Artificial intelligence technologies for engine control development: State-of-the-art review and outlook

doi:10.3969/j.issn.1674-8484.2021.02.002

Abstract

Abstract:

Connection, automation, sharing and electrification (CASE) are the future of vehicle and mobility systems. International Energy Agency (IEA) predicts that electric vehicles including plug-in hybrid vehicles will count for 97% of the market by 2050. The increasingly stringent emission legislations for CO₂ reduction, especially when involving real driving emissions (RDE) testing are the main challenges to the control system of the vehicle powertrains. This paper focus on artificial intelligence (AI) technologies for engine control developments that follow the standard model-based routine. By reviewing state-of-the-art AI technologies for feedforward control, feedback control, and global optimization at system level, the advantage and disadvantage of the AI technologies are compared and summarized. An outlook is provided based on the literature survey. It indicates that AI will promote the fusion of technologies in three representative domains, 1) fusion of cyber systems and physical systems, e.g., digital twin of engine; 2) fusion of machine learning systems and classical control systems, e.g., AI-based calibration of engine controllers; and 3) fusion of information from multiple sources, e.g., powertrain domain control network. The technology fusions in these three domains are expected to promote the development of advanced engines which aims to achieve zero emissions.

Key words: engine control, model-based development, artificial intelligence (AI), system optimization, controller calibration

CLC Number:

TK421.5

XU Hongming, ZHOU Quan. Artificial intelligence technologies for engine control development: State-of-the-art review and outlook[J]. Journal of Automotive Safety and Energy, 2021, 12(2): 150-162.

