Scholarlink

<p>Additive manufacturing (AM) has transformed the industrial sector through its capability to fabricate complex geometries and customized components. However, achieving optimal process parameters remains challenging due to the intricate interplay between material characteristics and mechanical responses. The present study investigates the influence of wire laser metal deposition (WLMD) parameters on the Ti-6Al-4V alloy. An L9 orthogonal array based on the Taguchi design of experiments was employed, considering three levels of laser power (800, 850, 900&#xa0;W) and gas flow rate (10,000, 15,000, 20,000&#xa0;mL/min). The surface microstructure was characterized using scanning electron microscopy (SEM) coupled with energy-dispersive x-ray spectroscopy (EDS) mapping, and electron back-scattered diffraction (EBSD),&#xa0;while density, microhardness, and surface roughness were evaluated as response variables. The microstructural analysis revealed a combination of lamellar <i>α</i>′ martensite and basketweave morphologies, with process parameters influencing the transition between colony and martensitic structures. The sample fabricated at 850&#xa0;W laser power and 10,000&#xa0;mL/min gas flow rate exhibited superior properties, achieving a density of 4.410 ± 0.22&#xa0;g/cm<sup>3</sup>, microhardness of 557.7 ± 11.15&#xa0;HV, and surface roughness of 0.396 ± 0.02&#xa0;<i>µ</i>m. Taguchi analysis incorporating the signal-to-noise (S/N) ratio, analysis of variance (ANOVA), and grey relational analysis (GRA) identified LP<sub>2</sub>GFR<sub>1</sub> as the optimal parameter combination. Furthermore, linear regression and artificial neural network (ANN) models were developed to correlate process parameters with responses variable. The ANN model, validated through <i>R</i><sup>2</sup> and MSE values, exhibited excellent agreement with experimental data, demonstrating its effectiveness for accurate and cost-efficient process optimization of Ti-6Al-4V components.</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

Optimization and Prediction of Mechanical and Surface Properties in Wire Laser Metal Deposition of Ti-6Al-4V Alloy Using Hybrid Taguchi–Grey–ANN–MLR Approach

  • 期刊论文

  • 发表日期：

    2026年7月22日

查看全文
  • Prashanth Muralishanker,
  • Senthilkumar Duraisamy,
  • Karunanithi Rasu,
  • Sivasankaran Subbarayan,
  • Kumaresan Gladys Ashok

摘要

Additive manufacturing (AM) has transformed the industrial sector through its capability to fabricate complex geometries and customized components. However, achieving optimal process parameters remains challenging due to the intricate interplay between material characteristics and mechanical responses. The present study investigates the influence of wire laser metal deposition (WLMD) parameters on the Ti-6Al-4V alloy. An L9 orthogonal array based on the Taguchi design of experiments was employed, considering three levels of laser power (800, 850, 900 W) and gas flow rate (10,000, 15,000, 20,000 mL/min). The surface microstructure was characterized using scanning electron microscopy (SEM) coupled with energy-dispersive x-ray spectroscopy (EDS) mapping, and electron back-scattered diffraction (EBSD), while density, microhardness, and surface roughness were evaluated as response variables. The microstructural analysis revealed a combination of lamellar α′ martensite and basketweave morphologies, with process parameters influencing the transition between colony and martensitic structures. The sample fabricated at 850 W laser power and 10,000 mL/min gas flow rate exhibited superior properties, achieving a density of 4.410 ± 0.22 g/cm3, microhardness of 557.7 ± 11.15 HV, and surface roughness of 0.396 ± 0.02 µm. Taguchi analysis incorporating the signal-to-noise (S/N) ratio, analysis of variance (ANOVA), and grey relational analysis (GRA) identified LP2GFR1 as the optimal parameter combination. Furthermore, linear regression and artificial neural network (ANN) models were developed to correlate process parameters with responses variable. The ANN model, validated through R2 and MSE values, exhibited excellent agreement with experimental data, demonstrating its effectiveness for accurate and cost-efficient process optimization of Ti-6Al-4V components.