检索结果-南通市图书馆

Hierarchical multihead self-attention for time-series-based fault diagnosis

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2024年第6期70卷 104-117页

作者： Chengtian Wang Hongbo shi Bing Song Yang Tao Key Laboratory of Smart Manufacturing in Energy Chemical Process of the Ministry of Education East China University of Science and TechnologyShanghai 200237China

Fault diagnosis is important for maintaining the safety and effectiveness of chemical *** the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fault diagnosis methods have been developed in recent ***,the existing methods have the problem of long-term dependency and are difficult to train due to the sequential way of *** overcome these problems,a novel fault diagnosis method based on time-series and the hierarchical multihead self-attention(HMSAN)is proposed for chemical ***,a sliding window strategy is adopted to construct the normalized time-series ***,the HMSAN is developed to extract the time-relevant features from the time-series process *** improves the basic self-attention model in both width and *** the multihead structure,the HMSAN can pay attention to different aspects of the complicated chemical process and obtain the global dynamic ***,the multiple heads in parallel lead to redundant information,which cannot improve the diagnosis *** the hierarchical structure,the redundant information is reduced and the deep local time-related features are further ***,a novel many-to-one training strategy is introduced for HMSAN to simplify the training procedure and capture the long-term ***,the effectiveness of the proposed method is demonstrated by two chemical *** experimental results show that the proposed method achieves a great performance on time-series industrial data and outperforms the state-of-the-art approaches.

关键词： Self-attention mechanism Deep learning Chemical process Time-series Fault diagnosis

Quaternion-Based Adaptive Trajectory Tracking Control of a Rotor-Missile with Unknown Parameters Identification

在线全文

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2024年第1期31卷 375-386页

作者： Jie Zhao Zhongjiao shi Yuchen Wang Wei Wang Beijing Institute of Technology Beijing 100081China

This paper investigates the adaptive trajectory tracking control problem and the unknown parameter identification problem of a class of rotor-missiles with parametric system ***,considering the uncertainty of structural and aerodynamic parameters,the six-degree-of-freedom(6Do F) nonlinear equations describing the position and attitude dynamics of the rotor-missile are established,respectively,in the inertial and body-fixed reference ***,a hierarchical adaptive trajectory tracking controller that can guarantee closed-loop stability is proposed according to the cascade characteristics of the 6Do F ***,a memory-augmented update rule of unknown parameters is proposed by integrating all historical data of the regression *** long as the finitely excited condition is satisfied,the precise identification of unknown parameters can be ***,the validity of the proposed trajectory tracking controller and the parameter identification method is proved through Lyapunov stability theory and numerical simulations.

关键词： Rotor-missile Adaptive control Parameter identification Quaternion control

Study on a probabilistic algorithm for the forming and 3D characterization of special-shaped surfaces under profile grinding

在线全文

学校读者我要写书评

暂无评论

Advances in Manufacturing 2024年第2期12卷 288-299页

作者： Zhao-Qing Zhang Kai-Ning shi Yao-Yao shi Yi-Hui Song Zhe He Ya-Song Pu School of Mechanical Engineering Northwestern Polytechnical UniversityXi’an710072People’s Republic of China Key Laboratory of High Performance Manufacturing for Aero Engine(Northwestern Polytechnical University) Ministry of Industry and Information TechnologyXi’an710072People’s Republic of China Engineering Research Center of Advanced Manufacturing Technology for Aero Engine(Northwestern Polytechnical University) Ministry of EducationXi’an710072People’s Republic of China

Profile grinding is the most crucial method for the ultra-precision machining of special-shaped ***,profile grinding produces a unique machining profile,and many random factors in the machining process lead to complex surface *** this study,the structural and probabilistic characteristics of the profile grinding of a special-shaped surface were analyzed,and a probabilistic algorithm for the forming and 3D characterization of special-shaped surfaces under profile grinding was *** forming process of a GH738 blade tenon tooth surface was considered as an example to demonstrate the *** comparison results showed that the simulation results had similar surface characteristics to the measurement results,and the relative error range of the 3D roughness parameter was 0.21%–19.76%,indicating an accurate prediction and characterization of the complex special-shaped surface under the action of multiple factors.

