Intelligent embedded system for decision support in pulsed eddy current corrosion detection using Extreme Learning Machine

• Published in: Measurement : journal of the International Measurement Confederation Vol. 185; p. 110069
• Main Authors: Silva, Manoel M., Simas Filho, Eduardo F., Farias, Paulo C.M.A., Albuquerque, Maria C.S., Silva, Ivan C., Farias, Claudia T.T.
• Format: Journal Article
• Language: English
• Published: London Elsevier Ltd 01.11.2021; Elsevier Science Ltd
• Subjects: Analog circuits; Artificial neural network; Artificial neural networks; Carbon steels; Classification; Computer architecture; Corrosion; Corrosion detection; Decision analysis; Decision support systems; Eddy currents; Electronic systems; Extreme Learning Machine; Fault diagnosis; Feature extraction; Fuzzy logic; Intelligent measurement system; Machine learning; Multilayers; Neural networks; Principal components analysis; Pulsed eddy current; Quantitative analysis; Signal processing; Steel pipes; Wavelet transforms; Extreme Learning Machine; Corrosion detection; Artificial neural network; Intelligent measurement system; Pulsed eddy current
• ISSN: 0263-2241; 1873-412X
• DOI: 10.1016/j.measurement.2021.110069

In this work an intelligent electronic system was proposed to generate, acquire and process Pulsed Eddy Currents (PEC) signals for corrosion detection in carbon steel pipes thermally insulated with composite coating. The system includes analog (excitation circuit and data acquisition) and digital (signal processing, feature extraction and decision support) sub-systems. The proposed signal processing chain comprises feature extraction using both discrete Fourier and Wavelet transforms, combined with information compaction by Principal Component Analysis (PCA) and decision support through intelligent classification techniques. Two neural network architectures were considered for classification, the traditional Multi-Layer Perceptron (MLP) and also the Extreme Learning Machine (ELM). The results obtained from thermally insulated carbon steel pipes subject to corrosion under isolation indicate the efficiency of the proposed method. Combining the ELM technique and data compaction it was possible to achieve a fast-training portable intelligent system for PEC evaluation and decision support. [Display omitted] •A portable & intelligent embedded system is proposed for PEC analysis.•Extreme learning machine is employed for corrosion detection.•Customized feature extraction and compaction modules ensure high efficiency.•It is possible to detect corrosion on inner and outer walls of the steel pipes.•A low computational cost prototype was designed.