|Table of Contents|

Intelligent assessment for collaborative simulation training in ship engine room(PDF)


Research Field:
Publishing date:


Intelligent assessment for collaborative simulation training in ship engine room
DUAN Zun-lei REN Guang ZHANG Jun-dong CAO Hui
School of Marine Engineering, Dalian Maritime University, Dalian 116026, Liaoning, China
ship engineering engine room simulator intelligent assessment collaborative training genetic algorithm neural network deep learning
The assessment for simulation training in ship engine room was studied based on the theory of man-machine-environment system engineering. The system model called role-mission-resource for collaborative training was constructed, and the intelligent assessment methods based on expert system and machine learning were proposed to improve the three dimensional engine room collaborative training system. The scene knowledge base, mission knowledge base and evaluation index system of simulation training in ship engine room were established. The assessment rules were extracted according to the expert experience and the evaluation criteria. The data were evaluated by using multiple fuzzy comprehensive evaluation and the weights were optimized by genetic algorithm. The structures of machine learning network were constructed appropriately according to the practical assessment problem. The computing steps were simplified by using the advantage of self-learning of BP neural network and deep learning algorithms. The normalized evaluation index was used as the input of evaluation model, and the evaluation results were used as the target data. The features of mass sample data were transformed by using sparse autocoder. Sample features were learned deeply and used for classification evaluation, thus the better evaluation model was achieved after repeated training. A comparative analysis of the intelligent assessment methods based on expert system and machine learning was conducted. Analysis result indicates that after the optimization of genetic algorithm, the assessment result error is smaller apparently. The average absolute error is 0.761 point, the average relative error is 0.983%, the mean square error is 0.938 point, the maximum error is 2.263 point, and the minimum error is 0.248 point. For the evaluation of simpler missions, the maximum absolute error of assessment result based on machine learning is 3.521 point, and the minimum absolute error is 0.304 point. The assessment errors of all indexes in the better assessment network based on deep learning are less than 1 point. 5 tabs, 9 figs, 26 refs.


