粒子过器引导的在线神经网络用于被动声纳系统中的多目标轴承单独跟踪
Jianan Wang1,2, Lujun Wang2, Zhuoran Wang1,2
1Science and Technology on Sonar Laboratory, Hangzhou 310023, China.
Sensors (Basel, Switzerland)
|September 27, 2025
概括
这项研究引入了一种新的神经网络方法,用于在被动声纳系统中稳定的多目标跟踪. 该方法显著提高了跟踪精度,并降低了可靠性能所需的信号噪声比 (SNR) 的最低要求.
科学领域:
- 声学信号处理 声学信号处理
- 机器学习用于目标跟踪跟踪.
- 被动声纳系统是被动声纳系统.
背景情况:
- 由于信号不稳定,被动声纳的多目标跟踪具有挑战性.
- 现有的方法在低信号噪声比率 (SNR) 和目标轨迹交叉方面扎.
- 准确的跟踪对于海军作战和水下监视至关重要.
研究的目的:
- 开发一种可靠的方法,用于在被动声纳中稳定的多目标单轴承追踪.
- 为了提高跟踪准确度,并减少可靠性能所需的最低SNR.
- 为了提高目标轨迹的连续性和顺性.
主要方法:
- 一个粒子过器引导的现场训练机制简化了多重分类到二进制分类.
- 每个目标都分配了一个独立的追踪器,用于同时训练和部署.
- 使用混合卷积神经网络 (CNN) 和双向长短期记忆 (BiLSTM) 网络.
- CNN增强了特征提取和非目标歧视;BiLSTM模型空间时间依赖.
主要成果:
- 拟议的方法将稳定跟踪所需的最低SNR降低到-31.78dB,而纯颗粒过则降低到-29.69dB.
- 平均跟踪误差从0.61°降低到0.34°.
- 在模拟和海上试验中,即使在目标轨迹穿越过程中,也保持了稳定的跟踪.
结论:
- 混合CNN-BiLSTM网络有效地解决了多目标轴承仅跟踪的不稳定性.
- 该方法在复杂的水下声环境中显著提高了跟踪精度和稳定性.
- 这种方法为被动声纳多目标追踪能力提供了实质性的进步.
相关概念视频
01:24One-Degree-of-Freedom System
1.0K
In mechanical engineering, one-degree-of-freedom systems form the basis of a wide range of electrical and mechanical components. Using these models, engineers can predict the behavior of various parts in a larger system, which gives them insight into how different forces interact with each other.
A one-degree-of-freedom system is defined by an independent variable that determines its state and behavior. One example of a one-degree-of-freedom system is a simple harmonic oscillator, such as a...
A one-degree-of-freedom system is defined by an independent variable that determines its state and behavior. One example of a one-degree-of-freedom system is a simple harmonic oscillator, such as a...
1.0K
01:28Automatic Processing and Automatic Social Behavior
376
Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...
376