检索结果-内蒙古大学图书馆

Prediction and control of strip thickness based on Bayesian neural networks

学校读者我要写书评

暂无评论

Beijing Keji Daxue Xuebao/Journal of University of Science a...

Beijing Keji Daxue Xuebao/Journal of University of Science and Technology Beijing 2010年第2期32卷 256-262页

作者： Peng, Kai-Xiang Yu, Shang-Zhi School of Information Engineering University of Science and Technology Beijing Beijing 100083 China Key Laboratory of the Ministry of Education for Advanced Control of Iron and Steel Process University of Science and Technology Beijing Beijing 100083 China

The Bayesian statistical theory was adopted to improve traditional neural network algorithms, and constraints representing network structural complexity were introduced to the network objective function in order to avoid over-fitting the networks and enhance the generalization ability. The improved networks were applied to strip thickness prediction in Jigang 1700mm mill, and the prediction result is superior to that of traditional neural networks in forecasting accuracy, training time and network stability. Then, the Bayesian neural networks were used to predict the plasticity coefficient of strips. Finally, the real-time forecasts of exit thickness and plasticity coefficient of strips were synthetically utilized in the thickness control system of hot strip rolling to improve strip quality further.

关键词： Forecasting

Multiple model adaptive control of a kind of discrete time nonlinear

学校读者我要写书评

暂无评论

Kongzhi yu Juece/control and Decision 2010年第6期25卷 841-846页

作者： Li, Xiao-Li School of Information Engineering University of Science and Technology Beijing Beijing 100083 China Key Laboratory of Advanced Control of Iron and Steel Process of Ministry of Education University of Science and Technology Beijing Beijing 100083 China

According to the varying scope of parameters, multiple models are set up for a kind of discrete time nonlinear system, and the corresponding controllers based on these models are given. At every sample time, the best model is selected by using an index switching function based on the estimation error of every model, and the controller based on this model is switched. "Localization" method is used to decrease the computing quantity of multiple model adaptive controller without the loss of control property. It can be proved that the closed-loop system is stable when different controllers are switched each other. Due to the existence of multiple models, the control performance is improved greatly.

关键词： controllers

A Risk-Averse Just-In-Time Scheme for Learning-Based Operation of Microgrids with Coupled Electricity-Hydrogen-Ammonia under Uncertainties

学校读者我要写书评

暂无评论

arXiv

arXiv 2024年

作者： Li, Longyan Ning, Chao Pan, Guangsheng Zhang, Leiqi Gu, Wei Zhao, Liang Du, Wenli Shahidehpour, Mohammad Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China School of Electrical Engineering Southeast University Nanjing210096 China Zhejiang Key Laboratory of Distributed Generations and Microgrid Technology State Grid Zhejiang Electric Power Research Institute Hangzhou310014 China Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education East China University of Science and Technology China Department of Electrical and Computer Engineering Illinois Institute of Technology ChicagoIL60616 United States

This paper proposes a Risk-Averse Just-In-Time (RAJIT) operation scheme for Ammonia-Hydrogen-based Micro-Grids (AHMGs) to boost electricity-hydrogen-ammonia coupling under uncertainties. First, an off-grid AHMG model is developed, featuring a novel multi-mode ammonia synthesis process and a hydrogen-ammonia dual gas turbine with tunable feed-in ratios. Subsequently, a state-behavior mapping strategy linking hydrogen storage levels with the operation modes of ammonia synthesis is established to prevent cost-ineffective shutdowns. The proposed model substantially improves operational flexibility but results in a challenging nonlinear fractional program. Based upon this model, a data-driven RAJIT scheme is developed for the real-time rolling optimization of AHMGs. Unlike conventional one-size-fits-all schemes using one optimization method throughout, the data-driven RAJIT intelligently switches between cost-effective deterministic optimization and risk-averse online-learning distributionally robust optimization depending on actual risk profiles, thus capitalizing on the respective strengths of these two optimization methods. To facilitate the solution of the resulting nonlinear program, we develop an equivalent-reformulation-based solution methodology by leveraging a constraint-tightening technique. Numerical simulations demonstrate that the proposed scheme guarantees safety and yields an overall cost reduction up to 14.6% compared with several state-of-the-art methods. © 2024, CC BY.

关键词： Ammonia

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. 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

Effect of Ph-Dependent Intermediate on the Performance of Lifepo4/C Cathode Material

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Lin, Sen Zhang, Ting Yu, Jianguo National Engineering Research Center for Integrated Utilization of Salt Lake Resources East China University of Science and Technology Shanghai China State Environmental Protection Key Laboratory of Environmental Risk Assessment and Control on Chemical Process East China University of Science and Technology Shanghai China Engineering Research Center of Salt Lake Resources Process Engineering Ministry of Education East China University of Science and Technology Shanghai China

