检索结果-内蒙古大学图书馆

Locust Behaved Particle Swarm optimization Technique

Journal of Donghua University(English Edition) 2014年第2期31卷 190-196页

作者：钟伟民谢雪勤梁毅罗娜张娟钱锋 Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of EducationEast China University of Science and Technology

The collective behavior of certain animals and insects has the characteristic of self-organization. The simple interactions among individuals can produce complex adaptive patterns at the level of the group. Recently,new scientific investigation pointed out that desert locusts show extreme phenotypic plasticity in transforming between the lonely phase and the swarming gregarious phase depending on the population density,which is controlled by a serotonin called 5-hydroxytryptamine( 5HT). In this paper,based on the mechanism of the locusts' collective behavior,a new particle swarm optimization technique called LBPSO is studied. The number of swarms is selfadaptively adjusted by the acquired outstanding particles coming from behind the previous global best solution. The swarm sizes are related to the corresponding serotonin 5HT,which is determined by the optimization parameters such as global best and iteration number. And each swarm adopts one of three rules below according to its density, generalized social evolution strategy, generalized cognition evolution strategy and the independent moving strategy. A comparative study of LBPSO,social particle swarm optimization( SPSO), improved SPSO and the standard particle swarm optimization( StdPSO) on their abilities of tracking optima is carried out. And the results under four static benchmark functions and a dynamic function generator moving peaks benchmark( MPB)show that LBPSO outperforms the other three functions in both static and dynamic landscapes due to the introduced locusts' collective behavior.

关键词： evolutionary algorithm particle swarm optimization(PSO) locust collective behavior

来源：评论

学校读者我要写书评

暂无评论

Novel Ensemble Modeling Method for Enhancing Subset Diversity Using Clustering Indicator Vector Based on Stacked Autoencoder

引用

Computer Modeling in Engineering & Sciences 2019年第10期121卷 123-144页

作者： Yanzhen Wang Xuefeng Yan Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education East China University of Science and TechnologyShanghai200237China

A single model cannot satisfy the high-precision prediction requirements given the high nonlinearity between *** contrast,ensemble models can effectively solve this *** key factors for improving the accuracy of ensemble models are namely the high accuracy of a submodel,the diversity between subsample sets and the optimal ensemble *** study presents an improved ensemble modeling method to improve the prediction precision and generalization capability of the *** proposed method first uses a bagging algorithm to generate multiple subsample ***,an indicator vector is defined to describe these subsample ***,subsample sets are selected on the basis of the results of agglomerative nesting clustering on indicator vectors to maximize the diversity between ***,these subsample sets are placed in a stacked autoencoder for ***,XGBoost algorithm,rather than the traditional simple average ensemble method,is imported to ensemble the model during *** machine learning public datasets and atmospheric column dry point dataset from a practical industrial process show that our proposed method demonstrates high precision and improved prediction ability.

关键词： Ensemble model deep learning bagging stacked autoencoder XGBoost

来源：评论

学校读者我要写书评

暂无评论

Multi-objective optimization of steam system based on GPU acceleration

引用

IFAC-PapersOnLine 2018年第21期51卷 183-188页

作者： Zhao, Liang Ye, Zhencheng Du, Wenli Key Laboratory of Advanced Control and Optimization for Chemical Processes East China University of Science and Technology Shanghai200237 China

The steam system is an important part of the utility systems in process industry. The energy consumption and operation cost of the existing plant were increased due to the inefficient configuration of the steam system. Meanwhile, the fossil fuels such as coal and oil were used to produce steam for the process industry, and the poisonous gases released from the burning process caused a lot of damage to the environments. Therefore, it is of great practical significance to reduce the operation cost and pollutant emissions simultaneously. This paper proposes an evolutionary multi-objective optimization (EMOO) algorithm to deal with this problems. But because of the complexity, higher dimension and rigid constraint conditions of the process industry, the computation time of EMOO algorithm can not meet the requirements of real-time optimization. Thus, Graphics processing Unit (GPU) computing, which was running on the CUDA platform was introduced to shorten the running time of the algorithm. A constraint handling mechanism was presented to improve the performance of the algorithm. The case study indicates that the proposed GPU-based EMOO algorithm can obtain the Pareto optimal solution of the steam system in a minute-level time. © 2018

