Research Article of Scientific Research and Reviews
Ship navigation safety risk assessment based on genetic algorithm and BP neural network
He Zhang1*, Zhuyun Shao1, Ji Zeng1
1Shanghai Maritime University, Shanghai 201306, China.
In order to ensure the safe navigation of ships and reduce the occurrence of marine accidents, through the analysis of ship historical navigation safety accident data and related accident literature research, taking into account various aspects such as marine meteorology, cargo loading, ship status and crew quality. Construct a ship navigation safety evaluation body. The BP neural network algorithm is used to design the ship navigation safety risk network structure. The sea damage data is used as the network input sample to train the BP neural network and data fitting. At the same time, the genetic algorithm is introduced to find the individual corresponding to the optimal fitness, and the weight and threshold of the network are further optimized. The purpose is to improve the accuracy of data fitting. The optimized BP neural network evaluation results show that there are many indicators affecting the safety of the ship’s navigation, and the relationship between the indicators is complicated. The optimized BP neural network utilizes the characteristics of online adaptive learning, which eliminates the construction of complex relationships among various indicators within the structure, and solves the difficult problems in ship risk assessment to a certain extent.
Keywords: Ship navigation safety; BP neural network; Genetic algorithm; Risk assessment
How to cite this article:
He Zhang, Zhuyun Shao, Ji Zeng. Ship navigation safety risk assessment based on genetic algorithm and BP neural network. Scientific Research and Reviews, 2020; 13:117. DOI:10.28933/srr-2020-08-1505
1. Xie Yiyang , Liu Dagang , Wu Danzhu , et al. Risk Prediction Technology of Ship Safety in the Yellow Sea and Bohai Sea during Severe Weathers[J]. Journal of Catastrophology, 2014, 29(1): 136-143.
2. Mengxuan Wang. Li Wei. Safe Assessment of Containerships Based on ReliefF-ANFIS[J]. Ship Electronic Engineering, 2018, 38(07): 100-105+121.
3. Duan Aiyuan , Zhao Yao , Preliminary evaluation on ship safety based on unascertained measure[J]. Journal of Shanghai Maritime University, 2007(02): 21-23+27.
4. Wang Zhijuan , Wei Hongchang . Precise Ship Attitude Prediction Technology based on Improved Neural Network[J]. Ship Science and Technology, 2019,41(12): 37-39.
5. Xiao Jingkun , Yin Peihai , Lin Jianguo et al. Identification of ship’s oil spill risk degree of sea area by using BP artificial network[J]. Marine Environmental Science, 2002(04): 42-45.
6. Chen Xiaoting , Wu Jingna , Lu Haixia et al. Analysis and evaluation of nutritional components in the muscle of decapterus maruadsi[J]. Fishery Modernization, 2016,43(01):47-51+61.
7. Chandre G C , Mayya S G . Comparison of Back Propagation Neural Network and Genetic Algorithm Neural Network for Stream Flow Prediction[J]. Journal of Computational Environmental Sciences, 2014, 2014:1-6.
8. Zhang Xinfang , Guan Keping , Research on Influencing Factors and Safety Evaluation of Ship Navigation Safety[J]. China Water Transport, 2015, 15(11):50-52.
9. Wu Haihua. Analysis of factors affecting ship navigation safety[J]. China Water Transport, 2006(5).
10. Liang Kailin . Analysis on human factors in maritime traffic accident based on CREAM[D]. Dalian Maritime University, 2014.
11. Zhang hui. The ship Capsizing Risk Assessment based on BP Neural Network[D]. Dalian Maritime University, 2018.
12. Zhang hui. The ship Capsizing Risk Assessment based on BP Neural Network[D]. Dalian Maritime University, 2018.