基于卷积神经网络的臂式斗轮机上部结构可靠性分析方法

doi:10.3901/JME.260067

机械工程学报 ›› 2026, Vol. 62 ›› Issue (2): 471-480.doi: 10.3901/JME.260067

• 交叉与前沿 • 上一篇

扫码分享

基于卷积神经网络的臂式斗轮机上部结构可靠性分析方法

刘鑫, 李飞虎, 刘凯, 万俊

长沙理工大学工程车辆安全性设计与可靠性技术湖南省重点实验室长沙 410114

收稿日期:2024-12-06 修回日期:2025-06-09 发布日期:2026-03-02
作者简介:李飞虎,男,1992年出生,硕士研究生。主要研究方向为结构优化设计。E-mail:2281723915@qq.com;刘凯,男,1992年出生,博士,讲师。主要研究方向为结构可靠性评估。E-mail:liukaiyjf@163.com;万俊,男,2000年出生,硕士研究生。主要研究方向为不确定性优化设计。E-mail:2842509357@qq.com;刘鑫,男,1981年出生,博士,教授。主要研究方向为机械结构可靠性优化设计。E-mail:lxym810205@163.com
基金资助:
国家自然科学基金(52275235,52205141),湖南省杰出青年科学基金(2021JJ10040),湖南省研究生科研创新(CX20220900,CX20230879)资助项目。

Reliability Approach for Topside Structure of Bucket Wheel Stacker Reclaimer Based on Convolutional Neural Network

LIU Xin, LI Feihu, LIU Kai, WAN Jun

Hunan Province Key Laboratory of Safety and Reliability Technology for Engineering Vehicle, Changsha University of Science and Technology, Changsha 410114

Received:2024-12-06 Revised:2025-06-09 Published:2026-03-02

摘要/Abstract

摘要： 针对不确定性因素对臂式斗轮机上部结构安全性的影响，提出一种基于卷积神经网络的臂式斗轮机上部结构可靠性分析方法。分析臂式斗轮机实际工况过程中的不确定性因素，并完成上部结构数值模型的建立；基于证据理论对臂式斗轮机上部结构可靠性分析过程中的不确定性变量进行描述，并建立其可靠性分析数学模型；利用拉丁超立方采样技术和序列二次规划算法完成样本焦元的采集和极值分析，并基于样本焦元的数据特征和极值分析结果对卷积神经网络模型(Convolutional neural network,CNN)进行训练，实现样本焦元的特征属性识别；基于训练好的卷积神经网络模型对未知焦元进行识别，计算出上部结构在不同工况条件下的可靠性置信区间。结果表明：该方法能有效对臂式斗轮机上部结构的可靠性进行分析和评估，从而确保上部结构的安全性，在散料输送装备技术领域具有广泛的应用前景。

关键词: 臂式斗轮机, 上部结构, 证据理论, 卷积神经网络, 可靠性分析

Abstract: Considering the influence of uncertainties on topside structure safety of bucket wheel stacker reclaimer, a reliability approach based on convolutional neural network is presented. Firstly, the uncertainty factors are analyzed in the actual working conditions for the bucket wheel stacker reclaimer and the numerical model of topside structure is established. Secondly, the uncertainty variables in the reliability analysis process of the topside structure are described based on the evidence theory and the reliability analysis model is established. Thirdly, the sample focal elements are collected by using Latin hypercube design and the extreme value is analyzed by using sequential quadratic programming algorithm. Then, the convolutional neural network model is trained to identify the feature attributes of sample focal elements based on the data characteristics and extreme value analysis results. Finally, the trained convolutional neural network model is employed to identify the unknown focal elements, and the reliability confidence intervals of the topside structure under different working conditions are calculated. The results demonstrate that the proposed method could effectively analyze and evaluate the reliability of topside structure of bucket wheel stacker reclaimer, which ensures the topside structure safety. The method can also be used in the field of other balk cargo delivery equipment.

Key words: bucket wheel stacker reclaimer, topside structure, evidence theory, convolutional neural network, reliability analysis

中图分类号:

V224

刘鑫, 李飞虎, 刘凯, 万俊. 基于卷积神经网络的臂式斗轮机上部结构可靠性分析方法[J]. 机械工程学报, 2026, 62(2): 471-480.

LIU Xin, LI Feihu, LIU Kai, WAN Jun. Reliability Approach for Topside Structure of Bucket Wheel Stacker Reclaimer Based on Convolutional Neural Network[J]. Journal of Mechanical Engineering, 2026, 62(2): 471-480.

