As a position sensor, the resolver system is widely used in robotic spindle machines to provide precise rotor angle, in which the complex-vector resolver-to-digital conversion (RDC) system is promising for its high accuracy under high speed. In addition, the systematic errors in resolver output should also be mitigated in RDC system, and the errors are normally compensated after the envelope demodulation. However, the current systematic error mitigation is not suitable for the complex-vector envelope demodulation since the systematic errors in sine and cosine outputs are coupled during the demodulation. To solve this, a novel prestage systematic error mitigation system before envelope demodulation is proposed in this paper for complex-vector RDC system. The systematic errors are observed by the combination of synchronous sampling and least-square observer, which can diminish the influence of motional voltage in high speed. Then, the prestage sequential error compensation is performed to directly calibrate the resolver outputs before envelope demodulation. By the simulation verification, by adding systematic error mitigation, the complex-vector RDC system can effectively reduce the 0.3 rad (i.e., 97%) angle error.

Axial flux machines (AFMs) have attracted significant attention for their exceptional torque density, while existing AFM topologies lack fault tolerance capability. This paper proposes a series of phase-unit AFMs with yokeless and segmented armature structure (PU-YASA) for direct drive applications. All phases of the machines are physically separated and distributed along the axial direction with a specific mechanical angle between the adjacent phases, meaning that the machine can be easily converted to the multi-phase structure by adjusting the mechanical angle between the adjacent phases. The isolated phase structure avoids the possibility of single-phase short-circuit fault escalating to interphase short-circuit fault. Moreover, YASA structure can perform higher power density due to the large cooling area. The study involves two models, with the key difference being that the angular offset is positioned on the rotor PMs in model I and on the stator side in model II. A simplification method is presented to increase simulation efficiency and reduce the required computational resources. The simulation results of different models are compared to validate the proposed approach.

The domain of time series forecasting has gained significant attention due to its critical applications in multimedia-rich web traffic (including video streaming workloads and dynamic content delivery) and cross-platform advertisement click predictions, which are essential for web operations planning. While models like TimeSieve have demonstrated strong capabilities in predicting web visitation metrics, they suffer from critical unfaithfulness issues, including sensitivity to random seeds, input noise, layer noise, and parametric perturbations. To address these limitations, we propose Faithful TimeSieve (FTS), an enhanced framework designed to improve prediction reliability and robustness. Our approach systematically detects and mitigates unfaithfulness in TimeSieve, significantly enhancing its stability and consistency. Experimental results demonstrate that FTS substantially improves the model's faithfulness, setting a new standard for temporal forecasting methods. This advancement not only increases TimeSieve's reliability but also contributes to more robust temporal modeling, particularly crucial for web traffic forecasting where prediction accuracy directly impacts operational decisions. Our work thus represents a significant step toward more dependable time series predictions in web-related applications.

The development and application of transverse flux machines (TFMs) with permanent magnet (PM) excitation have received more and more attention in recent years because of the high torque density at low rotating speed applications. This paper proposes a novel topology structure of TFM with dual-rotor and flat-type-stator (DRFTS-TFM). One of the advantages of the proposed structure is that the sandwiched design greatly reduces the manufacturing and assembling difficulties. Another advantage is that the number of the armature phase can be easily changed by converting the mechanical angle of the stator. To investigate the best electromagnetic torque performance of the machine, the multi-objective particle swarm optimization (MOPSO) algorithm is adapted and validated by the finite element method (FEM). The corresponding electromagnetic performances in different conditions are analyzed.

Existing sensitivity analysis methods suffer from issues such as small differentiation in parameter sensitivity and slow computational speed. To solve these problems, three machine learning methods, namely Ridge regression, Lasso regression, and Elastic Net, are investigated in this paper. First, a PMSM's performance is analyzed using Finite Element Method (FEM) to identify the variation range of the structural parameters that require optimization. Following that, a finite element sample database is established based on this range using the Design of Experiment (DOE). Next, the variable selection results of PMSM optimization are compared using different machine learning methods and traditional machine sensitivity analysis method. Finally, the performances of the PMSM optimized based on the three machine learning methods are evaluated. The results indicates that Lasso Regression proves to be the most effective method. It achieves rapid convergence and effectively identifies the most sensitive parameter, enhancing the optimization efficiency of PMSMs while retaining the global optimum.

The growing demand for accurate control in varying and unknown environments has sparked a corresponding increase in the requirements for power supply components, including permanent magnet synchronous motors (PMSMs). To infer the unknown part of the system, machine learning techniques are widely employed, especially Gaussian process regression (GPR) due to its flexibility of continuous system modeling and its guaranteed performance. For practical implementation, distributed GPR is adopted to alleviate the high computational complexity. However, the study of distributed GPR from a control perspective remains an open problem. In this paper, a control-aware optimal aggregation strategy of distributed GPR for PMSMs is proposed based on the Lyapunov stability theory. This strategy exclusively leverages the posterior mean, thereby obviating the need for computationally intensive calculations associated with posterior variance in alternative approaches. Moreover, the straightforward calculation process of our proposed strategy lends itself to seamless implementation in high-frequency PMSM control. The effectiveness of the proposed strategy is demonstrated in the simulations.

This paper provides a preliminary study of promoting the direct torque control (DTC) to series-end winding permanent magnet synchronous motor (SW-PMSM) drives. The DTC schemes of the conventional PMSM drives cannot be directly applied to the SW-PMSM drives since they have different drive topologies. With one more leg added to the inverter, the SW-PMSM drive has a different voltage vector distribution, which leads to a different switching table for the hysteresis controllers of the flux and the torque. In addition, the zero-sequence subspace also exists in the SW-PMSM drive, and it might generate the undesired zero-sequence current. Based on the above issues, the voltage vector distribution of the SW-PMSM drive is studied in this paper, and the voltage vectors without zero-sequence components are selected as the candidates to prevent generating zero-sequence current. Next, the switching table for the hysteresis controllers is re-derived according to the candidate voltage vectors, and the DTC for the SW-PMSM drive is obtained. Subsequently, the DTC of the multi-phase SW-PMSM drive is also investigated in the same manner. Finally, the effectiveness of the proposed DTC schemes for the SW-PMSM drives is verified.

This paper provides a preliminary study on applying Neural Network (NN) based proportional and integral (PI) controllers with the positional PI principle. This method is set into the speed loop of a dual-three-phase permanent magnet synchronous motor (PMSM), where the vector space decomposition method (VSD) is utilized. The proposed methods are single-layer neural network (SNN), backpropagation neural network (BPNN), and radial basis function neural network (RBFNN). These methods aim to reduce the overshoot of the speed tracking in control problems. By optimizing the current reference output, the copper loss can also be reduced at the same time. Finally, the control performances using traditional PI, SNN-based PI, BPNN-based PI, and RBFNN-based PI are compared by adopting a self-defined scorecard with different evaluation indices.

Researchers have recently attached more attention on permanent magnet brushless AC motors for electrified propulsion. Considering the further improvement of torque density, this paper proposes a novel pulse width modulation (PWM) magnet array and quantitatively analyzes the magnetic field with different magnet configurations. It is a good potential for reducing the magnet volume. Based on a slotless motor design which eliminates the influence of additional harmonic sources except for that from magnets, investigations on motor performance with proposed magnet array are made. Also, the improvement of torque density is discussed and verified.