检索结果-南通市图书馆

Building Simulation 2024年第4期17卷 639-655页

作者： Shanshuo Xing Jili Zhang Song Mu Dalian University of technology Dalian116024China Guangdong Airport Baiyun information technology co. Ltd.Guangzhou510000China

Optimization for the multi-chiller system is an indispensable approach for the operation of highly efficient chiller *** optima obtained by model-based optimization algorithms are dependent on precise and solvable objective *** classical neural networks cannot provide co.vex input-output mappings despite capturing impressive nonlinear fitting capabilities,resulting in a reduction in the robustness of model-based *** this paper,we leverage the input co.vex neural networks(ICNN)to identify the chiller model to co.struct a co.vex mapping between co.trol variables and the objective function,which enables the NN-based OCL as a co.vex optimization problem and apply it to multi-chiller optimization for optimal chiller loading(OCL).Approximation performances are evaluated through a four-model co.parison based on an experimental data set,and the statistical results show that,on the premise of retaining prior co.vexities,the proposed model depicts excellent approximation power for the data set,especially the unseen ***,the ICNN model is applied to a typical OCL problem for a multi-chiller system and co.bined with three types of optimization *** with co.ventional and meta-heuristic methods,the numerical results suggest that the gradient-based BFGS algorithm provides better energy-saving ratios facing co.secutive co.ling load inputs and an impressive co.vergence speed.

关键词： chiller plant input co.vex neural network optimal load distribution co.vex optimization

Cyber-Physical Resilience Enhancement for Power Transmission Systems with Energy Storage Systems

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CSEE Journal of Power and Energy Systems 2024年第2期10卷 844-855页

作者： Wenhao Zhang Dongyang Rui Weihong Wang Yang Guo Zhaoxia Jing Wenhu Tang School of Electric Power Engineering South China University of TechnologyGuangzhou 510640China guangzhou Zhiguang Electric co. Ltd and Zhiguang Research Institute(Guangzhou)Co.LtdGuangzhou 510765China

In a power system, when extreme events occur, such as ice storm, large scale blackouts may be unavoidable. Such small probability but high risk events have huge impact on power systems. Most resilience research in power systems only co.siders faults on the physical side, which would lead to overly idealistic results. This paper proposes a two-stage cyber-physical resilience enhancement method co.sidering energy storage (ES) systems. The first stage calculates optimal planning of ES systems, and the seco.d stage assesses resilience and enhancement of ES systems during the disaster. In the proposed model, cyber faults indirectly damage the system by disabling monitoring and co.trol function of co.trol center. As a result, when detection and response process of physical faults are blocked by cyber failures, serious load shedding occurs. Such a cyber-physical co.pling mechanism of fault, response, restoration process is demonstrated in the modified IEEE Reliable Test System-79 (RTS-79). Simulation results show co.pared with the physical-only system, the cyber-physical system has a more accurate but degraded resilient performance. Besides, ES systems setting at proper place effectively enhance resilience of the cyber-physical transmission system with less load Shedding.

关键词： Cyber-physical faults energy storage systems resilience enhancement transmission systems

Road sub-surface defect detection based on gprMax forward simulation-sample generation and Swin Transformer-YOLOX

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Structural and Civil Engineering 2024年第3期18卷 334-349页

作者： Longjian LI Li YANG Zhongyu HAO Xiaoli SUN Gongfa CHEN School of Civil and Transportation Engineering Guangdong University of TechnologyGuangzhou 510006China JSTI Group Guizhou Engineering Survey and Design co. Ltd.Guangzhou 510800China guangzhou Municipal Engineering Testing co. Ltd.Guangzhou 510520China

Training samples for deep learning networks are typically obtained through various field experiments,which require significant manpower,resource and time ***,it is possible to utilize simulated data to augment the training *** this paper,by co.paring the actual experimental model with the simulated model generated by the gprMax[1]forward simulation method,the feasibility of obtaining simulated samples through gprMax simulation is ***,the samples generated by gprMax forward simulation are used for training the network to detect objects in existing real *** the same time,aiming at the detection and intelligent reco.nition of road sub-surface defects,the Swin-YOLOX algorithm is introduced,and the excellence of the detection network,which is improved by augmenting the simulated samples with real samples,is further *** co.paring the prediction performance of the object detection models,it is observed that the model trained with mixed samples achieved a recall of 94.74%and a mean average precision(maP)of 97.71%,surpassing the model trained only on real samples by 12.95%and 15.64%,*** feasibility and excellence of training the model with mixed samples are *** potential of using a fusion of simulated and existing real samples instead of repeatedly acquiring new real samples by field experiment is demonstrated by this study,thereby improving detection efficiency,saving resources,and providing a new approach to the problem of multiple interpretations in ground penetrating radar(GPR)data.

关键词： ground penetrating radar gprMax forward modeling sample generation Swin-YOLOX object detection

Carbon efficiency modeling and optimization of solar-powered cellular networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(information Sciences) 2024年第5期67卷 228-243页

作者： Yuxi ZHAO Xiaohu GE Wen YAN Tao HAN Yi ZHONG School of Electronic information and co.munications Huazhong University of Science and Technology Huawei technology co. Ltd.

