Quality prediction modeling of piezoelectric ceramics sintering process based on ensemble learning

被引：0

作者：

Ma, Chao ^{[1
]}

Weng, Zhiyi ^{[1
]}

He, Fe ^{[1
]}

机构：

[1] College of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing

来源：

Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS | 2025年 / 31卷 / 01期

关键词：

Byesian optimization hyperband hyperparameter optimization algorithm; CatBoost algorithm; piezoelectric ceramics; quality prediction;

D O I：

10.13196/j.cims.2022.0512

中图分类号：

学科分类号：

摘要：

Sintering process is a key process affecting the quality of piezoelectric ceramics, which involves many fac-tors and has the characteristics of nonlinear and hysteresis, leading to the difficulty in ensuring the quality of the fin-ished products. To solve this prohlern, two indirect quality indexes, average grain size and sintering density were proposed by analyzing the change of ceramic microstructure during sintering process, and the relationship between the two indexes and the piezoelectric properties was analyzed. The quality prediction model was established to realize the quality prediction and control of sintering process. By ensemble learning CatBoost algorithm and Byesian Optimi-zation Hyperband (BOHB) hyperparameter optimization algorithm, the BOHB-CatBoost quality prediction model was established. Finally, the Performance of the model was evaluated by combining RMSE and R2, and compared with other prediction models. It was verified that the model had higher prediction accuracy and robustness, which could guide for the sintering process of piezoelectric ceramics significantly. © 2025 CIMS. All rights reserved.

引用

页码：147 / 157

页数：10

共 23 条

[1]

THONG H, CZHAO C L., ZHOU Z, Et al., Technology transfer of lead-free (K.Na) Nb03-based piezoelectric ceramics [J], Materials Today, 29, pp. 37-48, (2019)

[2]

YI Zhengming, SHAO Huijun, A predietion model for sintering quality based on eontrol of process parameters[J], Mining and Metallurgical Engineering, 38, 6, (2018)

[3]

LI Haoran, QIU Tong, Sintering production State predietion model based on causal analysis, CIESC Journal, 72, 3, pp. 1438-1446, (2021)

[4]

YUAN X F, GU YJ, WANC Y L, Et al., FeO content predietion for an industrial sintering process based on supervised deep belief network [J], IFACPapersOnLine, 53, 2, pp. 11883-11888, (2020)

[5]

Qmg LYU, LIU Yueming, ZHANG Zhenfeng, Et al., Predietion of FeO content in sinter based on production data of Chengde Steel Mill[j], Journal of Iron and Steel Re search, 30, 12, pp. 957-962, (2018)

[6]

WANG S H, LI H F, ZHANG Y J, Et al., A hybrid ensemble model based on ELM and improved AdaBoost. RT algorithm for predicting the iron ore sintering charactersLJJ, Computa-tional intelligence and neuroscience, 2019, 1, (2019)

[7]

DUTTA J, OccupancySense: Context-based indoor oc-cupancy detection &• predietion using CatBoost model[j], Applied Soft Computing, 119, (2022)

[8]

LI L, SJAMIESON K, DESALVO G, Et al., Hyperband:A no-vel bandit-based approach to hyperparameter optimization, Journal of Machine Learning Research, 18, 185, pp. 1-52, (2018)

[9]

LING Y S, HUANG T, YUE Q, Et al., Improving the estima-tion aecuraey of multi-nuclide source term estimation method for severe nuclear aeeidents using temporal convolutional net-work optimized by Bayesian optimization and hyperband[J], Journal of Environmental Radioactivity, 242, (2022)

[10]

HARIS M, HASAN M N, QIN S Y., Early and robust remai-ning useful life predietion of supercapacitors using BOHB optimized deep belief network, Applied Energy, 286, (2021)

← 1 2 3 →