To solve the problem of poor real-time performance and adaptability in existing minimum equivalent fuel consumption strategies for Plug-in Hybrid Electric Vehicles (PHEVs), an optimization method for online energy management based on Long Short-term Memory (LSTM) driving condition recognition is proposed. Firstly, an equivalent energy consumption model is established by fitting the engine and motor’s instantaneous energy consumption curves, and the optimal torque distribution is solved to improve the Equivalent Consumption Minimization Strategy (ECMS) optimization process. Secondly, an online energy management strategy is developed based on LSTM method, which is used to enhance adaptability of this strategy to driving conditions. Thirdly, the proposed energy management strategy is tested based on a random driving condition. The result showed that the proposed strategy reduces fuel consumption to 3.12 L/100 km, while the strategy without driving condition recognition consumes 3.45 L/100 km, achieving a 9.57% reduction in overall fuel consumption.
High-performance automotive active suspension systems, with real-time dynamic regulation capabilities for ride and handling enhancement, are drawing growing interest from both academia and industry. In order to solve the problems of inaccurate estimation of active suspension disturbance and difficulty in handling uncertainty with fault-tolerant control, this paper proposes a robust fault-tolerant control strategy for active suspension based on disturbance observer. A high-fidelity half-car suspension model is firstly established, incorporating both vertical and pitch dynamics with actuator fault characteristics. Secondly, in order to solve the problem of system uncertainty, an improved disturbance observer based on Kalman filter is further proposed, which realizes the accurate estimation of unmodeled dynamics and external interference by introducing disturbance estimators. Furthermore, based on the state estimation residuals, a multi-criterion fault detection and diagnosis unit is designed, and an active fault-tolerant control strategy with strong robustness to model parameter changes is proposed. The results demonstrate that the proposed fault-tolerant controller effectively compensates for actuator failures and preserves system stability under parameter and random disturbances. The proposed controller outperforms the control group, reducing the root mean square of vehicle body acceleration by 2.3% and the root mean square of tire dynamic stroke by 42.1%. Meanwhile, the enhanced Kalman filter embedded with a disturbance observer reduces the mean square error of state estimation by 5.12% and 4.81% respectively compared with the standard Kalman filter, yielding remarkable improvement in estimation accuracy.
Longitudinal speed estimation becomes difficult when a vehicle runs through roads with changing adhesion, because the wheel-speed signals can be strongly affected by slip, wheel lock-up, and short road impacts. This problem is more obvious for four-wheel-drive electric vehicles, where the estimator usually has to work with production wheel-speed sensors and an onboard IMU. To improve the robustness of this low-cost sensor fusion problem, this paper presents a prior-guided adaptive Kalman filtering method for longitudinal speed estimation. The longitudinal acceleration measured by the IMU is first corrected by considering vehicle pitch, road slope, and lateral-motion coupling. A wheel-speed observation is then built from the consistency of the four-wheel speeds, so that obviously unreliable wheel-speed information can be weakened before it enters the filter. In addition, road-adhesion-related features are extracted online and used in a hidden Markov inference process. The obtained state probabilities are directly introduced into the prediction-stage process-noise covariance, allowing the filter to adjust the balance between acceleration-based prediction and wheel-speed correction before large wheel-speed residuals are accumulated. Real-vehicle tests were carried out on a four-wheel-drive electric SUV under three representative conditions, including high-to-low adhesion transition, low-to-high adhesion transition, and one-side road-step braking. To further examine case-to-case variability, nine additional high–low adhesion-transition runs were included, resulting in 12 real-vehicle validation cases in total. In these 12 cases, the proposed method achieved the lowest mean absolute error in all cases and the lowest maximum absolute error in 9 out of 12 cases. Its average mean absolute error and maximum absolute error were 0.1181 and 0.3480 m/s, respectively. Within the tested validation cases, these results indicate that the proposed method can improve transient robustness while keeping a simple recursive structure suitable for real-time rapid-prototyping implementation.
The accelerating global transition toward sustainable electrification has established Permanent Magnet Synchronous Motors (PMSMs) as a key propulsion technology for electric vehicles and advanced industrial applications. However, the inherent nonlinear dynamics and parameter sensitivities of these systems pose significant control challenges, where conventional Proportional-Integral (PI) controllers often fail to maintain stability under varying operating conditions. To address this limitation, this study proposes a robust Field-Oriented Control (FOC) framework in which Particle Swarm Optimization (PSO) is employed for offline optimal tuning of controller gains. The optimization process is formulated based on multiple performance indices, including the Integral Absolute Error (IAE), Integral Square Error (ISE), and Integral Time-Absolute Error (ITAE), to ensure improved dynamic and steady-state performance. The obtained results demonstrate that the proposed FOC-PSO strategy significantly outperforms conventional controllers. In particular, the overshoot is completely eliminated (0%) compared to 4.8% in standard PID controllers, while achieving a faster rise time of 0.0053 s and reduced settling time. Moreover, the proposed approach effectively minimizes torque ripple and current ripple, and maintains robust performance under varying load conditions and parameter uncertainties. Consequently, this work provides a reliable and efficient control solution for enhancing the performance and robustness of PMSM-based electric drive systems.
In actual diesel engine operation, the mixture of steady-state and transient data significantly reduces the accuracy of machine learning models. Therefore, a simple, reliable, and online-achievable method for condition classification is urgently needed. Current research on classifying steady- and unsteady-state data predominantly relies on single-feature metrics, lacking comparative evaluations across multiple indicators and a systematic analysis of threshold effects. To address this issue, this study acquires multi-condition operational parameters through bench tests and proposes the relative power range as a classification feature based on a comparative analysis of data variations across eight variables under different operating conditions. By analyzing the impact of varying the relative range threshold on classification performance, the optimal relative power range threshold is determined. The modeling accuracy of a back-propagation (BP) neural network is adopted as the evaluation metric to compare the proposed method with the K-means clustering algorithm. The results show that after screening steady-state data via the proposed relative power range classification method with the optimal threshold of 0.2%, the determination coefficient R 2 of the BP torque prediction model reaches 97.40%, which is 4.45 percentage points higher than the model trained on raw mixed steady/unsteady data, and 4.39 percentage points higher than the optimal result of K-means clustering ( R 2 = 93.01%). Among three relative-range classification indicators (power, rotational speed, torque), the relative power range achieves the highest classification accuracy of 95.53%, far exceeding the relative rotational speed range (90.64%) and relative torque range (64.27%).
