Abstract
This paper demonstrates how tactile and proximity sensing can be used to perform automatic mechanical fractures detection (surface cracks). For this purpose, a custom-designed integrated tactile and proximity sensor has been implemented. With the help of fiber optics, the sensor measures the deformation of its body, when interacting with the physical environment, and the distance to the environment's objects. This sensor slides across different surfaces and records data which are then analyzed to detect and classify fractures and other mechanical features. The proposed method implements machine learning techniques (handcrafted features, and state of the art classification algorithms). An average crack detection accuracy of ~94% and width classification accuracy of ~80% is achieved. Kruskal-Wallis results (p < 0.001) indicate statistically significant differences among results obtained when analysing only integrated deformation measurements, only proximity measurements and both deformation and proximity data. A real-time classification method has been implemented for online classification of explored surfaces. In contrast to previous techniques, which mainly rely on visual modality, the proposed approach based on optical fibers might be more suitable for operation in extreme environments (such as nuclear facilities) where radiation may damage electronic components of commonly employed sensing devices, such as standard force sensors based on strain gauges and video cameras.
Highlights
An important task often performed in remote hazardous environments is the detection of mechanical fractures on the objects, such as containers, tanks, pipes, and other technical systems used for keeping chemical and radioactive waste
We propose a novel tactile sensing-based technique for mechanical fractures detection with the potential application to nuclear-decommissioning tasks performed by remotely operated robots
The best classification accuracy of 94% is achieved when implementing the Mean Absolute Value (MAV) or Root Mean Square (RMS) feature for the left and right displacement of the sensor and the proximity data
Summary
An important task often performed in remote hazardous environments is the detection of mechanical fractures on the objects, such as containers, tanks, pipes, and other technical systems used for keeping chemical and radioactive waste. Conventional automatic crack detection methods applied in industry to inspect large mechanical structures rely on acoustic methods (Chakraborty et al, 2019), use X-ray scanning (Barhli et al, 2017; Naragani et al, 2017), apply eddy currents techniques (Yao et al, 2014), or explore changes in a system’s motion dynamics (Lu and Chu, 2011; Nicoletti et al, 2018). The results highlight the time of onset and location that the crack started to form as well as the width and depth of the cracks
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
