Rodríguez-Ramos, A., Silva Neto, A. J. e Llanes-Santiago, O., An Improved Fault Diagnosis Scheme Based on a Type-2 Fuzzy Classification Algorithms, pp 84-95. In: Y. Hernandez Heredia et al., Lecture Notes in Computer Science – LNCS, vol. 14335, 8th International Congress on Artificial Intelligence and Pattern Recognition 2023 (IWAIPR 2023), ISSN 0302-9743, ISBN 978-3-031-49552-6, Editora Springer, Cham, 2024.
The Industry 4.0 paradigm aims to obtain high levels of productivity and efficiency, more competitive final products and compliance with the demanding regulations related to industrial safety. To achieve these objectives, the industrial systems must be equipped with condition monitoring systems for the detection and isolation of faults. The paper presents the design of a fault diagnosis system with robust behavior for industrial plants by using Type-2 Fuzzy algorithm. In order to improve the classification, a kernel variant is implemented in the proposed algorithms to accomplish a better differentiation between classes. Several experiments were conducted (without noise, 2%, and 5% of noise level) by using the T2FCM, IT2FCM, KT2FCM, and KIT2FCM algorithms for the DAMADCIS benchmark, obtaining excellent results.