关键词： Special-shaped surface Profile grinding Surface morphology 3D characterization

Diffractive neural networks with improved expressive power for gray-scale image classification

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Photonics Research 2024年第6期12卷 1159-1166页

作者： MINJIA ZHENG WENZHE LIU LEI shi JIAN ZI State Key Laboratory of Surface Physics Key Laboratory of Micro-and Nano-Photonic Structures(Ministry of Education)and Department of PhysicsFudan UniversityShanghai 200433China Institute for Nanoelectronic Devices and Quantum Computing Fudan UniversityShanghai 200433China Collaborative Innovation Center of Advanced Microstructures Nanjing UniversityNanjing 210093China Shanghai Research Center for Quantum Sciences Shanghai 210315China

In order to harness diffractive neural networks(DNNs)for tasks that better align with real-world computer vision requirements,the incorporation of gray scale is ***,DNNs are not powerful enough to accomplish gray-scale image processing tasks due to limitations in their expressive *** our work,we elucidate the relationship between the improvement in the expressive power of DNNs and the increase in the number of phase modulation layers,as well as the optimization of the Fresnel number,which can describe the diffraction *** demonstrate this point,we numerically trained a double-layer DNN,addressing the prerequisites for intensitybased gray-scale image ***,we experimentally constructed this double-layer DNN based on digital micromirror devices and spatial light modulators,achieving eight-level intensity-based gray-scale image classification for the MNIST and Fashion-MNIST data *** optical system achieved the maximum accuracies of 95.10%and 80.61%,respectively.

关键词： process mirror limitations

Neural Network Robust Control Based on Computed Torque for Lower Limb Exoskeleton

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Mechanical Engineering 2024年第2期37卷 83-99页

作者： Yibo Han Hongtao Ma Yapeng Wang Di shi Yanggang Feng Xianzhong Li Yanjun shi Xilun Ding Wuxiang Zhang School of Mechanical Engineering and Automation Beihang UniversityBeijing 100191China Beihang Goer(WeiFang)Intelligent Robot Co. Ltd.Beihang UniversityWeifangChina Research Center of Satellite Technology Harbin Institute of TechnologyHarbinChina Beijing Xinfeng Aerospace Equipment Co. LtdBeijingChina

The lower limb exoskeletons are used to assist wearers in various scenarios such as medical and industrial *** modeling errors of the exoskeleton in different application scenarios pose challenges to the robustness and stability of its control *** Radial Basis Function(RBF)neural network is used widely to compensate for modeling *** order to solve the problem that the current RBF neural network controllers cannot guarantee the asymptotic stability,a neural network robust control algorithm based on computed torque method is proposed in this paper,focusing on trajectory *** innovatively incorporates the robust adaptive term while introducing the RBF neural network term,improving the compensation ability for modeling *** stability of the algorithm is proved by Lyapunov method,and the effectiveness of the robust adaptive term is verified by the *** wearing the exoskeleton under different walking speeds and scenarios were carried out,and the results show that the absolute value of tracking errors of the hip and knee joints of the exoskeleton are consistently less than 1.5°and 2.5°,*** proposed control algorithm effectively compensates for modeling errors and exhibits high robustness.

关键词： Lower limb exoskeleton Model compensation RBF neural network Computed torque method

Evicting and filling attack for linking multiple network addresses of Bitcoin nodes

在线全文

学校读者我要写书评

暂无评论

Cybersecurity 2024年第3期7卷 49-68页

作者： Huashuang Yang Jinqiao shi Yue Gao Xuebin Wang Yanwei Sun Ruisheng shi Dongbin Wang School of Cyberspace Security Bejing University of Posts and TelecommunicationsBeijingChina Tsinghua University Bejing 100084China Institute of Information Engineering Chinese Academy of SciencesBeijingChina

