In the process of cycle cylinder deactivation, the different proportion of cylinder deactivation between adjacent working cycles will cause the problem of uneven operation of each cylinder. In this paper, a random dynamic cylinder deactivation (RD-CDA) control method based on nonlinear model prediction is proposed. The RBF neural network model of the RD-CDA system is built. The K-means algorithm is applied to the offline training of the center position c of the hidden layer node. The P-nearest algorithm is used to train the hidden layer node width σ offline. The recursive least squares (RLS) algorithm is applied to train the output layer weight vector w online. The online adaptive change of the model is realized, and the model verification is carried out. Then, the nonlinear model predictive control system structures with the minimum torque fluctuation and brake specific fuel consumption rate (BSFC) are built respectively. Under different working conditions, the average torque fluctuation per cycle is improved by about 9% to 18.75%, and the average BSFC is improved by about 2 % -3.9 %, which verifies the effectiveness of this strategy in reducing the dynamic fluctuation of random dynamic cylinder deactivation torque and improving fuel economy.
KutlarOAArslanHCalikAT.Methods to improve efficiency of four stroke, spark ignition engines at part load. Mana2005; 46(20): 3202–3220.
2.
ZhaoJXiQWangS, et al. Improving the partial-load fuel economy of 4-cylinder SI engines by combining variable valve timing and cylinder-deactivation through double intake manifolds. Appl Therm Eng2018; 141: 245–256.
3.
McGheeMWangZBechA, et al. The effects of cylinder deactivation on the thermal behaviour and fuel economy of a three-cylinder direct injection spark ignition gasoline engine. Proc. Inst. Mech. Eng. Part J. Automob. Eng2019; 233(11): 2838–2849.
4.
DingCRobertsLFainDJ, et al. Fuel efficient exhaust thermal management for compression ignition engines during idle via cylinder deactivation and flexible valve actuation. Int J Engine Res2016; 17(6): 619–630.
5.
LeeNParkJLeeJ, et al. Estimation of fuel economy improvement in gasoline vehicle using cylinder deactivation. Energies2018; 11(11): 3084.
6.
DatLVShiaoY.Proposing a valve train system for cylinder deactivation in SI engines. Trans Can Soc Mech Eng2017; 41(4): 543–553.
7.
KutlarOAArslanHCalikAT.Skip cycle system for spark ignition engines: an experimental investigation of a new type working strategy. Energy Convers Manag2007; 48(2): 370–379.
8.
ShiaoYDatLV.Efficiency improvement for an unthrottled SI engine at part load. Int J Adv Automot Technol2012; 13(6): 885–893.
9.
Muhamad SaidMFAbdul AzizABAbdul LatiffZ, et al. Investigation of cylinder deactivation (CDA) strategies on part load conditions, in: 2014: pp. 2014-01–2012549. https://doi.org/10.4271/2014-01-2549.
10.
AbasMMartinez-BotasR.Engine operational benefits with cylinder deactivation in Malaysian urban driving conditions, in: 2015: pp. 2015-01–2010983. https://doi.org/10.4271/2015-01-0983.
11.
BechAShaylerPJMcGheeM.The effects of cylinder deactivation on the thermal behaviour and performance of a three cylinder spark ignition engine. SAE Int J Engines2016; 9(4): 1999–2009.
12.
ChenSKMandalAChienL-C, et al. Machine learning for misfire detection in a dynamic skip fire engine. SAE Int J Engines2018; 11(6): 965–976.
13.
WilcuttsMSwitkesJShostM, et al. Design and benefits of dynamic skip fire strategies for cylinder deactivated engines. SAE Int J Engines2013; 6(1): 278–288.
14.
ChienLCYounkinsMWilcuttsM.Modeling and simulation of airflow dynamics in a dynamic skip fire engine, in: 2015: pp. 2015-01–2011717. https://doi.org/10.4271/2015-01-1717.
15.
Eisazadeh-FarKYounkinsM.Fuel economy gains through dynamic-skip-fire in spark ignition engines, in: 2016: pp. 2016-01–2010672. https://doi.org/10.4271/2016-01-0672.
16.
Van EssJWolkBFuschettoJ, et al. Method to compensate fueling for individual firing events in a four-cylinder engine operated with dynamic Skip Fire. SAE Int J Engines2018; 11(6): 977–991.
17.
MandalAArvanitisAChenSK, et al. Vibration rating prediction using machine learning in a dynamic skip fire engine. SAE Int J Adv Curr Pr -mob2019; 1(4): 1491–1501.
18.
LuoXHashemiSSubramanianR, et al. Fast catalyst light-off with dynamic skip fire. SAE Int J Adv Curr Pr -mob2020; 2(4): 1849–1861.
19.
WilcuttsMNagashimaMEisazadeh-FarK, et al. Electrified dynamic skip fire (eDSF): Design and benefits, in: 2018: pp. 2018-01–2010864. https://doi.org/10.4271/2018-01-0864.
20.
Ortiz-SotoEWolkBChenHMYounkins, mDSF: Improved fuel efficiency, drivability and vibrations via dynamic skip fire and Miller cycle synergies, in: 2019: pp. 2019-01–2010227. https://doi.org/10.4271/2019-01-0227.
21.
ScassaMGeorgeSNencioniM, et al. Dynamic skip fire applied to a diesel engine for improved fuel consumption and emissions, in: 2019: pp. 2019-01–2010549. https://doi.org/10.4271/2019-01-0549.
22.
GottschalkWFinkRSchultalbersM.Investigations on ventilation strategies for SI cylinder deactivation based on a variable valve train, in: 2016: pp. 2016-01–2012346. https://doi.org/10.4271/2016-01-2346.
23.
YüksekLÖzenerOSandalcıT.Cycle-skipping strategies for pumping loss reduction in spark ignition engines: an experimental approach. Energy Convers Manag2012; 64: 320–327.
24.
HuMChangSLiuL, et al. Design and analysis of skip fire valve strategies based on electromagnetic valve train. Appl Therm Eng2018; 129: 833–840.
25.
HuMChangSXuY, et al. Study on valve strategy of variable cylinder deactivation based on electromagnetic intake Valve Train. Appl Sci2018; 8(11): 2096.
26.
ZammitJ-PMcGheeMJShaylerPJ, et al. The influence of cylinder deactivation on the emissions and fuel economy of a four-cylinder direct-injection diesel engine. Proc. Inst. Mech. Eng. Part J. Automob. Eng2014; 228(2): 206–217.
27.
TangXZhangDLiuT, et al. Research on the energy control of a dual-motor hybrid vehicle during engine start-stop process. Energy2019; 166: 1181–1193.
28.
SoloiuVKnowlesARCarapiaCE, et al. n-butanol and oleic acid methyl ester, combustion and NVH characteristics in reactivity controlled compression ignition. Energy2020; 207: 1118183.
29.
SerranoJRoutledgeGLoN, et al. Methods of evaluating and mitigating NVH when operating an engine in dynamic Skip Fire. SAE Int J Engines2014; 7(3): 1489–1501.
30.
LeoneTGPozarM.Fuel economy benefit of cylinder deactivation - Sensitivity to vehicle application and operating constraints, in: 2001: pp. 2001-01–2003591. https://doi.org/10.4271/2001-01-3591.
31.
RitzmannJZsigaNPeterhansC, et al. A control strategy for cylinder deactivation. Control Eng Pract2020; 103: 104566.
32.
KambrathJKAlexanderAAWangY, et al. Dynamic analysis of diesel generator set under cylinder deactivation. In: 2017 IEEE Transp. Electrification Conf. Expo ITEC, IEEE, Chicago, IL, USA, 2017: pp. 370–375. https://doi.org/10.1109/ITEC.2017.7993299.
33.
DongSZhangYHeZ, et al. Investigation of support vector machine and back propagation artificial neural network for performance prediction of the organic Rankine cycle system. Energy2018; 144: 851–864.
34.
BenghanemMMellitA.Radial basis function network-based prediction of global solar radiation data: application for sizing of a stand-alone photovoltaic system at Al-Madinah, Saudi Arabia. Energy2010; 35(9): 3751–3762.
35.
DongX-JShenJ-NHeG-X, et al. A general radial basis function neural network assisted hybrid modeling method for photovoltaic cell operating temperature prediction. Energy2021; 234: 121212.
36.
HanYFanCGengZ, et al. Energy efficient building envelope using novel RBF neural network integrated affinity propagation. Energy2020; 209: 118414.
37.
HuangJXiaoQLiuJ, et al. Modeling heat transfer properties in an ORC direct contact evaporator using RBF neural network combined with EMD. Energy2019; 173: 306–316.
38.
ShiWYangJTangT.RBF NN based marine diesel engine generator modeling. In: Proc. 2005 Am. Control Conf. 2005, IEEE, Portland, OR, USA, 2005: pp. 2745–2749. https://doi.org/10.1109/ACC.2005.1470384.
39.
HaykinSS.Neural networks: a comprehensive foundation, Nachdr., Macmillan. [u.a.] New York, NY: Prentice Hall PTR, 1995.
40.
FuquanXYuelinLAifanL, et al. Gasoline engine intake flow forecast study of chaotic RBF neural network. In: 2015 Seventh Int. Conf. Meas. Technol. Mechatron. Autom., IEEE, Nanchang, China, 2015: pp. 506–511. https://doi.org/10.1109/ICMTMA.2015.129.
41.
CuiH.Research of optimizing ignition control system in gaseous fuel engine based on RBF neural network. In: 2008 Int. Conf. Intell. Comput. Technol. Autom. ICICTA, IEEE, changsha, Hunan, 2008: pp. 399–403. https://doi.org/10.1109/ICICTA.2008.482.
42.
ShiYYuD-LTianY, et al. Air–fuel ratio prediction and NMPC for SI engines with modified Volterra model and RBF network. Eng Appl Artif Intell2015; 45: 313–324.
43.
Cordeiro de AmorimRMakarenkovV.On k-means iterations and Gaussian clusters. Neurocomputing2023; 553: 126547.
44.
ZhangHLiJZhangJ, et al. Speeding up k-means clustering in high dimensions by pruning unnecessary distance computations. Knowl.-Based Syst2024; 284: 111262.
45.
HaqIUKhanDMHamrazM, et al. Optimal -k nearest neighbours based ensemble for classification and feature selection in chemometrics data. Chemometr Intell Lab Syst2023; 240: 104882.
46.
YangPBChanYJYazdiSK, et al. Optimisation and economic analysis of industrial-scale anaerobic co-digestion (ACoD) of palm oil mill effluent (POME) and decanter cake (DC) using machine learning models: A comparative study of Gradient Boosting Machines (GBM), K-nearest neighbours (KNN), and random forest (RF). J Water Process Eng2024; 58: 104752.
47.
WangNZhaoE.A new method for feature selection based on weighted k-nearest neighborhood rough set. Expert Syst Appl2024; 238: 122324.
48.
PaleologuCBenestyJStanciuC-L, et al. Recursive least-squares algorithm based on a third-order tensor decomposition for low-rank system identification. Signal Process2023; 213: 109216.
49.
ThannoonHHHashimIA.Efficient enhanced recursive least square algorithm adaptive filtering scheme for artifacts removal in ECG signals. Electr Eng Electron Energy2023; 6: 100318.
50.
FengSHongWXieF, et al. Influence of stratified charge organized by double injection strategy on combustion and emissions on an EGR diluted GDI engine. Appl Therm Eng2019; 158: 113803.
51.
JonscherCMöllerSLieseckeL, et al. Heteroscedastic Gaussian processes for data normalisation in probabilistic novelty detection of a wind turbine. Eng Struct2024; 305: 117786.
52.
TangYShangLZhangR, et al. Hybrid divergence based on mean absolute scaled error for incipient fault detection. Eng Appl Artif Intell2024; 129: 107662.
