Enhanced ANN Predictive Model for Composite Pipes Subjected to Low-Velocity Impact Loads

This paper presents an enhanced artificial neural network (ANN) to predict the displacement in composite pipes impacted by a drop weight having different velocities. The impact response of fiber-reinforced polymer depends on several factors including thickness, stacking sequence, and number layers. These were investigated earlier study using sensitivity analysis, it was found that they had most prominent effect resistance pipes. In this present study, with diameter 54 mm are considered explore damages induced low-velocity influence these their strength. To evaluate low-velocity, exposed impacts at velocities 1.5, 2, 2.5, 3 m/s, preliminary damage initiated. Next, we used Jaya E-Jaya algorithms enhance ANN algorithm for good training prediction. has basic structure needs only two requirements, namely, population size terminal condition. Recently, been widely utilized solve various problems. Due its single learning technique limited information, may quickly be trapped local optima while addressing complicated optimization For better prediction, (E-Jaya) presented global searchability. is based influential parameters test effectiveness. results showed effectiveness best prediction compared original algorithm.