Axial flux machines are typically analyzed by the 3-D finite element method. To solve the time-consuming issue, this paper proposes a nonlinear dynamic equivalent magnetic network model. The proposed model is able to account for non-linear magnetic saturation and calculate the flux linkage and torque under diverse loads during rotation. After verification, the proposed model achieves satisfactory precision and a computation speed much faster than the typical one.

Abstract The text matching is a basic task of NLP and is important for tasks such as text retrieval, question answering, and so forth. The development of pre‐trained language models has promoted the progress of text matching tasks. However, due to the natural particularity of Chinese characters and expressions, the Chinese text matching tasks still have problems such as word segmentation difficulty, serious semantic loss, and model instability. In this paper, we propose the DAINet model, which includes DMM, AA and IO modules. We use the Dynamic Multi‐Mask module (DMM) to enhance the completeness of word segmentation. Then we use the Augmented Adversarial module (AA) to further extraction of semantic information. Finally, we use the Integrated Output module (IO) for a more stable output. We conducted experiments on LCQMC, BQ and Xiaobu datasets and compared the results with seven strong baseline models. The results showed that DAINet model made great improvement, including improving ACC value of BQ dataset to , AUC value to , ACC value of LCQMC dataset to and AUC value to . The ACC value of Xiaobu dataset was improved to and the AUC value was improved to . Further ablation experiment results show that the proposed DMM, AA and IO modules have good adaptability and improvement over existing models.

With the rapid development of Web3D, virtual reality, and digital twins, virtual trajectories and decision data considerably rely on the analysis and understanding of real video data, particularly in emergency evacuation scenarios. Correctly and effectively evacuating crowds in virtual emergency scenarios are becoming increasingly urgent. One good solution is to extract pedestrian trajectories from videos of emergency situations using a multi-target tracking algorithm and use them to define evacuation procedures. To implement this solution, a trajectory extraction and optimization framework based on multi-target tracking is developed in this study. First, a multi-target tracking algorithm is used to extract and preprocess the trajectory data of the crowd in a video. Then, the trajectory is optimized by combining the trajectory point extraction algorithm and Savitzky–Golay smoothing filtering method. Finally, related experiments are conducted, and the results show that the proposed approach can effectively and accurately extract the trajectories of multiple target objects in real time. In addition, the proposed approach retains the real characteristics of the trajectories as much as possible while improving the trajectory smoothing index, which can provide data support for the analysis of pedestrian trajectory data and formulation of personnel evacuation schemes in emergency scenarios. Further comparisons with methods used in related studies confirm the feasibility and superiority of the proposed framework.

Abstract One of the most common solutions for the prevention of fire accidents is to conduct extensive fire evacuation drills in crowded places. However, there are multiple salient advantages to using virtual reality technology to simulate emergency solutions, for instance, saving costs and greatly decreasing uncertain risks or accidents. Therefore, in this article, a multiagent evacuation framework for complex virtual fire scenarios is proposed and effectively used to simulate a multiagent evacuation procedure to approximate the goal of fire drills in a less costly manner. Specifically, the concept of a multihierarchy agent group model is proposed; that is, the evacuation of multiple agents is separated into leader‐follower and freedom modes. Additionally, several complex actions of individual humans in actual fire drills are fully considered, and a multiaction agent schema is presented to characterize the associated real effects. In addition, generative adversarial imitation learning is adopted to obtain the evacuation path of the leader‐agent by training numerous learning epochs. Finally, extensive experiments are conducted to validate the feasibility of our proposed method. The results show that the proposed method is superior to other methods and that it realistically and reasonably shows the procedure of multiagent evacuation in complex fire emergency scenarios.

In this article, we present a deep learning approach to sketch-based shape retrieval that incorporates a few novel techniques to improve the quality of the retrieval results. First, to address the problem of scarcity of training sketch data, we present a sketch augmentation method that more closely mimics human sketches compared to simple image transformation. Our method generates more sketches from the existing training data by (i) removing a stroke, (ii) adjusting a stroke, and (iii) rotating the sketch. As such, we generate a large number of sketch samples for training our neural network. Second, we obtain the 2D renderings of each 3D model in the shape database by determining the view positions that best depict the 3D shape: i.e., avoiding self-occlusion, showing the most salient features, and following how a human would normally sketch the model. We use a convolutional neural network (CNN) to learn the best viewing positions of each 3D model and generates their 2D images for the next step. Third, our method uses a cross-domain learning strategy based on two Siamese CNNs that pair up sketches and the 2D shape images. A joint Bayesian measure is used to measure the output similarity from these CNNs to maximize inter-class similarity and minimize intra-class similarity. Extensive experiments show that our proposed approach comprehensively outperforms many existing state-of-the-art methods.

With the development of electric vehicles, more and more attentions have been put on understanding and attenuating the noise, vibration, and harshness (NVH) of traction machines. NVH in machines are mainly caused by the electromagnetic force, which is complex vector functions of both time and space, and models are desired for accurately evaluating its characteristics. In this paper, analytical models for estimating the air gap flux density and electromagnetic force in interior permanent magnet synchronous machine (IPMSM) with distributed windings are established. The effects of stator slots and rotor saliency are taken into consideration to ensure the validity of the model. Temporal and spatial harmonic distributions of electromagnetic force are studied separately. The electromagnetic force of a 44 kW 8-pole/48-slot IPMSM is evaluated using 2-D finite element analysis (FEA) and 2-D fast Fourier transformation (FFT) method. The simulation results agree well with that predicted from the analytical model. The relationship between mode numbers and temporal harmonics is identified. In addition, it is found that tooth harmonics and rotor harmonics have strong influences on the amplitude of electromagnetic force.

Doubly salient brushless dc (DSBLDC) motors have attracted increasing attention for drive system due to the simple and rugged rotor structure, brushless operation and low cost. Open circuit (OC) faults in power converter as a common fault reduce system performance. The majority of the tolerance approaches require additional hardware which increases the cost. This paper proposes a fault-tolerant control strategy, without extra hardware, for OC tolerance in DSBLDC motor drive. Firstly, a current-based method is proposed to detect OC faults. Then fault-tolerant control strategy based on non-working bridge arm commutation is proposed and corresponding control modes are introduced for OC faults. Finally, fault switch is identified by power converter work mode. Simulation results confirm the feasibility of the proposed fault-tolerant control strategy.

The mixed modulated Lagrange explicit time delay estimation (MMLETDE) algorithm provides an efficient time delay estimation between narrowband or sinusoidal signals. However, it does not explicitly consider the additive measurement noise at the input, which actually exists in practice. Aiming at this issue, an enhanced MMLETDE algorithm is proposed for noisy inputs based on the unbiased impulse response estimation technique, assuming that the noise power ratio is known a priori. Simulation results show that for narrowband signals or sinusoids over a wide frequency range, the proposed algorithm with a small filter order performs well in moderate and high noise scenarios.