多传感器信息融合技术在智能空气净化装置中的应用
|
摘要
随着传感器、计算机和通信技术的发展，各种面向复杂应用背景的多传感器系统的研究越来越受人们的关注；多传感器系统中，信息表现形式的多样性、信息数量的巨大性、信息关系的复杂性以及要求信息处理的及时性，都大大超出人脑的信息综合处理能力，多传感器信息融合理论应运而生。
本文主要对单片机和多传感器信息融合技术在智能空气净化装置的应用进行了研究。文章首先介绍了多传感器信息融合算法的思想，证明了将多传感器信息融合技术应用于智能空气净化装置的可行性。其次，结合智能空气净化装置的特殊要求，提出了一种将模糊理论和改进型D-S证据理论算法相结合的改进型模糊证据理论方法，并应用于智能空气净化装置。最后，针对复杂的和具有时变特性的室内空气状况，设计了一个集智能化、信息融合和预测控制理论于一体的智能空气净化装置。
As the technologies of sensor, computer and telecommunication have developed, studies on applications of complex sensor systems are being carrying out by more and more researchers. In sensor systems, the variety of information forms, the great number of information, the complex of information relations, the time limits of information process are much more difficult than human being's brain can deal with; therefore, multi-sensor information fusion theories are brought up.
The paper studies the application of single chip computer and multi-sensor information fusion technology for design of an intelligent air fresher device. At first, the paper states the multi-sensor information fusion algorithm, and proves that the algorithm has good feasibility. After that, according to the specifications of the air fresher, an improved fuzzy evidence theory, which combined fuzzy theory and D-S evidence theory, are used for design of the air fresher. At last, an intelligent air fresher with the function of information fusion and air varying forecast control is designed.
本文主要对单片机和多传感器信息融合技术在智能空气净化装置的应用进行了研究。文章首先介绍了多传感器信息融合算法的思想，证明了将多传感器信息融合技术应用于智能空气净化装置的可行性。其次，结合智能空气净化装置的特殊要求，提出了一种将模糊理论和改进型D-S证据理论算法相结合的改进型模糊证据理论方法，并应用于智能空气净化装置。最后，针对复杂的和具有时变特性的室内空气状况，设计了一个集智能化、信息融合和预测控制理论于一体的智能空气净化装置。
As the technologies of sensor, computer and telecommunication have developed, studies on applications of complex sensor systems are being carrying out by more and more researchers. In sensor systems, the variety of information forms, the great number of information, the complex of information relations, the time limits of information process are much more difficult than human being's brain can deal with; therefore, multi-sensor information fusion theories are brought up.
The paper studies the application of single chip computer and multi-sensor information fusion technology for design of an intelligent air fresher device. At first, the paper states the multi-sensor information fusion algorithm, and proves that the algorithm has good feasibility. After that, according to the specifications of the air fresher, an improved fuzzy evidence theory, which combined fuzzy theory and D-S evidence theory, are used for design of the air fresher. At last, an intelligent air fresher with the function of information fusion and air varying forecast control is designed.
