Research On Triangular Fuzzy Number Decision Method For Fault Diagnosis

With the rapid development of intelligent manufacturing industry,the failure of equipment cannot be avoided,and it also brings huge economic losses.Therefore,it is of great significance to quickly and accurately determine the failure of industrial equipment.Because most of the fault information of industrial equipment is fuzzy and the judgment of fault source is easily affected by many factors,the triangular fuzzy number with flexible conversion characteristics can accurately describe the fault information,and its corresponding decision-making methods can also comprehensively analyze the fault diagnosis problem.Therefore,the triangular fuzzy number decision-making methods for fault diagnosis is a research direction worthy of exploration and has strong applicability.In this paper,the fault diagnosis of untwisted roving weaving equipment in fiberglass manufacturing industry and steam turbine is taken as the research background,and the fault information is described as the form of triangular fuzzy number.The focus is on the relevant fuzzy multi-criteria decision-making methods and its application in the field of fault diagnosis.The main research of this paper is as follows:(1)Aiming at the problem that expert weight and criterion weight are given directly according to prior knowledge in existing fuzzy multi-criteria fault diagnosis methods,this paper proposes a VIKOR method based on triangular fuzzy number to calculate expert weight and criterion weight,and applies it to the fault diagnosis of glass fiber manufacturing equipment.In this method,the equipment fault information is first expressed as a more accurate triangular fuzzy number,and then the expert weight is calculated by combining the similarity and coefficient of variation method,and the criterion weight is calculated by maximizing the deviation based on the divergence matrix.Finally,the optimal fault diagnosis source is obtained by combining the VIKOR method.The experimental results show that,compared with other methods,it can obtain higher degree of differentiation and the result of fault scheme set is more intuitive by the proposed method in this paper.(2)Aiming at the problem that the interaction between the criteria and the relationship between the degree of membership and the degree of non-membership are ignored in the traditional fuzzy multi-criteria decision-making process,this paper proposes a decision-making method based on Pythagorean triangular fuzzy number and applies it to the fault diagnosis of steam turbines.In the Pythagorean fuzzy set environment where membership and non-membership are more widely used,this method proposes the Pythagorean triangular fuzzy geometric interaction Bonferroni mean operator that takes into account the interaction between the criteria,and based on this operator,the specific steps of the steam turbine fault diagnosis method are given.The experimental results show that the accuracy of this method in the detection of turbine fault mode is as high as 96%,and the robustness and feasibility of the proposed method are proved by sensitivity analysis and comparative experiments.(3)Aiming at the problem of low accuracy of decision results due to many fuzzy multi-criteria decision-making processes considering only a single measure,an improved comprehensive measure fault diagnosis method based on Pythagorean triangular fuzzy number is proposed in this paper.After obtaining the positive and negative ideal solutions,the improved method calculates the distance measure between the aggregation value and the ideal solution,and combines the score function value to give the comprehensive measurement value,and finally determines the equipment failure mode according to the comprehensive measurement value.The improved method is also applied to the fault diagnosis of steam turbine.The experimental results show that the improved method considers the influencing factors more comprehensively,and the accuracy rate is increased to 98.67%.