Failure caused by corrosion in industries are the major cause of breakdown maintenance. Acoustic emission during the accelerated corrosion testing is a reliable method for corrosion detection, however, classification of these acoustic emission signals by machine learning techniques is still in its infancy. Proposed approach uses a hybrid technique that combines the detection of corrosion through acoustic emission signals from accelerated corrosion testing with machine learning techniques to accurately predict the corrosion severity levels. Laboratory based experimentation setup was established for accelerated corrosion testing of mild steel samples for different time spans and mass loss of samples were recorded. Acoustic emission signals were acquired at high frequency sampling rate with Sound Well AE sensor, NI Elvis kit and NI Labview software. AE mean, AE RMS, AE energy, and kurtosis were selected as distinct features as they represent a linear relationship with the corrosion process. For multi-class problem, five Corrosion severity levels have been made based on mass loss occurred during accelerated corrosion testing for which Naive Bayes, BP-NN and RBF-NN showed accuracy of 90.4%, 94.57%, and 100% respectively.

工业腐蚀引起的故障是故障维修的主要原因。加速腐蚀测试期间的声发射是腐蚀检测的可靠方法，但是，通过机器学习技术对这些声发射信号进行分类仍处于起步阶段。提议的方法使用混合技术，该技术将通过来自加速腐蚀测试的声发射信号检测腐蚀与机器学习技术相结合，以准确预测腐蚀严重程度。建立了基于实验室的实验装置，用于对不同时间跨度的低碳钢样品进行加速腐蚀测试，并记录样品的质量损失。使用 Sound Well AE 传感器、NI Elvis 套件和 NI Labview 软件以高频采样率获取声发射信号。AE 平均值、AE RMS、AE 能量和峰度被选为不同的特征，因为它们代表与腐蚀过程的线性关系。对于多类问题，根据加速腐蚀测试过程中发生的质量损失制定了五个腐蚀严重性等级，其中朴素贝叶斯、BP-NN 和 RBF-NN 的准确度分别为 90.4%、94.57% 和 100%。