Reduction of noise pollution in CNC wood milling through multi-parameter optimization using response surface methodology

Abstract

Background CNC (Computer Numerical Control) wood milling machines offer significant productivity advantages but are associated with excessive noise pollution, posing health risks to workers. This study investigates the influence of machining parameters on Noise Pollution Level (NPL) in CNC wood milling and aims to optimize these parameters to minimize noise emissions. Methods A Response Surface Methodology (RSM) based on Box-Behnken Design (BBD) was employed to model the effects of cutting speed, feed rate, depth of cut, and step over on NPL. A total of 27 experimental runs were conducted. Statistical analysis, including ANOVA and regression modeling, was performed to determine the significance of each parameter. The model was further optimized using a Genetic Algorithm (GA). Results The NPL observed across experiments ranged from 97.4 dB to 103.8 dB, with all values exceeding the NIOSH recommended limit of 85 dB. ANOVA results revealed that cutting speed, cutting speed squared, feed rate, and depth of cut had a statistically significant effect on NPL (p  <  0.05). The regression model showed a high degree of fit (R²  =  0.945). Optimal parameters—cutting speed of 12,730 rpm, feed rate of 58 mm/s, depth of cut of 3.2 mm, and step over of 6.4 mm—were identified using GA, resulting in a predicted NPL of 96.2 dB, which closely matched the experimentally validated value of 95.8 dB. Conclusion The study confirms that NPL in CNC wood milling can be significantly reduced by optimizing machining parameters. The integration of RSM and GA provides a reliable framework for minimizing occupational noise exposure, thereby enhancing worker safety in woodworking environments.