Search results

The traditional failure mode and effect analysis (FMEA) has some limitations, such as the neglect of relevant historical data, subjective use of rating numbering and the less rationality and accuracy of the Risk Priority Number. The current study proposes a machine learning–enhanced FMEA (ML-FMEA) method based on a popular machine learning tool, Waikato environment for knowledge analysis (WEKA).

This work uses the collected FMEA historical data to predict the probability of component/product failure risk by machine learning based on different commonly used classifiers. To compare the correct classification rate of ML-FMEA based on different classifiers, the 10-fold cross-validation is employed. Moreover, the prediction error is estimated by repeated experiments with different random seeds under varying initialization settings. Finally, the case of the submersible pump in Bhattacharjee et al. (2020) is utilized to test the performance of the proposed method.

The results show that ML-FMEA, based on most of the commonly used classifiers, outperforms the Bhattacharjee model. For example, the ML-FMEA based on Random Committee improves the correct classification rate from 77.47 to 90.09 per cent and area under the curve of receiver operating characteristic curve (ROC) from 80.9 to 91.8 per cent, respectively.

The proposed method not only enables the decision-maker to use the historical failure data and predict the probability of the risk of failure but also may pave a new way for the application of machine learning techniques in FMEA.

This study aims to propose a facilitating methodology for the application of Fuzzy FMEA (Failure Mode and Effect Analysis), comparing the traditional approach with fuzzy variations, supported by a case application in the aeronautical sector.

Based on experts' opinions in risk analysis within the aeronautical sector, rules governing the relationship between severity, occurrence, detection and risk factor were defined. This served as input for developing a fuzzyfied FMEA tool using the Matlab Fuzzy Logic Toolbox. The tool was applied to the sealing process in a company within the aeronautical sector, using triangular and trapezoidal membership functions, and the results were compared with the traditional FMEA approach.

The results of the comparative application of traditional FMEA and fuzzyfied FMEA using triangular and trapezoidal functions have yielded valuable insights into risk analysis. The findings indicated that fuzzyfied FMEA maintained coherence with the traditional analysis in identifying higher-risk effects, aligning with the prioritization of critical failure modes. Additionally, fuzzyfied FMEA allowed for a more refined prioritization by accounting for variations in each variable through fuzzy rules, thereby improving the accuracy of risk analysis and providing a more realistic representation of potential hazards. The application of the developed fuzzyfied FMEA approach showed promise in enhancing risk assessment in the aeronautical sector by considering uncertainties and offering a more detailed and context-specific analysis compared to conventional FMEA.

This study emphasizes the potential of fuzzyfied FMEA in enhancing risk assessment by accurately identifying critical failure modes and providing a more realistic representation of potential hazards. The application case reveals that the proposed tool can be integrated with expert knowledge to improve decision-making processes and risk mitigation strategies within the aeronautical industry. Due to its straightforward approach, this facilitating methodology could also prove beneficial in other industrial sectors.

This paper presents the development and application of a facilitating methodology for implementing Fuzzy FMEA, comparing it with the traditional approach and incorporating variations using triangular and trapezoidal functions. This proposed methodology uses the Toolbox Fuzzy Logic of Matlab to create a fuzzyfied FMEA tool, enabling a more nuanced and context-specific risk analysis by considering uncertainties.

The automotive industry appears to overcome much of its obstacles, despite the constant struggle facing COVID-19. The pandemic has resulted in significant improvements in the habits and conduct of consumers. There is an increased preference for personal mobility. In this dynamic environment with unexpected changes and high market rivalry, automotive supply chains focus more on executing responsive strategies with minimum costs. This paper aims to identify and model the drivers to the responsiveness of automotive supply chain.

Seventeen drivers for supply chain responsiveness have been identified from the extensive literature, expert interview. An integrated methodology of fuzzy decision-making trial and evaluation laboratory–interpretive structural modelling (DEMATEL–ISM) is developed to establish the interrelationship between the drivers. The cause–effect relationship between the drivers was obtained through fuzzy DEMATEL technique, and a hierarchical structure of the drivers was developed using the ISM technique.

The result of the integrated methodology revealed that strategic decision-making of management, accurate forecasting of demand, advanced manufacturing system in the organisation and data integration tools are the critical drivers.

This study has conceptual and analytical limitations. In this study, a limited number of drivers are examined for supply chain responsiveness. Further research may examine the role of other key performance indicators in the broad field of responsiveness in the automotive supply chain or other industry sectors. Future study can uncover the interrelationships and relative relevance of indicators using advanced multi-criteria decision-making methodologies.

The authors proposed an integrated methodology that will be benefitted to the supply chain practitioners and automotive manufacturers to develop management strategies to improve responsiveness. This study further helps to compare the responsiveness of the supply chain between various automotive manufacturers.