海用載具聲紋智能辨識系統

Artificial Intelligence Application in a Marine Vehicle Identification System Using Acoustic Signatures

方銀營(Yin-Ying Fang)

指導教授 ： 陳琪芳

共同指導教授 ： 吳聖儒(Sheng-Ju Wu)

國立臺灣大學/工學院/工程科學及海洋工程學研究所/博士(2019年)

https://doi.org/10.6342/NTU201904025

摘要

透過水面或水下載具裝載水下聲紋辨識系統，進行水下特徵辨識的技術已被應用於反潛作戰和港灣防禦中。然而，水聲通道會受到海底地形、海況條件的時空變化、水文環境的時變性干擾，造成多路徑效應及噪音遮蔽等影響。因此，如何管控所收錄之聲學資料品質具有挑戰性。除此之外，水下聲紋辨識系統亦須解決的挑戰為如何從不同時空環境所錄製的聲學檔案中識別出相同的目標特徵-海洋研究船三號(Ocean Researcher III, OR3)。
本研究選定以海洋研究船三號之船舶聲紋為識別目標，參考挪威船級協會
DNV GL-Silent之量測規範，使用水下聲音錄製系統量測其水下輻射噪音並於2016年和2017年間共量測四次。水下聲紋辨識系統乃透過特徵萃取、特徵篩選與資料探勘等步驟，並用統計分法與機器學習兩種方法進行聲紋辨識並比較其優劣。由於基頻及其功率譜密度為船舶頻譜上之重要分類特徵。在特徵萃取過程中，先萃取出此特徵後，再透過特徵篩選及資料探勘等程序，分析出最重要之特徵。
第一種方法，利用多項式回歸(Polynomial Regression, PR)和田口方法(Taguchi method)及方差分析(analysis of variance,ANOVA)，求得不同因子在不同水準組合下之渴望函數(Desirability function)，篩選出最大渴望函數值為最佳組合。
第二種方法，採用自適應性神經模糊推論系統(Adaptive Network-Based FuzzyInference System, ANFIS)，同樣透過計算渴望函數值，利用遺傳演算法(geneticalgorithm, GA)找出最佳的因子組合。
由結果可知，特徵萃取步驟，所萃取之特徵可成功辨識不同時空下之同一目標船舶之水下輻射噪音，以倍頻作為辨識特徵，可解決噪音遮蔽的問題。利用統計分析及機器學習所建立之演算法皆可達到90%以上之準確度。由本研究所開發之「海用載具聲紋智能辨識系統(Artificial Intelligence Application in a Marine Vehicle Identification System Using Acoustic Signatures ) 」，可應於於港灣防禦作為船船監測之用， 若應用於海上即時監測，建議仍以智能學習演算法所建立之辨識器為主。

關鍵字

水下輻射噪聲 ； 航舶噪音 ； 海洋研究船 ； 聲紋特徵 ； 特徵萃取 ； 特徵篩選 ； 自適應性神經模糊推論系統 ； 徑向基函數神經網路 ； 田口法 ； 多項式回歸 ； 方差分析

並列摘要

Underwater acoustic signature identification has been employed as a technique for detecting underwater vehicles, such as in anti-submarine warfare or harbor security systems. The underwater sound channel, however, has interference due to spatial variations in topography or sea state conditions and temporal variations in water column properties, which causes multipath and scattering in acoustic propagation. Thus, acoustic data quality control can be very challenging. One of challenges for an identification system is how to recognize the same target signature from measurements following the rule of DNV GL-Silent under different temporal and spatial settings.
This paper deals with the above challenges by establishing an identification system composed of feature extraction, feature selection, and data mining with statistical analysis and machine learning approaches to recognize the target signatures of underwater radiated noise from a research vessel, Ocean Researcher III (OR3), with a bottom mounted hydrophone in four cruises in 2016 and 2017. The fundamental frequency and its power spectral density are significant features for classification. In feature extraction, we extract the features before deciding which of the two aforementioned features is more significant. The first approach utilizes Polynomial Regression (PR) classifiers and feature selection by Taguchi method and analysis of variance (ANOVA) for finding the maximum desirability function under a different combination of factors and levels. The second approach utilizes Adaptive Network-Based Fuzzy Inference System (ANFIS) and selecting the optimized desirability value via genetic algorithm (GA).
The result proves that the feature extraction process successfully detects the OR3 targets under different topography and temporal variations and solves the noise masking problem by utilizing harmonic frequency features extracted from unmasking the frequency bandwidth for ship noises. Nevertheless, the accuracy of PR and ANFIS classifiers all approach 90%. The “Artificial Intelligence Application in a Marine Vehicle Identification System Using Acoustic Signatures” developed here can be carried out in harbor security for monitoring acoustic signatures of a specific ship. In addition, it utilizes the artificial intelligence classifier, which has faster detecting performance than the regression classifier on real-time monitoring.

並列關鍵字

underwater radiated noise ； shipping noise ； Ocean Researcher ； acoustic signature ； feature extraction ； feature selection ； ANFIS ； RBFNN ； Taguchi method ； polynomial regression ； ANOVA

參考文獻

1. Jae-Byung, J., et al. Broadband Active Sonar Swimmer Detection and Identification. in Neural Networks, 2006. IJCNN '06. International Joint Conference on. 2006.

2. Merchant, N.D., et al., Measuring acoustic habitats. Methods in Ecology and Evolution, 2015. 6(3): p. 257-265.

3. Merchant, N.D., et al., Averaging underwater noise levels for environmental assessment of shipping. The Journal of the Acoustical Society of America, 2012. 132(4): p. EL343-EL349.

4. Hagerty, M., et al., Analysis of seismic and acoustic observations at Arenal Volcano, Costa Rica, 1995–1997. Journal of Volcanology and Geothermal Research, 2000. 101(1): p. 27-65.

5. Iyama, J. and H. Kuwamura, Application of wavelets to analysis and simulation of earthquake motions. Earthquake engineering & structural dynamics, 1999. 28(3): p. 255-272.