参考文献

[1] SUN Wei,PENG Xiang,DOU Jing,et al.Surrogate-based weight reduction optimization of forearm of bucket-wheel stacker reclaimer[J].Structural and Multidisciplinary Optimization,2020,61:1287-1301.
[2] ZOU Zhihong,PANG Xiaoping,CHEN Jin.Comprehensive theoretical digging performance analysis for hydraulic excavator using convex polytope method[J].Multibody System Dynamics,2019,47:137-164.
[3] YUAN Yongliang,LÜLiye,WANG Shuo,et al.Multidisciplinary co-design optimization of structural and control parameters for bucket wheel reclaimer[J].Frontiers of Mechanical Engineering,2020,15:406-416.
[4] CAO Lixiong,LIU Jie,JIANG Cao,et al.Optimal sparse polynomial chaos expansion for arbitrary probability distribution and its application on global sensitivity analysis[J].Computer Methods in Applied Mechanics and Engineering,2022,399:115368.
[5] 智鹏鹏,汪忠来,李永华,等.基于RMQGS-APS-Kriging的主动学习结构可靠性分析方法[J].机械工程学报,2022,58(16):420-429.ZHI Pengpeng,WANG Zhonglai,LI Yonghua,et al.RMQGS-APS-Kriging-based active learning structural reliability analysis method[J].Journal of Mechanical Engineering,2022,58(16):420-429.
[6] WANG Zhonglai,HUANG Hongzhong,DU Li.Reliability analysis on competitive failure processes under fuzzy degradation data[J].Applied Soft Computing Journal,2011,11:2964-2973.
[7] 刘鑫,尹来容,胡林.基于概率-椭球混合模型的缓冲气囊防护特性可靠性分析方法[J].机械工程学报,2020,56(2):130-137.LIU Xin,YIN Lairong,HU Lin.Hybrid reliability approach for airbag protection performance based on probability and ellipsoidal convex models[J].Journal of Mechanical Engineering,2020,56(2):130-137.
[8] DEMPSTER A P.Upper and lower probabilities induced by a multi-valued mapping[J].Annals of Mathematical Statistics,1967,38:325-339.
[9] SHAFER G A.Mathematical theory of evidence[M].Princeton:Princeton University Press,1976.
[10] XU Jintao,DING Rui,LI Muye,et al.A new Bayesian network model for risk assessment based on cloud model,interval type-2 fuzzy sets and improved D-S evidence theory[J].Information Sciences,2022,618:336-355.
[11] Zh ANG Qi,XIAO Jingyu,TIAN Chunwei,et al.A robust deformed convolutional neural network (CNN) for image denoising[J].CAAI Transactions on Intelligence Technology,2023,8(2):331-342.
[12] 张立,陈江涛,熊芬芬,等.基于元学习的多可信度深度神经网络代理模型[J].机械工程学报,2022,58(1):190-200.ZHANG Li,CHEN Jiangtao,XIONG Fenfen,et al.Meta-learning based multi-fidelity deep neural networks[J].Journal of Mechanical Engineering,2022,58(1):190-200.
[13] 吴强威,文龙.基于联合对抗训练的深度学习表面缺陷检测方法[J].机械工程学报,2023,59(12):173-182.WU Qiangewei,WEN Long.Union-adversarial training for deep learning based on surface defect detection[J].Journal of Mechanical Engineering,2023,59(12):173-182.
[14] 张仕军,金振林.基于多模型级联的双目视觉铸件缺陷检测方法[J].机械工程学报,2022,58(5):34-43.ZHANG Shijun,JIN Zhenlin.Casting defect detection method based on multi model cascade and binocular vision[J].Journal of Mechanical Engineering,2022,58(5):34-43.
[15] SHANKAR V,PARSANA S.An overview and empirical comparison of natural language processing (NLP) models and an introduction to and empirical application of autoencoder models in marketing[J].Journal of the Academy of Marketing Science,2022,50(6):1324-1350.
[16] JIA Lijie,LI Wenjing,QIAO Junfei.An online adjusting RBF neural network for nonlinear system modeling[J].Applied Intelligence,2023,53(1):440-453.
[17] LIU Xin,LIU Xiang,ZHOU Zhenhua,et al.An efficient multi-objective optimization method based on the adaptive approximation model of the radial basis function[J].Structural and Multidisciplinary Optimization,2021,63(3):1385-1403.
[18] 刘鑫,李飞虎.基于概率-区间混合模型的六足机器人运动稳定性优化设计方法[J].工程设计学报,2024,31(5):585-591.LIU Xin,LI Feihu.Optimization design method for kinematic stability of hexapod robot based on probability-interval hybrid model[J].Chinese Journal of Engineering Design,2024,31(5):585-591.
[19] ZHAO Yue,LIU Jie,HE Zhelong.A general multi-fidelity metamodeling framework for models with various output correlation[J].Structural and Multidisciplinary Optimization,2023,66:101.
[20] LIU Jie,ZHAO Yue,LEI Fei,et al.Net-HDMRmetamodeling method for high-dimensional problems[J].Journal of Mechanical Design,2023,145(9):091706.
[21] BOGGS P T,TOLLE J W.Sequential quadratic programming[J].Acta numerica,1995,4:1-51.

