大数据环境下的海量多维舰船故障信息控制系统设计

Design of massive multidimensional ship fault information control system in big data environment

作者单位:

1. 河南油田工程科技股份有限公司，河南 郑州 450000;2. 中国劳动关系学院 应用技术学院，北京 1000481. Henan Oilfield Engineering Technology Co., Ltd., Zhengzhou 450000, China;2. School of Applied Technology, China University of Labor Relations, Beijing 100048, China

大数据环境;海量多维;舰船故障信息;控制系统;征兆变量;概率神经网络big data environment; massive multidimensional; ship fault information; control system; symptom variables; probabilistic neural network

为充分发挥舰船故障信息对保证舰船安全航行的辅助功能，设计大数据环境下的海量多维舰船故障信息控制系统。使用大数据层的大数据采集模块获取海量多维舰船故障信息，并保存至大数据存储模块，利用网络通信层的网络传输通信模块，将存储的故障信息上传到核心服务层，该层运用总体控制模块控制接收到的故障信息，依次完成融合与征兆变量提取。在此基础上，舰船故障诊断模块运用概率神经网络，实现舰船故障辅助诊断。实验结果表明：该系统采集海量多维舰船故障信息时输出的动态范围符合规定标准，采集稳定性较好；能控制故障信息完成征兆变量的精准提取，且对不同海上环境的舰船故障诊断效果均较为理想。In order to give full play to the auxiliary function of ship fault information to ensure the safe navigation of ships, a massive multi-dimensional ship fault information control system under the big data environment is designed. Use the big data acquisition module of the big data layer to obtain massive and multi-dimensional ship fault information and save it to the big data storage module. Use the network transmission communication module of the network communication layer to upload the stored fault information to the core service layer. This layer uses the overall control module to control the received fault information and complete the fusion and symptom variable extraction in turn. On this basis, the ship fault diagnosis module uses the probabilistic neural network, realize auxiliary fault diagnosis of ships. The experimental results show that the dynamic range of the output of the system when collecting massive multidimensional ship fault information meets the specified standards, and the collection stability is good. It can control the fault information to complete the accurate extraction of symptom variables, and the effect of ship fault diagnosis in different marine environments is ideal.

参考文献：

[1]劲松, 李芳. 大数据环境下的安全多维数据聚合协议[J]. 西南师范大学学报(自然科学版), 2021, 46(7): 125–129

ZOU Jin-song, LI Fang. Secure multidimensional data aggregation protocol in big data environment[J]. Journal of Southwest China Normal University(Natural Science Edition), 2021, 46(7): 125–129

[2] 卢月, 李维波, 李巍, 等. 舰船电站控制系统的双CPU混成式故障检测技术[J]. 中国舰船研究, 2021, 16(3): 200–206

LU Yue, LI Wei-bo, LI Wei, et al. Dual CPU redundant communication hybrid fault detection technology for shipborne electrical plant control system[J]. Chinese Journal of Ship Research, 2021, 16(3): 200–206

[3] 吴康清, 黄利平, 李伯舒, 等. 基于故障知识库的机械零部件故障管理支持系统[J]. 图学学报, 2019, 40(3): 623–630

WU Kang-qing, HUANG Li-ping, LI Bo-shu, et al. Failure management and support system of mechanical parts based on failure Knowledge-Base[J]. Journal of Graphics, 2019, 40(3): 623–630

[4] 张新文, 刘愉强, 刘同木, 等. 基于混合加密的浮标数据安全管理系统研究[J]. 热带海洋学报, 2020, 39(5): 117–123

ZHANG Xin-wen, LIU Yu-qiang, LIU Tong-mu, et al. Research on buoy data security management system based on multi-encryption[J]. Journal of Tropical Oceanography, 2020, 39(5): 117–123

[5] 高泽宇, 张鹏, 曹乐乐, 等. 基于自适应阈值的船舶柴油淮态监控[J]. 船舶工程, 2021, 43(12): 172–177

GAO Ze-yu, ZHANG Peng, CAO Le-le, et al. Condition monitoring of marine diesel engine based on adaptive threshold[J]. Ship Engineering, 2021, 43(12): 172–177

[6] 刘国强, 林叶锦, 张志政, 等. 基于粗糙集和优化DAG-SVM的船舶主机故障诊断方法[J]. 中国舰船研究, 2020, 15(1): 68–73

LIU Guo-qiang, LIN Ye-jin, ZHANG Zhi-zheng, et al. Main marine engine fault diagnosis method based on rough set theory and optimized DAG-SVM[J]. Chinese Journal of Ship Research, 2020, 15(1): 68–73