检索结果-内蒙古大学图书馆

Congress on Evolutionary Computation

作者： Yao Wang Zhiming Dong Tenghui Hu Xianpeng Wang Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University) Ministry of Education China Liaoning Engineering Laboratory of operation Analytics and Optimization for Smart Industry Northeastern University Shenyang China Liaoning Key Laboratory of Manufacturing System and Logistics Northeastern University Shenyang China Institute of Industrial & Systems Engineering Northeastern University Shenyang China

ISBN: (数字)9781728169293

ISBN: (纸本)9781728169309

The make-to-order (MTO) manufacturers generally make production plans based on orders, which can help enterprises effectively avoid market risks, reduce market pressure and improve competitiveness. However, due to the characteristics of MTO production mode, the order static scheduling problem and rush order dynamic rescheduling problem have become more and more important for these MTO manufacturers. Therefore, in this paper, we take the packaging production line of a typical carbon black production enterprise as the research background to study the carbon black production line static and dynamic multiobjective scheduling problem. Firstly, multiobjective optimization models of both order static scheduling and rush order dynamic rescheduling are established. Then the improved MOEA/D algorithm combined the heuristic algorithm based on heuristic rules and discrete dynamic local search is developed to solve these two models. Based on the actual production data, eight instances of order static scheduling problems of different scales and four instances of rush order dynamic rescheduling problems of different scales are constructed respectively. Experimental results illustrate that the improved MOEA/D is effective and superior in solving these two problems.

关键词： Dynamic scheduling Job shop scheduling Mathematical model Heuristic algorithms Delays

来源：评论

学校读者我要写书评

暂无评论

Metavit-Trans: A Framework for Mixed-Type Defect Detection of Wafers with Vision Transformer Combined with Meta-Learning and Transfer Learning

Metavit-Trans: A Framework for Mixed-Type Defect Detection o...

引用

China Semiconductor Technology International Conference (CSTIC)

作者： Junfeng Zhao Lixin Tang National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China Ministry of Education Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University) Shenyang China

The defect detection of semiconductor wafer patterns is essential in the process of chip manufacturing. With the improvement of the IC process and design level, the types of wafer surface defects become more complex. In addition, the sample size of wafer map defect data is usually small, and the class is unbalanced, which poses higher challenges to the existing methods. To effectively identify mixed-type defects, a mixed-type defect detection framework with Vision Transformer (ViT) combined with meta-learning and transfer learning (MetaViT-Trans) is proposed. The results show that the MetaViT-Trans framework has a good defect feature extraction ability for imbalanced small-scale wafer map defect data, and has a good multi-scale information learning ability, which can effectively identify a variety of mixed-type defects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lithography Hotspot Detection Based on Transfer Learning With High Resolution Networks

Lithography Hotspot Detection Based on Transfer Learning Wit...

引用

China Semiconductor Technology International Conference (CSTIC)

作者： Hongzhe Wang Lixin Tang National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China The Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University) Ministry of Education Shenyang China

As integrated circuit (IC) technology continues to advance, lithography hotspot detection is of importance in physical verification flow and can affect the turn-around time and the yield of IC manufacturing. In this paper, a deep learning-based lithography hotspot detection method is proposed to overcome the problem of unbalanced positive and negative samples in detection. The proposed method uses the High-Resolution Network (HR-Net18) and pre-trained model from ImageNet to improve transferability. ICCAD 2012 benchmark suits is used for model train and test. The experimental results show that the proposed method performs well in terms of the values of AUC and precision.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Method for Predicting Mechanical Properties of Steel Based on Graph Convolutional Networks

SSRN

引用

SSRN 2024年

作者： Ban, Yunqi Yang, Yang Wang, Xianpeng Wu, Zhiyuan National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang110819 China Key Laboratory of Data Analytics and Optimization for Smart Industry Northeastern University Ministry of Education Shenyang110819 China Liaoning Engineering Laboratory of Data Analytics and Optimization for Smart Industry Shenyang China College of Electronic and Information Engineering Tongji University Shanghai201804 China Northeastern University China

