[1]钟小勇,刘志辉.基于IPSO-BP神经网络的钢丝绳断丝损伤识别模型研究[J].中国安全生产科学技术,2020,16(4):70-75.[doi:10.11731/j.issn.1673-193x.2020.04.011]
ZHONG Xiaoyong,LIU Zhihui.Research on identification model of broken wire damage on steel wire rope based on IPSO-BP neural network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2020,16(4):70-75.[doi:10.11731/j.issn.1673-193x.2020.04.011]
点击复制
基于IPSO-BP神经网络的钢丝绳断丝损伤识别模型研究
ZHONG Xiaoyong,LIU Zhihui.Research on identification model of broken wire damage on steel wire rope based on IPSO-BP neural network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2020,16(4):70-75.[doi:10.11731/j.issn.1673-193x.2020.04.011]
《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]
- 卷:
- 16
- 期数:
- 2020年4期
- 页码:
- 70-75
- 栏目:
- 职业安全卫生管理与技术
- 出版日期:
- 2020-04-30
文章信息/Info
- Title:
- Research on identification model of broken wire damage on steel wire rope based on IPSO-BP neural network
- 文章编号:
- 1673-193X(2020)-04-0070-06
- 关键词:
- 钢丝绳; 损伤; 识别; IPSO-BP神经网络; 惯性权重
- Keywords:
- steel wire rope; damage; identification; IPSO-BP neural network; inertia weight
- 分类号:
- X943
- 文献标志码:
- A
- 摘要:
- 为解决传统钢丝绳断丝损伤识别方法精度低，BP神经网络陷入局部最优等问题，提出改进粒子群算法（IPSO）的BP神经网络识别模型。通过采集钢丝绳断丝损伤信号，提取缺陷信号特征，用峰值、峰峰值、波宽、波形下面积和波动能量5个特征值组成特征向量作为神经网络的输人，断丝数量作为神经网络的输出；利用改进粒子群算法对BP神经网络的初始权值和阈值进行优化；建立基于IPSO-BP算法的神经网络模型，用于钢丝绳断丝的定量识别。结果表明：IPSO-BPS神经网络模型的钢丝绳断丝损伤识别精度、泛化能力均高于传统BP神经网络模型，且改进的粒子群算法迭代寻优速度更快。
- Abstract:
- In order to solve the problems that the accuracy of the traditional identification method of broken wire damage on the steel wire rope is low and the BP neural network fell into the local optimum,an identification model of BP neural network combined with the improved particle swarm optimization (IPSO) was put forward.The signals of broken wire damage on the steel wire rope were collected,and the characteristics of defect signals were extracted.The characteristic vector,which was composed of 5 characteristic values including the peak value,peaktopeak value,wave width,area under waveform and fluctuation energy,was input into the neural network,and the amount of broken wire was taken as the output of neural network.The initial weights and thresholds of BP neural network were optimized by using IPSO,then a neural network model based on IPSO-BP algorithm was established and applied in the quantitative identification of broken wire damage on the steel wire rope.The results showed that the IPSO-BP neural network model had higher identification accuracy and generalization ability for the broken wire damage on the steel wire rope than the traditional BP neural network model,and the IPSO algorithm was faster in the iterative optimization.
参考文献/References:
［1］曹原,强宝民,齐彦林，等.基于BP神经网络的钢丝绳损伤定量识别［J］.起重运输机械,2014(9):82-87.
CAO Yuan,QIANG Baomin,QI Yanlin,et al.Quantitative identification of wire rope damage based on BP neural network ［J］.Hoisting and Conveying Machinery,2014(9):82-87.
［2］刘志怀,秦芳,刘娜,等.基于主成分分析和BP神经网络的钢丝绳断丝定量检测方法［J］.振动与冲击,2018,37(18):271-276.
LIU Zhihuai,QIN Fang,LIU Na,et al.Quantitative testing method for broken wire in steel rope based on principal component analysis and BP artificial neural network model ［J］.Vibration and Shock,2018,37(18):271-276.
