Bayesian framework for fault variable identification

Turkoz, Mehmet; Kim, Sangahn; Jeong, Young-Seon; Jeong, Myong K.; Elsayed, Elsayed A.; Al-Khalifa, Khalifa N.

doi:10.1080/00224065.2018.1507561

Cited by 12 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Codetta-Raiteri et al described a fault detection, identification, and recovery cycle composed of the tasks of diagnosis, prognosis and recovery, which was characterized through a dynamic Bayesian network model for autonomous spacecrafts [32]. Turkoz et al developed a data-driven Bayesian approach for fault identification that addressed the limitations posed by the normality assumption, which was computationally efficient for high-dimensional data compared with existing approaches [33]. The current research on the application of BN cannot consider the causation and correlation of variables and keep the consistency of information from multiple sources.…”

Section: Related Workmentioning

confidence: 99%

A Novel Fault Identification Method Driven by Knowledge and Data

Wan

Zhang

2022

IEEE Access

View full text Add to dashboard Cite

In the field of intelligent manufacturing, fault identification is an effective way to improve product service by identifying the cause of failures. For addressing it, the Generalized Bayesian Network (GBN) model is extended based on the traditional Bayesian Network in this paper, which redefines the directed edges and probability parameters among nodes. Compared with Bayesian Network, the GBN model has the ability to simultaneously define causality and correlation of variables. In addition, the structure of network is not only based on statistical data but also driven by expert knowledge. In order to achieve the collaboration of data and knowledge while maintaining the consistency, a hierarchical collaborative framework is designed including the data layer and knowledge layer. Furthermore, a hierarchical multi-objective optimization algorithm, namely Hierarchical Non-dominated Sorting Genetic Algorithm II (HNSGA-II), is advanced to solve the proposed model. Finally, an industrial case study for fault cause identification targeting the product service helps illustrate all details.INDEX TERMS Fault identification, generalized bayesian network (GBN), data and knowledge, hierarchical collaborative framework, hierarchical non-dominated sorting genetic algorithm II (HNSGA-II).

show abstract

Section: Related Workmentioning

confidence: 99%

A Novel Fault Identification Method Driven by Knowledge and Data

Wan

Zhang

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The objective of this method is a simultaneous control of multiple correlated variables. Many researchers have applied the multivariate control chart in different works (Bersimis and Sachlas, 2019; Xiang et al ,2019; Turkoz et al , 2019; Haq et al , 2020).…”

Section: Lean Six Sigmamentioning

confidence: 99%

Monitoring of overall equipment effectiveness by multivariate statistical process control

