留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

船舶机舱协作式模拟训练智能评估

段尊雷 任光 张均东 曹辉

段尊雷, 任光, 张均东, 曹辉. 船舶机舱协作式模拟训练智能评估[J]. 交通运输工程学报, 2016, 16(6): 82-90.
引用本文: 段尊雷, 任光, 张均东, 曹辉. 船舶机舱协作式模拟训练智能评估[J]. 交通运输工程学报, 2016, 16(6): 82-90.
DUAN Zun-lei, REN Guang, ZHANG Jun-dong, CAO Hui. Intelligent assessment for collaborative simulation training in ship engine room[J]. Journal of Traffic and Transportation Engineering, 2016, 16(6): 82-90.
Citation: DUAN Zun-lei, REN Guang, ZHANG Jun-dong, CAO Hui. Intelligent assessment for collaborative simulation training in ship engine room[J]. Journal of Traffic and Transportation Engineering, 2016, 16(6): 82-90.

船舶机舱协作式模拟训练智能评估

基金项目: 

国家自然科学基金项目 51479017

详细信息
    作者简介:

    段尊雷(1981-), 男, 山东菏泽人, 大连海事大学工学博士研究生, 从事轮机自动化与智能控制研究

    任光(1952-), 男, 辽宁朝阳人, 大连海事大学教授, 工学博士

  • 中图分类号: U676.4

Intelligent assessment for collaborative simulation training in ship engine room

More Information
    Author Bio:

    DUAN Zun-lei(1981-), male, doctoral student, +86-411-84726983, admudzl@163.com

    REN Guang(1952-), male, professor, PhD, +86-411-84726983, reng@dlmu.edu.cn

  • 摘要: 基于人-机-环境系统工程理论, 研究了船舶机舱模拟训练评估问题, 建立了船舶的角色-任务-资源系统协作训练模型, 提出了基于专家系统和机器学习的智能评估方法, 并用于改进三维机舱协作训练系统; 建立了船舶机舱模拟训练情景知识库、任务知识库和评估指标体系, 结合专家经验和评估规范提取评估规则, 采用遗传算法优化后的权重对数据进行多重模糊综合评判; 针对实际的评估问题构造合适的机器学习网络结构, 利用BP神经网络和深度学习算法具备的自学习优势, 以简化运算步骤; 将评估指标数据进行归一化处理后作为评估模型的输入数据, 将评估结果作为目标数据, 采用稀疏自动编码器对大量数据样本进行特征变换, 深入学习样本特征并用于分类评估, 经反复训练后得到较好的评估模型; 对基于专家系统和机器学习的智能评估方法进行了对比分析。分析结果表明: 经遗传算法优化的评估结果误差明显较小, 平均绝对误差为0.761分, 平均相对误差为0.983%, 均方误差为0.938分, 最大误差为2.263分, 最小误差为0.248分; 对于较简单任务的评估, 基于机器学习评估的最大绝对误差为3.521分, 最小绝对误差为0.304分, 较好的深度学习评估网络的所有指标的评估误差均可小于1分。

     

  • 图  1  角色-任务-资源系统

    Figure  1.  Role-mission-resource system

    图  2  智能评估原理

    Figure  2.  Principle of intelligent assessment

    图  3  智能评估知识库结构

    Figure  3.  Structure of intelligent assessment knowledge base

    图  4  BP神经网络结构

    Figure  4.  Structure of BP neural network

    图  5  自动编码器结构

    Figure  5.  Structure of autocoder

    图  6  四种方法的评估结果对比

    Figure  6.  Comparison of assessment results of 4methods

    图  7  机器学习智能评估结果对比

    Figure  7.  Comparison of intelligent assessment results based on machine learning

