A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Application of artificial neural network in prediction of abrasion of rubber composites
Highlights ► Establishing a model predicting abrasion via mechanical properties is meaningful. ► Twenty sets of data of abrasion and six mechanical properties were used as samples. ► An artificial neural network model of SBR-based rubber was established by MATLAB. ► The accuracy of prediction for artificial neural network model was 96.0%.
Abstract Abrasion of the rubber composite is related to its mechanical properties closely, and so establishing a model predicting the abrasion via mechanical properties is of interest. Based on twenty sets of sample data of abrasion and six mechanical properties (shore A hardness, stress at 100%, stress at 300%, tensilestrength, elongation at break, tear strength) of styrene–butadiene (SBR) based rubber composites, an artificial neural network (ANN) model, which was composed of abrasion and these six mechanical properties of SBR-based rubber, was established by MATLAB7.0 software. According to the network training error, the number of hidden layer neurons, training functions, learning functions and performance functions were optimized. Compared the experimental value with predicted value, the accuracy of predictionfor artificial neural network model was 96.0%. The target of predicted abrasion was achieved by ANN.
Application of artificial neural network in prediction of abrasion of rubber composites
Highlights ► Establishing a model predicting abrasion via mechanical properties is meaningful. ► Twenty sets of data of abrasion and six mechanical properties were used as samples. ► An artificial neural network model of SBR-based rubber was established by MATLAB. ► The accuracy of prediction for artificial neural network model was 96.0%.
Abstract Abrasion of the rubber composite is related to its mechanical properties closely, and so establishing a model predicting the abrasion via mechanical properties is of interest. Based on twenty sets of sample data of abrasion and six mechanical properties (shore A hardness, stress at 100%, stress at 300%, tensilestrength, elongation at break, tear strength) of styrene–butadiene (SBR) based rubber composites, an artificial neural network (ANN) model, which was composed of abrasion and these six mechanical properties of SBR-based rubber, was established by MATLAB7.0 software. According to the network training error, the number of hidden layer neurons, training functions, learning functions and performance functions were optimized. Compared the experimental value with predicted value, the accuracy of predictionfor artificial neural network model was 96.0%. The target of predicted abrasion was achieved by ANN.
Application of artificial neural network in prediction of abrasion of rubber composites
Wang, Bin (author) / Ma, Jian Hua (author) / Wu, You Ping (author)
2013-01-23
6 pages
Article (Journal)
Electronic Resource
English
Application of artificial neural network in prediction of abrasion of rubber composites
| British Library Online Contents | 2013
Prediction of the fatigue life of natural rubber composites by artificial neural network approaches
| British Library Online Contents | 2014