京ICP备13020181号-2
© 《China Plastics》
© 《China Plastics》
China Plastics ›› 2023, Vol. 37 ›› Issue (8): 127-134.DOI: 10.19491/j.issn.1001-9278.2023.08.018
• Review • Previous Articles
WANG Lei, ZHAO Min, WENG Yunxuan, ZHANG Caili()
Received:
2023-05-22
Online:
2023-08-26
Published:
2023-08-21
CLC Number:
WANG Lei, ZHAO Min, WENG Yunxuan, ZHANG Caili. Research progress in applications and performance prediction of machine learning in PLA processing[J]. China Plastics, 2023, 37(8): 127-134.
ML模型 | 应用以及性能预测 | 参考文献 |
---|---|---|
线性回归、多项式回归、随机森林回归 | 研究PLA样条缺口形状、光栅方向和熔体内部空隙对疲劳寿命的影响 | [ |
支持向量机(SVM) | 监测PLA生产过程中的补全失效缺陷和几何缺陷 | [ |
人工神经网络(ANN)和人工神经网络⁃遗传算法(ANN⁃GN) | 预测PLA的韧性、零件 厚度和生产成本 | [ |
主成分分析与随机森林结合 | 预测PLA的拉伸性能,监测生产过程中的产品质量 | [ |
梯度提升、随机森林、核岭和支持向量回归模型 | 将PLA泡沫密度通过温度、时间、压力的函数表达 | [ |
使用回归树的统计分析 | 研究PLA复合材料的拉伸强度 | [ |
4个ANN、2个自适应神经模糊推理系统以及最小二乘支持向量回归 | 预测左旋聚乳酸/聚乙交酯(PLLA/PGA)复合材料的相对结晶度与结晶时间、温度和PGA含量的关系 | [ |
多分类逻辑回归和多分类神经网络 | 预测PLA的热降解程度 | [ |
ML模型 | 应用以及性能预测 | 参考文献 |
---|---|---|
线性回归、多项式回归、随机森林回归 | 研究PLA样条缺口形状、光栅方向和熔体内部空隙对疲劳寿命的影响 | [ |
支持向量机(SVM) | 监测PLA生产过程中的补全失效缺陷和几何缺陷 | [ |
人工神经网络(ANN)和人工神经网络⁃遗传算法(ANN⁃GN) | 预测PLA的韧性、零件 厚度和生产成本 | [ |
主成分分析与随机森林结合 | 预测PLA的拉伸性能,监测生产过程中的产品质量 | [ |
梯度提升、随机森林、核岭和支持向量回归模型 | 将PLA泡沫密度通过温度、时间、压力的函数表达 | [ |
使用回归树的统计分析 | 研究PLA复合材料的拉伸强度 | [ |
4个ANN、2个自适应神经模糊推理系统以及最小二乘支持向量回归 | 预测左旋聚乳酸/聚乙交酯(PLLA/PGA)复合材料的相对结晶度与结晶时间、温度和PGA含量的关系 | [ |
多分类逻辑回归和多分类神经网络 | 预测PLA的热降解程度 | [ |
机器学习方法 | 结构特性 | 模型 数量/个 | |
---|---|---|---|
固定属性 | 可调属性 | ||
多层感知器神经网络 | 隐藏层的数量为2。第一个隐藏层的激活函数使用的是双曲正切函数。第二个隐藏层的激活函数使用的是逻辑函数。训练算法采用的是Levenberg⁃Marquardt算法。 | 隐藏层神经元数量 | 200 |
级联前馈神经网络 | 隐藏层的数量为2。第一个隐藏层的激活函数为双曲正切。第二个隐藏层的激活函数是逻辑函数。所使用的训练算法是Levenberg⁃Marquardt算法。 | 隐藏层神经元数量 | 200 |
循环神经网络 | 隐藏层的数量为2。第一个隐藏层的激活函数是双曲正切函数。第二个隐藏层的激活函数是逻辑函数。所使用的训练算法是缩放共轭梯度算法。 | 隐藏层神经元数量 | 160 |
最小二乘支持向量回归 | 训练算法,即最小平方法。 | 核函数 | 150 |
具有减法聚类的自适应神经模糊推理系统 | 隶属函数,即减法聚类。 | 聚类训练算法半径 | 400 |
具有C均值聚类的自适应神经模糊推理系统 | 隶属函数,即C均值聚类。 | 聚类训练算法数量 | 400 |
机器学习方法 | 结构特性 | 模型 数量/个 | |
---|---|---|---|
固定属性 | 可调属性 | ||
多层感知器神经网络 | 隐藏层的数量为2。第一个隐藏层的激活函数使用的是双曲正切函数。第二个隐藏层的激活函数使用的是逻辑函数。训练算法采用的是Levenberg⁃Marquardt算法。 | 隐藏层神经元数量 | 200 |
级联前馈神经网络 | 隐藏层的数量为2。第一个隐藏层的激活函数为双曲正切。第二个隐藏层的激活函数是逻辑函数。所使用的训练算法是Levenberg⁃Marquardt算法。 | 隐藏层神经元数量 | 200 |
循环神经网络 | 隐藏层的数量为2。第一个隐藏层的激活函数是双曲正切函数。第二个隐藏层的激活函数是逻辑函数。所使用的训练算法是缩放共轭梯度算法。 | 隐藏层神经元数量 | 160 |
最小二乘支持向量回归 | 训练算法,即最小平方法。 | 核函数 | 150 |
具有减法聚类的自适应神经模糊推理系统 | 隶属函数,即减法聚类。 | 聚类训练算法半径 | 400 |
具有C均值聚类的自适应神经模糊推理系统 | 隶属函数,即C均值聚类。 | 聚类训练算法数量 | 400 |
1 | 郑卫, 赵振新, 马名杰, 等. 可降解材料的市场现状及发展前景[J]. 河南化工,2023, 40 (1): 1⁃5. |
ZHENG W, ZHAO Z X, MA M J,et al. Market status and development prospect of degradable materials[J]. Henan Chemical Industry, 2023, 40 (1): 1⁃5. | |
