检索结果-内蒙古大学图书馆

Chinese control Conference (CCC)

作者： Yanyu Chen Xiao Zhang Feng Ding Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education) School of Internet of Things Engineering Jiangnan University Wuxi PR China

Time series of natural phenomena including human behaviours usually show irregular fluctuations. In this paper, a fast tunable gradient radial basis function (GRBF) network based on the multi-innovation algorithm for modeling and predicting nonstationary and nonlinear time series is proposed. In the process of constructing the frame of the network, the orthogonal least squares algorithm is used to simplify the frame of the GRBF network. During the online adaption, the node with the minimal effection is replaced with an appropriate node while the network cannot track the changes of the time series. The algorithm based on the multi-innovation theory is used to refresh the weight vector. Lorenz time series is used to verify the online prediction performance of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DV-Hop Localization Algorithm based on Hop Distance Weight and Improved Particle Swarm Optimization

DV-Hop Localization Algorithm based on Hop Distance Weight a...

引用

2021 China Automation Congress, CAC 2021

作者： Yang, Ziqin Gao, Meifeng Key Laboratory of Advanced Control of Light Industry Process Ministry of Education School of Internet of Things Engineering Jiangnan University Wuxi China

ISBN: (纸本)9781665426473

For the purpose of overcoming the issue of lower localization accuracy in the DV-Hop localization algorithm, as well as addressing the problem that the Particle Swarm Optimization (PSO) is easy to slip into local optimization, an enhancement strategy, which is based on hop distance weight and improved PSO, is proposed. The anchor node broadcasts information with a dual communication radius to obtain the optimal inter-node hop value;the proportion of the anchor node's average hop distance to the communication radius is utilized as the weight utilized to figure out the unknown node's average hop distance. The enhanced PSO is employed to calculate the unknown node's location, while the dynamic weight and golden sine algorithm are employed to update the position of particles. On the basis of the simulation results, it is manifest that the proposed calculation has superior localization precision. © 2021 IEEE

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Interfacial Polarization-Enabled High Anti-Interference for Fiber Pressure Sensors

SSRN

引用

SSRN 2025年

作者： Liu, Lu Huang, Xin Zhao, Kezheng Jiang, Gaoming Cong, Honglian Ramakrishna, Seeram He, Haijun Engineering Research Center for Knitting Technology Ministry of Education Jiangnan University Wuxi214122 China Key Laboratory of Advanced Process Control for Light Industry Ministry of Education Jiangnan University Wuxi214122 China Faculty of Engineering Department of Mechanical Engineering National University of Singapore Singapore117574 Singapore

Fiber pressure sensors possess the ability to be integrated into intelligent fabrics or garments due to their flexible one-dimensional (1D) size, thus playing a crucial role in wearable electronics and robotics. However, due to the proximity effect, the signal accuracy of the reported capacitive sensors is inevitably degraded by interference from the surrounding environment. Therefore, minimizing interference while maintaining excellent sensing performance is a challenge for fiber capacitive sensors. One straightforward method to enhance anti-interference capability involves raising the initial capacitance. Based on it, this study proposed an anti-interference fiber capacitive sensor by enhancing the interfacial polarization effect between the nanofiller and the matrix. The modified CNTs@PDA with a core-shell structure increased the polarization interface as well as the charge storage capacity of the composite dielectric layer by improving the nanofillers’ dispersion, thereby significantly increasing the sensor’ initial capacitance to 1.6 times. This enables the sensor an ideal signal-to-noise ratio (SNR), reflecting negligible capacitive signal fluctuations when electromagnetic interference and proximity to objects are present. Moreover, with the synergy of interfacial polarization effect and excellent elastic recovery, the sensor achieved a linear response with high sensitivity in the ultra-high pressure range of 3500 kPa and long-term stability over 5000 cycles. With the flexible 1D structure, it was easily knitted into sensing textiles, and a 2D pressure recognization fabric and a traditional Chinese medicine (TCM) foot massage sock system were prepared by circuit integration. This demonstrates the potential application of high anti-interference fiber flexible pressure sensors in wearable electronic textiles. © 2025, The Authors. All rights reserved.

关键词： Flexible electronics

来源：评论

学校读者我要写书评

暂无评论

Structural Evolution of Biomass Pellets of Different Densities During High and Low Convection Pyrolysis

SSRN

引用

SSRN 2025年

作者： Sadeq, Abdullah Schmitt, Marian Wang, Shen Rothberg, Sophia Pietsch-Braune, Swantje Shen, Laihong Heinrich, Stefan Institute of Solids Process Engineering and Particle Technology Hamburg University of Technology Hamburg21073 Germany Key Laboratory of Energy Thermal Conversion and Control of Ministry of Education Southeast University Nanjing210096 China

