RT Journal Article ID 599f91af19152d6f A1 Ziane, Khaled A1 Zebirate, Soraya A1 Zaitri, Adel T1 PARTICLE SWARM OPTIMIZATION-BASED NEURAL NETWORK FOR PREDICTING FATIGUE STRENGTH IN COMPOSITE LAMINATES OF WIND TURBINE BLADES JF Composites: Mechanics, Computations, Applications: An International Journal JO CMCA YR 2015 FD 2015-09-29 VO 6 IS 4 SP 321 OP 338 K1 prediction K1 composite materials K1 fatigue strength K1 artificial neural networks, particle swarm optimization K1 wind turbine blades AB In this paper, the fatigue strength in multidirectional (MD)/unidirectional (UD) composite laminates of wind turbine blades is predicted by using particle swarm optimization-based artificial neural networks (PSO-ANN). In the PSO-ANN approach used in this work, the objective function was assessed using the mean square error (MSE) computed as the squared difference between the predicted values and the target values for a number of training set samples. Different materials based on different reinforcing fabrics and resins are compared in terms of the maximum tensile fatigue stress. Tension–tension constant amplitude fatigue loads were applied to thermoset materials including glass-fiber/epoxy, polyester and vinyl esters. All materials were treated in closed molds with resin infusion process, which were molded into their final dogbone shape without machining. The results show that the PSO-ANN can provide accurate fatigue strength prediction for different MD/UD composite laminates under different values of fiber orientation. PB Begell House LK https://www.dl.begellhouse.com/journals/36ff4a142dec9609,04c73e80135a5da7,599f91af19152d6f.html