Acoustic Localization Based on the D-S Evidence Theory for Pressurized Gas Leakage Detection

Ying-Wang Wang,Ji-Gong Li,Jing Yang

2023 5th International Conference on Industrial Artificial Intelligence (IAI)(2023)

引用 0|浏览0
暂无评分
摘要
The sound source localization of ultrasonic signals generated by pressurized gas leakage was studied. The TDOA based sound source localization algorithm is always used to locate the leakage source. Since the sensors used to locate the sound source are often far from the sound source, and often only far-field models can be applied to estimate the direction of the sound source relative to the sensors. To determine the location of the sound source, it is necessary to take acoustic measurements at different positions around the sound source, such as by using a mobile robot, and fuse the measurement data. In addition, the estimated directions of the sound source usually contain uncertainties due to the noise during the measurements. To localize the sound source precisely and reliably, the D-S evidence theory was carried out in our research, in which an acoustic mass function was constructed to calculate a spatial distribution of the leakage source’s location. The proposed method was verified with experiments in which the sound source was simulated with an ultrasonic transmitter, and a linearly and equidistantly distributed microphone linear array was used to estimate the direction where the ultrasonic wave came from. The experimental results show that the proposed method can be used to localize the sound source and has good accuracy and stability.
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要