Search

The presented control scheme in this paper aims at stabilizing uncertain time-delayed systems requiring all states to change within the preset time-varying constraints. The controller design framework is based on the backstepping method, drastically simplified by the dynamic surface control technique. Meanwhile, the radius basis function neural networks are utilized to deal with the unknown items. To prevent all state variables from violating time-varying predefined regions, we employ the time-varying barrier Lyapunov functions during the backstepping procedure. Moreover, appropriate Lyapunov-Krasovskii functionals are used to cancel the influence of the time-delay terms on the system's stability. Under the presented control laws and Lyapunov analysis, it is proven that constraints on all state variables are not breached, good tracking performance of desired output is achieved, and all signals in the closed-loop systems are bounded. The effectiveness of our control scheme is confirmed by a simulation example.

The mode transition process (MTP) from electric mode to hybrid electric mode (EM-to-HM) will cause the deterioration in occupant comfort of PHEV, to tickle this issue, a torsional oscillation-considered mode transition coordinated control strategy and a novel general evaluation index for MTP are developed in this research, the quality of mode transition and transient torsional oscillation of gears (TTOGs) during MTP are taken into consideration comprehensively. An action dependent heuristic dynamic programming algorithm which takes the vehicle jerk, friction loss and TTOGs as evaluation index is used to optimize the pressure curve of clutch oil and the compensation torque of motor in the entire EM-to-HM process. Finally, the simulation results and hardware-in-the-loop tests show that vehicle jerk and TTOGs are suppressed, and the driving comfort can be improved accordingly.

Advantages of planetary gear powertrain (PGT) for electric vehicles (EVs) are the high degree of efficiency, various reduction ratio, stress distribution by the planet gear and compaction in designing driving system. However there is noise in running at high rotational speed, so the transient torsional vibration suppression of the PGT for EVs become extremely essential and urgent. This study presents a 4 + N degree of freedom (DOF) nonlinear torsional system that essentially describes a PGT of EVs example, and further study on influence of novel TSB modification on transient vibration of planetary gear powertrain for an electric vehicle. In particular, the vibration of the PGT during the speed-up process, as excited by dynamic torque of motor generator (MG), time-varying mesh stiffness of front and back gear teeth, and also teeth backlashes, are investigated using a nonlinear torsional transient model. Then a full PGT model during the speed-up process is proposed and numerically solved to obtain the transient vibration acceleration. Dynamic response results of the PGT are also successfully compared and analyzed under different teeth backlashes. Finally, an improved genetic algorithm is applied to construct optimal relationship between the transient vibration and the TSB modification, and further the optimum three-dimensional TSB modification of sun-gear is finally obtained. The simulation and experiment results indicated that the proposed novel TSB modification method effectively suppressed the PGT transient vibration and vehicle jerk, at the same time, improved the ride comfort during the high-speed driving mode.

This paper presents a comprehensive dynamic efficiency model for the overall powertrain efficiency that considers the internal combustion engine and electric motor generators in depth as well as a planetary coupling transmission system of PHEVs example. In particular, the dynamic forces of planetary coupling transmission system with an effect on the dynamic transmission efficiency are taken into consideration. Then a dynamic efficiency optimization strategy is proposed to improve the fuel economy, and an improved dynamic efficiency optimization strategy, consisting in adding to the dynamic efficiency optimization strategy a penalty coefficient, is applied to reach the trade-off between energy consumption and fatigue life of planetary coupling transmission system. Eventually, the dynamic efficiency optimization strategy and improved dynamic efficiency optimization strategy are validated by hardware-in-the-loop experiments. The main contribution of this study is to explore a novel way to optimize the comprehensive dynamic efficiency of whole powertrain, and also improve ride comfort by avoiding planetary coupling transmission system working in the inefficient resonance region.

This paper investigates the fault-tolerant path following control problem of autonomous ground electric vehicles with in-wheel motors through hierarchical control strategy. The sliding mode observer with boundary layer is designed to estimate the vehicle state, and the time-delay estimation method is used to compute the actuator fault. Considering the actuator fault, the fault-tolerant path following control strategy is proposed, in which the upper layer controller is developed to achieve path following control and guarantee vehicle stability simultaneously by sliding mode control method, and the lower layer controller is presented to achieve the control efforts of upper layer controller by adaptive orientated tire force allocation method. The simulations are implemented in the CarSim-Simulink co-simulation platform, and the simulation results have verified the effectiveness of proposed fault-tolerant path following control method.

