scholarly journals From Fuzzy Clustering to a Fuzzy Rule-Based Fault Classification Model

Author(s):  
Enrico Zio ◽  
Piero Baraldi ◽  
Irina Crenguta Popescu
Author(s):  
Enrico ZIO ◽  
Piero BARALDI ◽  
Irina Crenguta POPESCU

2015 ◽  
Vol 21 (4) ◽  
pp. 456-477 ◽  
Author(s):  
S. P. Sarmah ◽  
U. C. Moharana

Purpose – The purpose of this paper is to present a fuzzy-rule-based model to classify spare parts inventories considering multiple criteria for better management of maintenance activities to overcome production down situation. Design/methodology/approach – Fuzzy-rule-based approach for multi-criteria decision making is used to classify the spare parts inventories. Total cost is computed for each group considering suitable inventory policies and compared with other existing models. Findings – Fuzzy-rule-based multi-criteria classification model provides better results as compared to aggregate scoring and traditional ABC classification. This model offers the flexibility for inventory management experts to provide their subjective inputs. Practical implications – The web-based model developed in this paper can be implemented in various industries such as manufacturing, chemical plants, and mining, etc., which deal with large number of spares. This method classifies the spares into three categories A, B and C considering multiple criteria and relationships among those criteria. The framework is flexible enough to add additional criteria and to modify fuzzy-rule-base at any point of time by the decision makers. This model can be easily integrated to any customized Enterprise Resource Planning applications. Originality/value – The value of this paper is in applying Fuzzy-rule-based approach for Multi-criteria Inventory Classification of spare parts. This rule-based approach considering multiple criteria is not very common in classification of spare parts inventories. Total cost comparison is made to compare the performance of proposed model with the traditional classifications and the result shows that proposed fuzzy-rule-based classification approach performs better than the traditional ABC and gives almost the same cost as aggregate scoring model. Hence, this method is valid and adds a new value to spare parts classification for better management decisions.


2016 ◽  
Vol 12 (3) ◽  
pp. 38-50 ◽  
Author(s):  
Saroj Kr. Biswas ◽  
Monali Bordoloi ◽  
Heisnam Rohen Singh ◽  
Biswajit Purkayastha

The efficient feature selection for predictive and accurate classification is highly desirable in many application domains. Most of the attempts to neuro-fuzzy classifier lose information to build interpretable neuro-fuzzy classification model. This paper proposes an interpretable neuro-fuzzy classification model with significant features without loss of knowledge, which is an extension of an existing interpretable neuro-fuzzy classification model. The proposed model is designed based on the consideration of feature importance that is determined by frequency of linguistic features. The rules are then made based on important features. Therefore, the knowledge acquired in network can be comprehended to logical rules using only important features. The proposed model finally performs classification task by rule-based approach. The average accuracy calculated by 10-fold cross validation finds that the proposed model can increase performance of the already proven neuro-fuzzy system for classification tasks.


2021 ◽  
pp. 1-10
Author(s):  
Kaijie Xu ◽  
Hanyu E ◽  
Yinghui Quan ◽  
Ye Cui ◽  
Weike Nie

In this study, we develop a novel clustering with double fuzzy factors to enhance the performance of the granulation-degranulation mechanism, with which a fuzzy rule-based model is designed and demonstrated to be an enhanced one. The essence of the developed scheme is to optimize the construction of the information granules so as to eventually improve the performance of the fuzzy rule-based models. In the design process, a prototype matrix is defined to express the Fuzzy C-Means based granulation-degranulation mechanism in a clear manner. We assume that the dataset degranulated from the formed information granules is equal to the original numerical dataset. Then, a clustering method with double fuzzy factors is derived. We also present a detailed mathematical proof for the proposed approach. Subsequently, on the basis of the enhanced version of the granulation-degranulation mechanism, we design a granular fuzzy model. The whole design is mainly focused on an efficient application of the fuzzy clustering to build information granules used in fuzzy rule-based models. Comprehensive experimental studies demonstrate the performance of the proposed scheme.


Author(s):  
Ignacio Requena ◽  
Armando Blanco ◽  
Miguel Delgado

This paper proposes a new method for identifying unknown systems with Fuzzy Rule-Based Systems (FRBSs). The method employs different methodologies from the discipline of Soft Computing (Artificial Neural Networks, Fuzzy Clustering) and follows a three-stage process. Firstly, the structure of the FRBS rules is determined using a feature selection process. A fuzzy clustering procedure is then used to establish the number of fuzzy rules. In the third step, the fuzzy membership functions are constructed for the linguistic labels. Finally, the empirical performance of the algorithm is studied by applying it to a number of classification and approximation problems.


1997 ◽  
Vol 5 (2) ◽  
pp. 223-233 ◽  
Author(s):  
M. Delgado ◽  
A.F. Gomez-Skarmeta ◽  
F. Martin

2021 ◽  
pp. 1-14
Author(s):  
Xingchen Hu ◽  
Yinghua Shen ◽  
Witold Pedrycz ◽  
Xianmin Wang ◽  
Adam Gacek ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document