引文
[1] 燕颢．信息融合几种算法的研究[D]：[硕士学位论文]．南京：南京理工大学，2003
[2] 康耀红．数据融合理论与应用[M]．西安：西安电子科技出版社，1997，5～13
[3] 王耀南，李树涛．多传感器信息融合及其应用综述[J]．控制与决策，2001．16(9)：518～521
[4] 张明路，戈新良，唐志强等．多传感器信息融合技术研究现状和发展趋势[J]．河北工业大学学报，2003，(2)：29～35
[5] 罗志增，蒋静坪．机器人感觉与多信息融合[M]．北京：机械工业出版社，2002．91～101
[6] 王国宏，何友，刘永，阎红星．数据融合系统中的传感器分类及模型[J]．航空电子技术，1995，3：34～37
[7] 曾庆茂，丁正生．多传感器信息融合技术综述[J]．赣南师范学院学报，2004，(6)：20～23
[8] 范新南，苏丽媛，郭建甲．多传感器信息融合综述[J]．河海大学常州分校学报，2005，19(1)：1～4
[9] 滕召胜，罗隆福．智能检测系统与数据融合[M]．北京：机械工业出版社，2000
[10] 李圣怡，吴学忠，范人鹏．多传感器融合理论及在智能制造系统中的应用[M]．长沙：国防科技大学出版社，1998
[11] 龚元明，萧德云，王俊杰．多传感器数据融合技术[J]．冶金自动化，2002，4(2)：3～7
[12] 郭惠勇．多传感器信息融合技术的研究与进展[J]．中国科学基金．2005，(1)：17～21
[13] 张菊秀．多传感器停息融合技术和发展[J]．电子世界．2005，(4)：6～7
[14] Ali Cheaito, Michel Lecours, Eloi Bosse. A non-ad-hoc decision rule for Dempster-shafer Method of Evidential Reasoning, SPIE, 1998, 3376: 43～57
[15] Dubios D, Prade H. A Survey of belief revision and updating rules in various uncertainty models. International Journal of Intelligent Systems, 1994, 9: 61～100
[16] 杨万海．多传感器数据融合及其应用[M]．西安：西安电子科技大学出版社．2004，10～11
[17] 徐从富，耿卫东，潘云鹤．面向数据融合的DS方法综述．电子学报， 2001，29(3)：393～396
[18] 罗志增，蒋静萍．应用模糊信息融合实现目标物体的分类[J]．仪器仪表学报，1999，20(4)：401～404
[19] Pongsak Ajjimarangsee and Terrance L. Huntsberger, Neural network model for fusion of visible and infrared sensor outputs, SPIE Vol. 1003, 1998:153～160
[20] Malur K. Sundareshan and Farid Amoozegar. Neural network fusion capabilities for efficient implementation of tracking algorithms, Opt. Eng. 1997,36(3):692～707
[21] Leonid Lperlovsky and Margaret M. Mcmanus. Maximum likelihood neural networks for sensor fusion and adaptive classification. Neural networks, 1991, no. 4: 89～102
[22] O. G. Jakubowica. Autonomous reconfiguration of sensor systems using neural nets. SPIE, vol. 931, 1988
[23] Thomopoulos Stelios C., wann Chin-Der, Clustering with unsupervised neural networks with applications to data fusion, SPIE 1994, 2093: 621～632
[24] Cao j.,Shridhar M.,Ahmadi m.,Handwritteen numeral recognition with neural networks and information fusion, proceedings of the 37th Midwest Symposium on Circuits and Systems, 1994:569～572
[25] Wong, Yee Chin, Sundareshan, Malur K., Data fusion and tracking of complex target maneuvers with a simplex-trained neural network-based architecture, Proceeding of the 1998 IEEE international Joint Conference on Neural Networks, 1998, 2: 1023～1028
[26] Gu, J., M. Cook, A., Faulkner, M. G., Micro sensor based eye movement detection and neural network based sensor fusion and fault detection and recovery, proceedings of IEEE Canadian Conference on Engineering, 2000, 1: 518～522
[27] 敬忠良等．基于模糊神经网络和D-S推理的智能特征信息融合研究．信息与控制，1997，26(2)：107～111
[28] 王敏等．基于神经网络的多传感器集成与融合技术．智能机器人93年会，1993：137～144
[29] 王琳．多传感器信息融合技术及其应用[D]：[硕士学位论文]．河北：华北电力大学，2002
[30] 何友，王国宏等．多传感器信息融合及应用[M]，北京：电子工业出版社，2000．21-22