One of the major issues for hybrid electric vehicles (HEVs) powertrain is the torsional vibration in the process of speed-up condition, which is unavoidable. The broader goal of this article is to re-examine the classical gear transmission machinery transient vibration problem in the context of a 4 + N degree of freedom nonlinear torsional system that essentially describes a planetary coupling transmission system (PCTS) of HEVs example, and further provide a new method for power allocation of multi-power sources considering speed-up transient vibration of planetary power-split HEVs driveline system. In particular, resonant amplifications during acceleration, as excited by angular displacement-based meshing stiffness of gear teeth, are investigated using a nonlinear torsional model, and the transient vibration predictions are successfully compared with test bench results. Then a quasi-linear model during acceleration process is proposed and numerically solved to obtain the transient vibration acceleration as well as its envelope curve. Dynamic response results of PCTS are also successfully compared and analyzed under different speed-allocation rules. Finally, an improved genetic algorithm method is applied to construct optimal relationship between the motor speeds and vehicle speeds, and the influences of vibration character and energy consumption are successfully considered in multi-optimized function. Experimental results under the speed-up condition show that transient vibration acceleration of the optimized powertrain is decreased within the safe range, thus new power-allocation solutions provide more insight to the enhancement of planetary power-split HEVs quality.

Functionalized graphene (PNFR@RGO) has been fabricated by decorating chemically reduced graphene oxide (RGO) with 9,10-dihydro-9-oxa-10-phosphaphenanthrene-10-oxide (DOPO) and branched polyethylenimine (BPEI) in this work. PNFR@RGO is then used to reduce the flammability of polylactic acid (PLA) via a melt compounding protocol. X-ray photoelectron spectroscopy (XPS) and Infrared spectroscopy (IR) have confirmed the successful fabrication of the target PNFR@RGO. The chemical decoration introduces phosphorus and nitrogen elements to the GO which can combine the formation of compact char barriers from graphene nanosheets and the elimination of free radicals when ignited or heated. The results show that the degradation temperature in air is increased and the heat release rate (HRR) is reduced. With the addition of 4 wt% PNFR@RGO, the average specific extinction area (ASEA) and the total smoke release (TSR) of PLA are noticeably suppressed by 92% and 79%, respectively. This is attributed to the combination of the corridor barrier functions of RGO and the radical-scavenging effects of PNFR.

A novel path and velocity planning method for lane changing collision avoidance of intelligent vehicle based on cubic 3-D Bezier curve is proposed in this paper to enhance the flexibility of path and guarantee the conformity to the realistic lane changing maneuver. Owing to the characteristic of 3-D Bezier curve, the velocity information is appended to the path to establish a real-time correspondence between them. In the XY plane, the integrated path is divided into a collision avoidance path and a lane changing path, which is combined with two asymmetrical Bezier curves. And the velocity planning of two paths is implemented by the same curve in the Z axis. The objective functions and dynamic constraints are formulated to solve the optimal problems of the path and velocity planning for satisfying different traffic situations. The simulations are performed in the CarSim-Simulink co-simulation platform and the results show the performance and effectiveness of the proposed approach.

A novel vision guided intelligent vehicle (IV) trajectory tracking control algorithm based on expected yaw velocity is proposed to compensate for traditional vision guided trajectory tracking controller limitations in robustness and trajectory tracking accuracy. In this paper, the structure and mechanism of trajectory tracking controller based on expected yaw velocity is briefly introduced at first. The designed trajectory tracking controller models of IV system are then derived through the dynamic models and motion models of IV by using Matlab/Simulink. Simulations under two different road conditions and different preview distances are used to validate the superiority of designed trajectory tracking controller in comparison with traditional vision guided trajectory tracking controller. The effectiveness of designed trajectory tracking controller has been verified by simulation results, in which the robustness and trajectory tracking accuracy of designed trajectory tracking controller has been improved significantly. Finally, the novel controller is designed based on Simulink results, and test results reconfirm that the partial performances of controller effectively.

