GA-T-S云推理网络板形模式识别的DSP实现

摘要/Abstract

摘要： 针对现有神经网络大多是在软件的基础上进行仿真，训练时间长，不利于工程实际应用的问题，提出了GA-T-S云推理网络板形模式识别的DSP实现方法。首先以设计的板形模式识别GA-T-S云推理网络模型为基础，利用TI TMS320F2812完成T-S云推理网络的DSP 设计；然后利用MATLAB遗传算法工具箱离线优化T-S云推理网络参数，将优化后的网络参数存入DSP中，进而分别在MATLAB与DSP上运行该网络；最后将运行结果分别进行显示与对比分析。实验结果证实了基于GA-T-S云推理网络的板形模式识别模型有较高的板形识别精度，能够正确识别出板形缺陷的类型,同时验证了GA-T-S云推理网络在硬件TI TMS320F2812上实现的可行性与快速性，从而为神经网络推广应用到实际工程中提供了依据。

关键词: T-S云推理网络, 板形识别, 数字信号处理器, 硬件实现, 遗传算法

Abstract: The existing neural networks we are mostly software simulation and the training time was long, thus that would not conducive to engineering applications. In view of the above problems, flatness pattern recognition via GA-T-S cloud inference network implemented by DSP was presented herein. Firstly, the DSP's design of T-S cloud inference network was implemented by using TI TMS320F2812 on the basis of flatness pattern recognition via GA-T-S cloud inference network. Then T-S cloud inference network parameters were optimized through genetic algorithm toolbox of MATLAB in off-line manner and these parameters were transmitted to DSP later. The network was run on MATLAB and DSP separately. Finally, the two results of T-S cloud inference network, which was run on MATLAB and DSP respectively, were compared and analyzed. Experimental results confirm that GA-T-S cloud inference network have high accuracy in terms of flatness pattern recognition, it can identify the defect types of flatness correctly. At the same time, the experimental results verify that the T-S cloud inference network can run on the hardware TI TMS320F2812 in a fast speed and it provides a basis for neural networks applied to practical engineering.

Key words: T-S cloud inference network, flatness recognition, digital signal processor(DSP), hardware implementation, genetic algorithm (GA)

中图分类号:

TP273

李海滨, 高武杨, 来永进, 张秀玲, . GA-T-S云推理网络板形模式识别的DSP实现[J]. 中国机械工程.

Li Haibin, Gao Wuyang, Lai Yongjin, Zhang Xiuling, . Flatness Pattern Recognition via GA-T-S Cloud Inference Network Implemented by DSP[J]. China Mechanical Engineering.

参考文献

[1]Zhang Yun, Yang Quan, Wang Xiaochen. Control Strategies of Asymmetric Strip Shape in Six-high Cold Rolling Mill [J]. Journal of Iron and Steel Research, International, 2011, 18(9): 27-32.

[2]张秀玲，张少宇，赵文保，等.板形模式识别的多输出最小二乘支持向量回归机新方法[J].中国机械工程,2013, 24(2): 258-262.

Zhang Xiuling, Zhang Shaoyu, Zhao Wenbao,et al.A Novel Method for Flatness Pattern Recognition via MLSSVR[J]. China Mechanical Engineering, 2013, 24(2): 258-262.

[3]牛培峰，李鹏飞，李国强,等.基于万有引力优化的支持向量机模型在板形识别中的应用[J].钢铁,2012,47(12): 45-49.

Niu Peifeng, Li Pengfei, Li Guoqiang,et al. Application of GSA-SVR Model in Flatness Pattern Recognition[J].Iron and Steel, 2012, 47(12): 45-49.

[4]Rashedi E, Nezamabadi-Pour H, Saryazdi S. GSA: a Gravitational Search Algorithm[J]. Intelligent Information Management, 2012, 4(6):390-395.

[5]张秀玲，徐腾，赵亮,等.基于GA-PID神经网络的板形模式识别方法[J].沈阳大学学报(自然科学版), 2013, 25(3): 209-214.

Zhang Xiuling, Xu Teng, Zhao Liang,et al. Method of Flatness Pattern Recognition Based on GA-PID Neural Network[J].Journal of Shenyang University(Natural Science Edition),2013, 25(3): 209-214.

[6]Li Deyi, Liu Changyu, Liu Luying. Study on the Universality of the Normal Cloud Mode [J]. Engineering Sciences, 2004, 6(8): 18-24.

[7]黄景春,肖建,周聪.一种基于T-S云模型的非线性系统的控制[J].电机与控制学报，2009,13(1):149-156.

Huang Jingchun, Xiao Jian, Zhou Cong.T-S Cloud Model for Nonlinear Systems Control[J].Electric Machines and Control,2009,13(1):149-156.

[8]张秀玲，赵文保，张少宇,等. 基于改进T-S云推理网络的板形模式识别方法[J].中南大学学报(自然科学版), 2013, 44(2): 580-586.

Zhang Xiuling, Zhao Wenbao, Zhang Shaoyu,et al. Method of Flatness Pattern Recognition Based on Improved T-S Cloud Inference Network[J].Journal of Zhongnan University(Natural Science Edition), 2013, 44(2): 580-586.

[9]Zhang X, Zhao L, Zang J, et al. Hybrid MATLAB and LabVIEW with T-S Cloud Inference Neural Network to Realize a Flatness Intelligent Control System[J]. Steel Research International, 2014, 85(12): 1639-1652.

[10]李德毅,杜鹢.不确定性人工智能[M].北京:国防工业出版社,2005.

[11]雷英杰. MATLAB遗传算法工具箱及应用[M].西安:西安电子科技大学出版社,2004.

[12]单修迎,刘宏民,贾春玉.含有三次板形的新型板形模式识别方法[J].钢铁,2010,45(8):56-60.

Shan Xiuying, Liu Hongmin, Jia Chunyu. A Recognition Method of New Flatness Pattern Containing the Cubic Flatness[J]. Iron and Steel,2010,45(8):56-60.

[13]张秀玲,刘宏民.板形模式识别的GA-BP模型和改进的最小二乘法[J].钢铁,2003,38(10):29-34.

Zhang Xiuling, Liu Hongmin.GA-BP Model of Flatness Pattern Recognition and Improved Least-Squares Method[J]. Iron and Steel,2003,38(10):29-34.

[14]何海涛,李楠.基于SVM的改进RBF网络板形模式识别方法[J].自动化仪表,2007,28(5):1-8.

He Haitao, Li Nan.The Improved RBF Network Approach to Flatness Pattern Recognition Based on SVM[J]. Process Automation Instrumentation,2007,28(5):1-8.

[15]Jung J Y, Im Y T. Simulation of Fuzzy Shape Control for Cold-rolled Strip with Randomly Irregular Strip Shape[J]. Materials Processing Technology,1997,63 (1/3):248-253.

[16]Xu Lejiang. Flatness Control in Cold Strip Polling and Mill Type Selection[M].Beijing:Metallurgical Industry Press,2007. [17]Peng Yan, Liu Hongmin, Wang Dongcheng. Simulation of Type Selection for 6-high Cold Tandem Mill Based on Shape Control Ability[J].Journal of Central South University of Technology, 2007, 14(2): 278-284.

[18]陈丽安.基于DSP的BP神经网络实时实现[C]//中国自动化学会华东地区第十九届学术年会.青岛,2006:124-126.

[19]顾卫钢.手把手教你学DSP——基于TMS320X-281X[M].北京:北京航空航天大学出版社,2011.