Recognizing Multitype Misalignments in Wireless EV Chargers With Orientation-Sensitive Coils: A Data-Driven Strategy Using Improved ResNet

In wireless electric vehicle charging systems, misalignments between a ground-assembled transmitter and a vehicle-assembled receiver are undesirable but inevitable, which may cause efficiency deterioration and even thermal risks. The recognition of horizontal misalignment, including that in the longitudinal and lateral direction, has made gradual progress in previous works. However, yaw angle, with rare attention, can also degrade the charging performance, especially for those employing noncentrosymmetric coupling coils, such as rectangular coils. In this article, a data-driven strategy based on an improved residual network (ResNet) is proposed to recognize the above multitype misalignments simultaneously, which is accurate, reliable, and of practical and general value. Large-scale data are sampled using the proposed detection coils by double-group cooperation, which features high sensitivity to misalignments of all kinds, especially yaw angle. Benefitting from the compression technique in the preprocessing phase, the number of training data and labels can be successfully reduced by three-fourths. As the core algorithm of the overall strategy, the adaptive channel parameter recalibration ResNet can effectively perceive slight differences among similar input samples and map them to proper labels. This is achieved by an adaptive operation of nonlinear transformation and recalibrated important channel features during the training process. The effectiveness of the proposed strategy is verified experimentally using a 6.6-kW prototype. Within the 24×24 cm range, 95.2% of the test cases have an error of less than 1.7 cm when recognizing horizontal misalignment, and 91.7% of the test cases have an error of less than 1.5° when recognizing yaw angle.