Figures/Tables 7

References 81

[1]	International Energy Agency. World energy outlook 2020[R/OL]. (2020-10-00), https://www.iea.org/events/world-energy-outlook-2020.
[2]	苏万华, 张众杰, 刘瑞林, 等. 车用内燃机技术发展趋势[J]. 中国工程学, 2018,20(1):97-103.
	SU Wanhua, ZHANG Zhongjie, LIU Ruilin, et al. Development trend for technology of vehicle internal combustion engine[J]. Strategic Study of CAE, 2018,20(1):97-103. (in Chinese)
[3]	国务院办公厅. 新能源汽车产业发展规划 (2021-2035年)[R]. (2020-11-00), http://www.gov.cn/zhengce/content/2020-11/02/content_5556716.htm.
	State Council of the People's Republic of China. Technical roadmap of new energy vehicles (2021-2035)[R]. (2020-11-00), http://www.gov.cn/zhengce/content/2020-11/02/content_5556716.htm. (in Chinese)
[4]	Isermann R. Engine-control methods and calibration[M/OL]// Engine Modeling and Control. Berlin, Heidelberg: Springer Berlin Heidelberg, 2014: 323-423. [2017-02-13], http://link.springer.com/10.1007/978-3-642-39934-3_6.
[5]	Jacob A, ashok B. An interdisciplinary review on calibration strategies of engine management system for diverse alternative fuels in IC engine applications[J/OL]. Fuel, 2020, 278(6): 118236. https://doi.org/10.1016/j.fuel.2020.118236.
[6]	Mathworks. Model-based design for embedded control systems[R/OL]. (2020-06-00), https://uk.mathworks.com/content/dam/mathworks/white-paper/gated/model-based-design-with-simulation-white-paper.pdf.
[7]	Tayarani M H N, YAO Xin, XU Hongming. Meta-Heuristic algorithms in car engine design: A literature survey[J]. IEEE Trans Evolu Comput, 2015,19(5):609-629. doi: 10.1109/TEVC.4235 URL
[8]	Cook J A, Powell B K. Modeling of an internal combustion engine for control analysis[J]. IEEE Contr Syst Maga, 1988,8(4):20-26.
[9]	胡松, 王贺春, 孙永瑞, 等. 增压柴油机零维预测燃烧建模方法[J]. 内燃机学报, 2016,34(4):311-318.
	HU Song, WANG Hechun, SUN Yongrui, et al. Zero-dimensional prediction comubstion modelling of a turbocharging diesel engine[J]. Trans CSICE, 2016,34(4):311-318. (in Chinese)
[10]	Togun N, Baysec S. Genetic programming approach to predict torque and brake specific fuel consumption of a gasoline engine[J/OL]. Appl Energ, 2010, 87(11): 3401-3408. http://dx.doi.org/10.1016/j.apenergy.2010.04.027.
[11]	XIA LU, De Jager B, Donkers T, et al. Robust constrained optimization for RCCI engines using nested penalized particle swarm[J/OL]. Contr Engi Pract, 2020, 99(April 2019): 104411. https://doi.org/10.1016/j.conengprac.2020.104411.
[12]	MA He. Control oriented engine modelling and engine multi-objective optimal feedback control[D]. University of Birmingham,Birmingham, 2013.
[13]	MA He, XU Hongming, WANG Jihong, et al. Model-based multi-objective evolutionary algorithm optimization for HCCI engines[J]. IEEE Trans Vehi Tech, 2014,9545(c):1-1.
[14]	Safieddin Ardebili S M, Solmaz H, İpci D, et al. A review on higher alcohol of fusel oil as a renewable fuel for internal combustion engines: Applications, challenges, and global potential[J]. Fuel, 2020,279(5):118516. doi: 10.1016/j.fuel.2020.118516 URL
[15]	Rahimi-Gorji M, Ghajar M, Kakaee A H, et al. Modeling of the air conditions effects on the power and fuel consumption of the SI engine using neural networks and regression[J]. J Brazilian Soci Mech Sci Engi, 2017,39(2):375-384.
[16]	朱观宏, 宋康, 谢辉, 等. 基于物理模型和支持向量机的柴油机冷却系统故障诊断算法[J]. 汽车安全与节能学报, 2020,11(4):529-537.
	ZHU Guanhong, SONG Kang, XIE Hui, et al. Fault diagnosis algorithm of diesel engine cooling system based on physical model and support vector machine[J]. J Autom Safe Energ, 2020,11(4):529-537. (in Chinese)
[17]	张斌, 李见波, 吴淑梅. 基于MATLAB的柴油机建模及欧VI标定方法研究[J]. 内燃机工程, 2016,37(2):101-110.
	ZHANG Bin, LI Jianbo, WU Shumei. Investigation on diesel engine modelling based on MATLAB and EU VI calibration method[J]. Chin Int'l Combu Engi Engineer, 2016,37(2):101-110. (in Chinese)
