Research Projects

Vibration control of structures, buckling and crack of beams and walls using method of active sensing, image processing and control actuation with distributed piezoelectric devices has been a major area of research in IoT. Smart CNT-reinforced composite structures are advanced systems equipped with distributed real-time monitoring sensors, actuators, and robotic enhancement devices integrated with intelligent controllers. These features allow them to function as "smart structures," capable of autonomous monitoring and adaptive response. This study presents an intelligent structural monitoring and fault-tolerant control system for buckling and vibration analysis of carbon nanotube (CNT) reinforced composite structures. The proposed approach leverages real-time data from strain, displacement, and acceleration sensors, utilizing machine learning to detect anomalies and predictive analytics to assess risk. This proposal presents a real- and online-time monitoring of beam buckling, vibration, beam’s crack and fault diagnosis with smart robotic devices and risk assessment techniques. Few studies have investigated machine learning algorithms tailored for identifying and responding to faults, such as early-stage cracks or structural instabilities, in CNT composites. However, limited research has addressed the real-time monitoring and adaptive control of these composites, especially under dynamic and variable loading conditions where issues like buckling and vibration are critical. When critical thresholds are exceeded, a fault-tolerant control system dynamically adjusts structural parameters, ensuring stability and safety. The system continuously updates its predictive models through self-learning, enhancing resilience against unexpected structural faults and improving longevity. This framework provides a robust, adaptive solution for monitoring and managing complex composite structures.