检索结果-内蒙古大学图书馆

Efficient Computer Vision-Based Excavator Bucket Fill Estimation Using Depth Map and Faster R-Cnn

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Helian, Bobo Huang, Xiaoqian Yang, Meng Bian, Yongming Geimer, Marcus Institute of Mobile Machines Karlsruhe Institute of Technology Karlsruhe76131 Germany State Key Laboratory of Fluid Power and Mechatronic System Zhejiang University Hangzhou310027 China School of Mechanical Engineering Tongji University Shanghai201804 China Shanghai Engineering Research Center for Safety Intelligent Control of Building Machinery Shanghai200032 China

Excavators play an essential role in the construction industry, and the development of autonomous excavator systems is important for increasing productivity and improving worker safety. Accurate estimation of the volume of material in the excavator bucket is a key metric for monitoring and evaluating system automation performance. In this study, a novel solution is proposed that utilizes 2D depth maps as input to a faster region convolutional neural network (Faster R-CNN) model for bucket volume fill estimation. This approach achieves a high estimation accuracy while maintaining a fast real-time processing speed. In addition, a custom loss function is proposed specifically for the classification-regression task of this study to improve the network's generalization despite the data out of distribution. Comparative experiments show that the proposed approach achieves an impressive 96.91% accuracy in fill factor estimation, demonstrating its advantages and promising potential in the practical estimation of automated excavator operations. © 2023, The Authors. All rights reserved.

关键词： Automation

Experimental study of smart buildings providing fast frequency response

学校读者我要写书评

暂无评论

Experimental study of smart buildings providing fast frequen...

Energy, Power and Grid (ICEPG), International Conference on

作者： Zhendong Zhao Longjun Wang Zhihui Deng Yiping Chen Shunxin Wei Ziqiang Wang School of Electric Power South China University of Technology Guangzhou China DC building laboratory Shenzhen Building Science Research Institute Co. LTD Shenzhen China Southern Power Grid Southern Power Grid New Power System (Beijing) Research Institute China Beijing China Shien-ming wu school of intelligent engineering South China University of Technology Guangzhou China Power dispatch control center Shenzhen Power Supply Bureau Co. LTD Shenzhen China

ISBN: (数字)9798350377798

ISBN: (纸本)9798350377804

As the penetration of renewable energy increases, the mechanical inertia of the power system decreases, weakening the system’s ability to withstand disturbances, particularly during large frequency events. Smart buildings on the demand side show promise as candidates for providing frequency regulation. This paper presents a fast frequency response test for smart buildings. A series of tests, including frequency step tests, frequency ramp tests, and hybrid tests, were conducted to assess the fast frequency response performance of smart buildings. The results indicate that the building has regulation capabilities comparable to traditional generator units in primary frequency control and demonstrates strong potential for fast frequency response. These findings are now being used to guide the development of standards for demand-side adjustable resources participating in fast frequency response.

关键词： Technical requirements Renewable energy sources Smart buildings Frequency response Regulation Generators Voltage control Protection Frequency control Standards

Atf-Bss: Adaptive Time-Frequency Blind Source Separation for High Reverberation and Echo Environments

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Xie, Yuan Zou, Tao Chen, Ci Sun, Weijun Xie, Shengli School of Mechanical and Electrical Engineering Guangzhou University Guangdong-Hong Kong-Macao Key Laboratory of Multi-scale Information Fusion and Collaborative Optimization Control of Complex Manufacturing Process Guangzhou510006 China School of Automation Guangdong University of Technology Joint International Research Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education of the P.R.C. Guangzhou510006 China School of Automation Guangdong University of Technology Guangdong Key Laboratory of IoT Information Processing Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China School of Automation Guangdong University of Technology Key Laboratory of Intelligent Detection and the IoT in Manufacturing Ministry of Education 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou510006 China

Blind source separation with high reverberation and echoes is an open and extremely challenging issue. Because the room reverberation and echoes have an important influence on acoustics quality, bringing great difficulty to the independent source separation. In the paper, an adaptive time-frequency blind source separation (ATF-BSS) algorithm is designed to deal with the high reverberation and echoes, which can adaptively attenuate the audible echoes and enhance the harmonic structure of the real-world audio signals, achieving excellent separation performance. Firstly, an equalizer network is designed for the room impulse response to weakening audible echoes under the high reverberation and echo environments without changing the perceived timbre. Furthermore, an adaptive time-frequency Wiener-like masking is presented to enhance the dominant signal and attenuate the other components having less energy than the dominant signal. To the best of our knowledge, this is the first attempt to incorporate the advantages of an equalizer network for removing or weakening audible echoes and adaptive time-frequency masking to solve blind separation with high reverberation and echoes. Experimental results on the public audio datasets demonstrate that the proposed ATF-BSS algorithm improves signal intelligibility and achieves much better separation performance than the state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Reverberation

A 4-Channel Ultrafast Wavelength-Swept REC-DFB Laser Array for Fiber Bragg Grating Interrogation

学校读者我要写书评

暂无评论

A 4-Channel Ultrafast Wavelength-Swept REC-DFB Laser Array f...