[18]	胡松, 王贺春, 王银燕, 等. 面向控制的多次喷射柴油机仿真模型建模方法[J]. 内燃机学报, 2020,38(5):392-400.
	HU Song, WANG Hechun, WANG Yinyan, et al. Stablishment of control-oriented model for multi-injection diesel engine[J]. Trans CSICE, 2020,38(5):302-400. (in Chinese)
[19]	Salam S, Choudhary T, Pugazhendhi A, et al. A review on recent progress in computational and empirical studies of compression ignition internal combustion engine[J/OL]. Fuel, 2020, 279(5): 118469. https://doi.org/10.1016/j.fuel.2020.118469.
[20]	谢辉, 聂振华, 陈韬 . 基于. Bayes 正则化的柴油机神经网络燃烧预测模型[J]. 汽车安全与节能学报, 2020,11(3):345-354.
	XIE Hui, NIE Zhenhua, CHEN Tao, et al. Predictive neural network model of diesel combustion based on bayesian regularization[J]. J Autom Safe Energ, 2020,11(3):345-354. (in Chinese)
[21]	焦宇飞, 刘瑞林, 周广猛, 等. 不同海拔下重型共轨柴油机喷油参数虚拟标定[J]. 内燃机学报, 2020,38(6):522-529.
	JIAO Yufei, LIU Ruilin, ZHOU Guangmeng, et al. Virtual calibration of injection parameters for a heavy-duty common rail diesel engine at different altitudes[J]. Trans CSICE, 2020,38(6):522-529. (in Chinese)
[22]	戴金池, 庞海龙, 俞妍, 等. 基于LSTM神经网络的发动机NO_x排放预测[J]. 内燃机学报, 2020,38(5):457-463.
	DAI Jinchi, PANG Hailong, YU Yan, et al. Prediction of diesel engine NO_x emissions based on long-short term memory neural network[J]. Trans CSICE, 2020,38(5):457-463. (in Chinese)
[23]	Cho J, Song S. Prediction of hydrogen-added combustion process in T-GDI engine using artificial neural network[J/OL]. Appl Therm Engi, 2020, 181(8): 115974. https://doi.org/10.1016/j.applthermaleng.2020.115974.
[24]	Mehra R K, Duan Hao, Luo Sijie, et al. Experimental and artificial neural network (ANN) study of hydrogen enriched compressed natural gas (HCNG) engine under various ignition timings and excess air ratios[J/OL]. Appl Energ, 2018, 228(6): 736-754. https://doi.org/10.1016/j.apenergy.2018.06.085.
[25]	Fagundez J L S, Lanzanova T D M, Martins M E S, et al. Joint use of artificial neural networks and particle swarm optimization to determine optimal performance of an ethanol SI engine operating with negative valve overlap strategy[J/OL]. Energy, 2020, 204: 117892. https://doi.org/10.1016/j.energy.2020.117892.
[26]	Giakoumis E G. Driving and Engine Cycles[M]. Springer,Cham, Switzerland, 2016: 1-408.
[27]	Pavlovic J, Marotta A, Ciuffo B. CO2 emissions and energy demands of vehicles tested under the NEDC and the new WLTP type approval test procedures[J/OL]. Appl Energ, 2016, 177(2016): 661-670. http://dx.doi.org/10.1016/j.apenergy.2016.05.110.
[28]	Howell M N, Best M C. On-line PID tuning for engine idle-speed control using continuous action reinforcement learning automata[J]. Contr Engi Pract, 2000, 8(2):147-154.
[29]	ZHANG Yunfan, ZHOU Quan, LI Ziyang, et al. Intelligent transient calibration of a dual-loop EGR diesel engine using chaos-enhanced accelerated particle swarm optimization algorithm[J]. Proceed Institut Mecha Engi, Part D: J Autom Engi, 2019,233(7):1698-1711.
[30]	LI Ziyang, ZHOU Quan, ZHANG Yunfan, et al. Enhanced intelligent proportional-integral-like fuzzy knowledge-based controller using chaos-enhanced accelerated particle swarm optimization algorithm for transient calibration of air-fuel ratio control system[J]. Proceed Institut Mecha Engi, Part D: J Autom Engi, 2020,234(1):39-55.
[31]	ZHAO Dezong, LIU Cunjia, Stobart R, et al. An explicit model predictive control framework for turbocharged diesel engines[J]. IEEE Trans Ind Electr, 2014,61(7):3540-3552. doi: 10.1109/TIE.2013.2279353 URL
[32]	LI Ziyang, LI Ji, ZHOU Quan, et al. Intelligent air/fuel ratio control strategy with a PI-like fuzzy knowledge-based controller for gasoline direct injection engines[J]. Proceed Institut Mecha Engi, Part D: J Autom Engi, 2018,233(8):2161-2173.
