检索结果-内蒙古大学图书馆

2024 Jiangsu Annual Conference on automation, JACA 2024

作者： Deng, Yixin Wang, Zairan Chen, Yang-Yang Liu, Qin Wang, Xiangyu School of Automation Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China School of Cyber Science and Engineering Southeast University Nanjing China

ISBN: (纸本)9781837242689

In the Off-Axis Integrated Cavity Output Spectroscopy (OA-ICOS) technique, single-stage filters are commonly used to reduce noise and improve the signal-to-noise ratio, enabling more precise CO2 concentration detection. However, these filters often underperform under real-time conditions. To enhance real-time performance, this paper proposes a novel framework based on Double Wavelet Threshold Filter (DWTF) that adaptively suppresses noise while preserving key features of CO2 concentration signal. Firstly, one wavelet threshold filter (WT) is introduced to calculate the mean of the current sequence, providing an initial denoising step. Secondly, another WT is employed to extract features from a longer sequence for adaptive computation of the discount factor. Finally, an exponential moving average filter (EMA) is applied to combine both current and historical data to produce a smoother aggregated output. To validate the effectiveness, DWTF was compared with other conventional algorithms for a CO2 dataset with three distinct states: smooth, ship and mutant, obtained by OA-ICOS. The experimental results demonstrate that DWTF performs effectively in all three states. © The Institution of engineering & Technology 2024.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Strategy via Reinforcement Learning for the Prisoner＇s Dilemma Game

引用

IEEE/CAA Journal of Automatica Sinica 2018年第1期5卷 301-310页

作者： Lei Xue Changyin Sun Donald Wunsch Yingjiang Zhou Fang Yu Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing 210096 China Department of Electrical and Computer Engineering Missouri University of Science and Technology Rolla MO 65409 USA College of Automation Nanjing University of Posts and Telecommunications Nanjing 210023 China Institute of Logistics Science and Engineering Shanghai Maritime University Shanghai 210096 China IEEE

The iterated prisoner's dilemma(IPD) is an ideal model for analyzing interactions between agents in complex networks. It has attracted wide interest in the development of novel strategies since the success of tit-for-tat in Axelrod's tournament. This paper studies a new adaptive strategy of IPD in different complex networks, where agents can learn and adapt their strategies through reinforcement learning method. A temporal difference learning method is applied for designing the adaptive strategy to optimize the decision making process of the agents. Previous studies indicated that mutual cooperation is hard to emerge in the IPD. Therefore, three examples which based on square lattice network and scale-free network are provided to show two features of the adaptive strategy. First, the mutual cooperation can be achieved by the group with adaptive agents under scale-free network, and once evolution has converged mutual cooperation, it is unlikely to shift. Secondly, the adaptive strategy can earn a better payoff compared with other strategies in the square network. The analytical properties are discussed for verifying evolutionary stability of the adaptive strategy.

关键词： complex network prisoner’s dilemma reinforcement learning temporal differences learning

来源：评论

学校读者我要写书评

暂无评论

Design of neural network disturbance observer using RBFN for complex nonlinear systems

Design of neural network disturbance observer using RBFN for...

引用

作者： Li, Juan Yang, Jun Li, Shihua Chen, Xisong School of Automation Southeast University Nanjing 210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education China

ISBN: (纸本)9789881725592

To solve the difficulty that the applications of disturbance observer (DOB) approaches have been limited to minimum phase systems, a neural network disturbance observer using RBFN (RBFNDOB) is proposed for complex nonlinear systems, i.e., minimum phase system and non-minimum phase system, which may be with matching or mismatching disturbances. The proposed RBFNDOB is a simple modification of the original DOB by using a RBFN to identify the inverse model of system which can track the parameter variations of real system by an on-line learning algorithm. The non-minimum phase system can be transformed into minimum phase system by constructing a pseudo-system to solve the zero dynamics in the right half plane. The RBFNDOB combining with a feedback controller can effectively suppress the disturbances of the closed-loop systems. The effectiveness and validity of the proposed control algorithm can be verified by simulations. © 2011 Chinese Assoc of Automati.

关键词： Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

GPIO-based rail pressure control for diesel high pressure common rail injection system

GPIO-based rail pressure control for diesel high pressure co...

引用

2019 Jiangsu Annual Conference on automation, JACA 2019

作者： Wang, Jiapeng Sun, Hao Dai, Chen Li, Shihua Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing Jiangsu210096 China

The rail pressure control in diesel high-pressure common rail (HPCR) system is considered as one of the key issues for precise control of fuel injection. This study investigates the application of generalised proportional integral observer (GPIO)based control in diesel HPCR system. Firstly, a non-linear mathematical model of HPCR system which uses the metering unit as the actuator is established based on hydromechanics under some proper simplifications. Secondly, a GPIO is developed to estimate the mismatched disturbance caused by the injection process. Then a composite controller combining GPIO and backstepping control method is designed. By introducing the disturbance estimations into the control design process, the disturbance rejection capability of the system is promisingly enhanced. The effectiveness of the proposed control method is validated by the simulation results. © 2019 Institution of engineering and Technology. All rights reserved.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

GPI observer-based composite current-constrained control approach for DC–DC buck converters

GPI observer-based composite current-constrained control app...

引用

2019 Jiangsu Annual Conference on automation, JACA 2019

作者： Wang, Zuo Guo, Tianliang Wang, Xiangyu Li, Shihua School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education China

In this study, overcurrent protection technique is investigated for the voltage regulation problem of the DC–DC buck converter system with time-varying disturbances and uncertainties. Normally, fast dynamics during the start-up phase generates large transient current. The overlarge transient current may lead to risks of hardware damage. By selecting conservative control parameters, the current constrained performance can be realised. However, the transient performance and disturbance rejection ability are sacrificed. It is of significant importance to design a controller which keeps a good balance between dynamic performance and overcurrent protection. Moreover, the control accuracy is inevitable affected by the time-varying disturbances effects, including load variations, input voltage fluctuations and circuit parameter perturbations. In this paper, the control design is divided into two parts. Firstly, by inserting a dynamic penalty term into the state feedback controller, a baseline current-constrained scheme is developed. Rigorous stability analysis and current constraint performance are given under the presented baseline controller. Secondly, taking the time-varying disturbances into account, a novel GPI observer-based composite current-constrained controller can be developed by combining disturbance estimations and the baseline controller. Experimental results are provide to demonstrate the effectiveness of the presented control strategy. © 2019 Institution of engineering and *** rights reserved.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Depth Completion with Adaptive Online Adaptation 23

Self-supervised Depth Completion with Adaptive Online Adapta...

引用

7th International Conference on Machine Learning and Soft Computing, ICMLSC 2023

作者： Chen, Yang Tan, Yang Key Laboratory of Measurement and Control of Complex System of Engineering Ministry of Education School of Automation Southeast University Nanjing210096 China

ISBN: (纸本)9781450398633

Although depth completion has achieved remarkable performance relying on deep learning in recent years, these models tend to suffer a performance degradation when exposed to new environments. