Determining optimal parameters for stereolithography processes via geneticalgorithm

Current part build accuracy of stereolithography processes needs to be impr oved because part inaccuracy and distortion still limit the processes' appl ication to other areas. This paper focuses on increasing build accuracy by optimally designing the process parameters. The process is modeled and desc ribed by a multilayer perceptron neural network. Based on this modeled proc ess, the genetic algorithm searches the optimal process parameters so that optimal conditions yield minimum part build error. In practice, genetic alg orithms find near-optimal conditions since they do not guarantee true optim al condition. The nearly optimized process is validated by actually buildin g H-parts and comparing these results with those obtained by the currently used nominal condition.