Prognostic and health management for engineering systems: a review of the data‐driven approach and algorithms

Sutharssan, Thamo; Stoyanov, Stoyan; Bailey, C.; Yin, Chunyan

doi:10.1049/joe.2014.0303

Cited by 83 publications

(45 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Literature proposes several FDI strategies, often conceived and implemented to specific problems or welldefined technical fields [6]; as regards onboard actuation systems based upon EMAs, it is possible to mention the followingmain FDI techniques:  model-based techniques founded on the comparison between the real system and related monitoring model (e.g. deterministic methods based upon appropriate merit coefficients [7]- [8], genetic algorithms [9]- [10] or further probabilistic approaches such as the simulated annealing method [11]);  approaches based on the spectral analysis of welldefined signals (i.e.…”

Section: Introductionmentioning

confidence: 99%

Prognostics of Onboard Electromechanical Actuators: a New Approach Based on Spectral Analysis Techniques

Belmonte

Vedova

Maggiore

2018

IREASE

View full text Add to dashboard Cite

In the last years, the layout of servomechanisms used in the aeronautical field to actuate the flight controls has changed radically and, nowadays electromechanical actuators (EMAs) are increasingly replacing the older hydraulic powered actuator types. The definition of special monitoring procedures, based on the analysis of the system response and aiming to evaluate the evolution of faults, represents an important task of the modern system engineering taking into account that onboard actuators are typically safety critical items. The present paper proposes a new prognostic procedure centered on the characterization of the state of health of an EMA used in aircraft primary flight controls. This approach, based on the innovative use of a model-based fault detection and identification method (FDI), identifies the actuator actual state of wear of the actuator analyzing proper system operational parameters, able to put in evidence the corresponding degradation path, by means of a numerical algorithm based on spectral analysis techniques. The proposed FDI algorithm has been tested in case of EMA affected by two progressive failures (rotor static eccentricity and stator phase turn-to-turn short-circuit), showing an adequate robustness and a suitable ability to early identify EMA malfunctions with low risk of false alarms or missed failures.

show abstract

Section: Introductionmentioning

confidence: 99%

Prognostics of Onboard Electromechanical Actuators: a New Approach Based on Spectral Analysis Techniques

Belmonte

Vedova

Maggiore

2018

IREASE

View full text Add to dashboard Cite

show abstract

“…Regarding the availability of degradation data, the main sources for large-scale processes include historical databases and event logs while the device level and component level data are mostly generated in the laboratories dedicated to the construction of aging models. To mitigate the problem of insufficient performance degradation data, further research efforts are required towards four strategies: (i) accelerated aging test [59], (ii) hardware-in-the-loop (HITL) simulation [60], (iii) semi-supervised online learning [60], and (iv) developing digital twins tools [61]. Generally speaking, the former two strategies need destructive tests while the latter two tend to be non-destructive.…”

Section: B Rul Estimation Approachesmentioning

confidence: 99%

Performance Supervised Plant-Wide Process Monitoring in Industry 4.0: A Roadmap

Jiang

Yin

Kaynak

2021

IEEE Open J. Ind. Electron. Soc.

114

View full text Add to dashboard Cite

“…The expansion of big data and IoT tends to make traditional machine learning algorithms like Hidden Markov Model (HMM) [70], Support Vector Machine (SVM) [71], and Neural Network (NN) with one hidden layer [61] vague, creating several challenges. First, traditional algorithms utilize shallow architectures, with only two stages of data-dependent computation elements.…”

Section: B Deep Learningmentioning

confidence: 99%

A Comprehensive Survey of Prognostics and Health Management Based on Deep Learning for Autonomous Ships

et al. 2019

View full text Add to dashboard Cite

The maritime industry widely expects to have autonomous and semi-autonomous ships (autoships) in the near future. In order to operate and maintain complex and integrated systems in a safe, efficient and cost-beneficial manner, autoships will require intelligent Prognostics and Health Management (PHM) systems. Deep learning (DL) is a potential area for this development, as it is rapidly finding applications in a variety of domains, including self-driving cars, smartphones, vision systems, and more recently in PHM applications. This paper introduces and reviews four well-established DL techniques recently applied to various practical PHM problems. The purpose is to support creativity and provide inspiration towards PHM based on DL (PHMDL) in autoships and the maritime industry. This paper discusses benefits, challenges, suggestions, existing problems, and future research opportunities with respect to this significant new technology. Index Terms-Autonomous ships, deep learning, maritime industry, prognostics and health management.

show abstract

Prognostic and health management for engineering systems: a review of the data‐driven approach and algorithms

Cited by 83 publications

References 33 publications

Prognostics of Onboard Electromechanical Actuators: a New Approach Based on Spectral Analysis Techniques

Prognostics of Onboard Electromechanical Actuators: a New Approach Based on Spectral Analysis Techniques

Performance Supervised Plant-Wide Process Monitoring in Industry 4.0: A Roadmap

A Comprehensive Survey of Prognostics and Health Management Based on Deep Learning for Autonomous Ships

Contact Info

Product

Resources

About