全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于故障树的锂电池模组生产线故障诊断专家系统研究
Research on Fault Diagnosis Expert System of Lithium Battery Module Production Line Based on Fault Tree

DOI: 10.12677/JSTA.2023.112022, PP. 201-211

Keywords: 故障树,生产线,故障诊断,专家系统
Fault Tree
, Production Line, Fault Diagnosis, Expert System

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对现代生产线故障排查困难、维修成本高及维修人员不足等问题,提出了一种基于故障树的锂电池模组生产线故障诊断专家系统,对生产线进行全线智能诊断。首先,建立激光清洁工位故障树,对故障进行定性定量分析;其次,确定系统整体框架结构,并在此基础上进一步分析诊断专家系统知识库和推理机构建方法;然后,采用C#语言设计并实现了锂电池模组生产线故障诊断系统;最后,采用工业相机故障案例检验了系统的可行性。实验结果表明:基于故障树和贝叶斯网络的锂电池模组生产线故障诊断专家系统能高效定位故障点,可以为维修人员快速查找检修目标提供可靠参考依据。
Aiming at the problems of trouble shooting, high maintenance cost and insufficient maintenance personnel in modern production line, a fault diagnosis expert system for lithium bat-tery module production line based on fault tree has been proposed to carry out intelligent diagnosis for the whole production line. First of all, the fault tree of laser cleaning station has been established to conduct qualitative and quantitative analysis of the fault; secondly, the overall framework of the system has been determined, and on this basis, the knowledge base and reasoning mechanism con-struction method of the diagnosis expert system have been further analyzed; then, the fault di-ag-nosis system of lithium battery module production line has been designed and implemented in C# language; finally, the feasibility of the system has been verified by the industrial camera fault case. The experimental result shows that the fault diagnosis expert system of lithium battery mod-ule production line based on fault tree can locate the fault point efficiently and provide reliable ref-erence for maintenance personnel to quickly find the maintenance target.

References

[1]  丁紫薇. 基于机器学习的复杂装备故障诊断研究[D]: [硕士学位论文]. 西安: 西安工业大学, 2022.
[2]  刘磊, 李舜酩, 陆建涛. 基于卷积神经网络的旋转传动部件故障诊断综述[J]. 机械设计, 2022, 39(10): 1-8.
[3]  王彦昆, 康丽锋. 基于物联网和卷积神经网络的拖拉机轴承故障诊断[J]. 农机化研究, 2023, 45(9): 245-249.
[4]  王兴, 张晗, 朱家正, 等. 多头注意力驱动的航空高速轴承故障诊断方法[J]. 振动与冲击, 2023, 42(4): 295-305.
[5]  李腾飞, 郝玉杰, 袁方, 等. 基于多源特征信息融合的油浸式变压器故障智能诊断模型[J]. 电工电能新技术, 2023, 42(1): 48-57.
[6]  何彦, 王优强. 故障树和灰色关联度在船用发电机组中的应用[J]. 中国修船, 2021, 34(6): 37-40.
[7]  安慧, 杨雯晶, 安敏, 黄艾, 张斓奇. 基于粗糙集—模糊理论的水电工程多维社会影响因素识别与评价[J]. 水电能源科学, 2022, 40(2): 161-164.
[8]  Cheng, X.Y., Liu, S.S., He, W., et al. (2022) A Model for Flywheel Fault Diagnosis Based on Fuzzy Fault Tree Analysis and Belief Rule Base. Machines, 10, 73-74.
https://doi.org/10.3390/machines10020073
[9]  陈洪转, 赵爱佳, 李腾蛟, 蔡匆聪, 程硕, 徐春丽. 基于故障树的复杂装备模糊贝叶斯网络推理故障诊断[J]. 系统工程与电子技术, 2021, 43(5): 1248-1261.
[10]  白旭, 汤荣铿, 罗小芳, 孙丽萍. 基于故障树分析和贝叶斯网络方法的半潜式钻井平台系统多状态可靠性分析[J]. 中国造船, 2020, 61(2): 220-228.
[11]  马建川, 种银保, 郎朗, 等. 基于故障树与贝叶斯网络的呼吸机故障智能诊断[J]. 中国医学物理学杂志, 2021, 38(9): 1129-1135.
[12]  Pang, J.H, Dai, J.K and Zhang, C.H. (2022) A New Dynamic Fault Tree Analysis Method of Electromagnetic Brakes Based on Bayesian Network Accompanying Wiener Process. Sym-metry, 14, 968-973.
https://doi.org/10.3390/sym14050968
[13]  Wang, C., Wang, L.D and Chen, H. (2021) Fault Diagnosis of Train Network Control Management System Based on Dynamic Fault Tree and Bayesian Network. IEEE ACCESS, 9, 2618-2632.
https://doi.org/10.1109/ACCESS.2020.3046681
[14]  范莉萍, 郎朗, 肖晶晶, 张诗慧, 种银保, 吕思敏. 基于故障树的多参数监护仪故障智能诊断专家系统研究[J]. 生物医学工程学杂志, 2022, 39(3): 586-595.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133