
[16] Zhang, S. and Gao, D., 2019. Flower pollination algorithm based on dynamic adjustment and collaborative search. Computer Engineering and Applications, 55(24), pp.46-53.
[17] Si H., Wang Q. and Ding J., 2015. A Sensitivity Analysis Method about Power Grid Planning Indexes, 3rd International Conference on Material, Mechanical and Manufacturing Engineering, pp.1892-1896.
[18] EN 12663: Railway applications- Structural requirements of railway vehicle bodies- Part 2: Freight wagons.
[19] Yu, S.U. and Hesheng, T.A.N.G., 2023. Multi-objective topology optimization design of truss structures based on evidence theory under limited information. Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University, 41(4), pp.722-731.