Optimization of Selective Laser Sintering Processing Parameters Based on ISMA-ELM Hybrid Model

A new hybrid model is proposed to address the issue of shrinkage in selective laser sintering parts, which combines the Improved Slime mould Algorithm ( ISMA) and Extreme Learning Machine ( ELM) to predict the shrinkage rate of the parts using limited input data. Firstly, three improvement strategies such as Levy flight, random opposition-based learning and highly disruptive polynomial mutation are used to improve the performance of the viscous bacteria optimization algorithm in all aspects. Subsequently, ISMA is used to optimize the key parameters of ELM, and an ISMA-ELM model is proposed to predict the shrinkage rate of SLS parts. Simulation results demonstrate that the proposed ISMA-ELM obtains optimal prediction results compared to the standard and other algorithm-optimized ELM models. Finally, the optimal processing parameters predicted by the ISMA-ELM model are used to guide the machining, and the dimensional accuracy of the obtained molded parts is improved by 29. 62% compared to the ELM model and 18. 02% compared to the SMA-ELM, which shows that the model can provide optimal process parameters for SLS molding processing and guide the machining effectively.