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Global Inference Preserving Projection for Semi-supervised Discriminant Analysis

引用

Journal of Donghua University(English Edition) 2012年第2期29卷 144-147页

作者：谷小婧孙韶媛方建安 Key Laboratory of Advanced Control and Optimization for Chemical Process Ministry of EducationEast China University of Science and Technology College of Information Science&Technology Donghua University

Semi-supervised dimensionality reduction is an important research area for data classification. A new linear dimensionality reduction approach, global inference preserving projection （GIPP）, was proposed to perform classification task in semi-supervised case. GIPP provided a global structure that utilized the underlying discriminative knowledge of unlabeled samples. It used path-based dissimilarity measurement to infer the class label information for unlabeled samples and transformd the diseriminant algorithm into a generalized eigenequation problem. Experimental results demonstrate the effectiveness of the proposed approach.

关键词： semi-supervised learning dimensionality reduction manifoM structure

来源：评论

学校读者我要写书评

暂无评论

OSF-JS: Orthonormal Slow Feature-Based Quality-Related Data Decomposition Network With Jensen–Shannon Divergence for chemical processes Incipient Fault Detection

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Wang, Jiayu Yao, Le Xiong, Weili Cui, Xiaohui Yu, Wei Young, Brent Ministry of Education Key Laboratory of Advanced Process Control for Light Industry Wuxi214122 China Jiangnan University School of Internet of Things Engineering Wuxi214122 China Hangzhou Normal University School of Mathematics Hangzhou311121 China Jiangnan University Science Center for Future Foods Wuxi214122 China Wuhan University School of Cyber Science and Engineering Hubei Wuhan430072 China University of Auckland Department of Chemical and Materials Engineering Auckland1010 New Zealand

In chemical processes, there are both nonlinearity and slow dynamics among process variables. Meanwhile, at the beginning of faults, slight variation may not prompt the significant parametric changes. Traditional fault detection methods, based on mean and variation shifts, often fail to achieve satisfactory performance. To improve the detection of incipient quality-related faults, a novel orthonormal slow feature-based quality-related data decomposition network with Jensen-Shannon divergence (OSF-JS) fault detection method is proposed. The orthonormal subspace analysis (OSA) is embedded with Siamese to extract orthonormal slow features (OSFs) from decomposed subspaces. Enhancing the detection of incipient faults, JS divergence combined with a sliding window algorithm is introduced to construct statistics. The effectiveness of OSF-JS is validated for a wastewater treatment process and a real-world chemical process. Results show that the proposed OSF-JS method not only improves the fault detection rate (FDR) and reduces false alarm rate (FAR) but also identifies whether faults occur in the quality-related component. © 1963-2012 IEEE.

关键词： Fault detection Feature extraction chemical processes Monitoring Kernel Principal component analysis Windows Wastewater treatment Industries Decoding

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Differential Evolution Algorithm Integrated with Particle Swarm optimization

引用

Journal of Donghua University(English Edition) 2014年第2期31卷 197-200页

作者：范勤勤颜学峰 Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of EducationEast China University of Science and Technology

To implement self-adaptive control parameters, a hybrid differential evolution algorithm integrated with particle swarm optimization （PSODE） is proposed. In the PSODE, control parameters are encoded to be a symbiotic individual of original individual, and each original individual has its own symbiotic individual. Differential evolution （ DE） operators are used to evolve the original population. And, particle swarm optimization （PSO） is applied to co-evolving the symbiotic population. Thus, with the evolution of the original population in PSODE, the symbiotic population is dynamically and self-adaptively adjusted and the realtime optimum control parameters are obtained. The proposed algorithm is compared with some DE variants on nine functious. The results show that the average performance of PSODE is the best.

