多级网络连铸漏钢预报系统的研究
|
摘要
漏钢预报系统的开发,大大减少了漏钢事故,降低了经济损失,减少了人员伤亡,但并不能消除漏报、误报的发生。本文从防止粘结发生和提高预报系统性能两方面进行了研究。
分析了粘结性漏钢机理,得出弯月面破损是粘结发生的根本原因。对影响弯月面的诸多因素进行了分析,并提出了改善措施,防止粘结的产生。
在对现有各种漏钢预报系统深入研究的基础上,利用BP神经网络、逻辑判断和T-S模糊神经网络构建了一套多级网络连铸漏钢预报系统。
采用了BP网络来对单偶的温度波形进行识别。提出了利用极大熵函数的曲线拟合技术对网络的输入数据进行处理,简化了网络结构,降低了不良数据的干扰,提高了网络的性能。根据粘结坯壳破裂线扩展规律,结合热电偶的实际埋设情况,得出了横向测温优于纵向测温,采用横向网络代替以往的纵向网络,缩短了预报时间。热电偶的温度模式经常受到一些因素影响,造成系统的误报。为了降低误报率,提出了利用模糊神经网络对这些因素进行建模,系统的误报率大大降低,提高系统预报的准确性。
整个系统在WINDOWS平台上,由MATLAB语言开发,系统可视化界面实现了热电偶温度云图的动态显示,并能及时给出预报结果,自动或手动采取相应的措施,避免漏钢的发生,实现了良好的人机交互。
Breakout is reduced greatly, economy loss is depressed, and personnel casualty is reduced, due to the development of breakout prediction system, but leaking alarm rate and false alarm rate can not be eliminated. In the paper, two aspects of how to prevent the sticking happened and how to improve the accurate of the system are studied.
The mechanism of sticking breakout is analyzed in the paper, educing that the essential reason of sticking is the damage of the liquid steel meniscus. Many factors influencing liquid steel meniscus are set forth, amend measures are put forward to prevent the sticking.
On the basis of deeply research to many breakout prediction systems, a new multilevel network breakout prediction system is established, composed of BP neural network and T-S fuzzy neural network. BP neural network is adopted to identify the temperature wave pattern of single thermocouple. Curve fitting technical based on maximum-entropy function is put forward in disposal of input data of the network, and the network framework is reduced. Based on the extend rule of sticking solidified shell breaching, combining the actual instance, measure temperature in transverse is superior to what in longitudinal, transverse network is replaced by longitudinal network, the prediction time is shortened.
The temperature pattern of thermocouples is often influenced by the fluctuation of the steel liquid surface in mold, and false alarm is formed. For the sake of reducing false alarm rate, a mould is put forward, in which fuzzy neural network is utilized to consider the factors what arose the fluctuation of the steel liquid surface. The simulation result showed that the false alarm rate of the system is greatly reduced.
The whole system is developed by MATLAB language on the Windows platform, the visible interface is also developed, by which the dynamic display of the temperature wave of the thermocouple is realized, and the prediction result is showed in time, prompting the operator to take measures to avoid the breakout incident.
分析了粘结性漏钢机理,得出弯月面破损是粘结发生的根本原因。对影响弯月面的诸多因素进行了分析,并提出了改善措施,防止粘结的产生。
在对现有各种漏钢预报系统深入研究的基础上,利用BP神经网络、逻辑判断和T-S模糊神经网络构建了一套多级网络连铸漏钢预报系统。
采用了BP网络来对单偶的温度波形进行识别。提出了利用极大熵函数的曲线拟合技术对网络的输入数据进行处理,简化了网络结构,降低了不良数据的干扰,提高了网络的性能。根据粘结坯壳破裂线扩展规律,结合热电偶的实际埋设情况,得出了横向测温优于纵向测温,采用横向网络代替以往的纵向网络,缩短了预报时间。热电偶的温度模式经常受到一些因素影响,造成系统的误报。为了降低误报率,提出了利用模糊神经网络对这些因素进行建模,系统的误报率大大降低,提高系统预报的准确性。
整个系统在WINDOWS平台上,由MATLAB语言开发,系统可视化界面实现了热电偶温度云图的动态显示,并能及时给出预报结果,自动或手动采取相应的措施,避免漏钢的发生,实现了良好的人机交互。
Breakout is reduced greatly, economy loss is depressed, and personnel casualty is reduced, due to the development of breakout prediction system, but leaking alarm rate and false alarm rate can not be eliminated. In the paper, two aspects of how to prevent the sticking happened and how to improve the accurate of the system are studied.
