Aero-engine bearing is the key component of aero-engine load-bearing transmission system, and its fault will affect the reliability and safety of aero-engine system, so it is particularly important to predict the fault of aeroengine bearings. The previous bearing researches are mainly based on the single-stage model, and the regression neural network has the problem of gradient disappearance, which leads to the uncertainty of prediction. Therefore, this paper proposes a novel model named LSS which combines the advantages of long short-term memory (LSTM) network with statistical process analysis to predict the fault of aero-engine bearings with multi-stage performance degradation. An algorithm based on the proposed model is put forward. Firstly, the time feature of bearing vibration signal is extracted and divided into multi-stage signals by statistical process analysis. Then, the multi-stage signals are input into LSS for prediction. The bearing datasets published by NASA and FEMTO-ST institute are used to prove the effectiveness of proposed method. The results show that the proposed method has higher prediction accuracy than recurrent neural network (RNN), support vector regression (SVR) and LSTM. Therefore, this method can divide the level of fault to reduce uncertainty, so as to improve prediction accuracy of the performance degradation trend and the RUL of bearings.

Junqiang Liu

Chunlu Pan

Fan Lei

Dongbin Hu

Hongfu Zuo

Reliability Engineering & System Safety

Reliability Engineering and System Safety is an international journal devoted to the development and application of methods for the enhancement of the safety and reliability of complex technological systems, like nuclear power plants, chemical plants, hazardous waste facilities, space systems, offshore and maritime systems, transportation systems, constructed infrastructure and manufacturing plants. The journal normally publishes only articles that involve the analysis of substantive problems related to the reliability of complex systems or present techniques and/or theoretical results that have a discernable relationship to the solution of such problems. An important aim is to achieve a balance between academic material and practical applications.

The following topics are within the scope of the journal: methods for reliability and probabilistic safety assessment; model and parameter uncertainties; aleatory and epistemic uncertainties, sensitivity analysis, data collection and analysis; engineering judgement and expert opinions; human reliability; test and maintenance policies; models for ageing and life extension; systems analysis of the impact of earthquakes, fires, tornadoes, winds, floods, etc.; codes, standards and safety criteria; operator decision support systems; software reliability; methods and applications of automatic fault detection and diagnosis; dynamic reliability; design and evaluation of man machine systems and human interfaces; design innovation for safety and reliability; safety culture; accident investigation and management. The journal does not normally publish articles that involve fuzzy sets and related non-probabilistic methods unless they contribute significantly to the solution of substantive problems related to the analysis of real systems.

The journal will contain contributed material in the form of original research papers, review articles, industrial case studies, safety recommendations, and short communications.

Reliability Engineering and System Safety is an international journal dedicated to the development and application of methods aimed at enhancing the safety and reliability of complex technological systems, such as nuclear power plants, chemical plants, hazardous waste facilities, space systems, offshore and maritime systems, transportation systems, constructed infrastructure, and manufacturing plants. The journal typically publishes articles that analyze substantive problems related to the reliability of complex systems or present techniques and/or theoretical results that have a clear relationship to solving such problems. A key objective is to achieve a balance between academic content and practical applications.

The following topics are within the scope of the journal: methods for reliability and probabilistic safety assessment; model and parameter uncertainties; aleatory and epistemic uncertainties; sensitivity analysis; data collection and analysis; engineering judgment and expert opinions; human reliability; test and maintenance policies; models for aging and life extension; systems analysis of the impacts of earthquakes, fires, tornadoes, winds, floods, etc.; codes, standards, and safety criteria; operator decision support systems; software reliability; methods and applications of automatic fault detection and diagnosis; dynamic reliability; design and evaluation of man-machine systems and human interfaces; design innovation for safety and reliability; safety culture; accident investigation and management. The journal does not typically publish articles involving fuzzy sets and related non-probabilistic methods unless they significantly contribute to solving substantive problems related to the analysis of real systems.

The journal will contain contributed material in the form of original research papers, review articles, industrial case studies, safety recommendations, and short communications.

《Reliability Engineering and System Safety》是一本国际期刊，致力于开发和应用方法，以提高复杂技术系统的安全性和可靠性。这些系统包括核电站、化工厂、有害废物设施、航天系统、海上和海洋系统、交通系统、建筑基础设施和制造工厂。期刊通常只发表涉及复杂系统可靠性相关实质性问题分析的文章，或提出与解决此类问题有明显关系的技术和/或理论结果。期刊的重要目标是实现学术材料与实际应用之间的平衡。

期刊的范围包括以下主题：可靠性和概率安全评估的方法；模型和参数的不确定性；随机和认知不确定性；敏感性分析；数据收集与分析；工程判断和专家意见；人类可靠性；测试和维护政策；老化和寿命延长模型；地震、火灾、龙卷风、风、洪水等影响的系统分析；规范、标准和安全标准；操作员决策支持系统；软件可靠性；自动故障检测和诊断的方法与应用；动态可靠性；人机系统和人机界面的设计与评估；安全和可靠性的设计创新；安全文化；事故调查与管理。期刊通常不发表涉及模糊集和相关非概率方法的文章，除非它们对解决与真实系统分析相关的实质性问题有显著贡献。

期刊将包含以原创研究论文、综述文章、工业案例研究、安全建议和简短通讯等形式提交的材料。

Reliability Engineering and System Safety

Fault prediction of bearings based on LSTM and statistical process analysis

A novel model named LSS which combines the advantages of long short-term memory (LSTM) network with statistical process analysis to predict the fault of aero-engine bearings with multi-stage performance degradation with higher prediction accuracy is proposed.

Category	Quartile
工程技术	1
工程技术, 工程工业	1
工程技术, 运筹学与管理科学	1

Fault prediction of bearings based on LSTM and statistical process analysis

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info

Category	Quartile
OPERATIONS RESEARCH & MANAGEMENT SCIENCE	1