基于盲数理论的萤火虫神经网络失效征候结构可靠度预测

中国机械工程

基于盲数理论的萤火虫神经网络失效征候结构可靠度预测

董青;徐格宁

太原科技大学机械工程学院，太原，030024

出版日期:2017-08-10 发布日期:2017-08-07
基金资助:
国家高技术研究发展计划(863计划)资助项目(2013AA040203）；
国家科技支撑计划资助项目（2011BAK06B05）
National High Technology Research and Development Program of China (863 Program)（No. 2013AA040203）
National Key Technology R&D Program (No. 2011BAK06B05)

Firefly Neural Network Failure Symptom Structure Reliability Prediction Based on Blind Number Theory

DONG Qing;XU Gening

School of Machinery and Electronics Engineering,Taiyuan University of Science and Technology, Taiyuan,030024

Online:2017-08-10 Published:2017-08-07
Supported by:
National High Technology Research and Development Program of China (863 Program)（No. 2013AA040203）
National Key Technology R&D Program (No. 2011BAK06B05)

摘要/Abstract

摘要： 在任意可行性工况下，针对大型臂架失效征候结构的载荷效应与抗力的多种不确定因素导致结构可靠度难以确定的问题，通过构建盲数失效征候结构可靠度模型（BNFSSRM）、串行式萤火虫神经网络预测模型——缺陷结构远场应力预测子模型（STFNN-DSSSPSM）与缺陷结构可靠度预测子模型（STFNN-DSRPSM）串联，提出了基于盲数理论的萤火虫神经网络失效征候结构可靠度预测方法。以应力-强度干涉模型为基础，萤火虫神经网络为预测方法，根据裂纹失稳扩展准则，将不确定性问题盲数化的思想引入裂纹强度因子与断裂韧性的干涉模型，通过试验仿真与STFNN-DSSSPSM，得到典型工况下裂纹缺陷结构的可靠度；再以此为扩展样本的目标输出、裂纹扩展尺寸为扩展样本的输入，通过BNFSSRM、STFNN-DSRPSM，实时预测不同工况下缺陷结构的可靠度，评估抵抗失效的能力以及不同工况退出可行性工况域的先后顺序。以QY130流动式起重机再制造臂架结构为例，验证了该方法的有效性，为结构再制造准入期实时判断以及再制造方案的选择提供了理论指导。

关键词: 盲数理论, 失效征候, 裂纹缺陷, 萤火虫神经网络

Abstract: Under any feasibility conditions, the reliability of large arm structure with failure symptoms was difficult to be determined due to various uncertain factors of load effects and resistances in notch-crack propagation. The firefly neural network prediction method of the reliability of structure with failure symptom was presented based on the blind number theory by building a blind number failure symptom structure reliability model (BNFSSRM), serial type firefly neural network prediction model consisting of far field stress prediction sub-model (STFNN-FFSPS) and reliability prediction sub-model (STFNN-RPS) of damaged structure. On the basis of the stress-strength interference model, the firefly neural network being as a forecasting method, the idea converting the uncertainty problems to blind numbers was introduced into the interference model of intensity factors of notch-crack and fracture toughness according to the rule of notch-crack instability propagation, and the reliability of notch-crack damaged structure was obtained by the experiments and finite element simulation combined with STFNN-FFSPS under typical working conditions. The reliability being taken as the target output and the notch-crack size being as the input data of expanded samples, the real-time prediction of reliability of damaged structure may be achieved by BNFSSRM and STFNN-RPS, thus realizing the evaluation of the capacity of the structure resistant to failure and determining the orders of different conditions out of the feasible condition regions. QY130 remanufacturing arm structure was taken as an example and the effectiveness of the proposed method were verified.

Key words: blind number theory, failure symptom, notch-crack damaged, firefly neural network

中图分类号:

TB114.3

董青;徐格宁. 基于盲数理论的萤火虫神经网络失效征候结构可靠度预测[J]. 中国机械工程.

DONG Qing;XU Gening. Firefly Neural Network Failure Symptom Structure Reliability Prediction Based on Blind Number Theory[J]. China Mechanical Engineering.

参考文献

[1]郭朋彦,石博强,肖成勇,等.基于盲数理论的机械结构复杂时变可靠性计算方法[J].农业机械学报, 2010, 41(9):210-213.
GUO Pengyan, SHI Boqiang, XIAO Chengyong, et al. Computing-algorithm for Time-dependent Reliability of Mechanical Structure Based on Blind Number[J].Transactions of the Chinese Society for Agricultural Machinery,2010, 41(9):210-213.