The mechanism of sticking breakout is analyzed in the paper, educing that the essential reason of sticking is the damage of the liquid steel meniscus. Many factors influencing liquid steel meniscus are set forth, amend measures are put forward to prevent the sticking.
On the basis of deeply research to many breakout prediction systems, a new multilevel network breakout prediction system is established, composed of BP neural network and T-S fuzzy neural network. BP neural network is adopted to identify the temperature wave pattern of single thermocouple. Curve fitting technical based on maximum-entropy function is put forward in disposal of input data of the network, and the network framework is reduced. Based on the extend rule of sticking solidified shell breaching, combining the actual instance, measure temperature in transverse is superior to what in longitudinal, transverse network is replaced by longitudinal network, the prediction time is shortened.
The temperature pattern of thermocouples is often influenced by the fluctuation of the steel liquid surface in mold, and false alarm is formed. For the sake of reducing false alarm rate, a mould is put forward, in which fuzzy neural network is utilized to consider the factors what arose the fluctuation of the steel liquid surface. The simulation result showed that the false alarm rate of the system is greatly reduced.
The whole system is developed by MATLAB language on the Windows platform, the visible interface is also developed, by which the dynamic display of the temperature wave of the thermocouple is realized, and the prediction result is showed in time, prompting the operator to take measures to avoid the breakout incident.
引文
1蔡开科,程士富.连续铸钢原理与工艺.北京:冶金工业出版社,1994:1
2郭戈,乔俊飞.连铸过程控制理论与技术.北京:冶金工业出版社,2003:1-80
3黄平生.连铸新技术.冶金信息导刊,1998(4):16-19
4罗振才.炼钢机械.北京:冶金工业出版社,1982:146-154
5 Emling, W.H. and Daoson, S. .Mold Instrumentation for Breakout Detection and Control. Steelmaking Conference Procceddings, 1991: 121-129
6 Langer M, Arzberger M. New Approaches to Breakout Prediction. Steel Times International, 2002,26(10): 23-26
7 Baek Seung-Hyun, Kim Chul-Min, Kim Young-Bae, Kim Jaek-Kung. Breakout Prevention by Mold Heat Flux Control in Thin Slab Caster. Kang T'ieh/Iron and Steel (Peking), 2004, 39, SUPPL:347-350
8 Hao Peifeng, Xu Xinhe, Xue Dingyu, Pei Yunyi, Huang Qi. Analysis on Thermal Behavior of Steel Slab in Continuous Casting Breakout. Kang T'ieh/Iron and Steel (Peking), 1997,32(4):31-34
9 Emling W. H. . Breakout prevention . Iron & Steelmaker, 1994, 21(7):47-48
10 Itoyama Seiji, Washio Masaru, Nishikawa Hiroshi, Yamanaka Hiromitsu, Tanaka Syuji, Fujii Tetsuya. Reduction of Friction Force in Mold and Prevention of Sticking Type Breakout for High Speed Continuous Casting of Slabs. Tetsu-To-Hagane/Journal of the Iron and Steel Institute of Japan, 1988, 74(7): 78-85
