; (2019), Numerical and experimental approach of various sectioned new concept of the crash-boxes to determine the reliability and crashworthiness of the vehicles during frontal impacts.
Studies on the development of energy absorbing systems that minimize vehicle chassis damage in traffic accidents are increasing day by day. Many designs have been made in the studies on crash boxes used to absorb the energy released in the event of an accident. The specific energy absorption/ energy/FP crashworthiness values used to determine the efficiency of the designed crash boxes in this study were estimated using the Artifical Neural Network (ANN). The input layer of the ANN model consists of materials (DP600, DP800 and DP1000), thickness of materials (between 0.8 and 2.2 mm) and initial speed (10m/s, 12m/s and 16 m/s). In the ANN model, 42 different models were created by changing the different training function (training, trainlm and trainrp), transfer function (tansig and logsig) and the number of neurons in the hidden layer (between 9 and 33). R2 and RSME methods were used to evaluate the efficiency of ANN models. The training function was found to be highly accurate (R2: 0.99999 and RSME: 0.314727E-05) when the training function was “Trainlm” and the number of neurons in the hidden layer was 33. The training and testing results of the ANN model show that ANN can be used to estimate the specific energy absorption/energy/PCH value of crash boxes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.