基于声纹及射频识别的轨道车监控系统研究
摘要
轨道车是用于铁路建设、设备维护、事故抢修和巡视检查等工作的自轮运转特种设备,其运行状态关系到铁路运输的整体安全。随着铁路列车运行速度的不断提高和运营密度的进一步加大,对轨道车在运行安全性方面的要求越来越高。
为保障运行安全,轨道车上目前装设有行车安全装备,对于防止冒进信号、超速运行以及溜逸等问题发挥了相当的作用。然而,轨道车的运行安全在很大程度上是靠以铁路规章约束司机及随乘人员的行为来保障的。由于未在技术上实现全面监控,一旦司机及随乘人员存在违规行为,就有可能发生行车安全事故。
本文针对轨道车的驾驶监控中的问题,在分析轨道车驾驶规章规定,提取行车安全关键因素基础上,力图在技术上实现对司机及随乘人员监控,实时消除驾驶工作状态不良形成的行车安全隐患。
本文提出了基于声纹识别和射频识别的轨道车驾驶监控系统方案,并对驾驶监控系统的硬件结构与组成、软件流程实现进行研究。最后,结合轨道车管理实际情况,本文对驾驶监控系统的应用进行了探讨。
Railcars are the special equipments for railway constructing, rail equipment maintaining, accident rush repairing, rail inspecting and so on. The operation safety of a railcar affects the whole railway transportation. With the continuous increasing of train-speed and the much intensifying of traffic density, the much higher safety of railcars'operation is demanded.
To guarantee the safety of railcars, the railway traffic safety equipments, which have played a significant role in such issues as overrun signals, over speed and railcars slipped, are equipped. However, it still largely relies on the drivers and passengers complying with the relevant railway rules and regulations to protect the railcars from accidents. Because it has not monitored that the drivers and passengers comprehensively through technical means, there is a good possibility of accidents once the drivers or passengers violate the rules.
This paper is aimed at the problems in railcars'monitoring. Based on analyzing the relevant railway rules and extracting the key factors related to the safety, this paper tries to monitor the drivers and passengers comprehensively through technical method and eliminate the security risk formed with the abnormal driving conditions timely.
This paper has proposed the railcars'monitoring system based on voiceprint recognition and radio frequency identification. And it has made a study of the design and implementation of the monitoring system hardware and software, including the structure and composition of the hardware and the process design of the software. At last, this paper makes analysis and discussions of the applications of this system based on the actual situation of the railcars' management.
为保障运行安全,轨道车上目前装设有行车安全装备,对于防止冒进信号、超速运行以及溜逸等问题发挥了相当的作用。然而,轨道车的运行安全在很大程度上是靠以铁路规章约束司机及随乘人员的行为来保障的。由于未在技术上实现全面监控,一旦司机及随乘人员存在违规行为,就有可能发生行车安全事故。
本文针对轨道车的驾驶监控中的问题,在分析轨道车驾驶规章规定,提取行车安全关键因素基础上,力图在技术上实现对司机及随乘人员监控,实时消除驾驶工作状态不良形成的行车安全隐患。
本文提出了基于声纹识别和射频识别的轨道车驾驶监控系统方案,并对驾驶监控系统的硬件结构与组成、软件流程实现进行研究。最后,结合轨道车管理实际情况,本文对驾驶监控系统的应用进行了探讨。
Railcars are the special equipments for railway constructing, rail equipment maintaining, accident rush repairing, rail inspecting and so on. The operation safety of a railcar affects the whole railway transportation. With the continuous increasing of train-speed and the much intensifying of traffic density, the much higher safety of railcars'operation is demanded.
To guarantee the safety of railcars, the railway traffic safety equipments, which have played a significant role in such issues as overrun signals, over speed and railcars slipped, are equipped. However, it still largely relies on the drivers and passengers complying with the relevant railway rules and regulations to protect the railcars from accidents. Because it has not monitored that the drivers and passengers comprehensively through technical means, there is a good possibility of accidents once the drivers or passengers violate the rules.
This paper is aimed at the problems in railcars'monitoring. Based on analyzing the relevant railway rules and extracting the key factors related to the safety, this paper tries to monitor the drivers and passengers comprehensively through technical method and eliminate the security risk formed with the abnormal driving conditions timely.
This paper has proposed the railcars'monitoring system based on voiceprint recognition and radio frequency identification. And it has made a study of the design and implementation of the monitoring system hardware and software, including the structure and composition of the hardware and the process design of the software. At last, this paper makes analysis and discussions of the applications of this system based on the actual situation of the railcars' management.
