Tingting Wang

It is a research hotspot to restore decoded videos with existing bitstreams by applying deep neural network to improve compression efficiency at decoder-end. Existing research has verified that the utilization of redundancy at decoder-end, which is underused by the encoder, can bring an increase of compression efficiency. However, most existing research neglects the abundant multi-scale information among video frames as a typical type of such redundancy. It remains an interesting yet challenging topic how to build an effective, interpretable and fast deep neural network for the purpose of using the multi-scale similarity at decoder-end and further enhancing compression efficiency. To this end, this paper considers the use of underused inter multi-scale information, and proposes the Fast Multi-Scale Deep Decoder (Fast MSDD) for the state-of-the-art video coding standard HEVC. The advantages of Fast MSDD are three-fold. First, it achieves a higher coding efficiency without modifying any encoding algorithm. Second, Fast MSDD is interpretable based on the framework of using the underused redundancy. Third, it guarantees the model's inference speed while fully using the multi-scale similarity among video frames. Extensive experiment results verify Fast MSDD's effectiveness, interpretability, and computational efficiency. Fast MSDD obtains averagely 14.3%, 10.8%, 8.5% and 7.6% BD gains for AI, LP, LB and RA respectively. Compared with our previous work MSDD, Fast MSDD achieves increases of 59.3%, 49.1%, 61.0% and 29.3%. Meanwhile, 16.9%, 11.2%, 9.2% and 8.3% BD gains are observed on videos with scaling changes, which validate the interpretability of the proposed method. Furthermore, Fast MSDD can save at most 56.3% time compared to MSDD.

The operating temperature plays a key role in the service reliability of ball bearings used in the traction motor of high-speed trains. Studies on the heat generation and temperature distributions of the bearing under the vehicle vibration environment are critical for designing the high-speed train traction motor bearing and to monitor its operation. In this paper, an SKF friction torque model that considers the inlet shear heating reduction and kinematic replenishment/starvation reduction was used to calculate the power loss of the bearing operating in a high-speed train. A thermal analysis model of the bearing, which takes into account the vehicle vibration due to track irregularities, was developed to study the thermal characteristics of the bearing operating in a high-speed train. Experiments were conducted on a service high-speed train (i.e. CRH380B) to validate the proposed bearing thermal analysis model. The thermal characteristics of the bearing and the influence of key factors on the operating temperature of the bearing under vehicle vibration due to track irregularities were studied with the proposed bearing thermal analysis model. The results show that the thermal failure of the bearing subassemblies most likely occurs at the balls region owing to the highest temperature in that region, compared to the inner and outer raceway of the bearing. The method of applying grease with appropriate kinematic viscosity should be adopted to reduce the power loss of bearing while meeting the lubrication requirement. The vehicle vibration due to track irregularities significantly influences the thermal characteristics of high-speed train motor bearings, which cannot be ignored in the thermal analysis of bearings operating in a high-speed train.