基于改进灰色马尔可夫链的电传动装甲车辆负载需求功率预测

doi:10.3969/j.issn.1000-1093.2021.10.009

摘要/Abstract

摘要： 为解决电传动装甲车辆负载需求功率预测精度偏低的问题，提出一种基于改进灰色马尔可夫链的组合功率预测方法。采用改进灰色预测方法和马尔可夫链预测方法对负载需求功率中的主体功率和残差功率进行预测，并在每个预测时刻将两种功率预测结果进行代数相加，建立改进灰色马尔可夫链组合预测方法。仿真结果表明：该负载需求功率组合预测方法相对于传统单一预测方法，能够较好地预测负载功率的强随机性变化特征，准确预测负载需求功率的变化趋势，预测精度最高提升了16.49%，可为后续能量管理策略提供有效参考信息。

关键词: 电传动装甲车辆, 负载需求, 灰色模型, 马尔可夫链, 功率预测

Abstract: A combined power prediction method based on improved grey Markov chain is proposed to solve the problem of low accuracy of demand power prediction for electric drive armored vehicles. The improved grey prediction method and Markov chain prediction method are used to predict the main power and residual power in the load demand power. The predicted results of demand and residual powers at each prediction moment are algebraically added to establish an improved grey Markov chain combination prediction method. The simulated results show that，compared with the traditional prediction method，the proposed demand power combination prediction method can better predict the strong randomness of load power and accurately predict the variation trend of demand power，and the prediction accuracy is increased by 16.49%，which can provide effective reference information for the energy management strategy.

Key words: electricdrivearmoredvehicle, loaddemand, greymodel, Markovchain, powerprediction

中图分类号:

TJ810.2

刘春光，陈路明，张运银，张征，徐浩轩. 基于改进灰色马尔可夫链的电传动装甲车辆负载需求功率预测[J]. 兵工学报, 2021, 42(10): 2130-2144.

LIU Chunguang， CHEN Luming， ZHANG Yunyin， ZHANG Zheng， XU Haoxuan. Prediction of Demand Power of Electric Drive Armored Vehicle Based on Improved Grey Markov Chain[J]. Acta Armamentarii, 2021, 42(10): 2130-2144.