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Lingxin Meng Pan Dai Qilu Ban Kaichuan Xu Jiacheng Wang Zhen Li Feng Wang Jie Zeng Shaobo Li Xiang Ma Xiangfei Chen Key Laboratory of Intelligent Optical Sensing and Manipulation of the Ministry of Education & Engineering National Laboratory of Solid State Microstructures Research Center of Precision Photonics Integration and System Application of the Ministry of Education College of Engineering and Applied Sciences Nanjing University Nanjing China State Key Laboratory of Mechanics and Control for Aerospace Structures Nanjing University of Aeronautics and Astronautics Nanjing China Optical Communication Research and Development Center the 54th Research Institute of China Electronics Technology Group Corporation Shijiazhuang China

We present a four-channel ultrafast wavelength-swept distributed feedback (DFB) semiconductor laser array based on the reconstruction-equivalent-chirp (REC) technique using instantaneous injection current modulation. With the aid of our designed laser driving circuit system consists of the microcontroller unit (MCU), field-programmable gate array (FPGA) and negative metal-oxide-semiconductor field effect transistors (n-MOSFETs), the precise pulse driving current for the 4-channel wavelength-swept REC-DFB laser array can be generated and a fast tuning of 16.424 nm within 10 μs is achieved. To further investigate the tuning performance of the proposed wavelength-swept laser source, we then applied it to the fiber Bragg grating (FBG) interrogation system and four FBG temperature sensor arrays were successfully demodulated. The development of high-efficient optical sensing systems heavily relies on the significance of the ultrafast wavelength-swept laser source, which has the potential to greatly enhance FBG interrogator performance in the future.

关键词：

Atf-Bss: Adaptive Time-Frequency Blind Source Separation for High Reverberation and Echo Environments

学校读者我要写书评

暂无评论

SSRN 2023年

Blind source separation with high reverberation and echoes is an open and extremely challenging issue. Room reverberation and echoes have an important influence on acoustics quality, causing great difficulty in independent source separation. In the paper, an adaptive time-frequency blind source separation algorithm (ATF-BSS) is designed to deal with high reverberation and echoes, which can adaptively attenuate audible echoes and enhance the harmonic structure of real-world audio signals, achieving excellent separation performance. Firstly, an equalizer network is designed for the room impulse response to weakening audible echoes under high reverberation and echo environments without changing the perceived timbre. Furthermore, an adaptive time-frequency Wiener-like masking is presented to enhance the dominant signal and attenuate the other components that have less energy than the dominant signal. To the best of our knowledge, this is the first attempt to incorporate the advantages of an equalizer network for removing or weakening audible echoes and adaptive time-frequency masking to solve blind separation with high reverberation and echoes. Experimental results on public audio datasets demonstrate that the proposed ATF-BSS algorithm improves signal intelligibility and achieves much better separation performance than state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Reverberation

Atf-Bss: Adaptive Time-Frequency Blind Source Separation for High Reverberation and Echo Environments

学校读者我要写书评

暂无评论

SSRN 2023年

Blind source separation with high reverberation and echoes is an open and extremely challenging issue. Room reverberation and echoes have an important influence on acoustics quality, causing great difficulty in independent source separation. In the paper, an adaptive time-frequency blind source separation algorithm (ATF-BSS) is designed to deal with high reverberation and echoes, which can adaptively attenuate audible echoes and enhance the harmonic structure of real-world audio signals, achieving excellent separation performance. Firstly, an equalizer network is designed for the room impulse response to weakening audible echoes under high reverberation and echo environments without changing the perceived timbre. Furthermore, an adaptive time-frequency Wiener-like masking is presented to enhance the dominant signal and attenuate the other components that have less energy than the dominant signal. ATF-BSS algorithm incorporates the advantages of an equalizer network for removing or weakening audible echoes and adaptive time-frequency masking for high reverberation and echoes scene, improving the performance of blind separation. Experimental results on public audio datasets demonstrate that the proposed ATF-BSS algorithm improves signal intelligibility and achieves much better separation performance than state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Reverberation

Room Impulse Response Reshaping-Based Blind Source Separation in an Underdetermined Reverberant Environment

