A Survey of Data-Driven Prognostics

Schwabacher, Mark

doi:10.2514/6.2005-7002

Cited by 220 publications

(166 citation statements)

References 18 publications

Supporting

Mentioning

149

Contrasting

Unclassified

Order By: Relevance

“…The Condition Monitoring Sensors (CMS) attached to the components continuously send the readings of the state of the components via the SCADA systems and store the data in databases or clouds as big data. Processing of these data is vital for the prediction of the future state of the components, which is done by using different models such as ANN, Support Vector Machine (SVM), Gradient Boosting Machine (GBM), Deep Learning (DL), Random Forest (RF), the Generalized Linear Model (GLM), Grid Search (GS) and Statistical Matching Performance Pattern (SMPP) [8,25,26,[29][30][31][32][33].…”

Section: Framework For Complex System's Prognosismentioning

confidence: 99%

Integrated Big Data Analytics Technique for Real-Time Prognostics, Fault Detection and Identification for Complex Systems

Ossai

2017

Infrastructures

View full text Add to dashboard Cite

Real-time prediction of the state of complex systems is vital for integrity management since it is easier to plan for asset maintenance, reduce risks associated with unplanned downtime and reduce the cost of maintenance. This study utilized a four-fold cross-validation ensemble for an Artificial Neural Network (ANN) that used Multi-Layer Perceptron (MLP) in a backward propagation technique for haul crane prognosis. Big data on components' degradation states obtained from the Supervisory Control And Data Acquisition (SCADA) systems were used to implement the study. After preprocessing the dataset, importance scoring was used to compute the Cumulative Target-component Percentage-influence (CTP) of the input variables (source components) on the output variable (the target component) at the 95.5%, 99.3%, 99.9% and 100% levels. The specific source components responsible for the CTP levels of the target component were later used for the ANN network training that followed the cross-validation ensemble technique. The cross-validation ensemble ANN technique was also compared to the classic ANN and other machining learning algorithms. Finally, the best-trained cross-validation ensemble ANN network, which was obtained at the 99.9% CTP level, was used for future estimation of the time of failure of the system to enhance planning for the expected maintenance program that will be required at such times.

show abstract

Section: Framework For Complex System's Prognosismentioning

confidence: 99%

Integrated Big Data Analytics Technique for Real-Time Prognostics, Fault Detection and Identification for Complex Systems

Ossai

2017

Infrastructures

View full text Add to dashboard Cite

show abstract

“…They validate their models using induced faults from a laboratory setting. Schwabacher [33] has made a survey of artificial intelligence (AI) for failure prognosis and concluded that for realistic systems ''fully implementing prognosis is very difficult''. Several researchers have stated their intention to do prognostics, and have described the progress they have made in fault detection, but have left estimation of useful life remaining to future work.…”

Section: Dm For Zdmmentioning

confidence: 99%

Towards zero-defect manufacturing (ZDM)—a data mining approach

Wang

2013

Adv. Manuf.

114

View full text Add to dashboard Cite

The quality of a product is dependent on both facilities/equipment and manufacturing processes. Any error or disorder in facilities and processes can cause a catastrophic failure. To avoid such failures, a zero-defect manufacturing (ZDM) system is necessary in order to increase the reliability and safety of manufacturing systems and reach zero-defect quality of products. One of the major challenges for ZDM is the analysis of massive raw datasets. This type of analysis needs an automated and self-organized decision making system. Data mining (DM) is an effective methodology for discovering interesting knowledge within a huge datasets. It plays an important role in developing a ZDM system. The paper presents a general framework of ZDM and explains how to apply DM approaches to manufacture the products with zero-defect. This paper also discusses 3 ongoing projects demonstrating the practice of using DM approaches for reaching the goal of ZDM.

show abstract

“…Machine Prognostics and Health Management (PHM) is the process of detecting abnormal conditions, diagnosis of the fault and their cause and prognostics of future fault progression, as reviewed by Tobon-Mejia et al (2012), Heng et al (2009) and Schwabacher (2005). Maintenance strategies can be classified into three categories 1) Breakdown maintenance, 2) Preventive maintenance and 3) Condition-based maintenance (CBM) Jardine et al (2006).…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Trend Extraction for Prognostics and Condition Assessment

Mosallam

Medjaher

Zerhouni

2012

IFAC Proceedings Volumes

View full text Add to dashboard Cite

Maintenance is becoming more expensive nowadays due to the increased complexity in design and function of industrial systems. Continuous health monitoring is thus of high importance to increase the availability of industrial systems and consequently reduce the costs. This paper presents an algorithm for unsupervised trends extraction from multidimensional sensory data so as to use such trend in machinery health monitoring and maintenance needs. The proposed method does not assume any prior knowledge about the nature and type of the input signals. It is based on extracting successive multi-dimensional features from machinery sensory signals. Then, unsupervised feature selection on the features domain is applied without making any assumptions concerning the source of the signals and the number of the extracted features. Finally, empirical mode decomposition algorithm (EMD) is applied on the projected features with the purpose of following the evolution of data in a compact representation over time. The algorithm is demonstrated on accelerated degradation dataset of bearings acquired from PRONOSTIA experimental platform and a second dataset acquired form NASA repository where it is shown to be able to extract interesting signal trends.

show abstract

A Survey of Data-Driven Prognostics

Cited by 220 publications

References 18 publications

Integrated Big Data Analytics Technique for Real-Time Prognostics, Fault Detection and Identification for Complex Systems

Integrated Big Data Analytics Technique for Real-Time Prognostics, Fault Detection and Identification for Complex Systems

Towards zero-defect manufacturing (ZDM)—a data mining approach

Unsupervised Trend Extraction for Prognostics and Condition Assessment

Contact Info

Product

Resources

About