Integrated Power System Health Assessment of Large-Scale Unmanned Surface Ships Based on Convolutional Neural Network Algorithm

2nd International Symposium on Resource Exploration and Environmental Science

生态环境科学

Shang, Lei^1 ; Cheng, Yanming^1

Wuhan University of Technology, WhuHan

430070, China^1

关键词: Comparative simulation;    Convolution neural network;    Convolutional neural network;    Deep belief networks;    Environmental parameter;    Evaluation algorithm;    Health assessments;    Integrated Power Systems;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/170/4/042052/pdf
DOI  :  10.1088/1755-1315/170/4/042052

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

These paper studies the large unmanned ship of the most advanced electric propulsion method. Its integrated power system is complex in structure with many equipment and often performs long-range operations. The key factor of the large unmanned ship is the integrated power system of healthy operation. This paper analyzes the parameters affecting the health of the system from three aspects: the system parameters, the unmanned ship's navigation state parameters, and the environmental parameters and designs a kind of unmanned ship integrated power system health based on Evaluation algorithm of convolutional neural network with high accuracy. In this paper, the feasibility and superiority of convolution neural network algorithm are verified through the comparative simulation analysis of BP neural network and deep belief network.