Fault diagnosis for battery systems is essential for ensuring safe operation of electric vehicles (EVs). In this study, a novel model for battery fault diagnosis is established by combining the long short-term memory recurrent neural network (LSTM) and the equivalent circuit model (ECM). The modified adaptive boosting method is utilized to improve diagnosis accuracy, and a prejudging model is employed to reduce computational time and improve diagnosis reliability. Considering the influence of drivers’ behaviors on battery systems, the proposed diagnosis scheme is able to achieve potential failure risk assessment and accordingly to issue early thermal runaway warning. A large volume of real-world operation data is acquired from the National Monitoring and Management Center for New Energy Vehicles (NMMC-NEV) in China to verify its robustness, feasibility and reliability. The results show that the proposed method exhibits superior performance, and can achieve accurate fault prediction for potential battery cell failure and precise locating of thermal runaway cells.

This paper presents a novel battery aging assessment method based on the incremental capacity analysis (ICA) and radial basis function neural network (RBFNN) model. The RBFNN model is used to depict the relationship between battery aging level and its influencing factors based on real-world operation data sets of electric city transit buses. The ICA method together with the Gaussian window (GW) filter method is used to derive the peak values of IC curves which are utilized to represent the battery aging level. The support vector regression (SVR) method is used in several scenarios for data preprocessing. The considered influencing factors include accumulated mileage of vehicles and initial charging SOC, average charging temperature, average charging current and average operating temperature of battery systems. The datasets collected from real-world electric city buses are used for RBFNN model training, validation and test. The results show that an average prediction error of 4.00% is reached, and the derived model has a confidential interval of 92% with the prediction of 10%. This work provides insights for battery aging prediction based on massive real-time operation data.

There is an increasing awareness of the need to reduce traffic accidents and fatality rates due to vehicle rollover incidents. Accurate detection of impending rollover is necessary to effectively implement vehicle rollover prevention. To this end, a real-time rollover index and a rollover tendency evaluation system are needed. These should give high accuracy and be of a low application cost. This paper proposes a rollover evaluation system taking lateral load transfer ratio (LTR) as the rollover index, with inertial measurement unit (IMU) as the system input. A nonlinear suspension model and a rolling plane vehicle model are established for state and parameter estimation. An adaptive extended Kalman filter (AEKF) is utilized to estimate the roll angle and rate, which adjusts noise covariance matrices to accommodate the nonlinear model characteristic and the unknown noise characteristic. In the meantime, the recursive least squares method with forgetting factor (FFRLS) is utilized to identify the height of the center of gravity (CG). The Butterworth filter is used to filter out the high frequency noise of acceleration signal and the index of LTR is accordingly calculated based on the estimation results. The proposed scheme is verified and compared through hardware-in-loop (HIL) tests. The results show that the developed scheme performs well in a variety of operating conditions.

In this article, a robust control scheme for an in-wheel-motor-drive electric vehicle (IWMD EV) is put forward to enhance vehicle lateral stability considering network-induced time delays. A robust sliding mode controller (RSMC) is devised, and the derived control law is partitioned into two portions, i.e., the continuous and discontinuous parts. A Linear-Quadratic- Regulator (LQR) problem with network-induced time delays is formulated with the objectives of minimizing the reference states tracking errors and reducing the control efforts. Then, it is transformed into an iterative solution derivation of a two-point boundary value problem without delays, and the derived solution is obtained and constitutes the continuous part of the control law. Meanwhile, the global sliding mode theory is applied to deriving the discontinuous part of the control law, which has robustness to vehicle parameters variation and modeling uncertainties. The proposed control scheme exhibits better performance in dealing with network-induced time delays compared with the original optimal LQR controller strategies in simulation and Hardware-in-the-Loop (HIL) tests.

The overheat abuse experiment of a 12S1P 37 Ah prismatic Lithium-ion battery module in a nominal energy of 1.65 kWh is conducted in this work. The cell behaviors and characterization in the process of thermal runaway propagation is investigated, including the gas eruption, the fire ejection, the flame combustion, the audio features, and the heat transfer, respectively. In the experiment, the central cell is heated on both sides until the pole temperature moves beyond 300 °C, the thermal runaway undergoes about 43 min and propagates from the central to both sides in the module, and all 12 cells burn. Results show that the first three runaway cells spout gas at first, and, then, emit sound with close amplitudes, frequencies, and energies, about 200 s earlier than the fire ejection. Then, the characteristic of the internal short circuit is the temperature rate zone of 1.0 K/s with time greater than 20 s. Moreover, the proposed thermal propagation coefficient is used to assess the thermal propagation capabilities of the runaway cells on their adjacent cells, and this explains the runaway sequence. It is anticipated that the experimental results can provide the deep understanding, thermal runaway warning, and evaluation method for the module safety design.