DAMAGE SENSING AND SELF-HEALING SYSTEM OF CARBON FIBER REINFORCED POLYMER COMPOSITES USING DEEP-LEARNING

Abstract

In this work, damage sensing and self-healing of carbon fiber reinforced polymer composite (CFRP) was conducted based on an addressable conducting network (ACN). For the high accuracy of damage sensing, a deep-learning based damage sensing system was developed. The training data was generated through Kirchhoff's circuits laws. Then, the Artificial Neural Network (ANN) based deep learning algorithm was used for damage sensing. In addition, selfhealing of the detected damage was performed. The self-healing was conducted by supplying an electric current to the damaged area. Supplied electric current generates joule heat in the damaged area. As a result, it was noteworthy that established deep-learning algorithm based on ACN exhibited high accuracy damage sensing resolution under compression test. In addition, the self-healing for damaged CFRP panels was also successfully performed.