Detection of Corrosion on Aircraft Structures Using an Electromagnetic Testing Sensor and a Spiking Convolutional Neural Network

The nondestructive testing (NDT) of aircraft intake structures is an important task to ensure the safety and integrity of the aircraft. Corrosion often appears at rivet locations and at the far-side surface or at hidden layers, presenting a challenge for NDT methods. To tackle this issue, we present a spiking NDT system that includes an electromagnetic testing probe with a spiking convolutional neural network (SCNN). The magnetic image of the rivet and corrosion is captured by a high spatial resolution Hall sensor array while scanning on the surface of the intake’s structure. The SCNN model is developed to analyze the obtained magnetic image and detect the presence of corrosion. The SCNN model, inspired by the principles of biological neurons, utilizes discrete and asynchronous spikes, resulting in remarkable energy efficiency. Our proposed SCNN model demonstrates a remarkable detection accuracy of approximately 93.67%, surpassing the performance of both the prior support vector machine (SVM) model (89.48%) and a conventional convolutional neural network (CNN) model (92.86%) on the same dataset. Importantly, when evaluated on the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mu $ </tex-math></inline-formula>Brain chip, our SCNN model exhibits power consumption approximately four orders of magnitude lower than that of a conventional CNN model running on an edge device (Jetson Nano). This substantial reduction in power consumption underscores the practicality and efficiency of our approach for concealed corrosion detection within aircraft intake structures, holding promises for enhanced maintenance practices in the aviation industry.