Scholarlink

<p>Laser additive manufacturing (LAM) has enormous potential for engineering applications. However, how to control the mechanical properties of the deposited layer remains a key challenge hindering its development. To address this challenge, this study introduces micro-hammer forging technology to regulate the mechanical properties of the LAM deposited layer. By combining the whale optimization algorithm(WOA) with support vector regression(SVR), a predictive model for the process parameters of micro-hammer forging and the mechanical properties of the LAM deposited layer was established. Subsequently, the performance of the WOA-SVR model was evaluated and compared with the particle swarm optimization SVR model (PSO-SVR) and the genetic algorithm-optimized neural network model (GA-BP). The results showed that the determination coefficients of the WOA-SVR, PSO-SVR, and GA-BP models for predicting the tensile strength of the deposited layers were 99%, 98.3%, and 95.3%, respectively; the coefficients of determination for the elongation prediction models were 96.7%, 94.2%, and 88%, respectively; and the coefficients of determination for the microhardness prediction models were 97.9%, 93.8%, and 87.3%, respectively. Among these, the WOA-SVR model demonstrated superior prediction accuracy. This proves that the model can assist micro-hammer forging in regulating the mechanical properties of the LAM deposition layer.</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

Prediction of Mechanical Properties in Micro-hammer Forging Assisted Laser Additive Manufacturing Using WOA-SVR

  • 期刊论文

  • 发表日期：

    2026年3月13日

查看全文
  • Junhua Wang,
  • Mingxin Liu,
  • Yuanming Mao,
  • Luhaotian Feng,
  • Junhang Wang,
  • Dongbo Lu,
  • Junfei Xu,
  • Kun Li,
  • Tancheng Xie,
  • Ruijie Gu

摘要

Laser additive manufacturing (LAM) has enormous potential for engineering applications. However, how to control the mechanical properties of the deposited layer remains a key challenge hindering its development. To address this challenge, this study introduces micro-hammer forging technology to regulate the mechanical properties of the LAM deposited layer. By combining the whale optimization algorithm(WOA) with support vector regression(SVR), a predictive model for the process parameters of micro-hammer forging and the mechanical properties of the LAM deposited layer was established. Subsequently, the performance of the WOA-SVR model was evaluated and compared with the particle swarm optimization SVR model (PSO-SVR) and the genetic algorithm-optimized neural network model (GA-BP). The results showed that the determination coefficients of the WOA-SVR, PSO-SVR, and GA-BP models for predicting the tensile strength of the deposited layers were 99%, 98.3%, and 95.3%, respectively; the coefficients of determination for the elongation prediction models were 96.7%, 94.2%, and 88%, respectively; and the coefficients of determination for the microhardness prediction models were 97.9%, 93.8%, and 87.3%, respectively. Among these, the WOA-SVR model demonstrated superior prediction accuracy. This proves that the model can assist micro-hammer forging in regulating the mechanical properties of the LAM deposition layer.