Scholarlink

<p>Specific cutting energy (<i>SCE</i>) has significant advantages in assessing cutting energy consumption. However, <i>SCE</i> for the cutting level has been rarely studied to be directly expressed in terms of cutting parameters. To overcome the above problem as much as possible, a <i>SCE</i> prediction model with power-exponential mapping relationship with cutting parameters is proposed as an example of milling machining. Firstly, the cutting force prediction models are established based on linear regression analysis and particle swarm optimization (<i>PSO</i>), respectively, in order to select a set of models with smaller errors. Secondly, based on the relationship between cutting force, cutting power, and <i>SCE</i>, a <i>SCE</i> prediction model based on the cutting force model is established to achieve the prediction of energy consumption in milling machining. Finally, the effects of cutting parameters on <i>SCE</i> are explored based on the extreme deviation analysis and control variable method. The experimental results show that in the validation experiments, the <i>SCE</i> prediction model established in this study improves the accuracy by 13.39% compared with the conventional prediction model. Therefore, the study can provide theoretical references for the selection of low-energy cutting parameters.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Analysis on specific cutting energy prediction model based on cutting force prediction model built by particle swarm optimization: a case study of milling machining

  • 期刊论文

  • 发表日期：

    2025年10月7日

查看全文
  • Chenglong Zhai,
  • Lida Zhu,
  • Shaoqing Qin,
  • Mingxi Chen,
  • Jiuyang Yuan

摘要

Specific cutting energy (SCE) has significant advantages in assessing cutting energy consumption. However, SCE for the cutting level has been rarely studied to be directly expressed in terms of cutting parameters. To overcome the above problem as much as possible, a SCE prediction model with power-exponential mapping relationship with cutting parameters is proposed as an example of milling machining. Firstly, the cutting force prediction models are established based on linear regression analysis and particle swarm optimization (PSO), respectively, in order to select a set of models with smaller errors. Secondly, based on the relationship between cutting force, cutting power, and SCE, a SCE prediction model based on the cutting force model is established to achieve the prediction of energy consumption in milling machining. Finally, the effects of cutting parameters on SCE are explored based on the extreme deviation analysis and control variable method. The experimental results show that in the validation experiments, the SCE prediction model established in this study improves the accuracy by 13.39% compared with the conventional prediction model. Therefore, the study can provide theoretical references for the selection of low-energy cutting parameters.