Ferric phosphate (FePO4), as the precursor for LiFePO4 preparation, is customary to be obtained by coprecipitation for its convenience and low cost. In this study, FePO4 with different morphology were prepared at gradient coprecipitation pH and reduced to form LiFePO4/C cathode materials to quantitatively investigate the pH-dependent intermediate influence. The characterization results showed that the structure and morphology of FePO4 changed markedly from crystalline hydro-micro ball to amorphous and to fusiform intermediate with the increase of coprecipitation basicity, while high concentration of NH4+ would occur in the intermediate composition with a severe particle growth and aggregation at exorbitant pH. The electrochemical analysis manifested that FePO4 morphology and crystallinity would not affect the cyclic stability of cathode materials, however, a more even and porous FePO4 obtained from intermediate at highly acidic solution would equip the LiFePO4/C with an excellent performance. Besides, the hydro-crystalline intermediate-oriented FePO4 could provide LiFePO4/C with an excellent low charging-rate performance and the LiFePO4/C from amorphous spherical intermediate-oriented precursor was endowed with an advantageous high-rate capacity via the excellent crystallinity and charge transfer. Uneven morphology and severe particle growth would bring about obvious reduction to the discharge capacity of LiFePO4/C that the discharge capacity at 1 C rate would decrease from the optimum of 157.79 mAh·g-1 to less than 104.38 mAh·g-1 and 82.79mAh·g-1 for the FePO4 prepared with intermediates precipitated at pH of 3.0 and 2.0, respectively. © 2022, The Authors. All rights reserved.

关键词： Iron compounds

Molten Salt-Mediated Surface Reconstruction Induced Orientation-Growth of 1d/2d Heterostructure for High-Sensitivity H2s Gas Sensing

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Yang, Xuan-Yu Zhao, Rui-Jie Xie, Ke-Feng Xu, Hua Fang, Shao-Ming Zhang, Yong-Hui College of Materials and Chemical Engineering Collaborative Innovation Center of Environmental Pollution Control and Ecological Restoration Zhengzhou University of Light Industry Zhengzhou450002 China Key Laboratory of Applied Surface and Colloid Chemistry Ministry of Education Shaanxi China Key Laboratory for Advanced Energy Devices School of Materials Science and Engineering Shaanxi Normal University Xi’an710119 China College of Chemistry and Chemical Engineering Lanzhou Jiaotong University Lanzhou730070 China

Multi-dimensional heterostructure with integrative dimensionality and synergic effects are intriguing, but the rational synthesis and further study into the influence of structure on the surface reaction performance are still urgent tasks. Here, we report a molten salt mediated method to synthesize 1D/2D heterostructure. Particularly, the Sn-O bonds and Cu-O bonds on the surface of materials can be destabilized due to the strong polarization of LiCl-KCl molten salt, and the newly formed CuCl species can be homogeneously dispersed in amorphous SnOx. Notably, the surface reconstruction induced orientation-growth of 1D Cu-doped SnO2 single crystal along the (110) facet occurs in the recrystallization process to form the 1D nanoribbon/2D nanosheet. As a proof of the concept, the unique 1D/2D heterostructure integrate the merits of fast electron transfer and numerous surface active O2-(ad) species, which endow it superior gas sensing performance to H2S. Experimental and theoretical studies reveal high sensing response (4.14-fold than pristine SnO2), fast response and recovery rate and high selectivity at 150 oC is attributed to the construction of 1D/2D heterostructure and the two-pathway sensing mechanism. It is believed the surface-reconstruction induced orientation-growth method in molten salt can be extended to synthesize other 1D/2D heterostructures for various applications. © 2023, The Authors. All rights reserved.

关键词： Gas detectors

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

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. 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 novel hybrid algorithm based on improved marine predators algorithm and equilibrium optimizer for parameter extraction of solar photovoltaic models

学校读者我要写书评

暂无评论

Heliyon 2024年第19期10卷 e38412页

作者： Liang, Ziyuan Wang, Zhenlei Mohamed, Ali Wagdy Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education East China University of Science and Technology Shanghai 200237 China State Key Laboratory of Industrial Control Technology East China University of Science and Technology Shanghai 200237 China Operations Research Department Faculty of Graduate Studies for Statistical Research Cairo University Giza 12613 Egypt

In the field of solar photovoltaic (PV) systems, the accurate and reliable extraction of parameters from PV models is crucial for effective simulation, evaluation, and control. Although various optimization algorithms have been widely used for parameter extraction in solar PV systems, the accuracy and reliability of the parameters extracted by these methods usually fall short of the expected standards. To address these shortcomings, a novel hybrid algorithm that combines the improved marine predators algorithm (MPA) with the equilibrium optimizer (EO), named IMPAEO, is proposed. In the IMPAEO, an elite opposition-based learning strategy is introduced to expand the exploration range of the algorithm to enhance population diversity;an adaptive weight coefficient is employed to improve the updating rule of the MPA, facilitating a balance between global exploration and local exploitation;the EO operator is integrated to enhance the performance of the MPA in the local exploitation phase to improve the solution quality and convergence speed;and the linear population size reduction (LPSR) technique is introduced to dynamically reduce the population size and improve the search performance. The effectiveness of the proposed IMPAEO is validated using the CEC2017 benchmark test suite, which is also applied to extract parameters of the single diode model, the double diode model, and three different PV modules. Comparative analysis with other algorithms demonstrates that the IMPAEO exhibits significant advantages in terms of solution quality, convergence speed, and algorithm stability. Consequently, the proposed IMPAEO not only proves to be efficient and reliable in parameter extraction for solar PV models but also offers a promising alternative in this field. © 2024

关键词： Equilibrium optimizer Marine predators algorithm Parameter extraction Photovoltaic models Solar cell