Mode-switching-based active control of a powertrain system with non-linear backlash and flexibility for an electric vehicle during regenerative deceleration

SAE Technical Paper Series

et al. 2017

Self Cite

Recently, the development of braking assistance system has largely benefit the safety of both driver and pedestrians. A robust prediction and detection of driver braking intention will enable driving assistance system response to traffic situation correctly and improve the driving experience of intelligent vehicles. In this paper, two types unsupervised clustering methods are used to build a driver braking intention predictor. Unsupervised machine learning algorithms has been widely used in clustering and pattern mining in previous researches. The proposed unsupervised learning algorithms can accurately recognize the braking maneuver based on vehicle data captured with CAN bus. The braking maneuver along with other driving maneuvers such as normal driving will be clustered and the results from different algorithms which are K-means and Gaussian mixture model (GMM) will be compared. Additionally, the importance evaluation of features from raw dataset respect to driving maneuvers clustering will be proposed. The experiment data are collected from a pure electric vehicle in real world. Final results show that the proposed method can detect driver's braking intention in a very beginning moment with a high accuracy and the most important features for driving maneuver clustering are selected.

Section: K-means Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Recognizing Driver Braking Intention with Vehicle Data Using Unsupervised Learning Methods

Xing

SAE Technical Paper Series

et al. 2017

Self Cite

“…Sgn(S) is the sign function, and it equals to 1, 0, and -1, when the corresponding element of S is larger than 0, equals to 0, and is less than 0, respectively. Remark 2: It is well known that in standard SMC, the discontinuous sign function, sgn(S), may cause chatter when the state trajectories are approaching the sliding surfaces [31], [32].…”

Section: A Sliding Mode Controller Designmentioning

confidence: 99%

High-Precision Hydraulic Pressure Control Based on Linear Pressure-Drop Modulation in Valve Critical Equilibrium State

IEEE Trans. Ind. Electron.

Cao

2017

Self Cite

121

High precision and fast response are of great significance for hydraulic pressure control in automotive braking systems. In this paper, a novel sliding mode control based high-precision hydraulic pressure feedback modulation is proposed. Dynamical models of the hydraulic brake system including valve dynamics are established. An open loop load pressure control based on the linear relationship between the pressure-drop and coil current in valve critical open equilibrium state is proposed, and also experimentally validated on a hardware-in-the-loop test rig. The control characteristics under different input pressures and varied coil currents are investigated. Moreover, the sensitivity of the proposed modulation on valve's key structure parameters and environmental temperatures are explored with some unexpected drawbacks. In order to achieve better robustness and precision, a sliding mode control based closed loop scheme is developed for the linear pressure-drop modulation. Comparative tests between this method and the existing methods are carried out. The results validate the effectiveness and superior performance of the proposed closed loop modulation method.Index Terms-Sliding mode control, linear pressuredrop modulation, switching valve, hardware-in-the-loop test, experimental validation.

“…In designing the sliding-mode controller, an integral-type sliding surface S is chosen with the error term e defined in equations (8) and (9).…”

Section: /20/2015mentioning

confidence: 99%

Cyber-Physical System Based Optimization Framework for Intelligent Powertrain Control

SAE Int. J. Commer. Veh.

Zhao

et al. 2017

Self Cite

The interactions between automatic controls, physics, and driver is an important step towards highly automated driving. This study investigates the dynamical interactions between human-selected driving modes, vehicle controller and physical plant parameters, to determine how to optimally adapt powertrain control to different human-like driving requirements. A cyber-physical system (CPS) based framework is proposed for co-design optimization of the physical plant parameters and controller variables for an electric powertrain, in view of vehicle's dynamic performance, ride comfort, and energy efficiency under different driving modes. System structure, performance requirements and constraints, optimization goals and methodology are investigated. Intelligent powertrain control algorithms are synthesized for three driving modes, namely sport, eco, and normal modes, with appropriate protocol selections. The performance exploration methodology is presented. Simulationbased parameter optimizations are carried out according to the objective functions. Simulation results show that an electric powertrain with intelligent controller can perform its tasks well under sport, eco, and normal driving modes. The vehicle further improves overall performance in vehicle dynamics, ride comfort, and energy efficiency. The results validate the feasibility and effectiveness of the proposed CPS-based optimization framework, and demonstrate its advantages over a baseline benchmark.