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

In order to achieve the fault diagnostic and degradation assessment of the electro-hydraulic servo valve, a system of prognostic and health management based on the data-driven approach for the electro-hydraulic servo valve is presented. FMMEA performed in this study considered the degree of sub-components in electro-hydraulic servo valve. In order to use only five parameters to assess the cause of degradation, a physical model of the EH servo valve was built up to simulate the failure modes. The simulation results are very useful because the methods can be applied to assess the cause of degradation such as leakage, jamming, clogging and so on.

Download Full-text

The application of big data-driven prognostic and health management on complex equipment based on internet of things

Proceedings of the 2nd Annual International Conference on Electronics, Electrical Engineering and Information Science (EEEIS 2016) ◽

10.2991/eeeis-16.2017.106 ◽

2017 ◽

Author(s):

Guo-Shun Chen ◽

Gang Niu

Keyword(s):

Big Data ◽

Internet Of Things ◽

Health Management ◽

Data Driven ◽

Complex Equipment ◽

Prognostic And Health Management

Download Full-text

Prognostics and Health Management A Data-Driven Approach to Supporting the F-35 Lightning II

2007 IEEE Aerospace Conference ◽

10.1109/aero.2007.352833 ◽

2007 ◽

Cited By ~ 28

Author(s):

Edward R. Brown ◽

Neal N. McCollom ◽

Erin-Elaine Moore ◽

Andy Hess

Keyword(s):

Health Management ◽

Data Driven ◽

Prognostics And Health Management ◽

Data Driven Approach

Download Full-text

A Review of Data-Driven Oil and Gas Pipeline Pitting Corrosion Growth Models Applicable for Prognostic and Health Management

International Journal of Prognostics and Health Management ◽

10.36001/ijphm.2018.v9i1.2695 ◽

2020 ◽

Vol 9 (1) ◽

Author(s):

Roohollah Heidary ◽

Steven A. Gabriel ◽

Mohammad Modarres ◽

Katrina M. Groth ◽

Nader Vahdati

Keyword(s):

Stochastic Process ◽

Pitting Corrosion ◽

Oil And Gas ◽

Health Management ◽

Assessment Model ◽

Data Driven ◽

Gas Pipelines ◽

Oil And Gas Pipelines ◽

Process Based Models ◽

Prognostic And Health Management

Pitting corrosion is a primary and most severe failure mechanism of oil and gas pipelines. To implement a prognostic and health management (PHM) for oil and gas pipelines corroded by internal pitting, an appropriate degradation model is required. An appropriate and highly reliable pitting corrosion degradation assessment model should consider, in addition to epistemic uncertainty, the temporal aspects, the spatial heterogeneity, and inspection errors. It should also take into account the two well-known characteristics of pitting corrosion growing behavior: depth and time dependency of pit growth rate. Analysis of these different levels of uncertainties in the amount of corrosion damage over time should be performed for continuous and failure-free operation of the pipelines. This paper reviews some of the leading probabilistic data-driven prediction models for PHM analysis for oil and gas pipelines corroded by internal pitting. These models categorized as random variable-based and stochastic process-based models are reviewed and the appropriateness of each category is discussed. Since stochastic process-based models are more versatile to predict the behavior of internal pitting corrosion in oil and gas pipelines, the capabilities of the two popular stochastic process-based models, Markov process-based and gamma process-based, are discussed in more detail.

Download Full-text

Prognostics and Health Management for Complex system Based on Fusion of Model-based approach and Data-driven approach

Physics Procedia ◽

10.1016/j.phpro.2012.02.124 ◽

2012 ◽

Vol 24 ◽

pp. 828-831 ◽

Cited By ~ 3

Author(s):

Wang Hong-feng

Keyword(s):

Complex System ◽

Health Management ◽

Data Driven ◽

Prognostics And Health Management ◽

Model Based ◽

Data Driven Approach

Download Full-text

A Data-Driven Approach for the Diagnosis of Mechanical Systems Using Trained Subtracted Signal Spectrograms

Sensors ◽

10.3390/s19051055 ◽

2019 ◽

Vol 19 (5) ◽

pp. 1055 ◽

Cited By ~ 2

Author(s):