In steel materials, several mechanical properties are interrelated and there is an inherent topology structure among these mechanical properties. Based on this motivation, a multitask neural network model based graph convolutional network is proposed to predict mechanical properties. First, a directed graph is built over the mechanical properties, with each mechanical property representing a node on the graph. Then this graph convolutional network, which represents the information propagation among mechanical properties, is combined with a multitask neural network and trained together. By comparing with K-NearestNeighbor (KNN), support vector regression (SVR), random forest (RF), Extreme Gradient Boosting (XGBoost), Cross-Stitch Network, Multi-gate Mixture-of-Experts (MMOE) and multitask neural (MTN) algorithms, the proposed algorithm is optimal in all of the metrics root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2) that indicate the predictive performance on the prediction of tensile strength (TS), yield strength (YS) and elongation (EL). Specifically, R2 is 0.9797 in tensile strength, R2 is 0.9747 in yield strength and R2 is 0.8316 in elongation. In addition, a deep representation of the various influences on mechanical properties is obtained through the parameters of the model with validity and interpretability. Material insights are extracted from this deep representation, including the comprehensive interaction of processing and chemical composition on the mechanical properties as well as the mechanical properties with each other. Further, the prediction accuracy can be improved by the combination of different structures of neural networks with graph convolutional network to prove the effectiveness of graph convolutional network. © 2024, The Authors. All rights reserved.

关键词： Tensile strength

来源：评论

学校读者我要写书评

暂无评论

A Novel Speech Recognition Model with Bayesian optimization

A Novel Speech Recognition Model with Bayesian Optimization

引用

Chinese Automation Congress (CAC)

作者： Yunfei Zhang Meiling Xu Institute of Industrial & Systems Engineering Northeastern University Shenyang China Key Laboratory of Data Anlytics and Optimization for Smart Industry Northeastern University Minstry of Education Shenyang China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

In order to solve the problem of the speech recognition, this paper proposes a novel framework to process speech signals by using the deep fully convolutional neural network (DFCNN) as the acoustic model and the Transformer as the linguistic model. DFCNN can learn more about speech signals through a deep network structure, while Transformer's self-attention mechanism makes it an efficient linguistic model. In order to better extract the characteristic information of speech signal, we transform the speech signal into a two-dimensional language spectrum by frame division and Fourier transform. In this way, the language spectrum can be processed by using convolutional neural network, which has promising ability to process two-dimensional data. The output of the acoustic model is passed into the linguistic model, and a complete sentence is output. At the same time, considering that there are many hyper parameters in the model, in order to adjust these hyper parameters efficiently, we employ the Bayesian optimization algorithm to optimize the hyper parameters of the acoustic model and the linguistic model, so as to further improve the accuracy of speech recognition. Experimental results on speech recognition library THCHS30 show that compared with other models, the optimized model has higher recognition rate for audio and stronger generalization ability.

关键词： Speech recognition Acoustics Hidden Markov models Linguistics Speech processing optimization Modeling

来源：评论

学校读者我要写书评

暂无评论

Piecewise Time Series Prediction Based on Stacked Long Short-Term Memory and Genetic Algorithm

Piecewise Time Series Prediction Based on Stacked Long Short...

引用

Chinese Automation Congress (CAC)

作者： Lu Chen Meiling Xu Institute of Industrial & Systems Engineering Northeastern University Shenyang China Key Laboratory of Data Anlytics and Optimization for Smart Industry (Northeastern University) Minstry of Education Shenyang China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

Time series prediction is an active area and attracts the attention of researchers from lots of fields. With the expansion of the application of time series forecasting in the real world, many traditional methods that predicted time series with a few data are no longer applicable. Motivated by the demand of accurate prediction, we come up with the piecewise time series prediction model combining stacked long short-term memory network with genetic algorithm. Stacked long short-term memory network (LSTM) is an advanced sequence learning technology. We divide the time series into several segments and then use the stacked LSTM trained on the previous segment to predict the next segment to realize online prediction. The parameters of the stacked LSTM for each segment prediction are optimized by improved genetic algorithm. For purpose of demonstrating the feasibility and effectivity of the proposed model, we carry out simulation experiments on basis of a hybrid benchmark chaotic time series and a real-world dataset of the hourly ozone concentration. Experimental results demonstrate that the proposed model can automatically select the proper structure according to the data, which avoids the structure being too redundant or too simple. Furthermore, it can improve the prediction accuracy of time series and has good practicability.

