改进型BP 神经网络对球面磨削最高温度的模拟与预测

上海交通大学学报（自然版） ›› 2011, Vol. 45 ›› Issue (06): 901-906.

改进型BP 神经网络对球面磨削最高温度的模拟与预测

蒋天一, 胡德金, 许开州, 许黎明

(上海交通大学机械与动力工程学院 , 上海 200030)

收稿日期:2010-08-03 出版日期:2011-06-29 发布日期:2011-06-29
基金资助:
国家自然科学基金资助项目（51075273），机械系统与振动国家重点实验室资助项目（MSVMS201104），华中科技大学数字制造装备与技术国家重点实验室开放课题（2008-DMET-KF-001）

Simulation and Prediction of the Maximum Temperature in sphere Grinding with Improved BP Neural Network Model

JIANG Tian-Yi, HU De-Jin, XU Kai-Zhou, XU Li-Ming

(School of Mechanical Engineering, Shanghai Jiaotong University, Shanghai 200030, China)

Received:2010-08-03 Online:2011-06-29 Published:2011-06-29

摘要/Abstract

摘要： 基于人工神经网络良好的非线性逼近特性，利用正交试验结果作为神经网络的训练样本，建立基于批训练的改进型误差反向传播(BP)神经网络，并通过Levenberg-Marquardt算法使网络误差最小化，配合Bayesian正则化使网络的误差平方和、网络权重以及阈值平方和实现最优化组合.结果表明，改进型BP神经网络具有较快的收敛速度、较好的泛化性和较强的稳定性，能够准确模拟和预测球面磨削中的最高温度.

关键词: 神经网络, 球面磨削, 正交试验, 磨削温度, Levenberg-Marquardt算法

Abstract: Based on the outstanding characteristic of nonlinear convergence of neural network, an improved BP neural network was established. Orthogonal experiments were carried out to provide batch training samples for the network. And the LevenbergMarquardt algorithm was used to minimize the errors of the network. In addition, the Bayesian regularization was employed to optimize the combination of squared errors, weights and the sum of squared threshold. The experimental results show that the improved BP neural network has fast rate of convergence, strong generalization capability and good stability, which can simulate and predict the maximum temperature in sphere grinding with high accuracy.

Key words: neural network, sphere grinding, rthogonal experiment, grinding temperature, Levenberg-Marquardt algorithm

中图分类号:

TG580

蒋天一, 胡德金, 许开州, 许黎明. 改进型BP 神经网络对球面磨削最高温度的模拟与预测[J]. 上海交通大学学报（自然版）, 2011, 45(06): 901-906.

JIANG Tian-Yi, HU De-Jin, XU Kai-Zhou, XU Li-Ming. Simulation and Prediction of the Maximum Temperature in sphere Grinding with Improved BP Neural Network Model[J]. Journal of Shanghai Jiaotong University, 2011, 45(06): 901-906.

参考文献

［1］Malkin S, Guo C. Thermal analysis of grinding［J］. Manufacturing Technology, 2007, 56(2): 760782.

［2］毛聪, 周志雄, 周德旺,等. 平面磨削温度场三维数值仿真的研究［J］. 中国机械工程, 2009, 20(5): 589595.

MAO Cong, ZHOU Zhixiong, ZHOU Dewang, et al. Research on three dimensional finite element simulation of the temperature field in surface grinding［J］. China Mechanical Engineering, 2009, 20(5): 589595.

［3］Biermann D, Schneider M. Modeling and simulation of workpiece temperature in grinding by finite element analysis［J］. Machining Science and Technology, 1997, 1(2): 173183.

［4］MAO Cong, ZHOU Zhixiong, REN Yinghui, et al. Analysis and FEM simulation of temperature field in wet surface grinding［J］. Materials and Manufacturing Processes, 2010, 25(6): 399406.

［5］Lefebvre A, Vieville P, Lipinski P, et al. Numerical analysis of grinding temperature measurement by the foil/workpiece thermocouple method［J］. International Journal of Machine Tools and Manufacture, 2006, 46(14): 17161726.

［6］Anderson D, Warkentin A, Bauer R. Experimental validation of numerical thermal models for dry grinding［J］. Journal of Materials Processing Technology, 2008, 202(13): 269278.

［7］邓朝晖, 程文涛. 基于神经网络的成形磨削表面粗糙度的研究［J］. 机械制造, 2006, 44(7): 3940.

