Rodríguez Ramos, A., Bernal de Lázaro, J.M., Silva Neto, A.J. e Llanes-Santiago, O., Fault Detection Using Kernel Computational Intelligence Algorithms, Capítulo 14, pp. 263-281, em Computational Intelligence, Optimization and Inverse Problems with Applications in Engineering, (Eds.), ISBN: 978-3-319-96432-4, Editora Springer, 2018
In this chapter an indirect optimization criterion for the parameter setting of the kernel-based fault detection process is applied. The procedures analyzed involve the data preprocessing through the Kernel Independent Component Analysis (KICA) method, and the fault detection by using a classifier based on the Kernel Fuzzy C-means (KFCM) algorithm to achieve greater separability among the classes and reduce the classification errors. The main objective of this chapter is the adjustment of the kernel parameters to obtain the best possible performance in the fault detection. To achieve this, two different metaheuristic algorithms are compared: an evolutionary algorithm (Differential Evolution), and an algorithm based on group intelligence (Particle Swarm Optimization). The proposed approaches were evaluated and compared by using the Tennessee Eastman (TE) process benchmark.