( 1. 湖南大學(xué) 材料科學(xué)與工程學(xué)院， 長(zhǎng)沙 410082;
2. 湖南大學(xué) 應(yīng)用物理系， 長(zhǎng)沙 410082)
摘 要: 針對(duì)選擇性激光燒結(jié)成型件變形大、 精度較低的問(wèn)題， 將神經(jīng)網(wǎng)絡(luò)方法應(yīng)用于選擇性激光燒結(jié)(SLS)加工工藝的研究。 根據(jù)SLS加工工藝的特點(diǎn)， 研究的工藝參數(shù)包括： 層厚、 掃描間距、 激光功率、 掃描速度、 環(huán)境溫度、 層與層之間的加工時(shí)間間隔和掃描方式。 建立了SLS加工工藝參數(shù)與加工變形、 收縮率之間的神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)模型。 實(shí)驗(yàn)結(jié)果與神經(jīng)網(wǎng)絡(luò)模型計(jì)算結(jié)果十分吻合， 說(shuō)明該神經(jīng)網(wǎng)絡(luò)模型能定量地反映出工藝參數(shù)與加工材料變形、 收縮率之間的關(guān)系。
關(guān)鍵字: 快速成型; 選擇性激光燒結(jié); 工藝參數(shù); 神經(jīng)網(wǎng)絡(luò)
neural network
（ 1. College of Materials Science and Engineering,
Hunan University, Changsha 410082, China;
2. Department of Applied Physics, Hunan University,
Changsha 410082, China）
Abstract: To solve the problem of large deforming and poor accuracy of SLS product ,the method of the artificial neural network is applied in the study of selective laser sintering (SLS) process. According to the feature of SLS, the parameters of interest are layer thickness, hatch spacing, laser power, scan speed, work surroundings temperature, interval time and scanning mode. The neural network model on the relationship between the processing parameter and distortion, shrinkage ratio of the job was built. The calculation results of neural network model are in good agreement with the experimental results, which indicating that the neural network model can analysis the relationship quantitatively.
Key words: rapid prototyping; selective laser sintering(SLS); processing parameter; neural network