2 | 王艺涵, 贾丹, 詹胜鹏, 等. 机器学习在聚合物材料研究中的应用进展[J]. 高校化学工程学报,2023, 37(2):170⁃180. |
WANG Y H, JIA D, ZHAN S P,et al. Review on application of machine learning in polymer material research[J]. Journal of Chemical Engineering of Chinese Universities,2023,37(2):170⁃180 | |
3 | Xia K, Gao H, Liu C, et al. A novel superhard tungsten nitride predicted by machine⁃learning accelerated crystal structure search[J]. Science Bulletin, 2018, 63(13):817⁃824. |
4 | 刘海知, 徐辉, 包红军, 等. 机器学习分类算法在降雨型滑坡预报中的应用[J]. 应用气象学报,2022, 33(3): 282⁃292. |
LIU H Z, XU H, BAO H J,et al.Application of machine learning classification algorithm to precipitation⁃induced landslides forecasting[J].Journal of Applied Meteorological Science,2022, 33(3): 282⁃292. | |
5 | Levin S, Toerper M, Hinson J, et al. Machine⁃learning⁃based electronic triage: a prospective evaluation[J]. Annals of Emergency Medicine, 2018, 72(4):116. |
6 | 钱琦淼, 张朵, 王映艨, 等. 机器学习在股价预测上的应用[J]. 中国市场, 2022, 21: 7⁃10. |
7 | Doan T H, Chiho K, Lihua C, et al. Machine⁃learning predictions of polymer properties with polymer genome[J]. Journal of Applied Physics, 2020, 128(17):171104. |
8 | Jha A, Chandrasekaran A, Kim C, et al. Impact of dataset uncertainties on machine learning model predictions: the example of polymer glass transition temperatures[J]. Modelling and Simulation in Materials Science and Engineering, 2019, 27(2): 024002. |
9 | 黄飞鸿, 李凤红, 笪伟, 等. 3D打印聚乳酸复合材料的改性研究进展[J]. 工程塑料应用, 2022, 50(11): 151⁃156. |
HUANG F H, LI F H,DA W,et al.Research progress on modification of 3D printed polylactic acid composites[J]. Engineering Plastis Application, 2022, 50(11): 151⁃156. | |
10 | Hassanifard S, Behdinan K. Anisotropy and internal flaws effects on fatigue response of notched 3D⁃printed PLA parts[J]. Materials Today Communications, 2023, 35:105734. |
11 | Delli U, Chang S. Automated process monitoring in 3D printing using supervised machine learning[J]. Procedia Manufacturing 2018, 26: 865⁃870. |
12 | Meiabadi M S, Moradi M, Karamimoghadam M, et al. Modeling the producibility of 3D printing in polylactic acid using artificial neural networks and fused filament fabrication[J]. Polymers(Basel), 2021, 13(19) :13103219. |
13 | Wang C, Tan X P, Tor S B, et al. Machine learning in additive manufacturing: State⁃of⁃the⁃art and perspectives[J].Additive Manufacturing, 2020, 36:101538. |
14 | 李小强. 基于机器学习的零件加工在线监测研究[J]. 自动化与仪器仪表, 2022, 11:124⁃128,133. |
LI X Q.Research on on⁃line monitoring of parts machining based on deep learning[J].Automation and Instruentation, 2022, 11:124⁃128,133. | |
15 | Mulrennan K, Donovan J, Creedon L, et al. A soft sensor for prediction of mechanical properties of extruded PLA sheet using an instrumented slit die and machine learning algorithms[J]. Polymer Testing, 2018, 69: 462⁃469. |
