In machining activities, sound emission is one of the key factors toward the operator's health and safety. Sound generation during cutting is the outcome of the interaction between tool and work. The intensity of sound greatly influences the cutting power consumption and surface finish obtained during machining. Therefore, the current work emphasized the analysis of sound emission, power consumption, and surface roughness in hard turning of AISI 4340 steel using a CBN tool which was rarely found in the literature. Response surface methodology (RSM) and artificial neural network (ANN) techniques were utilized to formulate the model for each response. The results indicated that the maximum value of input parameters exhibited the highest level of sound due to the creation of vibration in the machine and tool. Higher sound level indicates the generation of lower power consumption but at the same instant surface roughness was leading with increment in sound level. The feed rate exhibited the utmost noteworthy consequence on surface quality with 87.71% contribution. The cutting power can be decreased by choosing the high level of cutting parameters. The RSM and ANN have a good correlation with experimental data, but the accuracy of the ANN is better than the RSM.

在加工活动中，声音排放是影响操作员健康和安全的关键因素之一。切削过程中产生的声音是刀具和工件相互作用的结果。声音的强度极大地影响加工过程中获得的切削功率和表面光洁度。因此，目前的工作重点分析了使用文献中很少见的 CBN 刀具对 AISI 4340 钢进行硬车削时的声发射、功耗和表面粗糙度。响应面方法 (RSM) 和人工神经网络 (ANN) 技术被用来为每个响应制定模型。结果表明，由于在机器和工具中产生振动，输入参数的最大值表现出最高水平的声音。较高的声级表明产生较低的功耗，但同时表面粗糙度随着声级的增加而领先。进给率对表面质量的影响最为显着，贡献率为 87.71%。选择高水平的切削参数可以降低切削功率。RSM 和 ANN 与实验数据有很好的相关性，但 ANN 的准确性优于 RSM。