Open circuit voltage (OCV) is crucial for battery degradation analysis. However, high-precision OCV is usually obtained offline. To this end, this paper proposes a novel self-evaluation criterion based on the capacity difference of State of Charge (SoC) unit interval. The criterion is integrated into extended Kalman filter (EKF) for joint estimations of OCV and SoC. The proposed method is evaluated in a typical application scenario, energy storage system (ESS), using a ${\mathrm{LiFePO}}_4$ (LFP) battery. Extensive experimental results show that a more accurate OCV and incremental capacity and differential voltage (IC-DV) can be achieved online with the proposed method. Our method also greatly improves the accuracy of SoC estimation at each SoC point where the maximum estimation error of SoC is less than 0.3%.

This paper studies the speed control strategy of a switched reluctance motor based on angle-position control (APC). The switched reluctance motor has three control parameters: turn-on angle, turn-off angle and voltage PWM duty cycle. This paper studies the function of the three parameters and designs the control algorithms of the parameters, respectively, which can reduce the coupling degree, simplify the control process, and realize the optimal control of the switched reluctance motor. By studying the nonlinear characteristics of the switched reluctance motor, the optimal current waveform in the effective working range of the inductor is obtained, and then a control strategy of the turn-on angle is designed to realize the ideal winding current waveform. According to the torque characteristics of the motor, taking the coincidence of the freewheeling zero point and the position angle at the end of the maximum inductance interval as the control target, a control strategy for the turn-off angle that makes full use of the effective inductance working interval is proposed, which improves the efficiency of the system. For the nonlinear and time-variant switched reluctance motor running process, a data-driven model-free adaptive control algorithm is introduced, and a switched reluctance motor speed control algorithm based on voltage PWM duty cycle is designed. The main contribution of this paper is to propose a control strategy that is generally applicable to switched reluctance motors, which does not depend on the precise mathematical model of the motor. The control algorithms are designed separately for the three control parameters according to the characteristics of the motor, which reduces the degree of coupling among them. A switched reluctance motor drive system based on angle-position control is designed. This strategy is especially suitable for driving the load with sudden large torque pulsation.

The rapid advancement of edge artificial intelligence (AI) has unlocked transformative applications across various domains. However, it also poses significant challenges in efficiently updating models on edge devices, which are often constrained by limited computational and communication resources. Here, we present low-rank adaptation method for Edge AI (LoRAE), Leveraging low-rank decomposition of convolutional neural networks (CNNs) weight matrices, LoRAE reduces the number of updated parameters to approximately 4% of traditional full-parameter updates, effectively mitigating the computational and communication challenges associated with model updates. Extensive experiments across image classification, object detection, and image segmentation tasks demonstrate that LoRAE significantly decreases the scale of trainable parameters while maintaining or even enhancing model accuracy. Using the YOLOv8x model, LoRAE achieves parameter reductions of 86.1%, 98.6%, and 94.1% across the three tasks, respectively, without compromising accuracy. These findings highlight the potential of LoRAE as an efficient and precise solution for resource-constrained edge AI systems.

Accurate multi-step traffic-flow forecasting requires dynamic spatial modeling and adaptation to heterogeneous temporal and node-level patterns. This study proposes FAMoE-ST, a hierarchically frozen attention network with hybrid-memory experts. Historical flow, temporal context, and node identity are encoded as sensor tokens and processed by a six-layer Transformer initialized from GPT-2. To avoid dependence on arbitrary sensor indexing, the causal mask is replaced by all-to-all bidirectional spatial attention and every sensor uses the same GPT position ID. The lower four blocks are frozen, while the upper two blocks are adapted and their feed-forward networks are replaced by four-expert modules. A linear router is fused with a 32-slot memory router; each token retrieves four slots and activates two experts. With 12 observations predicting the next 12 steps, FAMoE-ST achieves MAE/RMSE/MAPE of 18.55/30.35/12.91% on PEMS04 and 14.57/24.08/9.71% on PEMS08. Relative to ST-LLM, MAE decreases by 6.97% and 7.39%, respectively. Component and capacity-matched controls support the roles of restricted adaptation, sparse expert capacity, and memory routing. A separate PEMS04 initialization control finds no advantage from GPT-2 pretraining over random initialization; the contribution is therefore attributed to the proposed structural adaptation rather than to transferred linguistic knowledge.

Accurate multi-step traffic flow forecasting requires dynamic spatial modeling and adaptation to heterogeneous temporal and node-level patterns. This study proposes FAMoE-ST, a hierarchically frozen attention network with a hybrid-memory mixture of experts. Historical flow and temporal and node context are encoded as sensor tokens and processed by a six-layer Transformer initialized from GPT-2. To remove dependence on arbitrary sensor indexing, causal masking is replaced by all-to-all bidirectional spatial attention, and all nodes share the zero GPT position ID. The lower four blocks are frozen, whereas the upper two blocks are adapted and their feed-forward networks are replaced by four-expert modules. A linear router is fused with a 32-slot memory router; each token retrieves four slots and activates two experts. With 12 observations predicting the next 12 steps, FAMoE-ST achieves MAE/RMSE/MAPE values of 18.55/30.35/12.91% on PEMS04 and 14.57/24.08/9.71% on PEMS08. Relative to ST-LLM, MAE decreases by 6.97% and 7.39%, respectively. Ablations show complementary benefits from restricted adaptation, sparse experts, and memory routing. A parameter-matched control further indicates that the gains are not attributable solely to stored capacity, although the experiments do not isolate the effect of GPT-2 pretraining.