[1] 蒋德志,赵晓玲.基于轮机模拟器的“机舱资源管理”研究与实践[J].中国航海,2011,34(1):22-25.
JIANG De-zhi, ZHAO Xiao-ling. “Engine room resource management” using engine room simulator[J]. Navigation of China, 2011, 34(1): 22-25.(in Chinese)
[2] 范敏毅,杨新明,马 强,等.飞行模拟器训练的计算机智能评估[J].系统仿真学报,2013,25(8):1811-1815.
FAN Min-yi, YANG Xin-ming, MA Qiang, et al. Application of computer brainpower evaluating in flight simulator training[J]. Journal of System Simulation, 2013, 25(8): 1811-1815.(in Chinese)
[3] 贾宝柱,林叶锦,曹 辉,等.轮机模拟器中机舱资源管理培训及评估功能[J].中国航海,2013,36(3):28-33.
JIA Bao-zhu, LIN Ye-jin, CAO Hui, et al. Engine-room resource management training and assessment module in marine engineering simulator[J]. Navigation of China, 2013, 36(3): 28-33.(in Chinese)
[4] 曹 辉,马玉鑫,贾宝柱.基于模糊综合评判的轮机模拟器智能评估系统[J].大连海事大学学报,2015,41(1):104-108.
CAO Hui, MA Yu-xin, JIA Bao-zhu. An intelligent evaluation system of marine engine room simulator based on fuzzy comprehensive evaluation [J]. Journal of Dalian Maritime University, 2015, 41(1): 104-108.(in Chinese)
[5] 张桂臣.船舶电站实操考试自动评分系统的设计与实现[J].中国航海,2010,33(3):27-30.
ZHANG Gui-chen. Design and implementation of an automatic grading system for practical examination in marine power station[J]. Navigation of China, 2010, 33(3): 27-30.(in Chinese)
[6] 张巧芬,孙建波,史成军,等.新型轮机仿真平台实操考试自动评估算法[J].哈尔滨工程大学学报,2014,35(6):725-730.
ZHANG Qiao-fen, SUN Jian-bo, SHI Cheng-jun, et al. An automatic-evaluation algorithm for the operation examination of the novel marine engine simulation platform[J]. Journal of Harbin Engineering University, 2014, 35(6): 725-730.(in Chinese)
[7] 谭 娟,王胜春.基于深度学习的交通拥堵预测模型研究[J].计算机应用研究,2015,32(10):2951-2954.
TAN Juan, WANG Sheng-chun. Research on prediction model for traffic congestion based on deep learning[J]. Application Research of Computers, 2015, 32(10): 2951-2954.(in Chinese)
[8] 夏春江,王培良,张 媛.基于深度学习的木材含水率预测[J].杭州电子科技大学学报:自然科学版,2015,35(1):31-35.
XIA Chun-jiang, WANG Pei-liang, ZHANG Yuan. Prediction of moisture content of wood based on deep learning[J]. Journal of Hangzhou Dianzi University: Natural Sciences, 2015, 35(1): 31-35.(in Chinese)
[9] JOO K H, PARK N H. Cooperative learning strategy with a mobile environment[J]. International Journal of Control and Automation, 2015, 8(10): 251-260.
[10] 鲁道毅,贾宝柱,张均东.轮机故障模拟及仿真训练系统[J].船舶工程,2013,35(2):70-72,75.
LU Dao-yi, JIA Bao-zhu, ZHANG Jun-dong. Marine engineering fault and training simulation system[J]. Ship Engineering, 2013, 35(2): 70-72, 75.(in Chinese)
[11] 曾 鸿,张均东,任 光,等.船舶机舱三维视景仿真系统设计与实现[J].系统仿真学报,2014,26(2):363-368,375.
ZENG Hong, ZHANG Jun-dong, REN Guang, et al. Design and implementation of marine engine room three-dimensional visual simulation system[J]. Journal of System Simulation, 2014, 26(2): 363-368, 375.(in Chinese)
[12] 何 清,李 宁,罗文娟,等.大数据下的机器学习算法综述[J].模式识别与人工智能,2014,27(4):327-336.
HE Qing, LI Ning, LUO Wen-juan, et al. A survey of machine learning algorithms for big data[J]. Pattern Recognition and Artificial Intelligence, 2014, 27(4): 327-336.(in Chinese)
[13] DENG Jun, ZHANG Zi-xing, EYBEN F, et al. Autoencoder-
based unsupervised domain adaptation for speech emotion recognition[J]. IEEE Signal Processing Letters, 2014, 21(9): 1068-1072.
[14] LEE C J, KANG S Y, KANG S G, et al. Development of key functions for flight simulator[J]. International Journal of Control and Automation, 2016, 9(1): 347-358.
[15] WANG Si-hua, TAN Guo-liang. Fuzzy evaluation of insulator pollution flashover based on improved EMD de-noising and entropy weight method[J]. Journal of Information and Computational Science, 2015, 12(15): 5687-5696.
[16] 聂 伟,巫 影,胡大斌,等.轮机模拟器考核自动评分算法研究[J].武汉理工大学学报:交通科学与工程版,2013,37(4):834-838.
NIE Wei, WU Ying, HU Da-bin, et al. Research of automatic scoring arithmetic for examination of engine room simulator[J]. Journal of Wuhan University of Technology: Transportation Science and Engineering, 2013, 37(4): 834-838.(in Chinese)
[17] 王英杰,王 磊,荣起国,等.基于熵值理论的泥石流评估因子选取[J].交通运输工程学报,2014,14(2):28-33.
WANG Ying-jie, WANG Lei, RONG Qi-guo, et al. Evaluation index selection of debris flow based on entropy value theory[J]. Journal of Traffic and Transportation Engineering, 2014, 14(2): 28-33.(in Chinese)
[18] CHAN K C C, LEE V, LEUNG H. Generating fuzzy rules for target tracking using a steady-state genetic algorithm[J]. IEEE Transactions on Evolutionary Computation, 1997, 1(3): 189-200.
[19] 张占安,蔡兴国.采用熵理论确定抽水蓄能容量[J].电机与控制学报,2014,18(3):34-39.
ZHANG Zhan-an, CAI Xing-guo. Determination of pumped storage capacity based on entropy[J]. Electric Machines and Control, 2014, 18(3): 34-39.(in Chinese)
[20] SHENG Wei-guo, SWIFT S, ZHANG Lei-shi, et al. A weighted sum validity function for clustering with a hybrid niching genetic algorithm[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 2005, 35(6): 1156-1167.
[21] YANG Zhen-lin. A building management evaluation method based on BP neural networks[J]. The Open Automation and Control Systems Journal, 2015, 7(1): 1262-1267.
[22] VINCENT P, LAROCHELLE H, LAJOIE I, et al. Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion[J]. Journal of Machine Learning Research, 2010, 11(12): 3371-3408.
[23] CIRESAN D, MEIER U, MASCI J, et al. Multi-column deep neural network for traffic sign classification[J]. Neural Networks, 2012, 32(1): 333-338.
[24] FISCHER A, IGEL C. Training restricted Boltzmann machines: an introduction[J]. Pattern Recognition, 2014, 47(1): 25-39.
[25] 尹宝才,王文通,王立春.深度学习研究综述[J].北京工业大学学报,2015,41(1):48-59.
YIN Bao-cai, WANG Wen-tong, WANG Li-chun. Review of deep learning[J]. Journal of Beijing University of Technology, 2015, 41(1): 48-59.(in Chinese)
[26] SHIN H C, ORTON M R, COLLINS D J, et al. Stacked autoencoders for unsupervised feature learning and multiple organ detection in a pilot study using 4D patient data[J]. IEEE Transactions on Software Engineering, 2013, 35(8): 1930-1943.


Last Update: 2016-12-20