In this study, wood pellets of different densities were produced from wood shavings of the same batch using a flat die press. Their structure and mechanical properties were investigated and compared to the properties after subsequent pyrolysis with two setups: high convection (HC) pyrolysis in a fluidized bed and low convection (LC) pyrolysis. Various measurement methods were used to investigate the structural properties and the applicability of wood pellets and pellet char. It could be shown that although pellet chars from LC-pyrolysis exhibit a cylindrical shape, their mechanical stability is significantly reduced due to the greatly increased porosity. However, the characteristics in the radial porosity distribution remained as in the untreated pellets. In contrast, HC-pyrolysis in a fluidized bed led to severe structural damage resulting in pellet chars with larger cavities, mainly in their central regions. Consequently, a higher porosity in the center and a lower mechanical stability was determined. Furthermore, it became clear that low-density wood pellets produced with a flat die press equipped with short press channels are especially prone to these structural changes. It is assumed that an open pore network with big cracks and gaps between wood shavings within wood pellets in combination with high heat and mass transfer during pyrolysis can enhance the release of volatiles from the pellet. With micro computed tomography (µCT), it could be shown that cavities in pellet chars are likely formed at wood pellet regions with smaller wood shavings. © 2025, The Authors. All rights reserved.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

A Novel Variable Selection Algorithm for Soft Sensor Using Gated Recurrent Unit and Garrote Variable Attention Mechanism

A Novel Variable Selection Algorithm for Soft Sensor Using G...

引用

Chinese control Conference (CCC)

作者： Lin Sui Weili Xiong School of Internet of Things Engineering Jiangnan University Wuxi China Ministry of Education Key Laboratory of Advanced Process Control for Light Industry Wuxi China

This paper proposed a variable selection algorithm for soft sensor applications using the garrote variable attention mechanism and gated recurrent unit (GRU). Firstly, a well-trained GRU deep neural network is obtained by hyperparameter optimization. Secondly, a set of variable attention coefficients was designed based on the maximal information coefficient and embedded in the nonnegative garrote (NNG) algorithm constraints to overcome the disadvantage of biased coefficient estimation in this algorithm. Finally, the GRU network input weights are sparsely optimized using the optimized NNG algorithm to eliminate redundant variables and simplify the model structure. A numerical simulation case verifies the effectiveness of the proposed algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of indirect-type iterative learning control for continuous-time batch processes with the repetitive process setting

Design of indirect-type iterative learning control for conti...

引用

Asian control Conference

作者： Robert Maniarski Wojciech Paszke Hongfeng Tao Zhihe Zhuang Institute of Automation Electronic and Electrical Engineering University of Zielona Zielona Góra Poland Key Laboratory of Advanced Process Control for Light Industry of Ministry of Education Jiangnan University Wuxi China

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

An indirect iterative learning control law is proposed for a class of continuous-time batch processes with time-varying uncertainties, input delay, and disturbances. First, by designing a predictor based on a state observer we are able to estimate the future state and compensate for the input delay. Then, based on the estimated state we design a robust $H$ ∞ controller in the presence of time-varying uncertainties and load disturbances. Additionally, the differential repetitive process setting for the design of the iterative learning control scheme is applied and hence the convergence of the tracking error in trial-to-trial direction occurs. Finally, the simulation results verify the new method's effectiveness.

关键词： Uncertainty Simulation Batch production systems process control Observers Delays Iterative learning control

来源：评论

学校读者我要写书评

暂无评论

A Transfer State Estimator for Uncertain Parameters and Noise Statistics ⁎

引用

IFAC-PapersOnLine 2024年第14期58卷 192-197页

作者： Shuang Gao Xiaoli Luan Biao Huang Shunyi Zhao Fei Liu Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education) Jiangnan University Wuxi 214122 China Department of Chemical and Materials Engineering University of Alberta Edmonton AB T6G 1H9 Canada

This paper proposes a novel approach to tackle uncertainties in model parameters and noise statistics for state estimation. The proposed method leverages transfer learning to combine the strengths of the unbiased finite impulse response (UFIR) filter and the Kalman filter (KF), with UFIR serving as the source domain filter and KF as the target domain filter. To bolster the robustness of state estimation within the target domain, the proposed method transfers the predicted state probability density functions (pdfs) from UFIR and fine-tunes the error covariance of the KF filter to achieve seamless integration. Unlike conventional fusion techniques, this method avoids the need for UFIR’s error covariance, thus mitigating its adverse impact on estimation accuracy. We demonstrate the competitiveness of this transfer state estimator in handling parameter uncertainties through moving target tracking, showing superior performance compared to existing fusion methods for state estimation.

关键词： State estimation parameter uncertainty variational inference transfer learning

来源：评论

学校读者我要写书评

暂无评论

Grafted Pbi with Multiple Proton Hopping Sites with Enhanced Performance for Application in Ht-Pemfcs

SSRN

引用

SSRN 2024年

作者： You, Yamei Liu, Binghui Wang, Jiaqi Deng, Xinyang Liu, Qian Liang, Jinli Zhao, Chengji Hou, Yanjun Zhang, Haiqiu The Key Laboratory of Functional Inorganic Material Chemistry Ministry of Education Heilongjiang University Harbin150080 China The Key Laboratory of High Performance Plastics Ministry of Education College of Chemistry Jilin University Changchun130012 China Key Laboratory of Chemical Engineering Process and Technology High Efficiency Conversion College of Heilongjiang Province School of Chemistry and Materials Science Heilongjiang University Harbin150080 China