Bitcoin is a decentralized P2P *** supports users to use pseudonyms instead of network addresses to send and receive transactions at the data layer,hiding users'real network *** transaction tracing attack cuts through the network layer to directly associate each transaction with the network address that issued it,thus revealing the sender's network *** this attack can be mitigated by Bitcoin's network layer privacy *** Bitcoin protects the unlinkability of Bitcoin addresses and there may be a many-to-one relation-ship between addresses and nodes,transactions sent from the same node via different addresses are seen as com-ing from different nodes because attackers can only use addresses as node *** this paper,we proposed the evicting and flling attack to expose the correlations between addresses and cluster transactions sent from different addresses of the same *** attack exploited the unisolation of Bitcoin's incoming connection processing *** particular,an attacker can utilize the shared connection pool and deterministic connection eviction strategy to infer the correlation between incoming and evicting connections,as well as the correlation between releasing and flling *** on inferred results,different addresses of the same node with these connections can be linked together,whether they are of the same or different network *** designed a multi-step attack procedure,and set reasonable attack parameters through analyzing the factors that affect the attack effciency and *** mounted this attack on both our self-run nodes and multi-address nodes in real Bitcoin network,achieving an aver-age accuracy of 96.9% and 82%,***,we found that the attack is also applicable to Zcash,Litecoin,Dogecoin,Bitcoin Cash,and *** analyzed the cost of network-wide attacks,the application scenario,and proposed countermeasures of this attack.

关键词： Security and privacy Bitcoin Address linking

Design strategies and recent advancements of solid-state supercapacitor operating in wide temperature range

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Carbon Energy 2024年第6期6卷 248-281页

作者： Jie Zhou Zhengfeng Zhu Wenhui shi Xiangyu shi Zhuoyuan Zheng Ye Xiong Yusong Zhu School of Energy Science and Engineering Nanjing Tech UniversityNanjingJiangsuChina Kucap Smart Technology(Nanjing)Co. Ltd.NanjingJiangsuChina

Solid-state supercapacitors(SSCs)are emerging as one of the promising energy storage devices due to their high safety,superior power density,and excellent cycling ***,performance degradation and safety issues under extreme conditions are the main challenges for the practical *** the expansion of human activities,such as space missions,polar exploration,and so on,the investigation of SSC with wide temperature tolerance,high energy density,power density,and sustainability is highly *** this review,the effects of temperature on SSC are systematically illustrated and clarified,including the properties of the electrolyte,ion diffusion,and reaction dynamics of the ***,we summarize the recent advances in wide-temperature-range SSCs from the aspect of electrolyte modification,electrode design,and interface adjustment between electrode and electrolyte,especially with critical concerns on ionic conductivity and cycling *** the end,a perspective is presented,expecting to promote the practical application of the SSC in harsh conditions.

关键词： electrode interface solid-state electrolyte solid-state supercapacitor wide temperature

A synthetic microbial community used as a bioinoculant can overcome rice production constraints in acid soils

维普期刊数据库评论

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(Life Sciences) 2024年第5期67卷 1085-1086页

作者： Maureen O’Callaghan Shengjing shi Resilient Agriculture Group AgResearchLincolnChristcurch 8140New Zealand

A customised synthetic microbial community(SynCom)composed of carefully selected rhizosphere-competent bacterial strains improved rice growth,yield and resistance to soil acidity and Al toxicity.

关键词： soil soils rhizosphere

NeuroPrim:An attention-based model for solving NP-hard spanning tree problems

在线全文

学校读者我要写书评

暂无评论

Science China Mathematics 2024年第6期67卷 1359-1376页

作者： Yuchen shi Congying Han Tiande Guo School of Mathematical Sciences University of Chinese Academy of SciencesBeijing100049China

Spanning tree problems with specialized constraints can be difficult to solve in real-world scenarios,often requiring intricate algorithmic design and exponential ***,there has been growing interest in end-to-end deep neural networks for solving routing ***,such methods typically produce sequences of vertices,which make it difficult to apply them to general combinatorial optimization problems where the solution set consists of edges,as in various spanning tree *** this paper,we propose NeuroPrim,a novel framework for solving various spanning tree problems by defining a Markov decision process for general combinatorial optimization problems on *** approach reduces the action and state space using Prim's algorithm and trains the resulting model using *** apply our framework to three difficult problems on the Euclidean space:the degree-constrained minimum spanning tree problem,the minimum routing cost spanning tree problem and the Steiner tree problem in *** results on literature instances demonstrate that our model outperforms strong heuristics and achieves small optimality gaps of up to 250 ***,we find that our model has strong generalization ability with no significant degradation observed on problem instances as large as 1,*** results suggest that our framework can be effective for solving a wide range of combinatorial optimization problems beyond spanning tree problems.

关键词： degree-constrained minimum spanning tree problem minimum routing cost spanning tree problem Steiner tree problem in graphs Prim's algorithm reinforcement learning