Search

Your search keyword '"Liu Ding"' showing total 248 results
Start Over Author "Liu Ding" Publisher ieee
248 results on '"Liu Ding"'

13. Residual Local Feature Network for Efficient Super-Resolution

Author

Kong, Fangyuan, Li, Mingxi, Liu, Songwei, Liu, Ding, He, Jingwen, Bai, Yang, Chen, Fangmin, and Fu, Lean

Subjects
FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition
Abstract

Deep learning based approaches has achieved great performance in single image super-resolution (SISR). However, recent advances in efficient super-resolution focus on reducing the number of parameters and FLOPs, and they aggregate more powerful features by improving feature utilization through complex layer connection strategies. These structures may not be necessary to achieve higher running speed, which makes them difficult to be deployed to resource-constrained devices. In this work, we propose a novel Residual Local Feature Network (RLFN). The main idea is using three convolutional layers for residual local feature learning to simplify feature aggregation, which achieves a good trade-off between model performance and inference time. Moreover, we revisit the popular contrastive loss and observe that the selection of intermediate features of its feature extractor has great influence on the performance. Besides, we propose a novel multi-stage warm-start training strategy. In each stage, the pre-trained weights from previous stages are utilized to improve the model performance. Combined with the improved contrastive loss and training strategy, the proposed RLFN outperforms all the state-of-the-art efficient image SR models in terms of runtime while maintaining both PSNR and SSIM for SR. In addition, we won the first place in the runtime track of the NTIRE 2022 efficient super-resolution challenge. Code will be available at https://github.com/fyan111/RLFN.

Published
2022

16. NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

Author

Li, Yawei, primary, Zhang, Kai, additional, Timofte, Radu, additional, Van Gool, Luc, additional, Kong, Fangyuan, additional, Li, Mingxi, additional, Liu, Songwei, additional, Du, Zongcai, additional, Liu, Ding, additional, Zhou, Chenhui, additional, Chen, Jingyi, additional, Han, Qingrui, additional, Li, Zheyuan, additional, Liu, Yingqi, additional, Chen, Xiangyu, additional, Cai, Haoming, additional, Qiao, Yu, additional, Dong, Chao, additional, Sun, Long, additional, Pan, Jinshan, additional, Zhu, Yi, additional, Zong, Zhikai, additional, Liu, Xiaoxiao, additional, Hui, Zheng, additional, Yang, Tao, additional, Ren, Peiran, additional, Xie, Xuansong, additional, Hua, Xian-Sheng, additional, Wang, Yanbo, additional, Ji, Xiaozhong, additional, Lin, Chuming, additional, Luo, Donghao, additional, Tai, Ying, additional, Wang, Chengjie, additional, Zhang, Zhizhong, additional, Xie, Yuan, additional, Cheng, Shen, additional, Luo, Ziwei, additional, Yu, Lei, additional, Wen, Zhihong, additional, Wul, Qi, additional, Li, Youwei, additional, Fan, Haoqiang, additional, Sun, Jian, additional, Liu, Shuaicheng, additional, Huang, Yuanfei, additional, Jin, Meiguang, additional, Huang, Hua, additional, Liu, Jing, additional, Zhang, Xinjian, additional, Wang, Yan, additional, Long, Lingshun, additional, Li, Gen, additional, Zhang, Yuanfan, additional, Cao, Zuowei, additional, Sun, Lei, additional, Alexander, Panaetov, additional, Wang, Yucong, additional, Cai, Minjie, additional, Wang, Li, additional, Tian, Lu, additional, Wang, Zheyuan, additional, Ma, Hongbing, additional, Liu, Jie, additional, Chen, Chao, additional, Cai, Yidong, additional, Tang, Jie, additional, Wu, Gangshan, additional, Wang, Weiran, additional, Huang, Shirui, additional, Lu, Honglei, additional, Liu, Huan, additional, Wang, Keyan, additional, Chen, Jun, additional, Chen, Shi, additional, Miao, Yuchun, additional, Huang, Zimo, additional, Zhang, Lefei, additional, Ayazoglu, Mustafa, additional, Xiong, Wei, additional, Xiong, Chengyi, additional, Wang, Fei, additional, Li, Hao, additional, Wen, Ruimian, additional, Yang, Zhijing, additional, Zou, Wenbin, additional, Zheng, Weixin, additional, Ye, Tian, additional, Zhang, Yuncheng, additional, Kong, Xiangzhen, additional, Arora, Aditya, additional, Zamir, Syed Waqas, additional, Khan, Salman, additional, Hayat, Munawar, additional, Khan, Fahad Shahbaz, additional, Gao, Dandan, additional, Zhou, Dengwen, additional, Ning, Qian, additional, Tang, Jingzhu, additional, Huang, Han, additional, Wang, Yufei, additional, Peng, Zhangheng, additional, Li, Haobo, additional, Guan, Wenxue, additional, Gong, Shenghua, additional, Li, Xin, additional, Liu, Jun, additional, Wang, Wanjun, additional, Zeng, Kun, additional, Lin, Hanjiang, additional, Chen, Xinyu, additional, and Fang, Jinsheng, additional