基于卷积神经网络的臂式斗轮机上部结构可靠性分析方法

Reliability Approach for Topside Structure of Bucket Wheel Stacker Reclaimer Based on Convolutional Neural Network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王祺, 叶仁传, 马国杰, 马佩珏, 范杰, 杨文龙. 钢材表面缺陷轻量化识别算法研究[J]. 机械工程学报, 2025, 61(8): 18-31.
[2]	程军, 朱煜龙, 汪步云, 梁艺, 许德章, 刘蒙蒙, 刘有余. 基于改进迁移学习的CFRP缺陷涡流检测与识别[J]. 机械工程学报, 2025, 61(6): 53-65.
[3]	陈国强, 申正义, 杨宇驰, 李腾, 徐丽. FCN优化GA的飞行模拟座舱意象仿生视觉焦点预测模型[J]. 机械工程学报, 2025, 61(3): 154-166.
[4]	刘翰儒, 陈桂映, 许泽林, 彭世通, 郭嘉楠, 刘伟嵬, 王奉涛. 基于SERepVGG-A2的轻量化卷积神经网络在熔池状态识别中的应用[J]. 机械工程学报, 2025, 61(3): 440-448.
[5]	丁梦珂, 高东岳, 顾海洋, 王博睿, 周国泰, 武湛君. 基于BO-CNN模型的复合材料疲劳损伤超声导波监测方法[J]. 机械工程学报, 2025, 61(24): 38-47.
[6]	门志辉, 宫岛, 周劲松, 周凯. 基于格拉姆角场与并行卷积Transformer的列车传动系统故障诊断方法[J]. 机械工程学报, 2025, 61(24): 168-179.
[7]	孟德彪, 杨恒飞, 杨世源, 苏晓燕, 朱顺鹏. 自适应多保真度Kriging模型辅助的一阶可靠性分析方法[J]. 机械工程学报, 2025, 61(18): 344-365.
[8]	付助, 陈伟民, 陈俐. 基于波高与光伏实时预测的光柴储无人艇能量管理策略[J]. 机械工程学报, 2025, 61(16): 293-304.
[9]	狄子钧, 袁东风, 李东阳, 梁道君, 周晓天, 信苗苗, 曹凤, 雷腾飞. 基于多尺度-高效通道注意力网络的刀具故障诊断方法[J]. 机械工程学报, 2024, 60(6): 82-90.
[10]	韦新鹏, 姚中洋, 宝文礼, 张哲, 姜潮. 一种基于主动学习克里金模型的证据理论可靠性分析方法[J]. 机械工程学报, 2024, 60(2): 356-368.
[11]	王文林, 张子波, 李英子, 吴永明, 王起新, 梁若霜. 液压缸可靠性试验与数据分析研究平台[J]. 机械工程学报, 2024, 60(18): 385-393.
[12]	杨旭锋, 程鑫, 刘泽清. 一种融合交叉熵自适应抽样与ALK模型的可靠性分析方法[J]. 机械工程学报, 2024, 60(16): 73-82.
[13]	胡俊宇, 韩旭, 陶友瑞, 李珊瑚, 张建宁. 一种考虑跟随误差的S形轨迹残余振动抑制可靠性分析方法[J]. 机械工程学报, 2024, 60(16): 390-399.
[14]	胡伟飞, 廖家乐, 郭云飞, 鄢继铨, 李光, 岳海峰, 谭建荣. 基于物理信息神经网络的时变可靠性分析方法[J]. 机械工程学报, 2024, 60(13): 141-153.
[15]	袁静, 任港星, 蒋会明, 赵倩, 魏臣隽, 朱骏. 基于多元提升核神经网络的机械故障诊断方法及其特征提取可解释性研究[J]. 机械工程学报, 2024, 60(12): 51-64.