[31] Walley P, Measures of Uncertainty in Expert System. Artif, Intell, 1996, 83(1): 1～58
[32] Voorbraak F. On the Justification of Dempster Rule of Combination. Artif. Intell, 1991, 48(2): 171～197
[33] Klawoon F, Schwecke E, On the Axiomatic Justification of Dempster's Rule of Combination. Intell. Syste, 1990(7): 469～478
[34] 肖人彬，王雪，周济，相关证据合成方法的研究，模式识别与人工智能，1993，6(3)：227～234
[35] Denceux T. An Evidence-Theoretic Neural network Classifier. IEEE Int. Conf. on Syst., Man, and Cybern., 1995,25(3):712～714
[36] Mahler R. Unified Data Fusion:Fuzzy logic, Evidence and Rules. In Proceeding of Signal Processing. Sensor Fusion and Target Recognition. V. Orlando, Florida, 1996,226～237
[37] Pager R R. On the D-S framework and new Combination Rules, Information Sciences, 1987, 41(2): 93～138
[38] John Yen. Generalizing the Dempster-Shafer Theory to fuzzy sets. IEEE Trans. On SMC, 1990,20(3):559～570
[39] Belur V. Dasarathy, Fuzzy evidential reasoning approach to target identity and state fusion in multisensor environments, Opt. Eng. 1997, 36(3):669～683
[40] 方明．模糊证据合成方法的研究．计算机应用与软件，1998，15(4)：44～46
[41] 吴根秀．模糊证据理论．计算机与现代化，1998(2)：1～4，25
[42] 范风强，兰婵丽．单片机语言C51应用实战集锦[M]．北京：电子工业出出版社，2005，8～11
[43] 梁力，原盛，韩菁．程序设计与C语言[M]．西安：西安交通大学出版社，2005，55～96
[44] 胡建平．C语言程序设计[M]．天津：天津大学出版社，2005，127～160
[45] 赵晓安．MCS-51单片机原理及应用[M]．天津：天津大学出版社，2006，65～110
[46] 朱定华．单片机原理及接口技术[M]．北京：清华大学出版社，2002，173～181
[2] 康耀红．数据融合理论与应用[M]．西安：西安电子科技出版社，1997，5～13
[3] 王耀南，李树涛．多传感器信息融合及其应用综述[J]．控制与决策，2001．16(9)：518～521
[4] 张明路，戈新良，唐志强等．多传感器信息融合技术研究现状和发展趋势[J]．河北工业大学学报，2003，(2)：29～35
[5] 罗志增，蒋静坪．机器人感觉与多信息融合[M]．北京：机械工业出版社，2002．91～101
[6] 王国宏，何友，刘永，阎红星．数据融合系统中的传感器分类及模型[J]．航空电子技术，1995，3：34～37
[7] 曾庆茂，丁正生．多传感器信息融合技术综述[J]．赣南师范学院学报，2004，(6)：20～23
[8] 范新南，苏丽媛，郭建甲．多传感器信息融合综述[J]．河海大学常州分校学报，2005，19(1)：1～4
[9] 滕召胜，罗隆福．智能检测系统与数据融合[M]．北京：机械工业出版社，2000
[10] 李圣怡，吴学忠，范人鹏．多传感器融合理论及在智能制造系统中的应用[M]．长沙：国防科技大学出版社，1998
[11] 龚元明，萧德云，王俊杰．多传感器数据融合技术[J]．冶金自动化，2002，4(2)：3～7
[12] 郭惠勇．多传感器信息融合技术的研究与进展[J]．中国科学基金．2005，(1)：17～21
[13] 张菊秀．多传感器停息融合技术和发展[J]．电子世界．2005，(4)：6～7
[14] Ali Cheaito, Michel Lecours, Eloi Bosse. A non-ad-hoc decision rule for Dempster-shafer Method of Evidential Reasoning, SPIE, 1998, 3376: 43～57
[15] Dubios D, Prade H. A Survey of belief revision and updating rules in various uncertainty models. International Journal of Intelligent Systems, 1994, 9: 61～100
[16] 杨万海．多传感器数据融合及其应用[M]．西安：西安电子科技大学出版社．2004，10～11
[17] 徐从富，耿卫东，潘云鹤．面向数据融合的DS方法综述．电子学报， 2001，29(3)：393～396
[18] 罗志增，蒋静萍．应用模糊信息融合实现目标物体的分类[J]．仪器仪表学报，1999，20(4)：401～404
[19] Pongsak Ajjimarangsee and Terrance L. Huntsberger, Neural network model for fusion of visible and infrared sensor outputs, SPIE Vol. 1003, 1998:153～160
[20] Malur K. Sundareshan and Farid Amoozegar. Neural network fusion capabilities for efficient implementation of tracking algorithms, Opt. Eng. 1997,36(3):692～707