11 Sowka Eberhard, Schulze-Diekhoff Paul, Harder Jurgen, Munscher Franz, Beirer Gerold. Breakout Avoidance System, BASYS, for Continuous Slab Casting. Iron and Steel Engineer, 1999,76(5): 30-34
12 Emling W. H., Mis S. D., Simko D. J.. Thermocouple-based System for Breakout Prevention and Practice Development. Iron & Steelmaker, 1988, 15(9):47-51
13 Anon. Prediction and Prevention System for Sticking Type Breakout in Continuous Casting. Transactions of the Iron and Steel Institute of Japan, 1987,28(2): 147
14职建军,文昊,裴云毅.宝钢板坯连铸漏钢预报系统(BBPS)的开发与应用.炼钢,2001,17(3):24
15 Kominami Hidetaka, Kamada Noriyuki, Tanaka Takehiko, Naitoh Syuji, Hamaguchi Chiyokatsu, Endoh Hideichi. Neural Network System for Breakout Prediction in Continuous Casting Process. Nippon Steel Technical Report, 1991,49: 34-38
16 Hatanaka Kazunari, Tanaka Takehiko, Kominami Hidetaka. Breakout Forecasting System Based on Multiple Neural Networks for Continuous Casting. Steel production Fujitsu Scientific and Technical Journal, 1993, 29( 3):265-270
17 Harcrs F. and Thomtaon S. G.. Application of Mould Monitoring on The Two Strand Scab Caster at Sidmar. Ironmaking and Steelmaking, 1994,21(5):390-398
18焦李成.神经网络的应用与实现.西安,西安电子科技大学出版社,1993:1-3
19李文兵.一种组合漏钢预报模型.钢铁,2004,V39:540
20范建东.基于神经网络和模糊理论的连铸漏钢预报研究与软件开发.[上海大学硕士学位论文].2006:33-34
21胡志刚,毕学工,陈崇峰,等.BP网络在漏钢模式识别中的应用研究.武汉科技大学学报(自然科学版) , 2000, 23(2):121-123
22史忠科.神经网络控制理论.西安:西北工业大学出版社, 1997: 39-42
23蒲筱琼,何航.专家系统在连铸生产中的应用.南方金属,2006,总150:25-27
24周汉香.连铸漏钢预报技术.炼钢,1999,15(4):57
25王雅贞,张岩,刘术国.新编连续铸钢工艺及设备.北京:冶金工业出版社, 1999:172-173
26郝培锋,徐心如,裴云毅,等.东北大学学报(自然科学版). 1997,8(4):40-403
27何环宇.连铸结晶器内弯月面行为的实验研究和数值模拟.武汉科技大学学报(自然科学版)2001, 24(1):1-4
28蔡开科.连续铸钢.北京:科学出版社,1990: 221-229
29 Hong sha. Metallurgical and Meterials Transactions. The Minerals:Metals and Materials Society, 1996:278-305
30胡志刚.连铸结晶器内粘结漏钢形成机理.炼钢,1998, (6):31-36
31 K.C Mills and R.F Brooks. Measurements of thermophysical properties in hightemperature melts. Materials Science and Engineering. 1994,A, Volume 178, Issues 1-2, 30:77-81
32 Bikerman J J. Physical Chemistry of Surface Phenomena at High Temperature. Materials Science and Engineering, 1972(10):300
33 Mills K. C., Billany T. J. H., Normanton A. S.,Walker B.,Grieveson P.. Causes of Sticker Breakout during ContinuousCasting. Ironmaking and Steelmaking, 1991, 18( 4):253-265
34王常珍.冶金物理化学研究方法.北京:冶金工业出版社,2001.328-330
35曹运涛,孙风晓.济钢大板坯连铸机粘结漏钢原理分析.山东冶金,2005,27(4):9
36马学忠.板坯连铸机粘结漏钢与保护渣的关系.炼钢,1996, (2):7-10
37 AS Normanton等.粘结性漏钢的研究.第一届欧洲连铸会议译文集.弗罗伦萨:中国金属学会连续铸钢学会, 1991:30-253
38 KC Mills.欧洲煤钢联盟提供资金的结晶器保护渣研究的总述.第一届欧洲连铸会议译文集.弗罗伦萨:中国金属学会连续铸钢学会,1991.30-39
39许庆太,张楠,王英林.连铸板坯表面纵向裂纹缺陷的检验与分析.鞍钢技术,2002,6:17-20
