Explore the vast range of titles available.

The electro-hydraulic composite braking system of a pure electric vehicle can select different braking modes according to braking conditions. However, the differences in dynamic response characteristics between the motor braking system (MBS) and hydraulic braking system (HBS) cause total braking torque to fluctuate significantly during mode switching, resulting in jerking of the vehicle and affecting ride comfort. In this paper, torque coordination control during mode switching is studied for a four-wheel-drive pure electric vehicle with a dual motor. After the dynamic analysis of braking, a braking force distribution control strategy is developed based on the I-curve, and the boundary conditions of mode switching are determined. A novel combined pressure control algorithm, which contains a PID (proportional-integral-derivative) and fuzzy controller, is used to control the brake pressure of each wheel cylinder, to realize precise control of the hydraulic brake torque. Then, a novel torque coordination control strategy is proposed based on brake pedal stroke and its change rate, to modify the target hydraulic braking torque and reflect the driver’s braking intention. Meanwhile, motor braking torque is used to compensate for the insufficient braking torque caused by HBS, so as to realize a smooth transition between the braking modes. Simulation results show that the proposed coordination control strategy can effectively reduce torque fluctuation and vehicle jerk during mode switching.

In this work, we developed a novel system to detect the braking intention of drivers in emergency situations using electroencephalogram (EEG) signals. The system acquired eight-channel EEG and motion-sensing data from a custom-designed EEG headset during simulated driving. A novel method for accurately labeling the training data during an extremely short period after the onset of an emergency stimulus was introduced. Two types of features, including EEG band power-based and autoregressive (AR)-based, were investigated. It turned out that the AR-based feature in combination with artificial neural network classifier provided better detection accuracy of the system. Experimental results for ten subjects indicated that the proposed system could detect the emergency braking intention approximately 600 ms before the onset of the executed braking event, with high accuracy of 91%. Thus, the proposed system demonstrated the feasibility of developing a brain-controlled vehicle for real-world applications.

Background Current research related to electroencephalogram (EEG)-based driver’s emergency braking intention detection focuses on recognizing emergency braking from normal driving, with little attention to differentiating emergency braking from normal braking. Moreover, the classification algorithms used are mainly traditional machine learning methods, and the inputs to the algorithms are manually extracted features. Methods To this end, a novel EEG-based driver’s emergency braking intention detection strategy is proposed in this paper. The experiment was conducted on a simulated driving platform with three different scenarios: normal driving, normal braking and emergency braking. We compared and analyzed the EEG feature maps of the two braking modes, and explored the use of traditional methods, Riemannian geometry-based methods, and deep learning-based methods to predict the emergency braking intention, all using the raw EEG signals rather than manually extracted features as input. Results We recruited 10 subjects for the experiment and used the area under the receiver operating characteristic curve (AUC) and F1 score as evaluation metrics. The results showed that both the Riemannian geometry-based method and the deep learning-based method outperform the traditional method. At 200 ms before the start of real braking, the AUC and F1 score of the deep learning-based EEGNet algorithm were 0.94 and 0.65 for emergency braking vs. normal driving, and 0.91 and 0.85 for emergency braking vs. normal braking, respectively. The EEG feature maps also showed a significant difference between emergency braking and normal braking. Overall, based on EEG signals, it was feasible to detect emergency braking from normal driving and normal braking. Conclusions The study provides a user-centered framework for human–vehicle co-driving. If the driver's intention to brake in an emergency can be accurately identified, the vehicle's automatic braking system can be activated hundreds of milliseconds earlier than the driver's real braking action, potentially avoiding some serious collisions.

Regenerative braking energy recovery is of critical importance for electric vehicles due to their range limitations. To further enhance regenerative braking energy recovery, a dual-fuzzy regenerative braking control strategy based on braking intention recognition is proposed. Firstly, the distribution strategy for braking force is devised by considering classical curves like ideal braking force allocation and ECE regulations; secondly, taking the brake pedal opening and its opening change rate as inputs, the braking intention recognition fuzzy controller is designed for outputting braking strength. Based on the recognized braking strength, and considering the battery charging state and the speed of the vehicle as inputs, a regenerative braking duty ratio fuzzy controller is developed for regenerative braking force regulation to improve energy recovery. Furthermore, a control experiment is established to evaluate and compare the four models and their respective nine braking modes, aiming to define the dual fuzzy logic controller model. Ultimately, simulation validation is conducted using Matlab/Simulink R2019b and CRUISE 2019. The results show that the strategy in this paper has higher energy savings compared to the single fuzzy control and parallel control methods, with energy recovery improved by 26.26 kJ and 96.13 kJ under a single New European Driving Cycle (NEDC), respectively.

The loader has a lot of recoverable braking energy due to its larger mass and frequent starts/stops. For a 5-ton pure electric drive loader, an emergency braking intention recognition strategy based on hydraulic braking pressure was proposed. The braking intention recognition strategy of an acceleration pedal and brake pedal was used to distinguish different braking intentions, and the hydraulic braking system pressure was used as a feedback parameter for emergency braking intention recognition to improve braking safety. Aiming at electro-hydraulic composite braking mode switching, a collaborative control strategy of walking regenerative braking and mechanical braking is proposed. Simulation analysis by AMESim and vehicle test results show that the proposed control strategy can realize driver braking intention recognition and electro-hydraulic braking force distribution under different working conditions and improve braking smoothness. According to the calculation of the energy recovery effect evaluation index, the energy recovery efficiency is up to 71.64%, the braking recovery rate is above 42.50%, and the maximum energy saving for the whole vehicle is 7.58% under one cycle condition. The proposed strategy has a good energy-saving effect.

Prediction of a driver’s braking intention enables the advanced driver assistance system (ADAS) to intervene in the braking system as early as possible, which may shorten braking distance and improve driving safety. This paper proposes a novel deep learning model called LSTM-CNN-Attention that combines a long short-term memory (LSTM) neural network, convolutional neural network (CNN), and Attention mechanism for extracting spatiotemporal features of multi-sensor data to improve prediction accuracy. The proposed model inherits both temporal and spatial feature extraction abilities from LSTM and CNN. The LSTM-CNN-Attention model has a parallel architecture, which enhances the feature extraction ability of the model for multi-sensor time series data and improves the prediction accuracy of the driver’s braking intention before the braking action. Furthermore, a driving simulator is set up to sample driving data for training and evaluating the proposed method. According to the results of the experiment, the model obtains up to 3.16% higher accuracy than the baseline models such as LSTM, CNN, and bidirectional LTSM (Bi-LSTM). Additionally, the influence of sliding window size and prediction horizon on the performance of the method is investigated. A method of tuning hyperparameters using the genetic algorithm is presented. The results demonstrate that the prediction accuracy increases by about 2% after being optimized by GA.

As a widely-used construction machinery, the electric loader has the potential to recover braking energy due to its large mass and frequent starts and stops. Identifying braking intention accurately is the foundation of braking energy recovery. The typical braking condition of an electric loader is analyzed; the braking intention is divided into sliding brake, mild braking, moderate braking, and emergency braking. A large number of braking data were collected under different braking intentions, which are used as the basis for fuzzy control variable partitioning, fuzzy controller parameter setting and fuzzy control rule formulation. The control strategies of deceleration intention identification based on accelerator pedal, braking intention identification based on brake pedal and sliding brake intention identification are proposed in this paper, respectively. This paper takes the hydraulic brake pressure as a feedback parameter, even if there is hysteresis or failure based on the intention of pedal identification, the system can still provide sufficient braking strength to ensure the braking safety. The AMESim(R12)-Matlab/Simulink co-simulation model and prototype are built to verify the feasibility of the control strategy under different braking intention identification. The results show that the braking strength under stronger braking intention can satisfy the braking demand whether at a speed of 2 m/s or 12 m/s, which ensures the safety of emergency braking, and the electric loader can provide stable braking strength under different braking intention and different speed. This has good braking stability.

Driving intention has been widely used in intelligent driver assistance systems, automated driving systems, and electric vehicle control strategies. The accuracy, practicality, and timeliness of the driving intention identification model are its key issues. In this paper, a novel driver’s braking intention identification model based on the Gaussian mixture-hidden Markov model (GHMM) and generalized growing and pruning radial basis function neural network (GGAP-RBFNN) is proposed to improve the identification accuracy of the model. The simplest brake pedal and vehicle speed data that are easily obtained from the vehicle are used as an observation sequence to improve practicality of the model. The data of the pressing brake pedal stage are used to identify the braking intention to improve the timeliness of the model. The experimental data collected from real vehicle tests are used for off-line training and online identification. The research results show that the accuracy of driver’s braking intention identification model based on the GHMM/GGAP-RBFNN hybrid model is 94.69% for normal braking and 95.57% for slight braking, which are, respectively, 26.55% and 17.72% higher than achieved by the GHMM. In addition, the data of the pressing brake pedal stage are used for intention identification, which is 1.2 s faster than that of the existing identification model based on the GHMM.

The accurate identification of a driver’s braking intention is crucial to the formulation of regenerative braking control strategies for electric vehicles. In this paper, a braking intention recognition model based on the sample entropy of the braking signal and a probabilistic neural network (PNN) is proposed to achieve the accurate recognition of different braking intentions. Firstly, the brake pedal travel signal is decomposed to extract the effective components via variational modal decomposition (VMD); then, the features of the decomposed signal are extracted using sample entropy to obtain the multidimensional feature vector of the braking signal; finally, the sparrow search algorithm (SSA) and probabilistic neural network are combined to optimize the smoothing factor with the sparrow search algorithm and the cross-entropy loss function as the fitness function to establish a braking intention recognition model. The experimental validation results show that combining the sample entropy features of the braking signal with the probabilistic neural network can effectively identify the braking intention, and the SSA-PNN algorithm has higher recognition accuracy compared with the traditional machine learning algorithm.

In order to improve the safety and braking energy recovery rate of the composite braking system for extended-range heavy commercial electric vehicle, AMT shift control strategy is studied based on Layering Hidden Markov Model/Adaptive Neuro-fuzzy Inference System (LHMM/ANFIS) braking intention identification model. Firstly, according to the requirement of the AMT shift strategy in braking process, the braking intentions were classified into normal braking condition and emergency braking condition. Then combined with the composite braking force distribution, the motor braking power generation characteristics and the critical condition of dangerous working state, the AMT shift strategy was analyzed and established under two braking conditions. Finally, to verify the control effect, the verification test was carried out with the initial braking speed of 60 km h −1 under the normal braking condition and the emergency braking condition separately on the hardware in the loop simulation platform based on A&D 5435 and the testing vehicle. Meanwhile, simulation study was completed in Matlab/Simulink under NEDC_90 cycle condition. The experiment and simulation results show that the developed AMT shift control strategy can accurately identify the braking intention, and the transmission shifts correctly according to corresponding conditions, which can also make the motor operating points closer to the high efficiency area. Therefore, the AMT shift control strategy proposed in this paper can effectively improve the braking energy recovery rate, and ensure the braking safety and stability.