A comparison of statistical learning approaches for engine torque estimation

Rakotomamonjy, Alain; Riche, Rodolphe Le; Gualandris, David; Harchaoui, Zaïd

doi:10.1016/j.conengprac.2007.03.009

Cited by 15 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover only a static behavior is taken into account with those maps. To overcome this drawback, some methods deal with a dynamic model of the engine to estimate the torque [12] [13]. Nevertheless problems appear due to the parameter identification techniques of nonlinear systems and requirements of important sets of data.…”

Section: Introductionmentioning

confidence: 99%

Discrete angular torque observer applicated to the engine torque and clutch torque estimation via a dual-mass flywheel

Losero¹,

Lauber²,

Guerra³

2015

2015 IEEE 10th Conference on Industrial Electronics and Applications (ICIEA)

View full text Add to dashboard Cite

The interest in engine torque and clutch torque estimation is important in the automotive industry. They are determinant variables in engine and powertrain management like hybrid engine vehicle, automated transmission and energy saving strategies. An instantaneous brake engine torque and transmitted clutch torque estimation method based on discrete angular domain fuzzy observer using a torsion angle calculation is proposed in this paper. It is applied on a filtration device; the dual mass flywheel. The observer permits to obtain good experimental results of the engine torque and clutch torque estimation.

show abstract

Section: Introductionmentioning

confidence: 99%

Discrete angular torque observer applicated to the engine torque and clutch torque estimation via a dual-mass flywheel

Losero¹,

Lauber²,

Guerra³

2015

2015 IEEE 10th Conference on Industrial Electronics and Applications (ICIEA)

View full text Add to dashboard Cite

show abstract

“…For this, linear models cannot estimate the torque accurately, and support vector machines (SVM) have good results, but for such problems, nonlinear neural network obviously has greater advantages. 24 The desired engine torque model can be obtained by training the experimental engine data. 19,25 However, the neural network requires considerable data and long training times.…”

Section: Introductionmentioning

confidence: 99%

Coordinated control strategy for mode switching of power-split hybrid electric bus

Yang

Weilai

Kunyu

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

In the dynamic process of mode switching of the power-split hybrid electric bus, the vehicle will have longitudinal shock due to the drastic change of the two motors’ torque and the engine’s slow response. To solved this problem, this paper will focus on the process of switching from pure electric mode to hybrid drive mode, considered the operational state changes before and after engine ignition, limited the torque fluctuation transmitted from the front planetary set to the output shaft based on the idea of motor compensation, and calculated the motor compensation torque of the rear planetary set to compensate the torque fluctuation of the output shaft, to reduce the jerk. Firstly, the dynamic models of the transmission system before and after the engine ignition are established, respectively, and then the dynamic torque of the engine is estimated by XGBoost. The estimated value is input into the model predictive controller (MPC) to track the engine speed and calculate the torque fluctuation generated by the front planetary set on the output shaft. Then, according to the estimated value of the engine torque and the predicted value of the engine’s speed, the compensation torque is calculated by the sliding mode controller (SMC). Finally, the vehicle model is built with AVL CRUISE and MATLAB/Simulink software to verify the mode switching control effect of hybrid electric bus under typical urban conditions in China. The results showed that this control strategy significantly reduces the jerk of the mode switching process.

show abstract

“…More recently, Support Vector Machines (SVMs) have been proposed as a new, though related, approach for nonlinear black box modeling [23,51,39] or monitoring [41] of automotive engines.…”

Section: Neural Network In Engine Controlmentioning

confidence: 99%

On Learning Machines for Engine Control

Bloch

Lauer

Colin

2008

Studies in Computational Intelligence

View full text Add to dashboard Cite

Summary. The chapter deals with neural networks and learning machines for engine control applications, particularly in modeling for control. In the first section, some basics on the common features of engine control are recalled, based on a layered engine management structure. Then the use of neural networks for engine modeling, control and diagnosis is briefly described. The need for descriptive models for model-based control and the link between physical models and black box models are emphasized at the end of this section by exposing the grey box approach taken in this chapter. The second section introduces the neural models most used in engine control, namely, MultiLayer Perceptrons (MLP) and Radial Basis Function (RBF) networks. A more recent approach, known as Support Vector Regression (SVR), to build models in kernel expansion form is then presented. The third section is devoted to examples of application of these models in the context of turbocharged Spark Ignition (SI) engines with Variable Camshaft Timing (VCT). This specific context is representative of modern engine control problems. In the first example, the airpath control is studied, where open loop neural estimators are combined with a dynamical polytopic observer. The second example considers modeling the in-cylinder residual gas fraction by Linear Programming SVR (LP-SVR), based on a limited amount of experimental data and a simulator built from prior knowledge. Each example tries to show that models based on first principles and neural models must be joined together in a grey box approach to obtain efficient and acceptable results.

show abstract

A comparison of statistical learning approaches for engine torque estimation

Cited by 15 publications

References 17 publications

Discrete angular torque observer applicated to the engine torque and clutch torque estimation via a dual-mass flywheel

Discrete angular torque observer applicated to the engine torque and clutch torque estimation via a dual-mass flywheel

Coordinated control strategy for mode switching of power-split hybrid electric bus

On Learning Machines for Engine Control

Contact Info

Product

Resources

About