基于烟花算法与长短时记忆网络的模温预测方法研究

doi:10.3969/j.issn.1000-1158.2020.06.02

摘要
图/表
参考文献(17)
相关文章 (15)

全文: PDF (994 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对传统神经网络模型预测模具温度准确度低,网络超参数选取困难等问题,提出一种基于烟花算法优化长短时记忆网络的模温预测模型,为铸造成型模温自动控制提供基础。首先根据铸造过程生产工艺选取影响铸造系统的主要变量,利用灰关联分析得出各变量灰色关联度并去除关联度小的变量,建立模具温度影响因子变量的数据集;其次采用烟花算法对长短时记忆网络进行优化,建立模具温度预测模型;最后与BP神经网络和长短时记忆网络预测效果进行对比。实验结果表明基于烟花算法优化的长短时记忆网络的模温预测方法绝对误差小于2.4℃,平均绝对百分比误差小于0.12。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	张典范
	栗子豪
	程淑红

关键词 ：计量学, 模具温度, 灰关联分析, 烟花算法, 长短时记忆网络

Abstract：Aiming at the problems of low precision of mold temperature and difficulty in selecting network parameters, based on fireworks algorithm to optimize the long and short time memory network, a mold temperature prediction model is proposed, which provides a basis for automatic control of casting mold temperature. Firstly, according to the production casting process, the main variables affecting the casting system are selected. The grey relational analysis is used to obtain the grey correlation degree of each variable and remove the small correlation degree, and the data set of the mold temperature influence factor variable is established. Secondly, the fireworks algorithm is used to optimize the long and short time memory network to establish a mold temperature prediction model. Finally, the prediction results are compared with BP neural network and long-term short-term networks. Experiments show that the absolute error of the model temperature prediction method based on the long-term and short-term memory network optimized by the firework algorithm is less than 2.4℃ and the mean absolute percentage error is less than 0.12.

Key words： metrology mold temperature gray correlation analysis fireworks algorithm long and short time memory network

收稿日期: 2019-12-10 发布日期: 2020-06-08

PACS:

TB942

基金资助:国家自然科学基金(61601400);"十三五"装备预研共用技术项目(41412040302)

作者简介: 张典范(1978-),男,吉林省吉林市人,燕山大学副研究员,博士,研究方向为并联机器人、智能控制、视觉检测等。Email: zdf@ysu.edu.cn

引用本文:

张典范,栗子豪,程淑红. 基于烟花算法与长短时记忆网络的模温预测方法研究[J]. 计量学报, 2020, 41(6): 640-645.
ZHANG Dian-fan,LI Zi-hao,CHENG Shu-hong. Research on Model Temperature Prediction Method Based on Fireworks Algorithm and Long and Short Time Memory Network. Acta Metrologica Sinica, 2020, 41(6): 640-645.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2020.06.02 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2020/V41/I6/640