Imane

Aoula

Achouyab

2021

IJLSS

View full text Add to dashboard Cite

Purpose This study aims to monitor the overall equipment effectiveness (OEE) indicator that is one of the best indicators used to monitor the performance of the company by the multivariate control chart. Design/methodology/approach To improve continually the performance of a company, many research studies tend to apply Lean six sigma approach. It is one of the best ways used to reduce the variability in the process by using the univariate control chart to know the trend of the variable and make the action before process deviation. Nevertheless, and when the need is to monitor two or more correlated characteristics simultaneously, the univariate control chart will be unable to do it, and the multivariate control chart will be the best way to successfully monitor the correlated characteristics. Findings For this study, the authors have applied the multivariate control chart to control the OEE performance rate which is composed by the quality rate, performance rate and availability rate, and the relative work from which the authors have adopted the same methodology (Hadian and Rahimifard, 2019) was done for project monitoring, which is done by following different indicators such as cost, and time; the results of this work shows that by applying this tool, all project staff can meet the project timing with the cost already defined at the beginning of the project. The idea of monitoring the OEE rate comes because the OEE contains the three correlated indicators, we can’t do the monitoring of the OEE just by following one of the three because data change and if today we have the performance and quality rate are stable, and the availability is not, tomorrow we can another indicator impacted and, in this case, the univariate control chart can’t response to our demand. That’s why we have choose the multivariate control chart to prevent the trend of OEE performance rate. Otherwise, and according to production planning work, they try to prevent the downtime by switching to other references, but after applying the OEE monitoring using the multivariate control chart, the company can do the monitoring of his ability to deliver the good product at time to meet customer demand. Research limitations/implications The application was done per day, it will be good to apply it per shift in order to have the ability to take the fast reaction in case of process deviation. The other perspective point we can have is to supervise the process according to the control limits found and see if the process still under control after the implementation of the Multivariate control chart at the OEE Rate and if we still be able to meet customer demand in terms of Quantity and Quality of the product by preventing the process deviation using multivariate control chart. Practical implications The implication of this work is to provide to the managers the trend of the performance of the workshop by measuring the OEE rate and by following if the process still under control limits, if not the reaction plan shall be established before the process become out of control. Originality/value The OEE indicator is one of the effective indicators used to monitor the ability of the company to produce good final product, and the monitoring of this indicator will give the company a visibility of the trend of performance. For this reason, the authors have applied the multivariate control chart to supervise the company performance. This indicator is composed by three different rates: quality, performance and availability rate, and because this tree rates are correlated, the authors have tried to search the best tool which will give them the possibility to monitor the OEE rate. After literature review, the authors found that many works have used the multivariate control chart, especially in the field of project: to monitor the time and cost simultaneously. After that, the authors have applied the same approach to monitor the OEE rate which has the same objective : to monitor the quality, performance and availability rate in the same time.

show abstract

“…Multivariate statistical process control is an efficient tool for assessing the product quality through the monitoring of industrial processes. Numerous researchers have recently investigated the aspects and applications of multivariate control chart, such as Bersimis and Sachlas, 2 Xiang et al, 3 Turkoz et al, 4 and Haq et al 5 Krupskii et al 6 developed new copula‐based multivariate monitoring techniques for possibly autocorrelated, non‐Gaussian data. In other study, Pascual and Akhundjanov 7 investigated an attribute control chart to monitor correlated multivariate Poisson processes by using copula models.…”

Section: Introductionmentioning

confidence: 99%

Robust T² control chart using median‐based estimators

Maleki

Mehri

Aghaie

et al. 2020

Quality & Reliability Eng

View full text Add to dashboard Cite

One of the most widely used multivariate control charts is the Hotelling T 2. In order to construct a Hotelling T 2 control chart, the mean vector (μ) and the variance-covariance matrix (Σ) must be first estimated. The classical estimators of μ and Σ are usually used to design Hotelling T 2 control chart. The classical estimators are sensitive to the presence of outliers. One way to deal with outliers is to use robust estimators. In this study, a robust T 2 control chart is proposed. The mean vector is obtained from the sample median. The median absolute deviation and the comedian are used as the estimates of the elements of the variance-covariance matrix. The proposed robust estimators of the mean vector and the variance-covariance matrix are compared with the sample mean vector and the sample variance-covariance matrix, and the M estimator of these parameters, through efficiency and robustness measures. The performances of the proposed robust T 2 control chart and the classical and the M estimators are also compared by means of average run length. Simulation results reveal that the proposed robust T 2 control chart has much better performance than the traditional Hotelling T 2 and similar performance to the M estimator in detecting shifts in process mean vector. Use of other robust estimators to estimate the process parameters is an area for further research.

show abstract

Bayesian framework for fault variable identification

Cited by 12 publications

References 32 publications

A Novel Fault Identification Method Driven by Knowledge and Data

A Novel Fault Identification Method Driven by Knowledge and Data

Monitoring of overall equipment effectiveness by multivariate statistical process control

Robust T² control chart using median‐based estimators

Contact Info

Product

Resources

About

Bayesian framework for fault variable identification

Cited by 12 publications

References 32 publications

A Novel Fault Identification Method Driven by Knowledge and Data

A Novel Fault Identification Method Driven by Knowledge and Data

Monitoring of overall equipment effectiveness by multivariate statistical process control

Robust T2 control chart using median‐based estimators

Contact Info

Product

Resources

About

Robust T² control chart using median‐based estimators