16 | Albuquerque R Q, Brütting C, Standau T, et al. A machine learning investigation of low⁃density polylactide batch foams[J]. E⁃Polymers, 2022, 22(1): 318⁃331. |
17 | 马喜峰. 聚乳酸复合材料在生物医学领域的应用研究[J]. 化学与粘合, 2022, 44(5): 436⁃440. |
MA X F.Application of polylactic acid composites in biomedical field[J].Chemistry and Adhesion, 2022, 44(5): 436⁃440. | |
18 | Alakent B, Soyer⁃Uzun S. Implementation of statistical learning methods to develop guidelines for the design of PLA⁃based composites with high tensile strength values[J]. Industrial & Engineering Chemistry Research, 2019, 58(8):3 478⁃3 489. |
19 | 冯晓雯, 胡灵芝, 张文, 等. 左旋聚乳酸等温结晶动力学的超快扫描量热研究[J]. 伊犁师范大学学报(自然科学版), 2022, 16(1): 39⁃43. |
FENG X W, HU L Z, ZHANG W,et al.Study on isothermal crystallization and kinetics of polymer PLLA by fast scanning calorimetry[J].Journal of Yili Normal University(Natural Science Edition), 2022, 16(1): 39⁃43. | |
20 | Wang J, Ayari M A, Khandakar A, et al. Estimating the relative crystallinity of biodegradable polylactic acid and polyglycolide polymer composites by machine learning methodologies[J]. Polymers (Basel), 2022, 14(3):14030527. |
21 | 殷嘉骏, 琚艳云, 孙政权, 等. 连续化静电纺尼龙6/改性聚乳酸复合膜的制备及性能[J]. 塑料工业, 2022, 50(10):30⁃35. |
YIN J J, JU Y Y, SUN Z Q,et al.Preparation and properties of continuous electrospinning nylon 6 /modified PLA composite film[J].China Plastis Industry, 2022, 50(10):30⁃35. | |
22 | Choi N Y, Shin B C, Zhang S U. A Comparative study of the linear⁃elastic and hyperelastic models for degradation of PLA prepared using fused filament fabrication[J]. Journal of the Korean Society of Manufacturing Process Engineers, 2020, 19(3):1⁃7. |
23 | Zhang S U. Classifying thermal degradation of polylactic acid by using machine learning algorithms trained on fourier transform infrared spectroscopy data[J]. Applied Sciences, 2020, 10(21):10217470. |
24 | Å Rinnan, Berg F V D, Engelsen S B. Review of the most common pre⁃processing techniques for near⁃infrared spectra[J]. Trends in Analytical Chemistry, 2009, 28(10): 1 201⁃1 222. |
25 | Andraju N, Curtzwiler G W, Ji Y, et al. Machine⁃learning⁃based predictions of polymer and postconsumer recycled polymer properties: a comprehensive review[J]. ACS Appl Mater Interfaces, 2022, 14(38): 42 771⁃42 790. |
[1] | WANG Jie, ZHANG Weimeng, HU Jing. Effect of poly(lactic acid)⁃co⁃hydroxyacetic acid copolymer coating on performance of poly(lactic acid) 3D printed scaffolds [J]. China Plastics, 2023, 37(1): 1-7. |
[2] | MENG Xin, WANG Xiaolong, GONG Weiguang, JIN Yi. Preparation of three⁃sources⁃in⁃one shell⁃core structural flame retardants and its application in poly(lactic acid) [J]. China Plastics, 2022, 36(9): 96-104. |
