摩擦学系统润滑磨损故障诊断特征提取研究综述

润滑磨损故障是机械装备安全、健康、可靠运行的严重威胁，在对其诊断中存在的数据源多，造成数据维度高、形式多样化、结构与关系复杂以及数据与故障之间的映射关系不明确等问题，严重影响了诊断的效率、准确性和针对性. 随着装备智能化、集成化和大型化发展，润滑磨损故障诊断也将进入大数据和智能化时代，对诊断数据的应用与分析水平要求更高. 特征提取能实现原始数据降维、数据关系建立和故障敏感性信息获取，是润滑磨损故障诊断的基础性工作，也是实现数据高效应用的前提. 通过对润滑磨损故障诊断流程与技术分析，从诊断实验室检测、工业现场监测和在线实时监测等3个方面，研究装备润滑磨损故障诊断所需获取信息的组成，明确了其特征提取研究的内容与方向；在对磨损颗粒图像、磨损定量数据、润滑油性能劣化和润滑油污染等4个方面特征提取研究现状进行综述的基础上，提出了当前装备润滑磨损故障诊断特征提取所面临的挑战性问题；最后根据以上挑战性问题，结合装备发展趋势，指出了今后润滑磨损故障特征提取的研究方向.

Lubrication and wear faults pose a severe threat to the safe, healthy, and reliable operation of mechanical equipment. In fault diagnosis of this type, the numerous data sources lead to issues such as high data dimensionality, diverse data formats, complex structures and internal relationships, and unclear mapping between data and faults, which seriously undermine the efficiency, accuracy, and targeted performance of diagnosis. With the development of intelligent, integrated, and large-scale mechanical equipment, lubrication and wear fault diagnosis has entered the era of big data and intelligentization, which places higher requirements on the application and analysis capabilities of diagnostic data. Feature extraction, which can reduce the dimensionality of raw data, establish data relationships, and acquire fault-sensitive information, is a fundamental task in lubrication and wear fault diagnosis and a prerequisite for efficient data application. Through the analysis of lubrication and wear fault diagnosis processes and technologies, this study investigates the composition of information required for equipment lubrication and wear fault diagnosis from three aspects: diagnostic laboratory testing, industrial on-site monitoring, and online real-time monitoring, and clarifies the research contents and directions of feature extraction in this field. Based on a review of the current research status of feature extraction in four aspects: wear particle images, quantitative wear data, lubricant performance degradation, and lubricant contamination, this paper proposes the challenging issues currently faced in feature extraction for equipment lubrication and wear fault diagnosis. Finally, combined with the development trends of mechanical equipment and the above-mentioned challenging issues, this study points out the future research directions of feature extraction for lubrication and wear faults.

搜集汇总

背景与挑战

背景概述

该数据集是一篇关于摩擦学系统润滑磨损故障诊断特征提取研究的综述，总结了当前研究的挑战、现状和未来方向，由广州机械科学研究院有限公司的团队完成，发布于2023年8月15日。