Data mining-based methods for fault isolation with validated FMEA model ranking

Yang, Chunsheng; Zou, Yanni; Lai, Pinhua; Jiang, Nan

doi:10.1007/s10489-015-0674-x

Cited by 20 publications

(14 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FMEA deployment, however, has been determined as a time-consuming methodology due to the resources required for its execution [11,12]. Because the current form of FMEA in its own application is not able to identify the primary functional requirements and the associated failure modes [4,10,11,13]. This means that it is difficult for the current form of FMEA to capture these requirements in a detailed bottom-up approach, which in turn, it impedes the systematic transfer of these requirements to the process domain, leading to an inability to shift and trace the product requirements and catch the associated failures that cascade over Functional, Design and Process FMEAs [4,10,13].…”

Section: Fig 2 Synchronising Fmea Applicationsmentioning

confidence: 99%

A Structured Approach for Synchronising the Applications of Failure Mode and Effects Analysis

Alruqi

Baumers

Branson

et al. 2021

Management Systems in Production Engineering

View full text Add to dashboard Cite

Failure Mode and Effects Analysis (FMEA) is a systematic approach for evaluating the potential failure modes in a system, and is mainly employed in three distinct tasks labelled: (1) Functional FMEA – evaluating those failures associated with product functional definition, (2) Design FMEA – analysing those failures associated with design definition and (3) Process FMEA – assessing potential failures in manufacturing and assembly processes. The literature review has shown limited works on the field of synchronising these different tasks into a working model. To address this gap, this research developed a framework for integrating these tasks of FMEAs, and then qualitatively validating the proposed framework. This research adopted a semi-structured questionnaire to collect experts’ feedback and validate the proposed framework. The t-test was then employed to evaluate the collected feedback. The findings highlight that the proposed framework is applicable and could facilitate the synchronisation of the different tasks of FMEA. This research presents a methodological approach for executing and synchronising FMEAs. Therefore, the proposed framework is practically relevant as an aid for the practitioners in catching the cascading failures and reducing the relevant impact.

show abstract

Section: Fig 2 Synchronising Fmea Applicationsmentioning

confidence: 99%

A Structured Approach for Synchronising the Applications of Failure Mode and Effects Analysis

Alruqi

Baumers

Branson

et al. 2021

Management Systems in Production Engineering

View full text Add to dashboard Cite

show abstract

“…On the other hand, occurrence is the likelihood of this failure that may occur again. Finally, detectability is the degree to which this failure could be detected [2][3][4]. Higher RPN value represents a higher priority of risk [5].…”

Section: Introductionmentioning

confidence: 99%

“…The RPN parameters' values are determined by engineers and experts which may include uncertainty and vagueness [12]. Moreover, the parameters that are used in FMEA are represented by (1)(2)(3)(4)(5)(6)(7)(8)(9)(10) crisp scale which is an unreliable representation of real-application cases [5,13]. Additionally, Chang, et al in [3] have criticized the RPN estimation by the inhomogeneous morphologic correlations between the three parameters.…”

Section: Introductionmentioning

confidence: 99%

“…Liu et al in [5] have used cloud model theory and hierarchical TOPSIS method to enhance FMEA effectiveness, overcoming bias probability of human judgment, and to facilitate the transformation of qualitative terms to quantitative values. Yang et al in [2] have utilized a data mining-based method for isolating faults based on FMEA parameters in order to enhance predictive maintenance by using historical big-data to create data-driven models, by which future failure can be predicted efficiently and accordingly avoid failures at a very critical operational item. Keskin and Özkan in [6] have applied a fuzzy adaptive resonance theory (ART) method for FMEA modeling in order to improve the classical methodology of calculating the RPN, which in total minimized cost and efforts needed to respond to corrective actions alerts.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, these documents need to be dynamically validated and updated on a continuous basis. Hence, utilizing new technologies is very vital to overcome these weaknesses and keep these documents updated and responsive [2].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Enhancing Failure Mode and Effects Analysis Using Auto Machine Learning: A Case Study of the Agricultural Machinery Industry

2020

View full text Add to dashboard Cite

In this paper, multiclass classification is used to develop a novel approach to enhance failure mode and effects analysis and the generation of risk priority number. This is done by developing four machine learning models using auto machine learning. Failure mode and effects analysis is a technique that is used in industry to identify possible failures that may occur and the effects of these failures on the system. Meanwhile, risk priority number is a numeric value that is calculated by multiplying three associated parameters namely severity, occurrence and detectability. The value of risk priority number determines the next actions to be made. A dataset that includes a one-year registry of 1532 failures with their description, severity, occurrence, and detectability is used to develop four models to predict the values of severity, occurrence, and detectability. Meanwhile, the resulted models are evaluated using 10% of the dataset. Evaluation results show that the proposed models have high accuracy whereas the average value of precision, recall, and F1 score are in the range of 86.6–93.2%, 67.9–87.9%, 0.892–0.765% respectively. The proposed work helps in carrying out failure mode and effects analysis in a more efficient way as compared to the conventional techniques.

show abstract