In the path following process, once vehicle steering system fails, the common path following control system will not work properly, and even worse, the vehicle will be seriously deviated from the ideal path and the risk of vehicle instability will also increase. Reliable fault-tolerant control strategy can promote the autonomous vehicle to maintain stability and path following accuracy in case of failure. In this paper, a passive fault-tolerant path following control method of autonomous distributed drive electric vehicle is presented considering the vehicle steering system fault. The reduced-order Kalman filter is applied to estimate the vehicle sideslip angle and the vehicle steering system fault. The hierarchical control strategy was developed, and in the upper layer controller, the adaptive sliding mode control method is proposed to facilitate the fault-tolerant path following controller and used to improve the lateral stability and anti-roll performance of vehicle and ensure path following accuracy at the same time, using the estimated sideslip angle and steering system fault as inputs. In the lower layer controller, a novel adaptive orientated tire force allocation method is proposed to execute the control efforts of upper layer controller. The simulations are implemented in the CarSim-Simulink co-simulation platform, and the effectiveness of proposed fault-tolerant path following control method is verified.

A simultaneous path following and lateral stability control method was presented for four-wheel independent drive and four-wheel independent steering (4WD-4WS) autonomous electric vehicles based on Hamilton energy function with the actuator saturation being considered in this paper. The hierarchical control strategy including upper layer controller and lower layer controller is used for simultaneous path following and lateral stability control. In the upper layer controller, the vehicle motion controller is designed using Hamilton energy function control theory and the convergence and stability of controller was proved, the control demand of simultaneous path following and lateral stability was obtained and messaged to the lower layer controller. In the lower layer controller, the orientated tire force allocation method was used to execute the control demand by real-time tire force allocation control of four wheels. The simulations are performed in the CarSim-Simulink co-simulation platform, and the effectiveness of proposed control method was verified.

Superhydrophobic surface (SHS) has always been considered to be favorable for reducing drag force due to the air layer in surface asperities, however, debates over whether such surface could reduce the drag force still remains. In this study, steel surface was sprayed with suspension that contained PMMA and hydrophobic nanoscale silica, and the obtained surface showed variable contact angle from 94° to 159°, sliding angle from 90° to 2°, suggesting the controllable wettability; besides, the facile preparation process showed promising prospect to be scaled up. We studied the drag-reducing property of treated steel via sailing test and rotary disc test, results showed that SHS could efficiently reduce the drag force under low fluidic condition; surprisingly, for the intense turbulent flow, the SHS exhibited a drag-increasing effect, indicating that such surface only functions under mild flow condition.

Electric regenerative braking systems have drawn much attention in the trends of energy-saving and emission-reduction requirements for electric vehicles. However, the significant differences between regenerative braking transmission chains and the traditional ones have lead to increasing oscillation and noise of electrical powertrain. With the application of planetary-gear transmission chains, adopting an advanced regenerative braking method becomes practical. This paper develops a novel regenerative braking method for transient torsional oscillation suppression of planetary-gear electrical powertrain (PGEP), which uses an angle-varying mesh stiffness-considered transmission model and a genetic algorithm-based method for allocation of electric regenerative braking torque. Simulations are conducted with various angle-varying mesh stiffness and backlash to compare the transient torsional oscillation-suppression performance of PGEP during regenerative braking transition process. For an initial speed of 80 km/h, simulation results show that the proposed torsional oscillation-considered electric regenerative braking torque allocating method performs the best comparing with the traditional methods, which has a 55% reduction in vehicle jerk and 36% improvement in torsional oscillation of PGEP. The AVL experiment results also demonstrated that torsional oscillation-considered regenerative braking method has considerable benefits in both transient torsional oscillation suppression of PGEP as well as enhancement of driving comfort.

In this paper, a novel piecewise affine (PWA) modeling framework and a hybrid optimal control scheme based on the developed PWA model for the intelligent vehicle longitudinal dynamics are proposed. The proposed methodology approximates the nonlinear characteristics of the system major components, i.e. the engine, the automatic transmission and the tire, using the PWA representation method firstly. Due to the affine submodel switching behaviors of the PWA model and the fact that the intelligent vehicle must be worked in two discrete modes (driving and braking) for regulating the longitudinal velocity automatically, the control procedure of the intelligent vehicle longitudinal dynamics actually shows a hybrid nature with both continuous variables and discrete events. Thus, to further solve the system hybrid control problem, the intelligent vehicle longitudinal dynamics whose major components are modelled in the PWA form is further transformed into a computational mixed logical dynamical (MLD) model in this work, based on which a hybrid model predictive control (HMPC) strategy, which can simultaneously calculate the switching sequences of the intelligent vehicle longitudinal working modes (binary control inputs) and the throttle angle and braking pressure (continuous control inputs) during autonomous velocity regulation, is designed by solving a mixed-integer quadratic programming (MIQP) problem. Simulation and experimental results are finally provided to verify the superior control performance of the designed hybrid controller in longitudinal velocity regulation under typical driving conditions.