Grafted polybenzimidazole (PBI) with multiple proton hopping sites was synthesized. The novel structure of anhydrous high-temperature proton exchange membrane had multiple quaternary ammonium groups on the side chains of PBI. These groups could interact with more phosphoric acid (PA) molecules and cross-link the chains of PBI, thus improving the PA absorption capacity and mechanical properties. Importantly, the cross-linked structure successfully prevented the loss of PA molecules. The proton conductivity of grafted PBI membranes was high (198.5 mS∙cm-1, 160 °C, anhydrous). Under anhydrous and free backpressure conditions, the grafted PTPBI showed an ideal peak power density of 361.7 mW∙cm-2 (180 °C). The open-circuit voltage of the aforementioned component was around 1.0 V, indicating commendable level of hermeticity. Further, the grafted polybenzimidazole membranes demonstrated superior antioxidant performance, compared to pure PBI after 204 hours of treatment with Fenton's reagent. The cross-linking also enhanced the mechanical properties (PTPBI-20%, undoped PA, 126.5 MPa) and dimensional stabilities of the membranes to some extent. The thermal stabilities of grafted PBI membranes were suitable for applications in high-temperature proton exchange membrane fuel cells (HT-PEMFCs). For HT-PEMFCs, the polymer electrolyte membrane materials with increased performance after grafting of quaternary ammonium groups showed tremendous promise. © 2024, The Authors. All rights reserved.

关键词： Membranes

来源：评论

学校读者我要写书评

暂无评论

Large Scale and High-Precision Crop Recognition using Satellite Remote Sensing Images

Large Scale and High-Precision Crop Recognition using Satell...

引用

2024 China Automation Congress, CAC 2024

作者： Tao, Xuanting Tan, Jinglu Zhang, Jianguo Allakhverdiev, Suleyman I. Xu, Zhenyu Guo, Ya Key Laboratory of Advanced Process Control for Light Industry Ministry of Education Jiangnan University Wuxi China Department of Chemical & Biomedical Engineering University of Missouri ColumbiaMO United States Wuxi Agricultural Equipment Technology Extension Center Wuxi China Timiryazev Institute of Plant Physiology RAS Moscow Russia Longcom Internet of Things Co. Ltd Hefei China

ISBN: (纸本)9798350368604

Precise large-scale crop recognition is crucial for estimating crop yield and carbon assimilation. Current research on crop type recognition based on deep learning is often limited to a single crop and small areas, with poor model transferability. When performing multi-crop recognition over large areas, the accuracy significantly decreases. Therefore, it is necessary to establish a high-precision crop type recognition model with strong generalization capability. A deep learning model (LSTM-Transformer Parallel, LTP) based on the combination of LSTM (Long Short-Term Memory) network and Transformer self-attention mechanism architecture is proposed in this paper. The model captures the dependencies among crop NDVI time series data to achieve high-precision recognition of large-scale crop types. Experimental results show that in crop recognition experiments using small-scale agricultural area data, the recognition results of the LTP, TSMixer, and SegRNN models all performed excellently, with average accuracies of 94.55%, 94.41%, and 94.79%, respectively. In contrast, in crop recognition experiments using large-scale agricultural area data, the average accuracy of the LTP model reaches 93.77%, while the accuracies of the TSMixer and SegRNN models are 82.30% and 84.13%, respectively. This indicates that the LTP model not only performs well on small-scale agricultural area datasets but also significantly outperforms models in the literature on large-scale agricultural area datasets, demonstrating strong generalization capability. It provides a reliable method for large-scale multi-crop recognition, contributing to global food security and carbon cycle assessment. © 2024 IEEE.

关键词： Deep Learning Model Generalization Multi-crop recognition Sentinel-2 Satellite Time-series Data

来源：评论

学校读者我要写书评

暂无评论

Improved Digital Costas Loop Design in Spread Spectrum Communication

引用

Chinese Journal of Electronics 2023年第2期20卷 299-302页

作者： Hongbo Wang Li Deng Zhonggui Ma Xuyan Tu School of Information Engineering University of Science and Technology Beijing Beijing China Key Laboratory of Advanced Control of Iron and Steel Process (Ministry of Education) University of Science and Technology Beijing Beijing China

Based on software radio technique, a novel improved design structure of digital Costas loop for spread spectrum communication is put forward in the paper. Main practical works includes: (1) For carrier recovery in the traditional Costas central, it improves a way applicable to the spread spectrum communication and gives a detailed mathematical deduction; (2) As for traditional QPSK modern methods, it joins the encoding, interleaving, de-interlacing, decoding, balanced module in the QPSK modulation and demodulation process in spread spectrum communications to reduce the system Bit error rate (BER); (3) a PN code magna-scope demodulator and two low power filers are added in order to get sensitive weighing signal. Simulation contrast results show that the improvement is feasible.

关键词： Phase shift keying Codes Voltage-controlled oscillators Bit error rate Spread spectrum communication Encoding Decoding

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：