[3] | SONG Danyang, ZHENG Hongjuan, LI Yilong. Research progress in PLA⁃based oil⁃water separation materials [J]. China Plastics, 2022, 36(9): 187-192. |
[4] | QU Yuting, WANG Limei, QI Bin. Effect of poly(ethylene glycol) on properties of poly(lactic acid)/starch nanocrystal composites [J]. China Plastics, 2022, 36(8): 56-61. |
[5] | SHEN Xuemei, ZHU Xiaolong, HU Yanchao, SONG Renyuan, ZHANG Xianfeng, LI Xi. Fabrication and properties of poly(lactic acid))/ibuprofen microspheres through electrostatic spray method [J]. China Plastics, 2022, 36(7): 61-67. |
[6] | SHAO Linying, XI Yuewei, WENG Yunxuan. Research progress in degradation characteristics of poly(lactic acid) composites [J]. China Plastics, 2022, 36(6): 155-164. |
[7] | WANG Rongchen, ZHANG Heng, SUN Huanwei, DUAN Shuxia, QIN Zixuan, LI Han, ZHU Feichao, ZHANG Yifeng. Research progress in preparation and hydrophilic modification of polylactic acid nonwovens for medical and health applications [J]. China Plastics, 2022, 36(5): 158-166. |
[8] | SUN Tao, YANG Qing, HU Jian, WANG Yangyang, LIU Bo, YUN Xueyan, DONG Tungalag. Preparation and properties of poly(lactic acid⁃co⁃glycolic acid) film [J]. China Plastics, 2022, 36(2): 33-40. |
[9] | YANG Shangshan, SHANG Pengpeng, XU Jing, XIE Jiazhuo, ZHANG Kun, ZHANG Lili. Preparation and characterizations of biodegradable PBAT/PLA/biomass garbage bags [J]. China Plastics, 2022, 36(11): 127-132. |
[10] | LI Guili, YU Qiuran, HAO Mingliang, LI Haimei. Effect of surface treatment of ramie fiber on crystallization behavior and tensile properties of poly(lactic acid) [J]. China Plastics, 2022, 36(11): 51-58. |
[11] | WEI Zongchen, XI Yuewei, WENG Yunxuan. Research Progress in Poly(lactic acid)⁃based Composite Materials for Bone Tissue Engineering [J]. China Plastics, 2021, 35(9): 136-146. |
[12] | TANG Yujing, WANG Yaqiao, NI Jingyue, WANG Conglong, WANG Xiangdong. Effect of Stereoscopic Composite Crystals on Foaming Behavior of PLA [J]. China Plastics, 2021, 35(8): 117-124. |
[13] | LI Yuzhu, YAO Lihui, YE Shiqiang, LYU Guoyong, LIU Panpan, XU Longfei, QIU Dan. Research Progress on Degradation Performance of Biodegradable Materials in Water Environment [J]. China Plastics, 2021, 35(7): 103-114. |
[14] | DUAN Xuyuan, ZHENG Hongjuan. Research Progress in Modified Poly(lactic acid) Foaming Technology [J]. China Plastics, 2021, 35(7): 134-139. |
[15] | YANG Wenjie, HE Jiawen, ZHU Hanbin, WANG Sisi, LI Xiping. Mechanical Properties and Foaming Behaviors of Graphene⁃reinforced Poly(lactic acid) [J]. China Plastics, 2021, 35(6): 26-32. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||