迁移学习在机械设备预测性维护领域的应用综述

Summary of Application of Transfer Learning in Predictive Maintenance of Machinery and Equipment

迁移学习是运用已有知识对不同但相关领域问题进行求解的一种新的机器学习方法,可有效地解决传统机器学习要求训练集和测试集服从独立同分布及需要大量样本进行训练的问题。本文针对迁移学习在预测性维护领域的应用进行了综述,总结了在复杂及变工况条件和小样本条件下基于迁移学习的诊断预测现状,并对迁移学习在预测性维护领域的未来研究方向进行了探讨。

Transfer learning is a new machine learning method that applies the knowledge from related but different domains to target domains.It can effectively solve the problems that traditional machine learning requires training sets and test sets follow the independent and identically distributed(i.i.d.)condition and requires a large number of samples for training.This paper reviews the application of transfer learning in predictive maintenance,summarizes the current situation of diagnosis and prediction based on transfer learning under complex and variable working conditions and small sample conditions,and finally discusses the f ut u re research direction of t ransfer learning in predictive maintenance.