关键词： differential evolution algorithm particle swann optimization self-adaptive co-evolution

来源：评论

学校读者我要写书评

暂无评论

A New Sample-Selection and Modeling Method Based on Near-Infrared Spectroscopy and Its Industrial Application

引用

Journal of Donghua University(English Edition) 2014年第2期31卷 207-211页

作者：贺凯迅程辉钱锋 Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of EducationEast China University of Science and Technology

Near-infrared( NIR) spectroscopy has been widely employed as a process analytical tool( PAT) in various fields; the most important reason for the use of this method is its ability to record spectra in real time to capture process properties. In quantitative online applications,the robustness of the established NIR model is often deteriorated by process condition variations,nonlinear of the properties or the high-dimensional of the NIR data set. To cope with such situation,a novel method based on principal component analysis( PCA) and artificial neural network( ANN) is proposed and a new sample-selection method is mentioned. The advantage of the presented approach is that it can select proper calibration samples and establish robust model effectively. The performance of the method was tested on a spectroscopic data set from a refinery process. Compared with traditional partial leastsquares( PLS),principal component regression( PCR) and several other modeling methods, the proposed approach was found to achieve good accuracy in the prediction of gasoline properties. An application of the proposed method is also reported.

关键词： gasoline blending near-infrared spectroscopy sample selection modeling method

来源：评论

学校读者我要写书评

暂无评论

Unsupervised learning of depth and ego-motion with absolutely global scale recovery from visual and inertial data sequences

引用

Cyber-Physical Systems 2021年第3期7卷 133-158页

作者： Meng, Yanwen Sun, Qiyu Zhang, Chongzhen Tang, Yang Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education East China University of Science and Technology Shanghai China

In this paper, we propose an unsupervised learning method for jointly estimating monocular depth and ego-motion, which is capable to recover the absolute scale of global camera trajectory. In order to solve the general problems of scale drift and scale ambiguity of monocular camera, we fuse geometric movement data from inertial measurement unit (IMU), and use Bi-directional Long Short-Term Memory (BiLSTM) to extract temporal features. Besides, we add a lightweight and efficient attention mechanism, Convolutional Block Attention Module (CBAM), to Convolutional Neural Networks (CNNs) to complete the extraction of image features. Considering the scenes with severe illumination changes, ambiguous structures, moving objects and occlusions, especially scenes with progressively-variant textures, the geometric features can provide adaptive estimation results in the case of the degeneration of visual features. Experiments on the KITTI driving dataset reveal that our scheme achieves promising results in the estimation of camera pose and depth. Moreover, the absolute scale recovery for the global camera trajectory is effective. © 2020 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Vision-based formation control of multiple UAVs with event-triggered integral sliding mode control

引用

Cyber-Physical Systems 2020年第4期6卷 231-251页

作者： Chen, Siqing Jin, Xin Zhang, Wenle Tang, Yang Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education East China University of Science and Technology Shanghai China

Vision-based formation control offers an alternate solution for unmanned aerial vehicles (UAVs) to work together in the external position system denied environment. In this paper, we present a vision-based formation control strategy with the advantages of high tracking performance and low consumption of communication resources. A vision-based multi-robot localisation methods is applied to get precise position information, and the extended Kalman filter (EKF) is used to fuse measurement data from different sensors. The integral sliding mode controller (ISMC) is utilised to ensure the fast convergence and robustness to the desired formation, and the event-triggered communication scheme is employed to reduce redundant transmission of state information used in the formation controller. The simulation results in Gazebo with a team of three UAVs are given to illustrate the effectness of the proposed control strategy. © 2020 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Trajectory planning in 3D dynamic environment with non-cooperative agents via fast marching and Bézier curve

引用

Cyber-Physical Systems 2019年第2期5卷 119-143页

作者： Zong, Xuepeng Sun, Qiyu Yao, Dachen Du, Wei Tang, Yang Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education East China University of Science and Technology Shanghai China

In this paper, we propose a framework for trajectory planning in a 3D dynamic environment where other non-cooperative agents may obstruct the active quadrotor. A trajectory predictor is designed for the non-cooperative agent via least squares. In addition, based on Euclidean signed distance field (ESDF), a velocity map configuration is developed for both dynamic and static obstacles, and then utilized in fast marching method to find a feasible discrete path. The smooth and dynamic feasible trajectory generation problem is formulated as a quadratic programming (QP) problem, where a safe flight corridor generator is developed for safe constraints in a dynamic environment. Piecewise Bézier curves are used to represent the generated trajectory. With the help of flight corridor, along with the convex hull property of Bézier curve, the quadratic programming problem turns into a convex optimization problem. Simulation results show that the proposed approach is validated for collision avoidance in a dynamic environment. © 2019, © 2019 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Collision avoidance

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：