Computational methods for predicting drug-target binding affinity (DTA) are critical for large-scale screening of prospective therapeutic compounds during drug discovery. Deep neural networks (DNNs) have recently shown significant promise for DTA prediction. By leveraging available data for training, DNNs can expand the use of DTA prediction to situations where only sequence information is available for potential drug molecules and their targets, and there is no prior knowledge regarding the molecular geometric conformations. We propose DHAG-DTA, a general dynamic hierarchical affinity graph DNN approach, for DTA prediction using molecular sequence information and already known drug-target interactions. DHAG-DTA introduces a two-level hierarchical graph structure: at the upper level, interactions between drug and target molecules are represented via an affinity graph and at the lower level, embedded molecular graphs represent interactions within the individual molecules. This allows for integration of information from both inter and intra molecular interactions for DTA prediction, which has also been addressed in other recent independent work. The fundamental innovations introduced by DHAG-DTA include: (a) a single overall hierarchical graph that allows better assimilation of information during the learning process compared with loosely-coupled individual graphs, (b) dynamic determination of the affinity graph structure via the introduction of unlabeled edges and a maximum entropy criterion for active edge selection, (c) skip connections in the DNN for fusing intra and inter molecular information, and (d) fusion of both model-based and similarity-based feature embeddings to get robust embeddings of unseen molecules. Experimental results on two common benchmark datasets demonstrate that DHAG-DTA outperforms other existing models on multiple evaluation metrics, achieving state-of-the-art performance.

Abstract Accurately predicting the Remaining Useful Life (RUL) of lithium-ion batteries is crucial for battery management systems. Deep learning-based methods have been shown to be effective in predicting RUL by leveraging battery capacity time series data. However, the representation learning of features such as long-distance sequence dependencies and mutations in capacity time series still needs to be improved. To address this challenge, this paper proposes a novel deep learning model, the MLP-Mixer and Mixture of Expert (MMMe) model, for RUL prediction. The MMMe model leverages the Gated Recurrent Unit and Multi-Head Attention mechanism to encode the sequential data of battery capacity to capture the temporal features and a re-zero MLP-Mixer model to capture the high-level features. Additionally, we devise an ensemble predictor based on a Mixture-of-Experts (MoE) architecture to generate reliable RUL predictions. The experimental results on public datasets demonstrate that our proposed model significantly outperforms other existing methods, providing more reliable and precise RUL predictions while also accurately tracking the capacity degradation process. Our code and dataset are available at the website of github.

A novel position estimation strategy for high-frequency (HF) pulsating injection based position sensorless permanent magnet synchronous machine (PMSM) drives is proposed in this paper. The method performs the inverse tangent of HF response currents to realize the decoupling of current information and the extraction of position tracking error can be obtained simply, which reduces the use of low-pass filters. In addition, there is no need to introduce additional demodulation signals, which simplifies the adjustment process. Finally, the feasibility and effectiveness of the proposed scheme are verified on a 2.2-kW sensorless PMSM drive.

In this paper, a fixed-time active disturbance rejection-based sliding mode control scheme is proposed for the three-phase three-level neutral-point-clamped (NPC) active front-end (AFE) converter to regulate the dc-link voltage. In order to further improve the disturbance rejection ability of the active disturbance rejection control (ADRC) when applied in NPC converter, a fixed-time disturbance observer is used to estimate the disturbances instead of the traditional extended state observer in ADRC. In addition, a sliding mode controller with constant plus proportional rate reaching law (CPPRL) is designed to regulate the dc-link voltage, and the dynamic performance and control accuracy of NPC converter is improved without increasing the chattering. Finally, the performance of the proposed control scheme is evaluated by a class of comparative simulations, and the results confirm the effectiveness and feasibility of the proposed approach.

In order to expand the modulation index of the single DC-link shunt permanent magnet synchronous motor drive and improve the motor's operating frequency and load capacity, an improved overmodulation strategy is proposed in this paper. A phase current reconstruction strategy based on vector phase shifting is applied to both modulation linear and nonlinear region. To improve the stability of the motor at high speed, an improved flux weakening strategy based on the voltage angle control method is applied, which can effectively reduce the current harmonics. In addition, this paper proposes a dual-mode overmodulation strategy considering the influence of vector phase shift, and the analysis shows that this strategy can effectively improve the modulation index. Finally, the experimental results show the effectiveness of the proposed method in different operation conditions.

The control accuracy of PMSM depends largely on the inductance. In the traditional inductance identification methods, the ideal PMSM mathematical model is applied, where d-axis and q-axis are assumed completely decoupled. In this case, only the d-axis and q-axis inductances are considered. However, the cross-coupling effect exists in the actual model of PMSM, which leads to the mutual inductance between d-axis and q-axis. In this paper, a high-frequency (HF) equivalent impedance model of PMSM under virtual axis is proposed. According to the HF signal injection, the inductance matrix of PMSM considering the cross-coupling effect can be accurately identified. The experimental results show the effectiveness of the proposed method under different PMSM operation conditions.