分段的飞机舱音记录器混合信号在线盲分离性能分析

应用科学学报 ›› 2010, Vol. 28 ›› Issue (2): 129-135.

分段的飞机舱音记录器混合信号在线盲分离性能分析

杨琳，博士生，高工，研究方向：航空记录器、飞行品质监控和事故调查，E-mail: yanglin@mail.castc.org.cn

1. 南京航空航天大学民航学院，南京210016
2. 中国民用航空总局航空安全技术中心，北京100028
3. 南京航空航天大学自动化学院，南京210016

收稿日期:2009-10-28 修回日期:2010-01-06 出版日期:2010-03-30 发布日期:2010-03-30
作者简介:杨琳，博士生，高工，研究方向：航空记录器、飞行品质监控和事故调查，E-mail: yanglin@mail.castc.org.cn
基金资助:
国家自然科学基金(No.60776819)资助

Performance of Online Blind Separation of Dynamically Segmented Mixed Acoustic Signal for CVR

1. Civil Aviation College, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
2. Civil Aviation Safety Technical Center of CAAC, Beijing 100028, China
3. College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China

Received:2009-10-28 Revised:2010-01-06 Online:2010-03-30 Published:2010-03-30

摘要/Abstract

摘要：

针对飞机驾驶舱话音记录器(CVR)中存在轻微时变特性和信号有大量近零值的情况，提出一种基于信号样本动态分段的在线盲分离算法. 应用独立分量分析的在线算法对CVR混合信号进行动态分段处理，再通过快速的FastICA算法进行精确化求解. 为了使估计器获得最佳性能，适当调整分离矩阵各行权值. 仿真结果表明，该算法可有效地将CVR混合信号中独立的声音信号分离出来，分离效果优良.

关键词: 驾驶舱话音记录器, 混合声音信号, 在线盲分离算法, 动态分段

Abstract:

Considering the existence of slight time-varying characteristics and a large number of near-zero signal values, we propose an online blind separation algorithm based on signal sample dynamic segmentation. The online algorithm of independent component analysis (ICA) is used to achieve dynamic segmentation. The FastICA algorithm is executed until converging to an optimal solution. To obtain better performance, weights of the rows in the separation matrix are adjusted. Simulation results show excellent performance of the proposed algorithm, indicating that the algorithm can effectively separate mixed acoustic signals recorded by CVR.

Key words: cockpit voice recorder (CVR),, mixed acoustic signal, on-line blind separation algorithm, dynamic segmentation

中图分类号:

杨琳，王从庆，张红占. 分段的飞机舱音记录器混合信号在线盲分离性能分析[J]. 应用科学学报, 2010, 28(2): 129-135.

YANG Lin, WANG Cong-qing, ZHANG Hong-zhan. Performance of Online Blind Separation of Dynamically Segmented Mixed Acoustic Signal for CVR[J]. Journal of Applied Sciences, 2010, 28(2): 129-135.