Indirect Measurement of Grinding Force in Cemented Carbide Processing Based on SSA-KELM Algorithm

In order to address the challenge of measuring grinding force during the cemented carbide grinding process, this study proposes an indirect monitoring approach for grinding force based on the power of the spindle motor. The objective of this study is to collect machining power data and develop an identification model using SSA-KELM (Sparrow Search Algorithm-Kernel Extreme Learning Machine) in order to enable indirect monitoring of grinding force. We developed SSA-KELM model for identifying grinding force, which significantly improves precision by using the Sparrow Search Algorithm to globally optimize the core parameters of the KELM algorithm, thereby overcoming identification errors caused by random parameter selection in both the ELM and KELM algorithms. Experimental results demonstrate that the SSA-KELM identification model significantly improves prediction accuracy compared to other models and can be effectively used for indirect monitoring of grinding forces.