Source localization technique using acoustic emission (AE) has been widely used to track the accurate location of the damaged structure. The principle of localization is based on signal velocity and the time difference of arrival (TDOF) obtained from different signals for the specific source. However, signal velocity changes depending on the frequency domain of signals. In addition, the TDOF is dependent on the signal threshold which affects the prediction accuracy. In this study, a convolutional neural network (CNN)-based approach is used to overcome the existing problem. The concrete block corresponding to 1.3×1.3×1.3 m size is prepared according to the mixing ratio of Wolseong low-to-intermediate level radioactive waste disposal concrete materials. The source is excited using an impact hammer, and signals were acquired through eight AE sensors attached to the concrete block and a multi-channel AE measurement system. The different signals for a specific source are time-synchronized to obtain TDOF information and are transformed into a time-frequency domain using continuous wavelet transform (CWT) for consideration of various frequencies. The developed CNN model is compared with the conventional TDOF-based method using the testing dataset. The result suggests that the CNN-based method can contribute to the improvement of localization performance.

요즘 중한 양국 문화 영역의 합작이 심화하고 있다. '원소스 멀티테리토리'모식으로 제작한 중한 영화들을 관객의 주목을 받았다. 하지만 <용하형경>과 <극한직업>이 개봉하면서 양극화 관영 평가와 현격 한 흥행 차이가 생겼다. 따라서 본 논문에서는 두 영화를 중심으로 내러티브, 캐릭터로서 현지화 원소의 운용을 대비하고 분석한다. 같은 스토리는 어떻게 다른 나라의 현지화 사회 문화를 표현할 수 있는 것에 대해 살펴보고 더 우수한 중국 영화를 만들기 위해 현지화 원소의 활용 방법을 총결해야 한다.

Acoustic signal is crucial for the autonomous navigation of underwater vehicles. For this purpose, this paper presents a method of acoustic source localization. The proposed method is based on the probabilistic estimation of time delay of acoustic signals received by two hydrophones. Using Bayesian update process, the proposed method can provide reliable estimation of direction angle of the acoustic source. The acquired direction information is used to estimate the location of the acoustic source. By accumulating direction information from various vehicle locations, the acoustic source localization is achieved using extended Kalman filter. The proposed method can provide a reliable estimation of the direction and location of the acoustic source, even under for a noisy acoustic signal. Experimental results demonstrate the performance of the proposed acoustic source localization method in a real sea environment.

In this paper, we present a Sound Source Localization (SSL) based GCC (Generalized Cross Correlation)–PHAT (Phase Transform) and new measurement method of angle with robot auditory system for a network-based intelligent service robot. The main goal of this paper is to analysis performance of TDOA and GCC-PHAT sound source localization method and new angle measurement method is compared. We use GCC-PHAT for measuring time delays between several microphones. And sound source location is calculated by using time delays and new measurement method of angle. The robot platform used in this work is wever-R2, which is a network-based intelligent service robot developed at Intelligent Robot Research Division in ETRI.