Traffic state prediction is an essential problem with considerable implications in the intelligent transportation system. This paper puts forward an approach for predicting urban road traffic states based on ISOMAP manifold learning. By establishing a distance measurement that represents the overall geometric structure based on the Isometric Feature Mapping (ISOMAP) algorithm, this approach utilizes all consistent information regarding the traffic flow, thus improving the prediction accuracy of the road traffic state. The experimental results indicate that, compared with a traditional prediction approach, the equality coefficient has a bigger increase in value and a much lower prediction error. The traffic state prediction approach based on ISOMAP manifold learning achieves a higher level of accuracy.

Recovering missing values (MVs) from incomplete data is an important problem for many real-world applications. Previous research efforts toward solving MVs problem primarily exploit the global and/or local structure of data. In this work, we propose a novel MVs imputation method by combing sample self-representation strategy and underlying local linear structure of data in a uniformed framework. Specifically, the proposed method consists of the following steps. First, an existing method is applied to obtain the first-round estimation of MVs. Then, a graph, characterizing local proximity structure of data, is constructed based on imputed data. Next, a novel model coined as graph regularized local self-representation (GRLSR) is proposed by integrating two crucial elements: local self-representation and graph regularization. The former assumes each sample can be well represented (reconstructed) by linearly combining the neighboring samples while the latter further requires the neighboring samples should not deviate too much from each other after reconstruction. By doing so, MVs can be more accurately restored due to the joint imputation as well as local linear reconstruction. We also develop an effective alternating optimization algorithm to solve GRLSR model, thereby achieving final imputation. The convergence and computational complexity analysis of our method are also presented. To evaluate our method, extensive experiments are conducted on both traffic flow dataset and UCI benchmark datasets. The results demonstrate the effectiveness of our proposed method compared with a set of widely-used competing methods.

In this paper, the influence of interference torques, time delay and noise of automatic steering system (ASS) on trajectory tracking accuracy of intelligent vehicle (IV) is analyzed to further study the coupling mechanism between automatic steering control system and IV trajectory tracking control system. The system architecture of ASS and IV trajectory tracking control system is briefly introduced at first. The correlation controller models are then established based on nonlinear ASS and IV dynamic models. The influence of ASS on the trajectory tracking of IV is validated through simulations with various forms of ASS nonlinear factors. And the results show clearly that the interference torques of ASS have great influence on the accuracy of IV trajectory tracking system, especially in the lateral deviation of IV trajectory tracking system, the noise and time delay of ASS have almost no influence on lateral deviation and azimuth deviation of IV trajectory tracking.

Due to the development of deep learning networks, a salient object detection based on deep learning networks, which are used to extract the features, has made a great breakthrough compared to the traditional methods. At present, the salient object detection mainly relies on very deep convolutional network, which is used to extract the features. In deep learning networks, an dramatic increase of network depth may cause more training errors instead. In this paper, we use the residual network to increase network depth and to mitigate the errors caused by depth increase simultaneously. Inspired by image simplification, we use color and texture features to obtain simplified image with multiple scales by means of region assimilation on the basis of super-pixels in order to reduce the complexity of images and to improve the accuracy of salient target detection. We refine the feature on pixel level by the multi-scale feature correction method to avoid the feature error when the image is simplified at the above-mentioned region level. The final full connection layer not only integrates features of multi-scale and multi-level but also works as classifier of salient targets. The experimental results show that proposed model achieves better results than other salient object detection models based on original deep learning networks.

In order to pursue high-accuracy localization for intelligent vehicles (IVs) in semi-open scenarios, this study proposes a new map creation method based on multi-sensor fusion technique. In this new method, the road scenario fingerprint (RSF) was employed to fuse the visual features, three-dimensional (3D) data and trajectories in the multi-view and multi-sensor information fusion process. The visual features were collected in the front and downward views of the IVs; the 3D data were collected by the laser scanner and the downward camera and a homography method was proposed to reconstruct the monocular 3D data; the trajectories were computed from the 3D data in the downward view. Moreover, a new plane-corresponding calibration strategy was developed to ensure the fusion quality of sensory measurements of the camera and laser. In order to evaluate the proposed method, experimental tests were carried out in a 5 km semi-open ring route. A series of nodes were found to construct the RSF map. The experimental results demonstrate that the mean error of the nodes between the created and actual maps was 2.7 cm, the standard deviation of the nodes was 2.1 cm and the max error was 11.8 cm. The localization error of the IV was 10.8 cm. Hence, the proposed RSF map can be applied to semi-open scenarios in practice to provide a reliable basic for IV localization.