关键词： Time series analysis Logic gates Genetic algorithms Predictive models Mathematical model data models Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Finite-time H∞ Control for Switched Systems:An Event-triggered Bumpless Transfer Approach

Finite-time H∞ Control for Switched Systems:An Event-trigge...

引用

第35届中国控制与决策会议

作者： Jinghan Li Guangxu He Qiang Zeng Jun Zhao State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Key Laboratory of Data Analytics and Optimization for Smart Industry(Northeastern University) Ministry of Education College of Information Science and Engineering Northeastern University

In this paper,the event-triggered finite-time H∞bumpless transfer control problem of switched systems is *** event-triggered bumpless transfer control method with local constraints is proposed to reduce the bump generated by switching event-triggered controller.A sufficient condition is given to ensure the solvability of the switched systems with eventtriggered finite-time H bumpless transfer *** positive lower bound of event-triggered integral is obtained,which implies that Zeno behavior is *** using the multiple Lyapunov functions method,a state-dependent switching law,an eventtriggered mechanism and a bumpless transfer controller are ***,a simulation example is given to verify the effectiveness of the proposed method.

关键词： switched systems bumpless transfer event-triggered finite-time H_∞control

来源：评论

学校读者我要写书评

暂无评论

Event-triggered control for switched descriptor systems based on sampled-data implementation

Event-triggered control for switched descriptor systems base...

引用

第33届中国控制与决策会议

作者： Jiasheng Shi Jun Zhao State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University) Ministry of Education College of Information Science and Engineering Northeastern University

This paper studies event-triggered control problem for a class of switched descriptor systems based on sampled-data *** switched descriptor systems are first to be decomposed into a equivalent form,and then a reduced-order switched system is ***,a sufficient condition ensures that the closed-loop system is exponentially stable under average dwell time switching ***,the Zeno behavior is ruled *** the end,a numerical examples is demonstrated the merit and effectiveness of the proposed methods.

关键词： Average dwell time Switched descriptor systems Event-triggered control Sampled-data

来源：评论

学校读者我要写书评

暂无评论

Passivity and Feedback Passification for Discrete-Time Switched Interval Type-2 Fuzzy Systems

Passivity and Feedback Passification for Discrete-Time Switc...

引用

第40届中国控制会议

作者： Siyuan Zhang Jun Zhao The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University The Key Laboratory of Data Analytics and Optimization for Smart Industry(Northeastern University) Ministry of Education The College of Information Science and Engineering Northeastern University

This paper investigates the passivity analysis and feedback passification problems for a class of discrete-time switched interval type-2 fuzzy *** interval type-2 T-S fuzzy model is employed to represent switched nonlinear systems subject to parameter *** the help of the IT2 fuzzy set theory,the parameter uncertainties can be captured by upper and lower membership *** on the multiple storage functions and the state-dependent switching strategy,the solvability conditions for feedback passification are derived by solving a set of linear matrix ***,the switched IT2 fuzzy passive controllers are designed ***,a simulation example is provided to illustrate the effectiveness and applicability of the proposed method.

关键词： Switched systems Interval type-2 fuzzy Passivity Feedback passification

来源：评论

学校读者我要写书评

暂无评论

Socially Optimal Nash Equilibrium of Switched Linear Quadratic Differential Games

Socially Optimal Nash Equilibrium of Switched Linear Quadrat...

引用

第40届中国控制会议

作者： Yabing Huang Jun Zhao State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Key Laboratory of Data Analytics and Optimization for Smart Industry Northeastern University Ministry of Education College of Information Science and Engineering Northeastern University

In this paper, the socially optimal Nash equilibrium of the N-player switched differential game is investigated. Specifically, the definition of the switched Nash equilibrium is presented, and the sufficient condition to construct the switched Nash equilibrium is proposed thereafter. In order to improve the efficiency of the switched Nash equilibrium, the switching strategy is designed to minimize the social costs of N players to guarantee the resulting switched Nash equilibrium is socially optimal.

关键词： Switched systems Nash equilibrium social optimum differential game

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：