Real-time monitoring of the corrosion behaviour of the 304SS in HCl solution using BPNN with joint image recognition and electrochemical noise

Electrochemical noise has an important reference role in the study of early corrosion; however, a direct correlation between the microscopic morphology and the electrochemical noise of the corrosion process is lacking. This study uses a back propagation artificial neural network (BPNN) optimized by three intelligent optimization algorithms to real-time monitor the local corrosion of 304 stainless steel in HCl solution with joint recognition and feature extraction of corrosion images and electrochemical noise. The results show that the corrosion monitoring model established by optimized BPNN with genetic algorithms exhibits the highest convergence speed and accuracy.