This paper investigates the trajectory tracking control problem of steer-by-wire autonomous ground vehicle considering the complete failure of vehicle steering motor. In order to achieve the trajectory tracking control of autonomous ground vehicle in presence of the complete failure of vehicle steering motor, the mechanical transmission mechanism of vehicle steering system is analyzed with the steering motor fault being considered, and the differential steering is used to actuate the turning of vehicle in case of emergency. A model predictive controller with the constraints of tire cornering angle and road adhesion is designed to compute the expected front-wheel steering angle for vehicle trajectory tracking control, and a nonsingular terminal sliding mode controller is proposed to track the expected front-wheel steering angle using differential-steering moment, in which a novel observer design method is presented to estimate the actual front-wheel steering angle. Two case studies are implemented in a CarSim-Simulink co-simulation platform, and the simulation results have verified that the proposed method have satisfactory trajectory tracking control effectiveness in presence of the complete failure of vehicle steering motor.

This paper presents the hybrid modeling and the model predictive control of an air suspension system with damping multi-mode switching damper. Unlike traditional damper with continuously adjustable damping, in this study, a new damper with four discrete damping modes is applied to vehicle semi-active air suspension. The new damper can achieve different damping modes by just controlling the on-off statuses of two solenoid valves, which makes its damping adjustment more efficient and more reliable. However, since the damping mode switching induces different modes of operation, the air suspension system with the new damper poses challenging hybrid control problem. To model both the continuous/discrete dynamics and the switching between different damping modes, the framework of mixed logical dynamical (MLD) systems is used to establish the system hybrid model. Based on the resulting hybrid dynamical model, the system control problem is recast as a model predictive control (MPC) problem, which allows us to optimize the switching sequences of the damping modes by taking into account the suspension performance requirements. Numerical simulations results demonstrate the efficacy of the proposed control method finally.

Low-rank matrix completion (LRMC) is a recently emerging technique which has achieved promising performance in many real-world applications, such as traffic data imputation. In order to estimate missing values, the current LRMC based methods optimize the rank of the matrix comprising the whole traffic data, potentially assuming that all traffic data is equally important. As a result, it puts more emphasis on the commonality of traffic data while ignoring its subtle but crucial difference due to different locations of loop detectors as well as dates of sampling. To handle this problem and further improve imputation performance, a novel correlation-based LRMC method is proposed in this paper. Firstly, LRMC is applied to get initial estimations of missing values. Then, a distance matrix containing pairwise distance between samples is built based on a weighted Pearson's correlation which strikes a balance between observed values and imputed values. For a specific sample, its most similar samples based on the distance matrix constructed are chosen by using an adaptive K-nearest neighboring (KNN) search. LRMC is then applied on these samples with much stronger correlation to obtain refined estimations of missing values. Finally, we also propose a simple but effective ensemble learning strategy to integrate multiple imputed values for a specific sample for further improving imputation performance. Extensive numerical experiments are performed on both traffic flow volume data as well as standard benchmark datasets. The results confirm that the proposed correlation-based LRMC and its ensemble learning version achieve better imputation performance than competing methods.

Pontryagin's minimum principle (PMP) based energy management strategy, which describes the optimal power distribution of hybrid electric vehicle as Hamiltonian minimization problem, gains the ability to ensure real-time performance and near-optimal solutions, but demonstrates poor cycle adaptability. Therefore, this paper proposes a novel fuzzy adaptive method for the PMP-based optimal strategy by utilizing real-time traffic information that is described by the average velocity and the standard deviation of the velocity on different road segments. The two velocity feature parameters are derived by the data of floating vehicles. A three-layer back-propagation neural network (BP-NN) is constructed to predict the average power with the velocity feature parameters. On the basis of battery charging sustainability, the fuzzy adaptive law is designed to calculate the co-state of the PMP-based strategy using the predicted average power and the actual battery SOC. Finally, the performance of the proposed strategy is evaluated by comparative simulation studies. It is validated that the average velocity and the standard deviation of the velocity can be well evaluated by the information of floating vehicles. Tested by the standard and practical sampled driving cycles, the BP-NN demonstrates good performance in predicting the average power with the selected velocity feature parameters. Compared with the strategy whose co-state is just corrected by the battery SOC in the feed-back manner, the proposed PMP-based fuzzy adaptive method demonstrates superiority in improving the vehicle fuel economy and maintaining the battery charging sustainability under various driving cycles.