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Xie, Yuan Zou, Tao Yang, Junjie Sun, Weijun Xie, Shengli School of Mechanical and Electrical Engineering Guangzhou University Guangdong-Hong Kong-Macao Key Laboratory of Multi-scale Information Fusion and Collaborative Optimization Control of Complex Manufacturing Process Guangzhou510006 China School of Automation Guangdong University of Technology Joint International Research Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education of the P.R.C. Guangzhou510006 China School of Automation Guangdong University of Technology Guangdong Key Laboratory of IoT Information Processing Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China School of Automation Guangdong University of Technology Key Laboratory of Intelligent Detection and the IoT in Manufacturing Ministry of Education 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou510006 China

Blind source separation in an underdetermined reverberation environment is a very challenging issue. The classical method is based on the expectation-maximization algorithm. However, it is limited in a high reverberation environment, resulting in bad or even invalid separation performance. To get rid of this restriction, a room impulse response reshaping-based blind source separation algorithm is designed to solve the signal separation problem in an underdetermined reverberant environment. Firstly, a room impulse response reshaping technology is designed to eliminate the influence of audible echo for the reverberant environment, improving the quality of the received signals. Then, a new mathematical model of time-frequency mixing signals is established to reduce the approximation error of model transformation caused by high reverberation. Furthermore, an improved expectation-maximization algorithm is proposed for real-time update learning rules of model parameters, and then the sources are separated using the estimators provided by the improved expectation maximization method. Experimental results based on source separation of speech and music mixtures demonstrate that the proposed algorithm achieves better separation performance while maintaining much better robustness than the popular expectation-maximization methods. © 2023, The Authors. All rights reserved.

关键词： Blind source separation

A Low Delay AES Round Transform Architecture Using Constant Matrix Multiplications Merging Technologies

学校读者我要写书评

暂无评论

A Low Delay AES Round Transform Architecture Using Constant ...

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Xinxing Zheng Xiaoqiang Zhang Fan Yang Mingyu Xu Han Yan College of Information Engineering Wuhu Institute of Technology Wuhu China Key Laboratory of Advanced Perception and Intelligent Control of High-end Equipment Ministry of Education Wuhu China Engineering Research Center of Vehicle-Mounted Display Integration System Wuhu China College of Electrical Engineering Anhui Polytechnic University Wuhu China

ISBN: (纸本)9781665409858

This paper presents a low delay architecture design method for the hardware implementation of the Advanced Encryption Standard (AES) algorithm. The proposed architecture is designed by using constant matrix multiplications (CMM) merging technologies. To reduce the area cost in hardware implementations, S-box/InvS-box is usually implemented with composite field arithmetic (CFA) technologies. In this paper, CMM in CFA-based S-box/InvS-box are further merged with constant coefficient multiplications in MixColumns/ InvMixColumns, which can also be expressed as CMM forms. By the merging, the delay of the hardware implementation of encryption round transform is reduced at the cost of slight area cost increasing, and both delay and area cost are reduced in hardware implementations of decryption round transform. Hardware complexities analysis indicates that our designs have less delay compared with previous works.

关键词： Industrial electronics Costs Design methodology Merging Transforms Hardware Delays

Scheduling optimization of silicon single crystal production process based on adaptive improved particle swarm optimization

学校读者我要写书评

暂无评论

Scheduling optimization of silicon single crystal production...

Chinese Automation Congress (CAC)

作者： Lu Kang Ding Liu Yali Wu Guozheng Ping School of Automation and Information Engineering Xi’an University of Technology National and Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an China School of Automation and Information Engineering Xi’an University of Technology National and Local Joint Engineering Research Center of Crystal Growth Xi’an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an China School of Automation and Information Engineering Xi’an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an China

ISBN: (纸本)9781665426480

Aiming at the potential safety hazards of silicon single crystal production enterprises in the process of multi-furnace silicon single crystal production, and considering the maximum power load requirements in actual enterprises, a silicon single crystal production process scheduling model with the goal of minimizing the maximum completion time was established. Based on this model, an adaptive improved particle swarm optimization algorithm (Adaptive GPSO) is proposed to solve it. The algorithm retains the individual optimal value and global optimal value of the particle swarm algorithm, and introduces the crossover operation and mutation operation in the genetic algorithm to improve the new individual generation mechanism. At the same time, it performs dynamic iterative calculations on the mutation probability and crossover probability to avoid the algorithm fall into the local optimum, and improve the diversity and convergence of the algorithm. By solving different scales scheduling problems of silicon single crystal production process, the experiments on real-world data shows that the feasibility and effectiveness of the proposed algorithm.

关键词： Adaptation models Heuristic algorithms Crystals Production Probability Silicon Scheduling