40陈雷.连续铸钢.北京:冶金工业出版社,1996:64-65
41杨海滨,魏励,张洪波,等.大板坯连铸粘结漏钢浅析.中国冶金,16(11) ,2006:44-47
42高君箐,阎朝红.板坯连铸粘结性漏钢的防止. 1999,V34增刊, 473-474
43张青贵.人工神经网络导论.北京:中国水利水电出版社,2004:11
44丛爽.面向MATLAB工具箱的神经网络理论与应用.合肥:中国科学技术大学出版社,1998:45
45谢庆生,尹健,罗延科.机械工程中的神经网络方法.北京:机械工业出版社,2003:39-50
46王玉民,赵登报,曹运涛,等.结晶器漏钢预报专家系统准确率的措施.炼钢,2006,22(2):9
47刘亚禄,刘昕,宋景英.基于极大熵法的曲线拟合及其应用.统计与决策,2007, 3: 133-134
48周继成.人工神经网络——第六代计算机的实现.北京:科学普及出版社,1993:56
49刘增良,刘有才.模糊逻辑与神经网络——理论研究与探讨.北京:北京航天航空大学出版社,1996:113-118
50张立明.人工神经网络的模型及其应用.上海:复旦大学出版社,1993:43-47
51赵振宇,徐用懋.模糊理论和神经网络的基础与应用.北京:清华大学出版社.1996:135-136
52 Waibel A, Hanazawa T, Hinton G. etal.Phoneme Recognition Using Time-delay Neural Networks. IEEE Transaction on Acoustics, Speech and Signal Processing.1989,37(3):328-339
53黄德双.神经网络模式识别理论.北京:电子工业出版社,1996:46-50
54 Patton M,Klein A,Wolf M M. Advanced Breakout Prevention System Custom-made to Product Steelmaking Conference Proceedings,1991:553
55郝培锋,徐心如,裴云毅,等.连铸漏钢预报系统数据采样与热电偶埋设方式.东北大学学报,1997,18(4):401
56吴国庆.板坯连铸结晶器漏钢预报系统浅析.第五届冶金工程科学论坛,冶金研究2006,134-136
57秦旭,陈智勇,周豪鸣,等.漏钢预报系统的原理分析.工艺技术,2005,3:22
58常宏伟,齐兵,仉勇.板坯漏钢预报系统在生产中的应用.鞍钢技术,2007,1:36-38
59王唯一.基于神经模糊技术的漏钢诊断预报模型的研究.自动化仪表,2001,22(10):12-13
60王士同.神经模糊系统凝固及其应用.北京:北京航空航天大学出版社,1998:1-186
61 Sun Zengqi, Deng Zhidong. A Fuzzy Neural Network and Its Application to Controls. Artificial Intelligence in Engineering,1996,(10):311-315
62 Wu Shiqian, Joo Meng, Gao Yang. A Fast Approach for Automatic Federation of Fuzzy Rules by Generalized Dynamic Fuzzy Neural Network. IEEE Transactions on Fuzzy Systems, 2001,9(4):578-594
63 Takagi, T, Sugeno, M.. Fuzzy Identification of Systems and Its Applications to Modeling and Control.IEEE Trans SMC,1985,(15):116-132
64李少远. Sugeno模糊模型的辨识.南开大学学报,1999,32(1):58-63
65 Fischer. O.Nelles.R. Isermann, Predictive Control Based on Local Linear FuzzyModels.Int. J. System Science, 1998,29(7):679-689
66程启明.T-S模型的模糊神经网络控制器及应用研究.电路与系统学报,1999,4(1):74-78
67 Shang-Ming zhou. A New Approach to Fuzzy Modeling based on Recurrent Neural Network for Fuzzy Dynamic Systems, Proceedings of 14th IFAC, Beijing,1999,K-3e-05-1:39-44
68 Li-Hong Xu, You-ling Yu, Qi-Di Wu. General Fuzzy Neural Networks Basic Structure. Algorithms and its applications, Proeedings of 14th IFAC, Beijing,1999,K-3e-06-3:87-92
2郭戈,乔俊飞.连铸过程控制理论与技术.北京:冶金工业出版社,2003:1-80
3黄平生.连铸新技术.冶金信息导刊,1998(4):16-19
4罗振才.炼钢机械.北京:冶金工业出版社,1982:146-154
5 Emling, W.H. and Daoson, S. .Mold Instrumentation for Breakout Detection and Control. Steelmaking Conference Procceddings, 1991: 121-129
6 Langer M, Arzberger M. New Approaches to Breakout Prediction. Steel Times International, 2002,26(10): 23-26
7 Baek Seung-Hyun, Kim Chul-Min, Kim Young-Bae, Kim Jaek-Kung. Breakout Prevention by Mold Heat Flux Control in Thin Slab Caster. Kang T'ieh/Iron and Steel (Peking), 2004, 39, SUPPL:347-350
