The permanent magnet linear synchronous motor (PMLSM) with segmented stator is applied in the long-distance auto-transportation system. For the PMLSM with the discontinuous stators, the mismatch between the permanent magnet (PM) mover and the stator would make electromagnetic (EM) parameters deflect nominal values, and then position/speed precision of the PM mover would be affected. In this article, the sensorless control based on the parameter calibration is used to drive the PM mover above the segmented stators during the drive process. Furthermore, an improved model reference adaptive integrator based on the parameter calibration is proposed to calibrate the EM parameters during the switch process. The simulation and experimental results confirm that the speed precision and the robustness of the segmented PMLSM are enhanced distinctly.

In order to solve the problem that deep learning method needs a lot of paired data sets in image enhancement, this paper proposes unsupervised feature attention network (UFANet), which uses a new illumination estimation that combines pixel estimation and channel estimation to guide the network to decompose underexposed images. In addition, a feature attention residual network is trained to decompose under-exposed images into illumination and reflectance. Through a set of carefully designed non reference loss functions, which implicitly enhance the quality and drive the learning of the network, we train UFANet without any paired images. A large number of experiments on various benchmarks have proved the advantages of our method over the latest methods in terms of quality and quantity. Compared to the state-of-the-art methods, our method only needs to be trained on 350 underexposed images. All the above advantages make our UFANet attractive in practical applications.

No abstract