参考文献

［1］项宇.新型电传动装甲车辆综合电力系统能量管理策略研究[D].北京:装甲兵工程学院，2016.
XIANG Y.Research on energy management strategy of integrated power system for new electric drive armored vehicles[D].Beijing:Academy of Armored Forces Engineering，2016.(in Chinese)
[2] 应天杏.基于功率需求预测的燃料电池汽车能量管理自适应控制策略研究[D].上海:上海交通大学，2018.
YING T X.Research on adaptive control strategy for energy ma-nagement of fuel cell vehicle based on power demand prediction[D].Shanghai:Shanghai Jiao Tong University，2018.(in Chinese)
[3] FRANCO F L，RICCO M，MANDRIOLI R，et al.Electric vehicle aggregate power flow prediction and smart charging system for distributed renewable energy self-consumption optimization[J].Energies，2020，13(19):418002.
[4] 付翔，铁鑫，刘会康.基于需求功率预测的混合动力越野车能量管理[J].江苏大学学报（自然科学版），2021，42(1):67-76.
FU X，TIE X，LIU H K.Energy management of hybrid off road vehicles based on demand power prediction[J].Journal of Jiangsu University (Natural Science Edition)，2021，42(1):67-76. (in Chinese)
[5] 廖自力，项宇，刘春光，等.电传动装甲车辆混合动力系统功率流控制策略[J].兵工学报，2017，38(12):2289-2300.
LIAO Z L，XIANG Y，LIU C G，et al.Power flow control strategy of hybrid power system of electric drive armored vehicle[J].Acta Armamentarii，2017，38(12):2289-2300.(in Chinese)
[6] 张杰，马晓军，刘春光，等.双侧独立电驱动履带车辆反馈线性化解耦与预测行驶控制[J].兵工学报，2021，42(4): 697-705.
ZHANG J，MA X J，LIU C G，et al.Feedback linearization decoupling and predictive driving control for dual independent electric drive tracked vehicle[J].Acta Armamentarii，2021，42(4): 697-705. (in Chinese)
[7] 王大鹏.灰色预测模型及中长期电力负荷预测应用研究[D].武汉:华中科技大学，2013.
WANG D P.Research on grey prediction models and their applications in medium- and long-term power load forecasting[D].Wuhan:Huazhong University of Science and Technology，2013.(in Chinese)
[8] 王子赟，纪志成.基于灰色-辨识模型的风电功率短期预测[J].电力系统保护与控制，2013，41(12):79-85.
WANG Z Y，JI Z C.Grey-identification model based wind power generation short-term prediction[J].Power System Protection and Control 2013，41(12):79-85. (in Chinese)
[9] YIN K D，GENG Y，LI X M.Improved grey prediction model based on exponential grey action quantity[J].Journal of Systems Engineering and Electronics，2018，29(3):560-570.
[10] 曾波，尹小勇，孟伟.实用灰色预测建模方法及其MATLAB程序实现[M].北京:科学出版社，2019.
ZENG B，YIN X Y, MENG W.Practical grey prediction modeling method and its MATLAB program implementation[M]. Beijing: Science Press，2019.(in Chinese)
[11] 邓聚龙.灰色系统理论教程[M].武汉:华中科技大学出版社，1990.
DENG J L.The grey system theory tutorial[M].Wuhan:Huazhong University of Science and Technology Press，1990.(in Chinese)
[12] CHEN L M，LIAO Z L，MA X J.Nonlinear model predictive control for heavy-duty hybrid electric vehicles using random power prediction method[J]. IEEE Access，2020，8: 202819-202835.
[13] 孙超.混合动力汽车预测能量管理研究[D].北京:北京理工大学，2016.
SUN C.Research on predictive energy management of hybrid electric vehicle[D].Beijing: Beijing Institute of Technology，2016. (in Chinese)
[14] 罗云馨.基于浮动车数据的城市道路交通评价分析[D]. 成都:电子科技大学，2019.
LUO Y X.Evaluation and analysis of urban road traffic based on floating car data[D].Chengdu: University of Electronic Science and Technology of China，2019.(in Chinese)
[15] 杨超.轻型汽车实际道路行驶排放特性研究[D].长春:吉林大学，2020.
YANG C.Study on real driving emission characteristics of light vehicle[D].Changchun:Jilin University，2020.(in Chinese)
[16] LI Q，ZHOU Q，HE Y，et al.Driver-identified supervisory control system of hybrid electric vehicles based on spectrum-guided fuzzy feature extraction[J].IEEE Transactions on Fuzzy Systems，2020，28(11):2691-2701.
[17] 季学武，费聪，何祥坤，等.基于LSTM网络的驾驶意图识别及车辆轨迹预测[J].中国公路学报，2019，32(6): 34-42.
JI X W，FEI C，HE X K，et al.Intention recognition and trajectory prediction for vehicles using LSTM network[J].China Journal of Highway and Transport，2019，32(6):34-42.(in Chinese)
[18] NIJHUIS M，GIBESCU M，COBBEN J F G.Bottom-up Markov Chain Monte Carlo approach for scenario based residential load modelling with publicly available data[J].Energy and Buildings，2016，112:121-129.
[19] ZOU Y，KONG Z H，LIU T，et al.A real-time Markov chain driver model for tracked vehicles and its validation: its adaptability via stochastic dynamic programming[J].IEEE Transactions on Vehicular Technology，2017，66(5):3571-3582.
[20] 傅妍芳，王赞，苏一昶，等.基于马尔可夫链的军用Ad hoc网络可用性建模[J].兵工学报，2021，42(1):65-73.
FU Y F，WANG Z，SU Y T，et al. Availability modeling of military Ad Hoc network based on Markov chain[J].Acta Armamentarii，2021，42(1):65-73.(in Chinese)
[21] ZHANG M，SHI S M，LIN N，et al.High-efficiency driving cycle generation using a Markov chain evolution algorithm[J]. IEEE Transactions on Vehicular Technology， 2019，68(2):1288-1301.
[22] LIU T，WANG B，YANG C L.Online Markov chain-based energy management for a hybrid tracked vehicle with speedy Q-learning[J].Energy，2018，160:544-555.
[23] 袁伟，付锐，郭应时，等.基于马尔可夫链的驾驶人视觉转移特征[J].长安大学学报(自然科学版)，2012，32(6): 88-93.
YUAN W，FU R，GUO Y S，et al. Driver's visual transition cha-racteristics based on the Markov chain[J].Journal of Chang'an University (Natural Science Edition)，2012，32(6):88-93. (in Chinese)
[24] 翁志坚，邱晨杰，邱福祥，等.基于马尔可夫优化的灰色GM(1，1) 沉降预测模型及应用[J].科学技术与工程，2020，20(29): 12065-12070.
WENG Z J，QIU C J，QIU F X，et al.An optimized GM(1，1) grey prediction model based on Markov chain and its application[J].Science Technology and Engineering，2020，20(29): 12065-12070. (in Chinese)
[25] 贾俊平，何晓群，金勇进.统计学[M].第7版.北京:中国人民大学出版社，2018.
JIA J P，HE X Q，JIN Y J.Statistics [M].7th ed. Beijing:China Renmin University Press，2018.(in Chinese)

