Material Removal Rate Prediction for Sapphire Double-Sided CMP Based on RSM-SVM

As a crucial substrate material for optoelectronic materials, sapphire has important applications in both military and civilian fields. In order to achieve the final processing quality of double-sided chemical mechanical polishing (DS-CMP) is necessary process, which also guarantee preparation high-end LED chips. this article, DS-CMP plan based on Box-Behnken design obtained experimented. Then, hybrid approach response surface method (RSM) support vector machines (SVM) algorithm established as removal rate (MRR) prediction model DS-CMP. Furthermore, process DS-CMP, influence variables MRR results RSM-SVM are analyzed respectively. From experimental results, maximum 387.59 nm min −1 , more than 6 times reported single-sided CMP under similar parameters. The mean square error predicted value through basically around ±10% value, possess satisfied validity Finally, top bottom wafers after was investigated.