[33]	张众杰, 刘瑞林, 周广猛, 等. 高海拔二级增压系统与喷油系统匹配模拟[J]. 内燃机学报, 2020,38(1):49-56.
	ZHANG Zhongjie, LIU Ruilin, ZHOU Guangmeng, et al. Simulation on performance matching of two-stage turbochargning system and common-rail fuel system at high altitudes[J]. Trans CSICE, 2020,38(1):49-56. (in Chinese)
[34]	XU Fang, CHEN Hong, GONG Xun, et al. Fast nonlinear model predictive control on FPGA using particle swarm optimization[J]. IEEE Trans Ind Electr, 2016,63(1):310-321. doi: 10.1109/TIE.2015.2464171 URL
[35]	ZHANG Yunfan. Optimization and control of a dual-loop EGR system in a modern diesel engine[D]. The University of Birmingham, Birmingham,UK, 2018.
[36]	Volkswagen. The modular electric drive matrix[EB/OL]. (2019-00-00), https://www.volkswagen-newsroom.com/en/modular-electric-drive-matrix-meb-3677.
[37]	CHANG’AN. CHANG’AN opens a new test centre and unveil blue core 1.5T engine[EB/OL]. (2019-00-00). http://www.changanuk.com/News-Media/changan-open-new-test-centre-and-unveil-blue-core-15t-engine.
[38]	Birch S. Mahle reveals modular,scalable integrated hybrid powertrain[EB/OL]. SAE International,2019. [2021-05-00], https://www.sae.org/news/2019/09/mahle-mmhd-hybrid-system.
[39]	Bayrak A E, Collopy A X, Epureanu B I, et al. A computational concept generation method for a modular vehicle fleet design[J]. 10th Annual Int'l Syst Conf, SysCon 2016 - Proceed, 2016: 1-8.
[40]	Silvas E, Hofman T, Murgovski N, et al. Review of optimization strategies for system-level design in hybrid electric vehicles[J]. IEEE Trans Vehi Tech, 2017,66(1):57-70.
[41]	Pourabdollah M, Egardt B, Murgovski N, et al. Convex optimization methods for powertrain sizing of electrified vehicles by using different levels of modeling details[J]. IEEE Trans Vehi Tech, 2018, 67(3):1881-1893.
[42]	ZHANG Lei, HU Xiaosong, WANG Zhenpo, et al. Multiobjective optimal sizing of hybrid energy storage system for electric vehicles[J]. IEEE Trans Vehi Tech, 2018, 67(2):1027-1035.
[43]	Shahverdi M, Mazzola M S, Grice Q, et al. Pareto front of energy storage size and series hev fuel economy using bandwidth-based control strategy[J]. IEEE Trans Transport Electr, 2016, 2(1):36-51.
[44]	XU Xiaoyang, SUN Hanqiao, LIU Yanfang, et al. Automatic enumeration of feasible configuration for the dedicated hybrid transmission with multi-degree-of-freedom and multiplanetary gear set[J]. J Mech Desig, Trans ASME, 2019,141(9):1-14.
[45]	ZHOU Quan, ZHANG Wei, CASH S, et al. Intelligent sizing of a series hybrid electric power-train system based on Chaos-enhanced accelerated particle swarm optimization[J/OL]. Appl Energ, 2017, 189: 588-601. http://dx.doi.org/10.1016/j.apenergy.2016.12.074.
[46]	WANG Xin, LIANG Qilian. Energy management strategy for plug-in hybrid electric vehicles via bidirectional vehicle-to-grid[J]. IEEE Syst J, 2017,11(3):1789-1798. doi: 10.1109/JSYST.4267003 URL
[47]	LV Chen, XING Yang, ZHANG Junzhi, et al. Levenberg-marquardt backpropagation training of multilayer neural networks for state estimation of a safety-critical cyber-physical system[J]. IEEE Trans Ind Inform, 2018,14(8):3436-3446. doi: 10.1109/TII.9424 URL
[48]	LV Chen, HU Xiaosong, Sangiovanni-Vincentelli A, et al. Driving-style-based codesign optimization of an automated electric vehicle: a cyber-physical system approach[J]. IEEE Trans Ind Electr, 2019, 66(4):2965-2975. doi: 10.1109/TIE.2018.2850031 URL
[49]	Mamun A Al, LIU Z, Rizzo D M, et al. An integrated design and control optimization framework for hybrid military vehicle using lithium-ion battery and supercapacitor as energy storage devices[J]. IEEE Trans Transport Electr, 2019,5(1):239-251.