Jiung Huh ◽

Huan Pham Van ◽

Soonyoung Han ◽

Hae-Jin Choi ◽

Seung-Kyum Choi

Keyword(s):

Frequency Conversion ◽

Time Synchronization ◽

Expert Knowledge ◽

Health Management ◽

Industrial Robot ◽

Mechanical Systems ◽

Data Driven ◽

Time Frequency ◽

Data Driven Approach ◽

The Difference

Toward the prognostic and health management of mechanical systems, we propose and validate a novel effective, data-driven fault diagnosis method. In this method, we develop a trained subtracted spectrogram, the so called critical information map (CIM), identifying the difference between the signal spectrograms of normal and abnormal status. We believe this diagnosis process may be implemented in an autonomous manner so that an engineer employs it without expert knowledge in signal processing or mechanical analyses. Firstly, the CIM method applies sequential and autonomous procedures of time-synchronization, time frequency conversion, and spectral subtraction on raw signal. Secondly, the subtracted spectrogram is then trained to be a CIM for a specific mechanical system failure by finding out the optimal parameters and abstracted information of the spectrogram. Finally, the status of a system health can be monitored accurately by comparing the CIM with an acquired signal map in an automated and timely manner. The effectiveness of the proposed method is successfully validated by employing a diagnosis problem of six-degree-of-freedom industrial robot, which is the diagnosis of a non-stationary system with a small amount of training datasets.

Download Full-text

Data-driven Decision-Making Methodology for Prognostic and Health Management of Wind Turbines

10.1109/anzcc53563.2021.9628240 ◽

2021 ◽

Author(s):

Khaoula Tidriri ◽

Ahmad Braydi ◽

Hussain Kazmi

Keyword(s):

Decision Making ◽

Wind Turbines ◽

Health Management ◽

Data Driven ◽

Data Driven Decision Making ◽

Prognostic And Health Management

Download Full-text

Data-driven process planning for shipbuilding

Artificial intelligence for engineering design analysis and manufacturing ◽

10.1017/s089006041600055x ◽

2017 ◽

Vol 32 (1) ◽

pp. 122-130 ◽

Cited By ~ 3

Author(s):

Jinsong Bao ◽

Xiaohu Zheng ◽

Jianguo Zhang ◽

Xia Ji ◽

Jie Zhang

Keyword(s):

Health Management ◽

Model Identification ◽

Production Performance ◽

Data Driven ◽

Complex Process ◽

Data Driven Approach ◽

Plan Change ◽

Major Factors ◽

Relevant Factors

AbstractErection planning in shipbuilding is a highly complex process. When a process change happens for some reason, it is often difficult to identify how many factors are affected and estimate how sensitive these factors can be. To optimize the planning and replanning of the shipbuilding plan for the best production performance, a data-driven approach for shipbuilding erection planning is proposed, which is composed of an erection plan model, identification of major factors related to the erection plan, and a data-driven algorithm to apply shipbuilding operation data for creating plans and forecasting, for plan adjustment, future availabilities of shipyard resources including machines, equipment, and man power. Through data clustering, the relevant factors are identified as a result of plan change, and critical equipment health management is carried out through data-driven anomaly detection. A case study is implemented, and the result shows that the proposed data-driven method is able to reschedule the shipbuilding plans smoothly.

Download Full-text

Deep Learning Enable Diagnostics and Prognostics of Machine Health Condition

Annual Conference of the PHM Society ◽

10.36001/phmconf.2019.v11i1.919 ◽

2019 ◽

Vol 11 (1) ◽

Author(s):

Wo Jae Lee ◽

John W. Sutherland

Keyword(s):

Deep Learning ◽

Health Management ◽

Health Condition ◽

Data Driven ◽

Future Research ◽

Annual Conference ◽

Machine Health ◽

Prognostic And Health Management

This paper presents an overview of the first author’s research being conducted and future research plans for the rest of PhD career. The content of this paper was presented at the PHM 2019 Doctoral Symposium, which was a part of the program at the 11th Annual Conference of the Prognostic and Health Management Society held in Scottsdale, Arizona from September 21-26, 2019. The paper covers the development and application of data-driven approaches to machine health management.

Download Full-text