引文
[1]胡跃进,李志锋.轨道车与接触网作业车[M].成都：西南交通大学出版社,2011：22-23
[2]李如年.基于RFID技术的物联网研究[J].中国电子科学研究院学报.2009,(6)：594-596
[3]李向文.欧、美、日韩及我国的物联网发展战略——物联网的全球发展行动[J].射频世界.2010,(3)：49-53
[4]卢瑞文.自动识别技术[M].北京：化学工业出版社,2005：206-207
[5]王晓亮,宓奇,彭苏勉,关忠良.物联网在我国铁路运输领域的应用与发展探讨[J].铁路通信信号.2010,(3)
[6]周晓光,王晓华,王伟.射频识别(RFID)系统设计、仿真与应用[M].北京：人民邮电出版社,2008
[7]董丽华.RFID技术与应用[M].北京：电子工业出版社,2008
[8]丁建.射频识别技术在我国的应用现状与发展前景[J].射频世界.2010,(5)
[9]田捷,杨鑫.生物特征识别理论与应用[M].北京：清华大学出版社,2009
[10]吴晓峰,陈大才.射频识别技术[M].第3版.北京：电子工业出版社,2006
[11]赵军辉.射频识别技术与应用[M].北京：机械工业出版社,2008
[12]田静.机车无线音视频监控系统的应用研究[J].西安科技.2010,(2)
[13]岳学军,徐兴,张文昭,蔡坤,徐湘华.嵌入式DSP声纹识别系统的设计与实现[J].湖南科技学院学报.2008,29(12)
[14]郭慧娟.声纹识别的特征参数提取[J].太原师范学院学报(自然科学版).2008,7(1)
[15]杨阳,陈永明.声纹识别技术及其应用[J].电声技术.2007,31(2)
[16]朱浩冰,郭东辉.声纹识别系统原理及其关键技术[J].计算机安全.2007,(9)
[17]王炳锡,屈丹,彭煊.实用语音识别基础[M].北京：国防工业出版社,2005
[18]吴朝晖,杨莹春.说话人识别模型与方法[M].北京：清华大学出版社,2009
[19]刘幺和,宋庭新.语音识别与控制应用技术[M].北京：科学出版社,2008
[20]屈丹,王波,李弼程.VoIP语音处理与识别[M].北京：国防工业出版社,2010
[21]徐光泽.电声原理与技术[M].北京：电子工业出版社,2007
[22]候丽敏.基于非线性理论和信息、融合的说话人识别[M].上海：上海大学出版社,2009
[23]李波.基于DSP的声纹识别技术的研究[J].辽宁工业大学学报(自然科学版).2010,30(4)
[24]TI, Spra602F, TMS320VC5416 BootLoader, Texas Instruments Inc,2005
[25]Reynolds, D. A., Automatic speaker recognition using Gaussian mixture speaker models, Lincoln Lab. J.8 (1996)
[26]C. S. Liu, M. T. Lin, W. J. Wang, H. C. Wang. Study of line spectrum pair frequencies for speaker recognition[A]. The 1990 IEEE International Conference on Acoustics, Speech and Signal Processing Conference Proceedings[C],1990
[27]DAVID K. BURTON, Member, IEEE, "Text-Dependent Speaker Verification Using Vector Quantization Source Coding" IEEE Trans On Acoustics, Speech and Signal Processing, Vol. ASSP-35, No.2, February,1987
[28]R. Auchenthaler, M. Carey, Score normalization for text-independent speaker verification systems, Digital Signal Process. October,2000
[29]Qi Li, "A Detection Approach to Search-Space Reduction for HMM state Alignment in Speaker Verification, "IEEE Trans, July,2001
[30]中华人民共和国铁道部.轨道车管理规则[M].北京：中国铁道出版社,2007
[31]中华人民共和国铁道部.铁路技术管理规程[M].北京：中国铁道出版社,2007
[32]中华人民共和国铁道部.铁路工务安全规则[M].北京：中国铁道出版社,2007
[33]张左琪,杨振怀.轨道车安全驾驶读本[M].北京：铁道出版社,2003
[34]铁道部运输局基础部.十年全路工务行车重大、大事故分析[M].北京：铁道出版社,2000
[35]铁道部工务局.轨道车司机[M].北京：铁道出版社,1982
[36]蒋丽川,王正生.轨道车司机[M].北京：铁道出版社,1996
[37]张雄伟,陈亮,徐光辉.DSP芯片的原理与开发应用[M].第4版.北京：电子工业出版社,2009
[38]Texas Instruments Incorporated TMS320c54x DSP Reference Set, Vol 6:Enhanced Peripherals [K]. Texas:Texas Instruments, Inc,1997
[39]Campbell J P. Prolog to Speaker Recognition:A Tutorial[J]. Proceedings of IEEE, 1997,85 (9)
[40]Farrel, Kevin R, Mammone, et al. Speaker Recognition Using Neural Networks and Conventional Classifiers. IEEE Trans Speech Audio Processing,1994,1 (2)
[41]Hermansky Hynek, Hanson Brian A, Wakita Hisashi. Perceptual Based linear predictive analysis of speech. IEEE International Conference on Acoustics, Speech and Signal Processing,1990,87 (4)
