On the use of fuzzy inference techniques in assessment models: part II: industrial applications

Abstract

In this paper, we study the applicability of the monotone output property and the output resolution property in fuzzy assessment models to two industrial Failure Mode and Effect Analysis (FMEA) problems. First, the effectiveness of the monotone output property in a single-input fuzzy assessment model is demonstrated with a proposed fuzzy occurrence model. Then, the usefulness of the two properties to a multi-input fuzzy assessment model, i.e., the Bowles fuzzy Risk Priority Number (RPN) model, is assessed. The experimental results indicate that both the fuzzy occurrence model and Bowles fuzzy RPN model are able to fulfill the monotone output property, with the derived conditions (in Part I) satisfied. In addition, the proposed rule refinement technique is able to improve the output resolution property of the Bowles fuzzy RPN model.Keywords Assessment models · Monotone output property · Output resolution property · Failure mode and effect analysis · Risk priority number

On the Use of Fuzzy Inference Systems for Assessment and Decision Making Problems

“…The use of the FIS model in assessment/measurement applications is popular in the literature. Examples include an FIS-based Risk Priority Number (RPN) model [1] for Failure Mode and Effect Analysis (FMEA), an FIS-based Occurrence model [2] for FMEA, an FIS-based education assessment model [3], an FIS-based groundwater vulnerability assessment model [4], and various FIS-based risk assessment models [5][6][7]. There are several reasons why an FIS-based model, instead of the conventional assessment models, is preferred.…”

“…Various methods to improve the FIS-based assessment/measurement paradigm, either in general or specific applications, have been proposed. Some recent advances include the hierarchical or multi-layer FIS-based assessment models [9,10], the FIS model with the grey relation theory [11], the monotonicity-relating properties of the FIS model [2,9], the FIS-based assessment model with a learning procedure [8].…”

“…It is also possible to explain the importance of the monotonicity property from the theoretical aspect of the length function in the field of measure theory [12]. A valid comparison and/or ranking (which eventually leads to decision making) scheme among different objects/ situations based on the predicted measuring index is important [2,13]. When tackling an assessment problem with an FIS-based model, the monotonicity property has to be satisfied so that meaningful results are obtained for decision making.…”

“…When tackling an assessment problem with an FIS-based model, the monotonicity property has to be satisfied so that meaningful results are obtained for decision making. For example, in the fuzzy RPN model, the monotonicity property ensures that the risks among different failure modes to be compared and ranked in a logical manner using the fuzzy RPN scores [2,13,14]. In [3], the significance of monotonicity in education assessment models is stressed, and the failure to fulfil monotonicity is considered as an anomaly.…”

“…In particular, the sufficient conditions for an FIS-based model to be monotone [2,9,13,15] are examined. In the derivation, an FIS is treated as a function, and the sufficient conditions are the mathematical conditions such that the first derivative is always greater than or equal to or less than or equal to zero for a monotonicincreasing or decreasing FIS, respectively.…”