[50]	ZHOU Quan, HE Yinglong, ZHAO Dezong, et al. Modified particle swarm optimization with chaotic attraction strategy for modular design of hybrid powertrains[J]. IEEE Trans Transport Electr, 2021,7(2):616-625.
[51]	牛亚卓, 聂国乐, 杨建军, 等. 基于多工况分析的插电式混合动力汽车节能控制策略[J]. 汽车安全与节能学报, 2020,11(4):546-552.
	NIU Yazhuo, NIE Guole, YANG Jianjun. Energy saving control strategy of PHEV based on multi-condition analysis[J]. J Autom Safe Energ, 2020,11(4):546-552. (in Chinese)
[52]	HUANG Yanjun, WANG Hong, Khajepour A, et al. A review of power management strategies and component sizing methods for hybrid vehicles[J/OL]. Renewable and Sustainable Energy Reviews, 2018, 96(April 2017): 132-144. https://doi.org/10.1016/j.rser.2018.07.020.
[53]	HU Yazhou, WANG Wenxue, LIU Hao, et al. Reinforcement learning tracking control for robotic manipulator with kernel-based dynamic model[J]. IEEE Trans Neural Networks Learning Syst, 2019, 31(9):3570-3578. doi: 10.1109/TNNLS.5962385 URL
[54]	LI Ji, ZHOU Quan, HE Yinglong, et al. Driver-identified supervisory control system of hybrid electric vehicles based on spectrum-guided fuzzy feature extraction[J]. IEEE Trans Fuzzy Syst, 2020,28(11):2691-2701. doi: 10.1109/TFUZZ.91 URL
[55]	PENG Jiankun, HE Hongwen, XIONG Rui. Rule based energy management strategy for a series-parallel plug-in hybrid electric bus optimized by dynamic programming [J/OL]. Appl Energ, 2016, 185: 1633-1643. http://www.sciemiddleclickncedirect.com/science/article/pii/S0306261915016049.
[56]	刘灵芝, 张冰战, 蒋通. 基于工况自适应的 PHEV 等效燃油最小策略[J]. 汽车安全与节能学报, 2020,11(3):371-378.
	LIU Lingzhi, ZHANG Bingzhan, JIANG Tong. Equivalent Consumption Minimization Strategy for PHEV Based on Driving Condition Adaptation[J]. J Autom Safe Energ. 2020,11(3):371-378. (in Chinese)
[57]	HE Yinglong, ZHOU Quan, Makridis M, et al. Multiobjective co-optimization of cooperative adaptive cruise control and energy management strategy for PHEVs[J]. IEEE Trans Transport Electr, 2020, 6(1):346-355.
[58]	Khayyam H, Bab-Hadiashar A. Adaptive intelligent energy management system of plug-in hybrid electric vehicle[J/OL]. Energy, 2014, 69: 319-335. http://dx.doi.org/10.1016/j.energy.2014.03.020.
[59]	ZHOU Quan, ZHANG Yunfan, LI Ziyang, et al. Cyber-physical energy-saving control for hybrid aircraft-towing tractor based on online swarm intelligent programming[J]. IEEE Trans Ind Inform, 2018,14(9):4149-4158. doi: 10.1109/TII.2017.2781230 URL
[60]	HOU Jun, SONG Ziyou. A hierarchical energy management strategy for hybrid energy storage via vehicle-to-cloud connectivity[J/OL]. Appl Energ, 2020, 257(Oct. 2019): 113900. https://doi.org/10.1016/j.apenergy.2019.113900.
[61]	HUANG Yanjun, WANG Hong, Khajepour A, et al. A review of power management strategies and component sizing methods for hybrid vehicles[J]. Renewable and Sustainable Energy Reviews, 2018,96:132-144. doi: 10.1016/j.rser.2018.07.020 URL
[62]	HUANG Yanjun, WANG Hong, Khajepour A, et al. Model predictive control power management strategies for HEVs: A review[J]. J Power Sources, 2017,341:91-106. doi: 10.1016/j.jpowsour.2016.11.106 URL
[63]	Martínez C M, CAO Dongpu. Integrated Energy Management for Electrified Vehicles[M/OL]. Butterworth-Heinemann, 2019. [2021-05-00], https://linkinghub.elsevier.com/retrieve/pii/B9780128150108000028. DOI: 10.1016/B978-0-12-815010-8.00002-8. doi: 10.1016/B978-0-12-815010-8.00002-8 URL
[64]	Silver D, HUANG Aja, Maddison C J, et al. Mastering the game of Go with deep neural networks and tree search[J]. Nature, 2016, 529(7587):484-489. doi: 10.1038/nature16961 pmid: 26819042
[65]	Bellman R. Dynamic programming and a new formalism in the calculus of variations[J]. Proceed National Academy of Sciences, 1954,40(4):231-235. doi: 10.1073/pnas.40.4.231 URL