[42]张磊.基于DSP和射频卡的嵌入式指纹识别系统设计与实现.电子科技大学硕士学位论文.2009.5
[43]张鹏.基于DSP的嵌入式声纹识别汽车锁的设计与实现.吉林大学硕士学位论 文.2007.4
[44]樊亚琴.浅谈视频监控系统的应用与发展.科技情报开发与经济.2010,20(5)
[45]Moonasar Viresh, Sandrasegaran, Venayagamoorthy Ganesh K, et al. Voice Recognition using neural networks. in:Proceedings of the South African Symposium on Communications and Signal Processing. New York, USA:IEEE Comp Soc,1998
[46]Zhi-peng Li, Shan-guang Chen, Xue Liang. Some mistakes in the algorithm for solving underflow problem in Baum Welch algorithm and their corrections [J]. Chinese Journal of Acoustics,2003 (2)
[47]Jing Deng, Fang Zheng, Wen-hu Wu. UBM based speaker segmentation and clustering for 2-speaker detection. ISCSLP 2006
[48]张东亮.DSP控制器原理及应用[M].北京：机械工业出版社,2011
[49]吕捷.GPRS技术[M].北京：北京邮电大学出版社,2001
[50]张小鸣.DSP控制器原理及应用[M].北京：清华大学出版社,2009
[51]Tomi Kinnunen and Ismo Kark kainen. Class-Discriminative Weighted Distortion Measure for VQ-based Speaker Identification[M]. SSPP&SPR2002, LNCS2396
[52]Bing Xiang, Berger. T, Efficient Text-independent Speaker Verification with Structural Gaussian Mixture Models and Neural Network, IEEE Transactions on Speech and Audio Processing, Sept 2003,11 (5)
[53]Kennedy, J. and Eberhart, R, Particle Swarm Optimization[C], IEEE International Conference on Neural Networks (Perth, Australia), IEEE Service Center, Piscataway, NJ,1995
[54]Millonas, M. M, Swarms, phase transition, and collective intelligence[C], In C. G Langton, (Eds.), Artificial life III, Addison-Wesley, MA,1994
[2]李如年.基于RFID技术的物联网研究[J].中国电子科学研究院学报.2009,(6)：594-596
[3]李向文.欧、美、日韩及我国的物联网发展战略——物联网的全球发展行动[J].射频世界.2010,(3)：49-53
[4]卢瑞文.自动识别技术[M].北京：化学工业出版社,2005：206-207
[5]王晓亮,宓奇,彭苏勉,关忠良.物联网在我国铁路运输领域的应用与发展探讨[J].铁路通信信号.2010,(3)
[6]周晓光,王晓华,王伟.射频识别(RFID)系统设计、仿真与应用[M].北京：人民邮电出版社,2008
[7]董丽华.RFID技术与应用[M].北京：电子工业出版社,2008
[8]丁建.射频识别技术在我国的应用现状与发展前景[J].射频世界.2010,(5)
[9]田捷,杨鑫.生物特征识别理论与应用[M].北京：清华大学出版社,2009
[10]吴晓峰,陈大才.射频识别技术[M].第3版.北京：电子工业出版社,2006
[11]赵军辉.射频识别技术与应用[M].北京：机械工业出版社,2008
[12]田静.机车无线音视频监控系统的应用研究[J].西安科技.2010,(2)
[13]岳学军,徐兴,张文昭,蔡坤,徐湘华.嵌入式DSP声纹识别系统的设计与实现[J].湖南科技学院学报.2008,29(12)
[14]郭慧娟.声纹识别的特征参数提取[J].太原师范学院学报(自然科学版).2008,7(1)
[15]杨阳,陈永明.声纹识别技术及其应用[J].电声技术.2007,31(2)
[16]朱浩冰,郭东辉.声纹识别系统原理及其关键技术[J].计算机安全.2007,(9)
[17]王炳锡,屈丹,彭煊.实用语音识别基础[M].北京：国防工业出版社,2005
[18]吴朝晖,杨莹春.说话人识别模型与方法[M].北京：清华大学出版社,2009
[19]刘幺和,宋庭新.语音识别与控制应用技术[M].北京：科学出版社,2008
[20]屈丹,王波,李弼程.VoIP语音处理与识别[M].北京：国防工业出版社,2010
[21]徐光泽.电声原理与技术[M].北京：电子工业出版社,2007
[22]候丽敏.基于非线性理论和信息、融合的说话人识别[M].上海：上海大学出版社,2009
[23]李波.基于DSP的声纹识别技术的研究[J].辽宁工业大学学报(自然科学版).2010,30(4)
[24]TI, Spra602F, TMS320VC5416 BootLoader, Texas Instruments Inc,2005
[25]Reynolds, D. A., Automatic speaker recognition using Gaussian mixture speaker models, Lincoln Lab. J.8 (1996)
[26]C. S. Liu, M. T. Lin, W. J. Wang, H. C. Wang. Study of line spectrum pair frequencies for speaker recognition[A]. The 1990 IEEE International Conference on Acoustics, Speech and Signal Processing Conference Proceedings[C],1990
