Density prediction of selective laser sintering parts based on support vector regression

摘要: The support vector regression （SVR） approach combined with particle swarm optimization for parameter optimization, is proposed to establish a model estimating the density of selective laser sintering parts under processing parameters, including layer thickness, hatch spacing, power, scanning speed, ambient temperature, interval time and mode. A comparison between prediction results from BP neural networks strongly supports that internal fitting capacity accuracy SVR are superior those identical training test samples; generation ability can be efficiently improved by increasing number samples. minimum error value provided leave-one-out cross validation SVR. These suggest an effective powerful tool parts.