[2]赵德祥, 石博强.基于盲数理论的车架结构可靠性计算[J].矿山机械, 2007(11):60-62.
ZHAO Dexiang, SHI Boqiang.Reliability Calculation of Frame Structure Based on Blind Number Theory[J].Mining & Processing Equipment, 2007(11):60-62.

[3]李海鹏,石博强, 张文明,等.基于盲数理论的机械强度可靠性优化设计[J].机械强度,2007, 29(3):425-428.
LI Haipeng, SHI Boqiang, ZHANG Wenming, et al. Reliability-based on Optimization Design of Mechanical Strength Based on Blind Number Theory[J]. Journal of Mechanical Strength, 2007, 29(3):425-428.

[4]杨恒, 徐格宁, 韩子渊. 基于盲数理论的性能退化数据可靠性分析[J].机械强度,2013, 35(6):777-782.
YANG Heng,XU Gening, HAN Ziyuan. Reliability Analysis on the Data of Performance Degradation Based on the Blind Number Theory[J]. Journal of Mechanical Strength, 2013, 35(6):777-782.

[5]王磊，张明文，王秋莎. 基于盲数理论的输电系统可靠性评估[J]. 电力科学与工程，2010，26(8):4-9.
WANG Lei,ZHANG Mingwen,WANG Qiusha. Reliability Evaluation of Transmission System Based on Blind Number Theory[J]. Electric Power Science and Engineering, 2010，26(8):4-9.

[6]陈剑勇，蔡红梅，苏浩益.盲数理论在发电系统可靠性评估中的应用[J]. 电力系统保护与控制，2012，40(13):74-77.
CHEN Jianyong, CAI Hongmei, SU Haoyi. Application of Blind Number Theory in Power Generation System Reliability Evaluation[J]. Power System Protection and Control, 2012，40(13):74-77.

[7]赵书强，王海巍. 基于盲数的配电系统可靠性评估[J]. 电力系统保护与控制，2011，39(16):8-12.
ZHAO Shuqiang, WANG Haiwei. Power Distribution System Reliability Evaluation Based on Blind Number[J]. Power System Protection and Control, 2011，39(16):8-12.

[8]刘开第，吴和琴，庞彦军，等.盲数的概念、运算与性质[J]. 运筹与管理，1998,7(3):14-17.
LIU Kaidi, WU Heqin, PANG Yanjun,et al. Concept Operations and Properties of Blind Number[J].Operations Research and Management Science, 1998, 7(3):14-17.

[9]孟衡，李建林. 基于盲数理论的关键块体稳定性分析研究[J]. 水电能源科学, 2009, 2(3):117-119.
MENG Heng, LI Jianlin. Research on Key Block Stability Based on Blind Number Theory[J]. Water and Electricity Energy Science, 2009, 2(3):117-119.

[10]赵章焰.机械承载结构裂纹诊断、控制与维修方法的研究及应用[D].武汉:武汉理工大学, 2001.
ZHAO Zhangyan.Study on Mehtod of Notch-crack Diagnosing,Controlling and Maintaining and Its Application for Mechanical Loading-carrying Structure[D].Wuhan:Wuhan University of Technology, 2001.

[11]刘惟信. 机械可靠性设计[M].北京:清华大学出版社，1996.
LIU Weixin. Mechanical Reliability Design[M]. Beijing: Tsinghua University Press, 1996.

[12]YANG X S.Nature-inspired Metaheuristic Algorithms[M].Luniver Press,2008.

[13]李国勇，杨丽娟.神经·模糊·预测控制及其MATLAB实现[M].北京:电子工业出版社,2013.
LI Guoyong, YANG Lijuan. Nerve, Fuzzy, Predictive Control and MATLAB Implementation [M].Beijing: Electronics Industry Press, 2013.

[14]翁胜龙. 基于萤火虫算法的聚类分析与神经网络诊断方法[D].广州：华南理工大学，2014.
WENG Shenglong. A Clustering Method and A Neural Network Based on Firefly Algorithm in Diagnostic Analysis[D].Guangzhou：South China University of Technology, 2014.

[15]韩晓君.在役实腹式臂架可视裂纹失效仿真及寿命评估[D]. 太原：太原科技大学, 2015.
HAN Xiaojun. Solid-web Boom in Service Visual Notch-crack Failure Simulation and Life Assessment[D].Taiyuan:Taiyuan University of Science and Technology,2015.