Published
2022
Full Text
View/download PDF

17. Iterative Learning-Based Predictive Control Method for Electronic Grade Silicon Single Crystal Batch Process.

Author

Wan, Yin, Liu, Ding, and Ren, Jun-Chao

Subjects
*ITERATIVE learning control, *BATCH processing, *SILICON crystals, *SINGLE crystals, *ELECTRONIC control, *PREDICTIVE control systems
Abstract

The growth process of silicon single crystal (SSC) is a typical batch production process, which has the characteristics of batch size, variety, complex process, and intensive technology. In order to accurately control the diameter and thermal field temperature of the Czochralski (Cz) SSC batch production process to ensure that the actual production requirements of electronic-grade SSC are met, this paper proposes an iterative learning-based batch process predictive control strategy Model Predictive Control - Iterative Learning Control - Extended State Observer (MPC-ILC-ESO). The control strategy consists of two parts. The time axis is a dual Model Predictive Control (MPC) controller, which is mainly used to deal with disturbance suppression and constraints in the production process of a single batch of SSC. The iterative axis is the Extended State Observer (ESO) based Iterative Learning Control (ILC) control algorithm to deal with uncertainty and disturbance estimation and compensation in the multi-batch production process. The control effects of the time axis and the batch axis are superimposed as the final controlled object input to ensure the crystal diameter and stable thermal field temperature. Finally, the effectiveness of the proposed control strategy is verified based on the data analysis of the semiconductor industry production process. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

31. Data-Driven and Mechanism-Based Hybrid Model for Semiconductor Silicon Monocrystalline Quality Prediction in the Czochralski Process.

Author

Ren, Jun-Chao, Liu, Ding, and Wan, Yin

Subjects
*SEMICONDUCTORS, *CRYSTAL growth, *CRYSTAL models, *ENERGY transfer, *MACHINE learning, *SEMICONDUCTOR manufacturing
Abstract

The Czochralski (CZ) process is the core technology for producing semiconductor silicon monocrystalline (SMC), and it is a complex batch process. However, the crystal growth rate and crystal diameter, which are key quality indicators, are difficult to detect directly online, and the offline calculation process lags seriously, which easily causes blind crystal quality control. Therefore, this paper proposes a data-driven and mechanism-based hybrid model for semiconductor SMC quality variables prediction in the CZ process. Firstly, a data-driven model JITL-SAE-ELM based on just-in-time learning (JITL) fine-tuning strategy is proposed. This model is used to solve the nonlinear and time-varying relationship of the energy transfer process in the CZ process that cannot be accurately described by traditional mechanism models. Here, the SAE-ELM model integrates a stacked autoencoder (SAE) and an extreme learning machine (ELM), which are used to deeply capture the nonlinear and time-varying features of process data. Secondly, according to the hydrodynamics and geometric behavior, a crystal pulling dynamic mechanism model based on the crystal growth mechanism is constructed, which avoids the complicated heat transfer link. Further, considering the unmodeled dynamics caused by model parameter uncertainty during the combination of the energy transfer model and crystal pulling dynamic mechanism model, a crystal diameter compensation model SAE-ELM was developed to improve the prediction accuracy of the CZ process hybrid model. Finally, an industrial data experiment based on a CZ monocrystal furnace illustrates the proposed method. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

37. Magnetic and Thermal Simulation Study on Vehicular Traction Transformer with Self-Circulating Evaporative Cooling System