To decrease vehicle crash, a new rear view vehicle detection system based on monocular vision is designed. First, a small and flexible hardware platform based on DM642 DSP micro-controller is built. Then, a two-step vehicle detection algorithm is proposed. In the first step, a fast vehicle edge and symmetry fusion algorithm is obtained and a low threshold is set so that all possible vehicles will selected and also maintain a high false detection rate. In the second step, a classifier using Haar and HoG fusion feature based Adaboost classifier is trained to classify the possible vehicles and eliminate the false detected vehicles from the candidate vehicles generated in the first step. Experimental results demonstrate that this classifier maintains very high detection rate and low false detection rate in different road, weather and lighting conditions.

For plug-in hybrid electric vehicles (PHEVs), mode transition might be the most effective way of energy conservation. However, the transient torsional vibration (TTV) during mode transition process, which is unavoidable, usually affect the drive comfort. This paper presents an innovative planetary hybrid power-split system (PHPS), which comprised of an epicyclic gear system, two compact clutches and a wedge brake device, and will been applied Chery PHEVs. First, powertrain vibration during mode transition process, as influenced by dynamic transfer friction torque of clutch, angle-varying mesh stiffness of epicyclic gear and external loads of multi-power sources, are investigated through a nonlinear TTV model. Then, the dynamic equations of mode transition process are established and numerically solved to get TTV response as well as vehicle jerk, and further new clutch oil-pressure establishing method design of PHEVs during mode transition process for relative torsional oscillation suppression of PHPS is presented. At last, bench tests are carried out, and results indicated that the proposed optimization model effectively suppressed PHPS torsional oscillation, vehicle longitudinal jerk, and improved driving smoothness during mode transition process.

In this paper, an adaptive energy management system consisting of off-line and online parts is presented to improve the energy efficiency of a parallel hybrid electric bus. The off-line part discusses how to precisely recognize the driver's driving style based on the hybrid algorithm. Specially, K nearest neighbor method is applied to reduce the number of samples as the preprocessor, and the expectation maximization method is leveraged to speculate the class using similar training samples. Furthermore, the driving style recognition module is built and employed to classify the driver's driving style from aggressive to conservative at each time step. On the other hand, the online part performs the involved energy management strategy, which incorporates driver's driving style into the equivalent consumption minimization strategy (ECMS). Simulation results demonstrate that the performance of charging sustainability and equivalent fuel consumption in the proposed strategy exceed those in the ECMS, as for both aggressive and conservative drivers. Comparative results obtained from HIL tests also indicate that the fuel economy of the proposed strategy is improved by 9.54% and 7.03% for aggressive and conservative drivers compared with ECMS, respectively.

A constant-current constant-voltage (CCCV) charge protocol is commonly used for lithium-ion batteries. The dynamic characteristic of the constant-voltage (CV) charging current is discovered to be related to battery aging. In order to quantitatively describe the load current during the CV charging period, an equivalent circuit model (ECM) based on the resistor-inductor (RL) network is proposed in this paper. Motivated by the current expression derived based on the conventional resistor–capacitor (RC) network-based ECM, an RL network-based ECM is developed to characterize the CV charging current. Then, the parallel-connected RL networks are employed to improve the model fidelity. The test data of four lithium iron phosphate (LiFePO4) batteries in different aging states are employed to validate the proposed model. Comparative results show that the proposed 2nd-order ECM is the best choice, considering both the model accuracy and complexity. In addition, a simplified 2nd-order model is proposed, achieving a satisfactory accuracy with only three model parameters to be identified. Therefore, this model can be easily implemented in the battery management system (BMS).

In this paper, a smart monocular vision based system to sense vehicles with a camera mounted inside a moving car is developed. The “smartness” is that the sensing ability of our system can be self improved when used. This system maintains an online learning ability which consists of two main stages: an initialization stage by applying an offline trained classifier and a retraining stage with queried and labeled new samples. The unlabeled examples are queried base on “most uncertainty” criterion, and an automatic labeling mechanism is used to assign a class label to some of the queried examples. Finally, the newly labeled training examples are then used to retrain the classifier and improve its performance continuously. Experiments show that the developed system maintains smart learning ability and performs well on real road situation.