8 Hao Peifeng, Xu Xinhe, Xue Dingyu, Pei Yunyi, Huang Qi. Analysis on Thermal Behavior of Steel Slab in Continuous Casting Breakout. Kang T'ieh/Iron and Steel (Peking), 1997,32(4):31-34
9 Emling W. H. . Breakout prevention . Iron & Steelmaker, 1994, 21(7):47-48
10 Itoyama Seiji, Washio Masaru, Nishikawa Hiroshi, Yamanaka Hiromitsu, Tanaka Syuji, Fujii Tetsuya. Reduction of Friction Force in Mold and Prevention of Sticking Type Breakout for High Speed Continuous Casting of Slabs. Tetsu-To-Hagane/Journal of the Iron and Steel Institute of Japan, 1988, 74(7): 78-85
11 Sowka Eberhard, Schulze-Diekhoff Paul, Harder Jurgen, Munscher Franz, Beirer Gerold. Breakout Avoidance System, BASYS, for Continuous Slab Casting. Iron and Steel Engineer, 1999,76(5): 30-34
12 Emling W. H., Mis S. D., Simko D. J.. Thermocouple-based System for Breakout Prevention and Practice Development. Iron & Steelmaker, 1988, 15(9):47-51
13 Anon. Prediction and Prevention System for Sticking Type Breakout in Continuous Casting. Transactions of the Iron and Steel Institute of Japan, 1987,28(2): 147
14职建军,文昊,裴云毅.宝钢板坯连铸漏钢预报系统(BBPS)的开发与应用.炼钢,2001,17(3):24
15 Kominami Hidetaka, Kamada Noriyuki, Tanaka Takehiko, Naitoh Syuji, Hamaguchi Chiyokatsu, Endoh Hideichi. Neural Network System for Breakout Prediction in Continuous Casting Process. Nippon Steel Technical Report, 1991,49: 34-38
16 Hatanaka Kazunari, Tanaka Takehiko, Kominami Hidetaka. Breakout Forecasting System Based on Multiple Neural Networks for Continuous Casting. Steel production Fujitsu Scientific and Technical Journal, 1993, 29( 3):265-270
17 Harcrs F. and Thomtaon S. G.. Application of Mould Monitoring on The Two Strand Scab Caster at Sidmar. Ironmaking and Steelmaking, 1994,21(5):390-398
18焦李成.神经网络的应用与实现.西安,西安电子科技大学出版社,1993:1-3
19李文兵.一种组合漏钢预报模型.钢铁,2004,V39:540
20范建东.基于神经网络和模糊理论的连铸漏钢预报研究与软件开发.[上海大学硕士学位论文].2006:33-34
21胡志刚,毕学工,陈崇峰,等.BP网络在漏钢模式识别中的应用研究.武汉科技大学学报(自然科学版) , 2000, 23(2):121-123
22史忠科.神经网络控制理论.西安:西北工业大学出版社, 1997: 39-42
23蒲筱琼,何航.专家系统在连铸生产中的应用.南方金属,2006,总150:25-27
24周汉香.连铸漏钢预报技术.炼钢,1999,15(4):57
25王雅贞,张岩,刘术国.新编连续铸钢工艺及设备.北京:冶金工业出版社, 1999:172-173
26郝培锋,徐心如,裴云毅,等.东北大学学报(自然科学版). 1997,8(4):40-403
27何环宇.连铸结晶器内弯月面行为的实验研究和数值模拟.武汉科技大学学报(自然科学版)2001, 24(1):1-4
28蔡开科.连续铸钢.北京:科学出版社,1990: 221-229
29 Hong sha. Metallurgical and Meterials Transactions. The Minerals:Metals and Materials Society, 1996:278-305
30胡志刚.连铸结晶器内粘结漏钢形成机理.炼钢,1998, (6):31-36
31 K.C Mills and R.F Brooks. Measurements of thermophysical properties in hightemperature melts. Materials Science and Engineering. 1994,A, Volume 178, Issues 1-2, 30:77-81
32 Bikerman J J. Physical Chemistry of Surface Phenomena at High Temperature. Materials Science and Engineering, 1972(10):300