[27]DAVID K. BURTON, Member, IEEE, "Text-Dependent Speaker Verification Using Vector Quantization Source Coding" IEEE Trans On Acoustics, Speech and Signal Processing, Vol. ASSP-35, No.2, February,1987
[28]R. Auchenthaler, M. Carey, Score normalization for text-independent speaker verification systems, Digital Signal Process. October,2000
[29]Qi Li, "A Detection Approach to Search-Space Reduction for HMM state Alignment in Speaker Verification, "IEEE Trans, July,2001
[30]中华人民共和国铁道部.轨道车管理规则[M].北京：中国铁道出版社,2007
[31]中华人民共和国铁道部.铁路技术管理规程[M].北京：中国铁道出版社,2007
[32]中华人民共和国铁道部.铁路工务安全规则[M].北京：中国铁道出版社,2007
[33]张左琪,杨振怀.轨道车安全驾驶读本[M].北京：铁道出版社,2003
[34]铁道部运输局基础部.十年全路工务行车重大、大事故分析[M].北京：铁道出版社,2000
[35]铁道部工务局.轨道车司机[M].北京：铁道出版社,1982
[36]蒋丽川,王正生.轨道车司机[M].北京：铁道出版社,1996
[37]张雄伟,陈亮,徐光辉.DSP芯片的原理与开发应用[M].第4版.北京：电子工业出版社,2009
[38]Texas Instruments Incorporated TMS320c54x DSP Reference Set, Vol 6:Enhanced Peripherals [K]. Texas:Texas Instruments, Inc,1997
[39]Campbell J P. Prolog to Speaker Recognition:A Tutorial[J]. Proceedings of IEEE, 1997,85 (9)
[40]Farrel, Kevin R, Mammone, et al. Speaker Recognition Using Neural Networks and Conventional Classifiers. IEEE Trans Speech Audio Processing,1994,1 (2)
[41]Hermansky Hynek, Hanson Brian A, Wakita Hisashi. Perceptual Based linear predictive analysis of speech. IEEE International Conference on Acoustics, Speech and Signal Processing,1990,87 (4)
[42]张磊.基于DSP和射频卡的嵌入式指纹识别系统设计与实现.电子科技大学硕士学位论文.2009.5
[43]张鹏.基于DSP的嵌入式声纹识别汽车锁的设计与实现.吉林大学硕士学位论 文.2007.4
[44]樊亚琴.浅谈视频监控系统的应用与发展.科技情报开发与经济.2010,20(5)
[45]Moonasar Viresh, Sandrasegaran, Venayagamoorthy Ganesh K, et al. Voice Recognition using neural networks. in:Proceedings of the South African Symposium on Communications and Signal Processing. New York, USA:IEEE Comp Soc,1998
[46]Zhi-peng Li, Shan-guang Chen, Xue Liang. Some mistakes in the algorithm for solving underflow problem in Baum Welch algorithm and their corrections [J]. Chinese Journal of Acoustics,2003 (2)
[47]Jing Deng, Fang Zheng, Wen-hu Wu. UBM based speaker segmentation and clustering for 2-speaker detection. ISCSLP 2006
[48]张东亮.DSP控制器原理及应用[M].北京：机械工业出版社,2011
[49]吕捷.GPRS技术[M].北京：北京邮电大学出版社,2001
[50]张小鸣.DSP控制器原理及应用[M].北京：清华大学出版社,2009
[51]Tomi Kinnunen and Ismo Kark kainen. Class-Discriminative Weighted Distortion Measure for VQ-based Speaker Identification[M]. SSPP&SPR2002, LNCS2396
[52]Bing Xiang, Berger. T, Efficient Text-independent Speaker Verification with Structural Gaussian Mixture Models and Neural Network, IEEE Transactions on Speech and Audio Processing, Sept 2003,11 (5)
[53]Kennedy, J. and Eberhart, R, Particle Swarm Optimization[C], IEEE International Conference on Neural Networks (Perth, Australia), IEEE Service Center, Piscataway, NJ,1995
[54]Millonas, M. M, Swarms, phase transition, and collective intelligence[C], In C. G Langton, (Eds.), Artificial life III, Addison-Wesley, MA,1994