As wireless co.munication traffic experiences rapid growth, the carbon emissions caused by the co.munication industry are also on the rise. To achieve “carbon neutrality”, researchers are co.sidering the use of renewable energy sources to power cellular networks, thereby reducing carbon emissions. However, a challenge arises when using renewable energy, specifically owing to the unpredictable nature of both the energy co.sumption of the cellular network and the power generation from renewable sources. This inco.sistency results in low renewable energy utilization and reduced carbon efficiency. Herein, we co.struct a carbon efficiency model of solar-powered cellular networks using practical data from solar radiation. We propose a mechanism that alternately optimizes the performance of the renewable energy network and the cellular network. This approach is based on co.vex optimization theory and the Dinkelback algorithm, and it leads to the design of a carbon efficiency optimization algorithm. This algorithm aims to improve the carbon efficiency of cellular networks and reduce their carbon emissions. Simulation results demonstrate that our optimization scheme yields a maximum improvement of 2.56 × 108bps/g in the carbon efficiency of the cellular network as co.pared to co.ventional power allocation schemes such as the traditional water filling method and heuristic energy sharing and charge/discharge algorithms.

关键词： cellular networks renewable energy carbon efficiency co.vex optimization theory dinkelbach

A Blockchain-Based Proxy Re-Encryption Scheme with co.ditional Privacy Protection and Auditability

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

China co.munications 2024年第7期21卷 267-277页

作者： Chen Guo PengWeijun Wu Jing Fang Youxuan Ye Keke Xin Yanshuang China Mobile information technology co. LtdBeijing 100037China China Mobile information technology co. LtdShenzhen 518048China

With the development of Internet of Things technology,intelligent door lock devices are widely used in the field of house *** the traditional housing leasing scenario,problems of door lock information disclosure,tenant privacy disclosure and rental co.tract disputes frequently occur,and the security,fairness and auditability of the housing leasing transaction cannot be *** solve the above problems,a blockchain-based proxy re-encryption scheme with co.ditional privacy protection and auditability is *** scheme implements fine-grained access co.trol of door lock data based on attribute encryption technology with policy hiding,and uses proxy re-encryption technology to achieve auditable supervision of door lock information *** encryption technology and zero-knowledge proof technology are introduced to ensure the co.fidentiality of housing rent information and the fairness of rent *** co.struct a decentralized housing lease transaction architecture,the scheme realizes the efficient co.laboration between the door lock data ciphertext stored under the chain and the key information ciphertext on the chain based on the blockchain and InterPlanetary File ***,the security proof and co.puting performance analysis of the proposed scheme are carried *** results show that the scheme can resist the chosen plaintext attack and has low co.putational co.t.

关键词： attribute encryption blockchain homomorphic encryption house leasing proxy re-encryption zero-knowledge proof

Feature Selection Using Tree Model and Classification Through co.volutional Neural Network for Structural Damage Detection

在线全文

学校读者我要写书评

暂无评论

Acta Mechanica Solida Sinica 2024年第3期37卷 498-518页

作者： Zihan Jin Jiqiao Zhang Qianpeng He Silang Zhu Tianlong Ouyang Gongfa Chen School of Civil and Transportation Engineering Guangdong University of TechnologyGuangzhou510006China Guangdong Tianxin Electric Power Engineering Testing co. LtdGuangzhou510663China

Structural damage detection(SDD)remains highly challenging,due to the difficulty in selecting the optimal damage features from a vast amount of *** this study,a tree model-based method using decision tree and random forest was employed for feature selection of vibration response signals in *** datasets were obtained by numerical experiments and vibration experiments,*** features extracted using this method were input into a co.volutional neural network to determine the location of structural *** indicated a 5%to 10%improvement in detection accuracy co.pared to using original datasets without feature selection,demonstrating the feasibility of this *** proposed method,based on tree model and classification,addresses the issue of extracting effective information from numerous vibration response signals in structural health monitoring.

关键词： Feature selection Structural damage detection Decision tree Random forest co.volutional neural network

Mode-dependent dynamic gain of all-fiber FM-EDFA under various pump manipulation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Optics Letters 2024年第2期22卷 128-134页

作者：方翼鸿张心怡黄锡恒曾研许鸥李建平付松年秦玉文 Institute of Advanced Photonics technology School of Information EngineeringGuangdong University of TechnologyGuangzhou 510006China Guangdong Provincial Key Laboratory of information Photonics technology Guangdong University of TechnologyGuangzhou 510006China Key Laboratory of Photonic technology for Integrated Sensing and co.munication Ministry of EducationGuangdong University of TechnologyGuangzhou 510006China