［1］Javahery M, Abbasi M. Simulation of casting process: case study on the gating and feeding design for outlet diaphragms of iron ore ball mill［J］. Heat and Mass Transfer, 2019, 55(7): 1959-1967.
［2］Kong Y, Chen D, Liu Q, et al. Research on the On-Line Simulation of a Three-Dimensional Temperature Field Model of Slab Continuous Casting［J］. Steel Research International, 2018, 89(8): 1800091.
［3］Fernandes C, Pontes A J, Viana J C, et al. Modeling and Optimization of the Injection-Molding Process: A Review［J］. Advances in Polymer Technology, 2018, 37(2): 429-449.
［4］李宁, 朱培浩, 胡亚辉, 等. 铝合金轮毂低压铸造的数值分析研究［J］. 铸造技术, 2017, 38(6): 1482-1486.
Li N, Zhu P H, Hu Y H, et al. Numerical analysis of low pressure casting of aluminum alloy wheels ［J］. Casting Technology, 2017, 38(6): 1482-1486.
［5］范伟, 林瑜阳, 李钟慎. 基于 BP 神经网络的压电陶瓷蠕变预测［J］. 计量学报, 2017, 38(4): 429-434.
Fan W, Lin Y Y, Li Z S. Creep prediction of piezoelectric ceramics based on BP neural network ［J］. Acta Metrologica Sinica, 2017, 38(4): 429-434.
［6］张淑清, 任爽, 陈荣飞, 等. 基于大数据简约及PCA改进RBF网络的短期电力负荷预测［J］. 计量学报, 2018, 39(3): 392-396.
Zhang S Q, Ren S, Chen R F, et al. Short-term power load forecasting of RBF network based on big data simplicity and PCA improvement ［J］. Acta Metrologica Sinica, 2018, 39(3): 392-396.
［7］牛培峰, 史春见, 刘楠, 等. 基于GSA-PELM的锅炉NOx预测模型［J］. 计量学报, 2018, 39(5): 741-746.
Niu P F, Shi C J, Liu N, et al. Boiler NOx prediction model based on GSA-PELM ［J］. Acta Metrologica Sinica, 2018, 39(5): 741-746.
［8］孙宪萍, 杨兵, 刘强强, 等. 基于BP神经网络与遗传算法的温挤压模具优化设计［J］. 润滑与密封, 2017, 42(4): 84-88.
Sun X P, Yang B, Liu Q Q, et al. Optimization design of warm extrusion die based on BP neural network and genetic algorithm ［J］. Lubrication Engineering, 2017, 42(4): 84-88.
［9］Greff K, Srivastava R K, Koutník J, et al. LSTM: A search space odyssey［J］. IEEE transactions on neural networks and learning systems, 2016, 28(10): 2222-2232.
［10］Liang X, Shen X, Feng J, et al. Semantic object parsing with graph lstm［C］//European Conference on Computer Vision. Amsterdam, Holland, 2016: 125-143.
［11］Kim J Y, El-Khamy M, Lee J W. Residual LSTM: Design of a deep recurrent architecture for distant speech recognition［R］. Ithaca: Cornell University, arXiv e-prints, arXiv:1701.03360, 2017.
［12］Han S, Kang J, Mao H, et al. Ese: Efficient speech recognition engine with sparse lstm on fpga［C］//Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays. California USA, 2017: 75-84.
［13］任智慧, 徐浩煜, 封松林, 等. 基于 LSTM 网络的序列标注中文分词法［J］. 计算机应用研究, 2017, 34(5): 1321-1324.
Ren Z Z, Xu H Y, Feng S L, et al. Chinese word segmentation based on sequence labeling based on LSTM network ［J］. Journal of Computer Applications, 2017, 34(5): 1321-1324.
［14］刘思峰, 蔡华, 杨英杰, 等. 灰色关联分析模型研究进展［J］. 系统工程理论与实践, 2013, 33(8): 2041-2046.
Liu S F, Cai H, Yang Y J, et al. Research progress of grey relational analysis model ［J］. Systems Engineering Theory & Practice, 2013, 33(8): 2041-2046.
［15］刘彬, 赵朋程, 高伟, 等. 基于粒子群算法与连续型深度信念网络的水泥熟料游离氧化钙预测［J］. 计量学报, 2018, 39(3): 420-424.
Liu B, Zhao P C, Gao W, et al. Prediction of free calcium oxide in cement clinker based on particle swarm optimization and continuous deep belief network ［J］. Acta Metrologica Sinica, 2018, 39(3): 420-424.
［16］Tan Y, Zhu Y. Fireworks algorithm for optimization［C］//International conference in swarm intelligence. Berlin, Heidelberg, 2010: 355-364.
［17］Tuba E, Tuba M, Dolicanin E. Adjusted fireworks algorithm applied to retinal image registration［J］. Studies in Informatics and Control, 2017, 26(1): 33-42.