[66]	Radac M B, Precup R E. Data-driven model-free slip control of anti-lock braking systems using reinforcement Q-learning[J]. Neurocomputing, 2018, 275:317-329. doi: 10.1016/j.neucom.2017.08.036 URL
[67]	LIU Teng, ZOU Yuan, LIU De-xing, et al. Reinforcement learning of adaptive energy management with transition probability for a hybrid electric tracked vehicle[J]. IEEE Trans Ind Electr, 2015,62(12):7837-7846. doi: 10.1109/TIE.2015.2475419 URL
[68]	LIU Chang, Murphey Y L. Optimal power management based on Q-learning and neuro-dynamic programming for plug-in hybrid electric vehicles[J]. IEEE Trans Neural Networks Learning Syst, 2019,31(6):1942-1954. doi: 10.1109/TNNLS.5962385 URL
[69]	SHUAI Bin, ZHOU Quan, LI Ji, et al. Heuristic action execution for energy efficient charge-sustaining control of connected hybrid vehicles with model-free double Q-learning[J]. Appl Energ, 2020,267: 114900. https://www.sciencedirect.com/science/article/pii/S0306261920304128.
[70]	HAN X, HE H, WU J, et al. Energy management based on reinforcement learning with double deep Q- learning for a hybrid electric tracked vehicle[J/OL]. Appl Energ, 2019, 254(1): 113708. https://doi.org/10.1016/j.apenergy.2019.113708.
[71]	ZHOU Quan, LI Ji, SHUAI Bin, et al. Multi-step reinforcement learning for model-free predictive energy management of an electrified off-highway vehicle[J]. Appl Energ, 2019, 255(2019):588-601.
[72]	DU Guodong, ZOU Yuan, ZHANG Xudong, et al. Intelligent energy management for hybrid electric tracked vehicles using online reinforcement learning[J/OL]. Appl Energ, 2019, 251(3): 113388. https://doi.org/10.1016/j.apenergy.2019.113388.
[73]	Lee H, Song C, Kim N, et al. Comparative analysis of energy management strategies for HEV : Dynamic programming and reinforcement learning[J]. IEEE Access, 2020,8:67112-67123. doi: 10.1109/Access.6287639 URL
[74]	HU Xiaosong, LIU Teng, QI Xue-wei, et al. Reinforcement learning for hybrid and plug-in hybrid electric vehicle energy management: recent advances and prospects[J]. IEEE Ind Electr Maga, 2019, 13(3):16-25.
[75]	MA He, LI Ziyang, Tayarani M, et al. Computational intelligence non-model-based calibration approach for internal combustion engines[J/OL]. J Dyna Syst, Measure, Contr, 2017, 140(4): 1-9. http://dynamicsystems.asmedigitalcollection.asme.org/article.aspx?doi=10.1115/1.4037835.
[76]	Al-Jarrah O Y, Maple C, Dianati M, et al. Intrusion detection systems for intra-vehicle networks: A review[J]. IEEE Access, 2019, 7:21266-21289. doi: 10.1109/ACCESS.2019.2894183
[77]	Sharma M, George J P. Digital twin in the automotive industry : Driving physical-digital convergence[R]. TATA Consultancy White Paper, 2019. https://www.tcs.com/content/dam/tcs/pdf/Industries/manufacturing/abstract/industry-4-0-and-digital-twin.pdf.
[78]	Ricardo. Virtual Calibration[EB/OL]. [2021-00-00], https://software.ricardo.com/product-families/software-solutions/virtual-calibration-en.
[79]	Continental Gmh. eHorizon[EB/OL]. [2021-00-00], https://www.continental-automotive.com/zh/Passenger-Cars/Vehicle-Networking/Software-Solutions-and-Services/eHorizon.
[80]	Birnie A. Using vehicle-to-cloud connectivity to extend electric vehicle range[EB/OL]. NXP website, 2019.[2021-05-00], https://www.nxp.com/applications/automotive/connectivity:AUTOMOTIVE-CONNECTIVITY.
[81]	Abuelsamid S, Gartner J. Connected Vehicles and the cloud - Enabling the future of the mobility user experience [R]. Amazaon Whitepaper, Q1,2018. [2021-05-00], https://d1.awsstatic.com/Industries/Automotive/V2/Navigant%20Research%20-%20Amazon%20White%20Paper%20Full%20-%204-24-2018.pdf.