[21] Leonid Lperlovsky and Margaret M. Mcmanus. Maximum likelihood neural networks for sensor fusion and adaptive classification. Neural networks, 1991, no. 4: 89～102
[22] O. G. Jakubowica. Autonomous reconfiguration of sensor systems using neural nets. SPIE, vol. 931, 1988
[23] Thomopoulos Stelios C., wann Chin-Der, Clustering with unsupervised neural networks with applications to data fusion, SPIE 1994, 2093: 621～632
[24] Cao j.,Shridhar M.,Ahmadi m.,Handwritteen numeral recognition with neural networks and information fusion, proceedings of the 37th Midwest Symposium on Circuits and Systems, 1994:569～572
[25] Wong, Yee Chin, Sundareshan, Malur K., Data fusion and tracking of complex target maneuvers with a simplex-trained neural network-based architecture, Proceeding of the 1998 IEEE international Joint Conference on Neural Networks, 1998, 2: 1023～1028
[26] Gu, J., M. Cook, A., Faulkner, M. G., Micro sensor based eye movement detection and neural network based sensor fusion and fault detection and recovery, proceedings of IEEE Canadian Conference on Engineering, 2000, 1: 518～522
[27] 敬忠良等．基于模糊神经网络和D-S推理的智能特征信息融合研究．信息与控制，1997，26(2)：107～111
[28] 王敏等．基于神经网络的多传感器集成与融合技术．智能机器人93年会，1993：137～144
[29] 王琳．多传感器信息融合技术及其应用[D]：[硕士学位论文]．河北：华北电力大学，2002
[30] 何友，王国宏等．多传感器信息融合及应用[M]，北京：电子工业出版社，2000．21-22
[31] Walley P, Measures of Uncertainty in Expert System. Artif, Intell, 1996, 83(1): 1～58
[32] Voorbraak F. On the Justification of Dempster Rule of Combination. Artif. Intell, 1991, 48(2): 171～197
[33] Klawoon F, Schwecke E, On the Axiomatic Justification of Dempster's Rule of Combination. Intell. Syste, 1990(7): 469～478
[34] 肖人彬，王雪，周济，相关证据合成方法的研究，模式识别与人工智能，1993，6(3)：227～234
[35] Denceux T. An Evidence-Theoretic Neural network Classifier. IEEE Int. Conf. on Syst., Man, and Cybern., 1995,25(3):712～714
[36] Mahler R. Unified Data Fusion:Fuzzy logic, Evidence and Rules. In Proceeding of Signal Processing. Sensor Fusion and Target Recognition. V. Orlando, Florida, 1996,226～237
[37] Pager R R. On the D-S framework and new Combination Rules, Information Sciences, 1987, 41(2): 93～138
[38] John Yen. Generalizing the Dempster-Shafer Theory to fuzzy sets. IEEE Trans. On SMC, 1990,20(3):559～570
[39] Belur V. Dasarathy, Fuzzy evidential reasoning approach to target identity and state fusion in multisensor environments, Opt. Eng. 1997, 36(3):669～683
[40] 方明．模糊证据合成方法的研究．计算机应用与软件，1998，15(4)：44～46
[41] 吴根秀．模糊证据理论．计算机与现代化，1998(2)：1～4，25
[42] 范风强，兰婵丽．单片机语言C51应用实战集锦[M]．北京：电子工业出出版社，2005，8～11
[43] 梁力，原盛，韩菁．程序设计与C语言[M]．西安：西安交通大学出版社，2005，55～96
[44] 胡建平．C语言程序设计[M]．天津：天津大学出版社，2005，127～160
[45] 赵晓安．MCS-51单片机原理及应用[M]．天津：天津大学出版社，2006，65～110
[46] 朱定华．单片机原理及接口技术[M]．北京：清华大学出版社，2002，173～181