A novel diagnostic and prognostic framework for incipient fault detection and remaining service life prediction with application to industrial rotating machines

Li, Xiaochuan; Yang, Xiaoyu; Yang, Yingjie; Bennett, I.J.; David, Éric

doi:10.1016/j.asoc.2019.105564

Cited by 38 publications

(19 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nascimento and Viana [44] discuss the use of recurrent neural networks merging physics-informed and data-driven knowledge to model the time evolution of structural fatigue. Jacazio et al [45,46] propose to employ particle filtering to estimate the system RUL; in [47] particle filtering is combined with Canonical Variate Analysis (CVA) and Exponentially Weighted Moving Average (EWMA) in order to determine the RUL of rotating equipment. However, these methods often require a significant computational effort, or may be highly influenced by the effect of uncertainty in the estimation of the fault condition.…”

Section: Prognostics and Health Management (Phm): Problem Formulationmentioning

confidence: 99%

Computational framework for real-time diagnostics and prognostics of aircraft actuation systems

Berri,

Vedova,

Mainini

2020

Preprint

View full text Add to dashboard Cite

Prognostics and Health Management (PHM) are emerging approaches to product life cycle that will maintain system safety and improve reliability, while reducing operating and maintenance costs. This is particularly relevant for aerospace systems, where high levels of integrity and high performances are required at the same time. We propose a novel strategy for the nearly real-time Fault Detection and Identification (FDI) of a dynamical assembly, and for the estimation of Remaining Useful Life (RUL) of the system. The availability of a timely estimate of the health status of the system will allow for an informed adaptive planning of maintenance and a dynamical reconfiguration of the mission profile, reducing operating costs and improving reliability. This work addresses the three phases of the prognostic flow -namely (1) signal acquisition,(2) Fault Detection and Identification, and (3) Remaining Useful Life estimation -and introduces a computationally efficient procedure suitable for real-time, on-board execution. To achieve this goal, we propose to combine information from physical models of different fidelity with machine learning techniques to obtain efficient representations (surrogate models) suitable for nearly real-time

show abstract

Section: Prognostics and Health Management (Phm): Problem Formulationmentioning

confidence: 99%

Computational framework for real-time diagnostics and prognostics of aircraft actuation systems

Berri,

Vedova,

Mainini

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…In this situations, the unsupervised techniques lead to more reliable results compared to supervised learning methods [12]. Clustering is the basic task for unsupervised learning and it helps to overcome data shortage problems [13][14][15].…”

Section: Introductionmentioning

confidence: 99%

Clustering Application for Condition-Based Maintenance in Time-Varying Processes: A Review Using Latent Dirichlet Allocation

et al. 2022

View full text Add to dashboard Cite

In the field of industrial process monitoring, scholars and practitioners are increasing interest in time-varying processes , where different phases are implemented within an unknown time frame. The measurement of process parameters could inform about the health state of the production assets, or products, but only if the measured parameters are coupled with the specific phase identification. A combination of values could be common for one phase and uncommon for another phase; thus, the same combination of values shows a high or low probability depending on the specific phase. The automatic identification of the production phase usually relies on clustering techniques. This is largely due to the difficulty of finding training fault data for supervised models. With these two considerations in mind, this contribution proposes the Latent Dirichlet Allocation as a natural language-processing technique for reviewing the topic of clustering applied in time-varying contexts, in the maintenance field. Thus, the paper presents this innovative methodology to analyze this specific research fields, presenting the step-by-step application and its results, with an overview of the theme.

show abstract

“…Krishnan et al [6] proposed a new method, such as generalised distance measurement and hierarchical dimensionality reduction, to monitor faults in manufacturing systems, which overcomes the problems often encountered in distance calculations in big data scenarios. Li et al [7] proposed a new monitoring index based on the analysis of typical variables and a Pearson correlation analysis method for early fault diagnosis and identification and improved the metabolic grey prediction model to predict the remaining life and solve the key safety problems often encountered in the prediction of sex and complex assets. Han and Si et al [8,9] proposed an industrial big data intelligent fault prediction method and implemented and compared a support vector machine (SVM) and neural network.…”

Section: Introductionmentioning

confidence: 99%

“…Li et al. [7] proposed a new monitoring index based on the analysis of typical variables and a Pearson correlation analysis method for early fault diagnosis and identification and improved the metabolic grey prediction model to predict the remaining life and solve the key safety problems often encountered in the prediction of sex and complex assets. Han and Si et al.…”

Section: Introductionmentioning

confidence: 99%

Research on condition monitoring and fault diagnosis of intelligent copper ball production lines based on big data

Zhang

Zhao

Zhao³

2021

IET Collab Intel Manufact

View full text Add to dashboard Cite

With the continuous upgrading and transformation of the intelligentisation of China's manufacturing industry, and in response to the requirements for further intelligentisation of the phosphor copper ball production line proposed by a new electronic material company, this study proposes a fault prediction and diagnosis method based on big data. A high-efficiency distributed big data platform is constructed, and a workshop-level monitoring centre with the Windows control centre (WinCC) as the core is formed. The WinCC configuration software is used to monitor the key parameters of the equipment during the operation phase, and the login interface is configured according to the requirements of workshop information integration, for example, display interface, alarm interface, debugging interface, trend graph and other common functions. Cloud platforms and virtual private network (VPN) communication are used to realise remote maintenance. Aiming at the common fault problems in the production process, an expert diagnosis system based on fault tree analysis is constructed by fusing the fault tree theory and expert systems. The fault tree model of the unqualified phosphor copper ball production quality and the failure of the hydraulic system is highlighted. Therefore, ensuring the safety of the phosphor copper ball production line is of great significance to the entire production system.

show abstract

A novel diagnostic and prognostic framework for incipient fault detection and remaining service life prediction with application to industrial rotating machines

Cited by 38 publications

References 41 publications

Computational framework for real-time diagnostics and prognostics of aircraft actuation systems

Computational framework for real-time diagnostics and prognostics of aircraft actuation systems

Clustering Application for Condition-Based Maintenance in Time-Varying Processes: A Review Using Latent Dirichlet Allocation

Research on condition monitoring and fault diagnosis of intelligent copper ball production lines based on big data

Contact Info

Product

Resources

About