Author

Liu Feihui, Xiong Bin, Cheng Ziran, and Liu Ding

Subjects
010302 applied physics, Coupling, Materials science, Field (physics), medicine.medical_treatment, 020208 electrical & electronic engineering, 02 engineering and technology, Mechanics, Traction (orthopedics), 01 natural sciences, Magnetic field, law.invention, Electromagnetic coil, law, Heat generation, 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, medicine, Transformer, Evaporative cooler
Abstract

To solve the serious heat dissipation problem caused by the confined installation condition of vehicular traction transformers, the disk winding structure has been introduced to apply the efficient self-circulating evaporative cooling system. In this paper, the magnetic field and the temperature field of the evaporative cooling traction transformer were analyzed for assessing its performances. According to the 3D magnetic model, the winding loss, the core loss and the tank loss of the evaporative cooling traction transformer at the full load condition were exactly calculated by the Field-Circuit Coupling method. Based on the results of loss calculation, the temperature distributions in the disk coils — the typical element of the main heat sources — were analyzed by the thermal model with the uniform heat generation rate assumption. The simulation results confirm the validity of the evaporative cooling scheme.

Published
2020

38. Research on Color Image Defogging Algorithm based on MSR and CLAHE

Author

Huang Weichao, Liu Ding, Jiao Shangbin, and Yang Zhi

Subjects
Color constancy, Channel (digital image), Computer science, Color image, 010401 analytical chemistry, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, 021001 nanoscience & nanotechnology, 01 natural sciences, 0104 chemical sciences, RGB color space, Primary color, Histogram, Lab color space, Adaptive histogram equalization, 0210 nano-technology, Algorithm, Image restoration, ComputingMethodologies_COMPUTERGRAPHICS, Interpolation
Abstract

To study the defogging of color images, an improved multi-scale Retinex (MSR) algorithm combined with contrast limited adaptive histogram equalization(CLAHE) algorithm is proposed in this paper. Two different defogging methods are proposed for the image without color deviation and the image with color deviation. For the image without color deviation, the RGB color space of the input image is converted to the lab color space. Then the image is converted to RGB color space after MSR processing of L channel. Finally, the image contrast is improved by CLAHE algorithm. Realize the image defogging while keeping the original color of the image. For the image with color deviation, the input image is processed by MSR, the stretch degree of contrast is determined according to the mean and variance of the separated reflection components. Finally, the image contrast is further improved by CLAHE processing to realize the defogging of the restored scene. The experimental results show that the two algorithms in this paper have better effects in image defogging, image primary color maintenance, image scene color recovery and so on.

Published
2020

50. Data-Driven Model Predictive Control of Cz Silicon Single Crystal Growth Process With V/G Value Soft Measurement Model.

Author

Wan, Yin, Liu, Ding, Liu, Cong-Cong, and Ren, Jun-Chao

Subjects
*SILICON crystals, *CRYSTAL growth, *SINGLE crystals, *PREDICTION models, *PREDICTIVE control systems, *CRYSTAL models
Abstract

The growth process of Czochralski (Cz) silicon single crystal is a dynamic time-varying system with nonlinearity, strong coupling, large hysteresis, and uncertain model. Traditional model-based control methods are difficult to achieve satisfactory crystal growth control effects, and it is difficult to ensure that the crystal quality meets the actual process requirements. Therefore, from the perspective of data-driven modeling and control, this paper proposes a model predictive control method for the crystal growth process with a V/G soft-sensing model for measuring crystal quality. First, because the V/G value to measure crystal quality is difficult to obtain directly, a hybrid variable weighted stacked autoencoder random forest (HVW-SAE-RF) soft-sensing model based on data-driven V/G value is established. Here, the HVW-SAE is used to extract the deep quality-related features of the measurable process data, and the RF is used for the regression prediction of the SAE output layer; Second, using the dual closed-loop control strategy, the inner loop is based on the HVW-SAE-RF soft-sensing model of the V/G value, and the predictive PI control method is used to control the V/G value closely related to the crystal quality within a reasonable range, and the outer loop based on real-time estimation of V/G values to achieve nonlinear model predictive control (NMPC) of crystal diameter; finally, the effectiveness of the proposed method is verified based on the industrial production process data of silicon single crystal. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results