[1]	王振峰，李飞，王新宇，杨建森，秦也辰. 基于交互式多模型无迹卡尔曼滤波的悬架系统状态估计[J]. 兵工学报, 2021, 42(2): 242-253.
[2]	傅妍芳，王赞，苏一昶，戴飞，钟联炯，郭登登，卢颖，梁洪涛. 基于马尔可夫链的军用Ad hoc网络可用性建模[J]. 兵工学报, 2021, 42(1): 65-73.
[3]	翟禹尧，史贤俊，吕佳朋. 基于广义随机Petri网的导弹系统测试性建模与指标评估方法研究[J]. 兵工学报, 2019, 40(10): 2070-2079.
[4]	潘显俊，张炜，赵田，郭小强. 分数阶离散灰色模型及其在备件需求预测中的应用[J]. 兵工学报, 2017, 38(4): 785-792.
[5]	廖自力，项宇，刘春光，李嘉麒. 电传动装甲车辆混合动力系统功率流控制策略[J]. 兵工学报, 2017, 38(12): 2289-2300.
[6]	易怀军，刘宁，张相炎，丁传俊. 基于优化的非等间隔灰色理论和BP神经网络的身管磨损量预测[J]. 兵工学报, 2016, 37(12): 2220-2225.
[7]	骆清国，尹洪涛，宁兴兴. 一种基于有向图的冷却系统原理方案设计方法[J]. 兵工学报, 2016, 37(1): 10-16.
[8]	赵建忠，叶文，张磊. 基于数据融合和改进新陈代谢不等间距GM(11)模型的导弹装备故障预测[J]. 兵工学报, 2014, 35(10): 1689-1695.
[9]	朱正福，李长福，何恩山，杨春华. 基于马尔可夫链的动态故障树分析方法[J]. 兵工学报, 2008, 29(9): 1104-1107.
[10]	刘建敏，刘艳斌，乔新勇. 发动机技术状况变化趋势预测研究[J]. 兵工学报, 2007, 28(7): 774-777.
[11]	吕宏，白桦，武旲鹏. 成本估算参数方法研究[J]. 兵工学报, 2007, 28(4): 477-480.
[12]	洪星，宋元，马爱民. 马尔可夫链用于扫雷作战期望损失评估探讨[J]. 兵工学报, 2006, 27(6): 1132-1135.
[13]	谢庆华，梁剑，张琦. 基于统计粗集的航空发动机维修成本组合预测模型[J]. 兵工学报, 2006, 27(5): 857-861.
[14]	梁庆卫，宋保维，贾跃. 基于历史费用的鱼雷经济寿命预测[J]. 兵工学报, 2006, 27(5): 865-868.