The dynamic gain of a few-mode erbium-doped fiber amplifier(FM-EDFA)is vital for the long-haul mode division multiplexing(MDM)***,we investigate the mode-dependent dynamic gain of an FM-EDFA under various manipulations of the pump ***,we numerically calculate the gain variation with respect to the input signal power,where a modedependent saturation input power occurs under different pump *** under the fixed intensity profile of the pump laser,the saturation input power of each spatial mode is ***,high-order mode pumping leads to a co.pression of the linear amplification region,even though it is beneficial for the mitigation of the differential modal gain(DMG)arising in all guided ***,we develop an all-fiber 3-mode EDFA,where the fundamental mode of the pump laser can be efficiently co.verted to the LP_(11)mode using the all-fiber mode-selective co.pler(MSC).In co.parison with the traditional LP_(01)pumping scheme,the DMG at 1550 nm can be mitigated from 1.61 dB to 0.97 dB under the LP_(11)mode pumping,while both an average gain of 19.93 dB and a DMG of less than 1 dB can be achieved from 1530 nm to 1560 ***,the co.responding signal input saturation powers are reduced by 0.3 dB for the LP_(01)mode and 1.6 dB for the LP_(11)mode,*** theoretical and experimental results indicate that a trade-off occurs between the DMG mitigation and the extension of the linear amplification range when the intensity profile of pump laser is manipulated.

关键词： few-mode erbium-doped fiber amplifier differential modal gain saturation input power

High-frequency Resonance Analysis and Impedance Reshaping co.trol of MMC-HVDC System Based on Frequency co.pling Impedance Model

在线全文

学校读者我要写书评

暂无评论

Journal of Modern Power Systems and Clean Energy 2024年第2期12卷 646-657页

作者： Juanjuan Wang Wei Chen Yuekun Liu Chuang Fu Yunming Ye Junjie Feng School of Electric Power South China University of TechnologyGuangzhouChina Guangdong Power Grid co. Ltd.GuangzhouChina Electric Power Research Institute China Southern Power GridGuangzhouChina

In recent years, high-frequency resonance (HFR) events occurred in several modular multilevel co.verter based high-voltage direct current (MMC-HVDC) projects. The time delay of an MMC-HVDC system is the critical factor that induces HFR. The frequency co.pling affects the impedance characteristics of an MMC and further deteriorates system stability. Therefore, in this paper, a multi-input multi-output admittance model of an MMC-HVDC system is developed to analyze its frequency characteristics. The effects of current loop, power loop, phase-locked loop, and operating point on the MMC frequency co.pling degree are analyzed in detail. Meanwhile, to further suppress HFR in the MMC-HVDC system, an enhanced impedance reshaping co.trol strategy based on the equivalent single-input single-output impedance model is proposed. Finally, the accuracy of the enhanced impedance model and the effectiveness of the impedance reshaping co.trol are verified by electromagnetic transient simulations in PSCAD.

关键词： Modular multilevel co.verter based high-voltage direct current(MMC-HVDC) high-frequency resonance frequency co.pling impedance model impedance reshaping co.trol

Predictive value of T cell receptor repertoire profiling for immunosuppressive therapy in severe aplastic anemia

在线全文

学校读者我要写书评

暂无评论

Genes & Diseases 2024年第1期11卷 95-98页

作者： Cunte Chen Yuling Zhang Dongpei Lu Zelong Zhang Jun Yang Xiaowei Chen Ming Zhou Wenjian Mo Caixia Wang Qinghua Cai Yumiao Li Ruiqing Zhou Shilin Xu Wei Zhou Tingfen Deng Shiyi Pan Yanli Xu Shunqing Wang Yuping Zhang Department of Hematology Guangzhou First People's HospitalSouth China University of TechnologyGuangzhouGuangdong 510180China guangzhou Junruikang Biotechnology co. LtdGuangzhouGuangdong 510700China

Increasing evidence supports the hypothesis of autologous immune attack in severe aplastic anemia(SAA):the predominant role of activated cytotoxic T cells(CTL)expressing-interferon in inhibiting the growth of bone marrow(BM)cells,putative autoantigens,and oligoclonal expansion of CD8+T cells.1 For SAA patients,the definitive therapies are immunosuppressive therapy(IST)or hematopoietic stem transplantation(HSCT).

关键词： anemia aplastic interferon

Style-co.ditioned music generation with Transformer-GANs

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of information technology & Electronic Engineering 2024年第1期25卷 106-120页

作者： Weining WANG Jiahui LI Yifan LI Xiaofen XING School of Electronic and information Engineering South China University of TechnologyGuangzhou 510600China

Recently,various algorithms have been developed for generating appealing ***,the style co.trol in the generation process has been somewhat *** style refers to the representative and unique appearance presented by a musical work,and it is one of the most salient qualities of *** this paper,we propose an innovative music generation algorithm capable of creating a co.plete musical co.position from scratch based on a specified target style.A style-co.ditioned linear Transformer and a style-co.ditioned patch discriminator are introduced in the *** style-co.ditioned linear Transformer models musical instrument digital interface(MIDI)event sequences and emphasizes the role of style ***,the style-co.ditioned patch discriminator applies an adversarial learning mechanism with two innovative loss functions to enhance the modeling of music ***,we establish a discriminative metric for the first time,enabling the evaluation of the generated music’s co.sistency co.cerning music *** objective and subjective evaluations of our experimental results indicate that our method’s performance with regard to music production is better than the performances enco.ntered in the case of music production with the use of state-of-the-art methods in available public datasets.

关键词： Music generation Style-co.ditioned Transformer Music emotion