Genetic Algorithm for Informative Basis Function Selection from the Wavelet Packet Decomposition with Application to Corrosion Identification Using Acoustic Emission

Chemical process installations are exposed to aggressive chemicals and conditions leading to corrosion. The damage from corrosion can lead to an unexpected plant shutdown and to the exposure of people and the environment to chemicals. Due to changes within and on the surface of materials subjected to corrosion, energy is released in the form of acoustic waves. This acoustic activity can be captured and used for corrosion monitoring in chemical process installations. Wavelet packet coefficients extracted from the acoustic activity have been considered to determine whether corrosion occurs, and to identify the type of corrosion process, at least for the most important corrosion processes in the chemical process industry. A challenging problem, after the extraction of the wavelet coefficients from the Wavelet Packet Transform (WPT), is to capture as much information as possible using a few wavelet coefficients to predict the corrosion type. Due to the statistical dependencies that potentially exist between the wavelet coefficients, the latter should not be selected independently from each other. Local discriminant basis selection algorithms do not take the statistical dependencies between wavelet coefficients into account. In this paper, we have used several mutual information-based approaches, that take into account these dependencies, to improve the selection of a few informative basis functions, and compared them to the wavelet-specific local discriminant basis selection algorithm. We have compared the following three mutual information filter approaches: a high-dimensional density-based method, a high-dimensional distance-based method, and a relevance-redundancy approach based on the normalized mutual information. Furthermore, a hybrid filter-wrapper genetic algorithm, which uses the relevance-redundancy approach as a local search procedure, was designed. All mutual information-based approaches require fewer coefficients than the local discriminant basis one and achieve a higher classification performance. The highest classification accuracies are most often obtained with the hybrid filter-wrapper genetic algorithm, for almost all classifiers used in this paper. A naïve Bayes classifier that uses the features selected by the hybrid filterwrapper genetic algorithm was able to identify the absence of corrosion, uniform corrosion, pitting and stress corrosion cracking, with an accuracy of up to 86.8%.