DENG Zhaohui, CHENG Wentao. Study on the surface roughness in grinding based on neural networks［J］. Machinery, 2006, 44(7): 3940.

［8］Costanza G, Tata M E, Ucciardello N. Application of neural network to the materials characterization［J］. International Journal of Computational Materials Science and Surface Engineering, 2010, 3(23): 96113.

［9］FAN Yongjian, MAI Jianying, SHEN YanGuang. Study of safety assessment model of coal mine based on BP neural network［C］//2009 2nd International Conference on Intelligent Computing Technology and Automation. Changsha: IEEE, 2009: 103106.

［10］DENG Ying, YIN Zhimin, HE Zhenbo, et al. Homogenization of AlZnMgSc alloy ingot and property predicting based on BP neural network［J］. Journal of Aeronautical Materials. 2010, 30(3): 59.

［11］陈小平, 胡树根. 神经网络与正交试验法结合优化注射工艺参数［J］. 模具工业, 2007, 33(7): 15.

CHENG Xiaoping, HU Shugen. Application of neural network and orthogonal experiment method in optimization of injection process parameter［J］. Die & Mould Industry, 2007, 33(7): 15.

［12］XU Kaizhou, HU Dejin, WEI Chenjun. Vogl fast BP network and orthogonal experiment method in optimization of sphere grinding process parameters［J］. Journal of Shanghai Jiaotong University, 2009, 43(12): 19561961.

[1]	李诗杰, 刘泰序, 刘佳仑, 董智霖, 徐诚祺. 基于GRU-MPC的双全回转推进拖轮轨迹跟踪控制[J]. 上海交通大学学报, 2026, 60(3): 418-426.
[2]	梁佳铭, 余音, 胡祎乐. 基于时空神经网络的金属疲劳裂纹扩展预测[J]. 上海交通大学学报, 2026, 60(3): 511-521.
[3]	. DSNet：用于语音情感识别的带有中性校准的解耦孪生网络[J]. J Shanghai Jiaotong Univ Sci, 2026, 31(2): 248-257.
[4]	. 类间隙滞后非线性系统复合双通道干扰估计自适应控制器设计[J]. J Shanghai Jiaotong Univ Sci, 2026, 31(1): 106-116.
[5]	夏筱彦, 张宇, 胡锡坤, 钟平. 基于扩散模型的无人机遥感目标检测物理对抗攻击方法研究[J]. 空天防御, 2026, 9(1): 52-62.
[6]	李湘, 陈思远, 张俊, 柯德平, 高杰迈, 杨欢欢. 基于物理信息嵌入的非固定长度电力系统暂态稳定快速评估[J]. 上海交通大学学报, 2025, 59(7): 962-970.
[7]	王晓倩, 周羽生, 毛源军, 李彬, 周文晴, 苏盛. 基于神经网络分位数的分布式光伏发电功率异常识别方法[J]. 上海交通大学学报, 2025, 59(6): 836-844.
[8]	. 基于深度学习序列方法的多人姿态估计用来检测人体与关键点位置[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(6): 1103-1113.
[9]	曾金灿, 何耿生, 李姚旺, 杜尔顺, 张宁, 朱浩骏. 基于卷积神经网络与轻量级梯度提升树组合模型的电力行业短期以电折碳方法[J]. 上海交通大学学报, 2025, 59(6): 746-757.
[10]	黄逸翔, 窦迅, 李林溪, 杨函煜, 于建成, 霍现旭. 基于全局灵敏度分析的综合能源设备响应价值量化方法[J]. 上海交通大学学报, 2025, 59(5): 569-579.
[11]	潘美琪, 贺兴. 基于零样本学习的风力机故障诊断方法[J]. 上海交通大学学报, 2025, 59(5): 561-568.
[12]	. 具有自动测量磁矩功能的磁跟踪系统[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(4): 646-657.
[13]	周添龙, 姚方競, 饶卫雄. 部分已知状态空间模型下的目标状态估计算法[J]. 空天防御, 2025, 8(3): 111-122.
[14]	. 基于基尼不纯度结构优化物理引导神经网络的薄膜型声学超材料传声损失预测[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(3): 613-624.
[15]	. 基于毫米波雷达的智能心率提取方法[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(3): 493-498.