［3］赵晓莉,郭宁,高鑫宇.基于RBF-BP组合神经网络的钢丝绳断丝定量识别［J］.煤炭技术,2019,38(5):148-151.
ZHAO Xiaoli,GUO Ning,GAO Xinyu.Quantitative identification of broken wires for steel rope based on RBF-BP combined neural network ［J］.Coal Technology,2019,38(5):148-151.
［4］KAUR A,GUPTA A,AGGARWAL H,et al.Non-destructive evaluation and development of a new wire rope tester using parallely magnetized NdFeB magnet segments［J］.Journal of Nondestructive Evaluation,2018,37(3):61.
［5］姜宵园,孙燕华,马文家,等.基于周向积分磁化的钢丝绳检测传感器［J］.传感器与微系统,2018,37(12):69-71,75.
JIANG Xiaoyuan,SUN Yanhua,MA Wenjia,et al.Steel wire rope detection sensor based on circumferential integral magnetization ［J］.Transducer and Microsystem Technologies,2018,37(12):69-71,75.
［6］SEUNGHEE P,JU W K,CHANGGIL L,et al.Magnetic flux leakage sensing-based steel cable NDE technique ［J］.Shock and Vibration,2014(2):1-8.
［7］RENALDAS R,RVMANTAS K,LIUDAS M,et al.Ultrasonic guided wave-based testing technique for inspection of multi-wire rope structures ［J］.NDT&E International,2014,62:40-49.
［8］曹青松,刘丹,周继惠,等.一种钢丝绳断丝无损定量检测方法［J］.仪器仪表学报,2011,32(4):787-794.
CAO Qingsong,LIU Dan,ZHOU Jihui,et al.Non-destructive and quantitative detection method for broken wire rope ［J］.Chinese Journal of Scientific Instrumen,2011,32(4):787-794.
［9］PAVEL P,PETER K,JOZEF K,et al.Prediction of fatigue fractures diffusion on the cableway haul rope［J］.Engineering Failure Analysis,2016,59(1):185-196.
［10］钟小勇,刘志辉,张小红.基于STM32的钢丝绳缺陷定量检测系统设计［J］.自动化与仪表,2019,34(5):56-59.
ZHONG Xiaoyong,LIU Zhihui,ZHANG Xiaohong.Design of steel wire rope defect quantitative detection system based on STM32 ［J］.Automation and Instrumentation,2019,34(5):56-59.
［11］朱良,谭继文,张义清.基于Shannon熵的钢丝绳断丝损伤信号小波包去噪研究［J］.煤矿机械,2019,40(3):31-33.
ZHU Liang,TAN Jiwen,ZHANG Yiqing.Study on wavelet packet denoising of broken wire signal of wire rope based on Shannon entropy ［J］.Coal Mine Machinery,2019,40(3):31-33.
［12］杨英杰.粒子群算法及其应用研究［M］.北京:北京理工大学出版社,2017.
［13］MARICHELVAM M K,GEETHA M,TOSUM .An improved particle swarm optimization algorithm to solve hybrid flowshop scheduling problems with the effect of human factors：a case study ［J］.Computers and Operations Research,2020,114:104812.
［14］管志川,胜亚楠,许玉强,等.基于PSO优化BP神经网络的钻井动态风险评估方法［J］.中国安全生产科学技术,2017,13(8):5-11.
GUAN Zhichuan,SHENG Yanan,XU Yuqiang,et al.Dynamic risk assessment method of drilling based on PSO optimized BP neural network ［J］.Journal of Safety Science and Technology,2017,13(8):5-11.
［15］SHI Y,EBERHART R C.Empirical study of particle swarm optimization ［M］.New York:Academic Press,1967.
相似文献/References:
备注/Memo
- 备注/Memo:
-
收稿日期： 2020-02-17
* 基金项目： 国家自然科学基金项目(51665019)
作者简介： 钟小勇,硕士,教授级高级工程师,主要研究方向为安全智能诊断与无损检测、嵌入式系统与应用。
