A Sensitized Plastic Fiber Sensor for Multi-Point Bending Measurement Based on Deep Learning
Shun Lu, Zhongwei Tan, Guangde Li, Yang Jingya
Abstract
As we all know, the change of mode interference caused by the curvature change in multi-mode fiber (MMF) can be well represented as a fiber specklegram recorded by CCD (Charge-coupled Device). However, it's difficult to identify the different bending occurred in several points in short distance. The paper proposes plastic fiber bending sensors can be used to detect the multi-point bending without adding any hardware. The convolutional neural network was used to classify the output speckles under different bending states. Specklegrams from fiber with three sensitization areas can be recognized by the neural network with a bending interval of 15°,10° and 5° with an accuracy rate of 99.2%, 96.1% and 93.5% respectively. Compared with traditional multi-point distributed sensors, this method is lower cost and easier to operate. The method proposed in this paper can find applications in distinguishing the status of certain structures, such as robotic arms and some disabled auxiliary equipment.