    图  8  浅层学习智能评估迭代曲线

    Figure  8.  Iterative curve of intelligent assessment based on shallow learning

    图  9  深度学习智能评估迭代曲线

    Figure  9.  Iterative curve of intelligent assessment based on deep learning

    表  1  试验数据

    Table  1.   Experimental data

    下载: 导出CSV

    表  2  指标权重

    Table  2.   Index weights

    下载: 导出CSV

    表  3  不同方法的评估结果

    Table  3.   Assessment results of different methods

    下载: 导出CSV

    表  4  不同方法的评估误差

    Table  4.   Assessment errors of different methods

    下载: 导出CSV

    表  5  机器学习智能评估结果

    Table  5.   Intelligent assessment result based on machine leaning

    下载: 导出CSV
  • [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. doi: 10.3969/j.issn.1000-4653.2011.01.006

    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). doi: 10.3969/j.issn.1000-4653.2011.01.006
    [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. https://www.cnki.com.cn/Article/CJFDTOTAL-XTFZ201308021.htm

    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). https://www.cnki.com.cn/Article/CJFDTOTAL-XTFZ201308021.htm
    [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. doi: 10.3969/j.issn.1000-4653.2013.03.007

    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). doi: 10.3969/j.issn.1000-4653.2013.03.007
    [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. https://www.cnki.com.cn/Article/CJFDTOTAL-DLHS201501022.htm

    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). https://www.cnki.com.cn/Article/CJFDTOTAL-DLHS201501022.htm
    [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. doi: 10.3969/j.issn.1000-4653.2010.03.007

    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). doi: 10.3969/j.issn.1000-4653.2010.03.007
    [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. https://www.cnki.com.cn/Article/CJFDTOTAL-HEBG201406013.htm

    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). https://www.cnki.com.cn/Article/CJFDTOTAL-HEBG201406013.htm
    [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. doi: 10.3969/j.issn.1001-3695.2015.10.016

    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). doi: 10.3969/j.issn.1001-3695.2015.10.016
    [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. https://www.cnki.com.cn/Article/CJFDTOTAL-HXDY201501006.htm

    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). https://www.cnki.com.cn/Article/CJFDTOTAL-HXDY201501006.htm
    [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. doi: 10.14257/ijca.2015.8.10.24
    [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. https://www.cnki.com.cn/Article/CJFDTOTAL-CANB201302021.htm

    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). https://www.cnki.com.cn/Article/CJFDTOTAL-CANB201302021.htm
    [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. doi: 10.3969/j.issn.1003-6059.2014.04.007

    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). doi: 10.3969/j.issn.1003-6059.2014.04.007
    [13] DENG Jun, ZHANG Zi-xing, EYBEN F, et al. Autoencoderbased unsupervised domain adaptation for speech emotion recognition[J]. IEEE Signal Processing Letters, 2014, 21(9): 1068-1072. doi: 10.1109/LSP.2014.2324759
    [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. doi: 10.14257/ijca.2016.9.1.30
    [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. doi: 10.12733/jics20106801
    [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. doi: 10.3963/j.issn.2095-3844.2013.04.039

    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). doi: 10.3963/j.issn.2095-3844.2013.04.039
    [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. doi: 10.3969/j.issn.1671-1637.2014.02.006

    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). doi: 10.3969/j.issn.1671-1637.2014.02.006
    [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. doi: 10.1109/4235.661549
    [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. doi: 10.3969/j.issn.1007-449X.2014.03.006

    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). doi: 10.3969/j.issn.1007-449X.2014.03.006
    [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. doi: 10.1109/TSMCB.2005.850173
    [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. doi: 10.2174/1874444301507011262
    [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. doi: 10.1016/j.patcog.2013.05.025
    [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. https://www.cnki.com.cn/Article/CJFDTOTAL-BJGD202103011.htm

    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). https://www.cnki.com.cn/Article/CJFDTOTAL-BJGD202103011.htm
    [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.
  • 加载中
图(9) / 表(5)
计量
  • 文章访问数:  3397
  • HTML全文浏览量:  162
  • PDF下载量:  3560
  • 被引次数: 0
出版历程
  • 收稿日期:  2016-07-05
  • 刊出日期:  2016-12-25

目录

    /

    返回文章
    返回