Tensile creep monitoring of basalt fiber-reinforced polymer plates via electrical potential change and artificial neural network

In this research, the long-term tensile creep (LTTC) failure in basalt fiber reinforced polymer (BFRP) composites under ambient conditions was detected and predicted via an expert system, in order to monitor the LTTC of BFRP laminate composites. This was accomplished by using the electrical potential change (EPC) technique that employs an electrical capacitance sensor (ECS) in conjunction with an artificial neural network (ANN). A finite element (FE) simulation model for tensile creep detection is generated by ANSYS and MATLAB. Therefore, FE analyses are employed to obtain groups of data for the training of the ANNs. The proposed method is applied to minimize the number of FE analysis for keeping the cost down and save the time of the creep behavior monitoring to a minimum. The paper first presents a study on the creep monitoring for different levels of tensile creep (%σc) as a percentage of ultimate tensile strength (UTS) equal to (25%, 50% and 75%) using EPC technique. Subsequently, the trained ANN is utilized to predict the creep behavior for the level of %σc not included in the FE data. Four different values are selected for the level of %σc; (15, 35%, 60% and 85%).