33 Mills K. C., Billany T. J. H., Normanton A. S.,Walker B.,Grieveson P.. Causes of Sticker Breakout during ContinuousCasting. Ironmaking and Steelmaking, 1991, 18( 4):253-265
34王常珍.冶金物理化学研究方法.北京:冶金工业出版社,2001.328-330
35曹运涛,孙风晓.济钢大板坯连铸机粘结漏钢原理分析.山东冶金,2005,27(4):9
36马学忠.板坯连铸机粘结漏钢与保护渣的关系.炼钢,1996, (2):7-10
37 AS Normanton等.粘结性漏钢的研究.第一届欧洲连铸会议译文集.弗罗伦萨:中国金属学会连续铸钢学会, 1991:30-253
38 KC Mills.欧洲煤钢联盟提供资金的结晶器保护渣研究的总述.第一届欧洲连铸会议译文集.弗罗伦萨:中国金属学会连续铸钢学会,1991.30-39
39许庆太,张楠,王英林.连铸板坯表面纵向裂纹缺陷的检验与分析.鞍钢技术,2002,6:17-20
40陈雷.连续铸钢.北京:冶金工业出版社,1996:64-65
41杨海滨,魏励,张洪波,等.大板坯连铸粘结漏钢浅析.中国冶金,16(11) ,2006:44-47
42高君箐,阎朝红.板坯连铸粘结性漏钢的防止. 1999,V34增刊, 473-474
43张青贵.人工神经网络导论.北京:中国水利水电出版社,2004:11
44丛爽.面向MATLAB工具箱的神经网络理论与应用.合肥:中国科学技术大学出版社,1998:45
45谢庆生,尹健,罗延科.机械工程中的神经网络方法.北京:机械工业出版社,2003:39-50
46王玉民,赵登报,曹运涛,等.结晶器漏钢预报专家系统准确率的措施.炼钢,2006,22(2):9
47刘亚禄,刘昕,宋景英.基于极大熵法的曲线拟合及其应用.统计与决策,2007, 3: 133-134
48周继成.人工神经网络——第六代计算机的实现.北京:科学普及出版社,1993:56
49刘增良,刘有才.模糊逻辑与神经网络——理论研究与探讨.北京:北京航天航空大学出版社,1996:113-118
50张立明.人工神经网络的模型及其应用.上海:复旦大学出版社,1993:43-47
51赵振宇,徐用懋.模糊理论和神经网络的基础与应用.北京:清华大学出版社.1996:135-136
52 Waibel A, Hanazawa T, Hinton G. etal.Phoneme Recognition Using Time-delay Neural Networks. IEEE Transaction on Acoustics, Speech and Signal Processing.1989,37(3):328-339
53黄德双.神经网络模式识别理论.北京:电子工业出版社,1996:46-50
54 Patton M,Klein A,Wolf M M. Advanced Breakout Prevention System Custom-made to Product Steelmaking Conference Proceedings,1991:553
55郝培锋,徐心如,裴云毅,等.连铸漏钢预报系统数据采样与热电偶埋设方式.东北大学学报,1997,18(4):401
56吴国庆.板坯连铸结晶器漏钢预报系统浅析.第五届冶金工程科学论坛,冶金研究2006,134-136
57秦旭,陈智勇,周豪鸣,等.漏钢预报系统的原理分析.工艺技术,2005,3:22
58常宏伟,齐兵,仉勇.板坯漏钢预报系统在生产中的应用.鞍钢技术,2007,1:36-38
59王唯一.基于神经模糊技术的漏钢诊断预报模型的研究.自动化仪表,2001,22(10):12-13
60王士同.神经模糊系统凝固及其应用.北京:北京航空航天大学出版社,1998:1-186
61 Sun Zengqi, Deng Zhidong. A Fuzzy Neural Network and Its Application to Controls. Artificial Intelligence in Engineering,1996,(10):311-315
62 Wu Shiqian, Joo Meng, Gao Yang. A Fast Approach for Automatic Federation of Fuzzy Rules by Generalized Dynamic Fuzzy Neural Network. IEEE Transactions on Fuzzy Systems, 2001,9(4):578-594
63 Takagi, T, Sugeno, M.. Fuzzy Identification of Systems and Its Applications to Modeling and Control.IEEE Trans SMC,1985,(15):116-132
64李少远. Sugeno模糊模型的辨识.南开大学学报,1999,32(1):58-63
65 Fischer. O.Nelles.R. Isermann, Predictive Control Based on Local Linear FuzzyModels.Int. J. System Science, 1998,29(7):679-689
66程启明.T-S模型的模糊神经网络控制器及应用研究.电路与系统学报,1999,4(1):74-78
67 Shang-Ming zhou. A New Approach to Fuzzy Modeling based on Recurrent Neural Network for Fuzzy Dynamic Systems, Proceedings of 14th IFAC, Beijing,1999,K-3e-05-1:39-44
68 Li-Hong Xu, You-ling Yu, Qi-Di Wu. General Fuzzy Neural Networks Basic Structure. Algorithms and its applications, Proeedings of 14th IFAC, Beijing,1999,K-3e-06-3:87-92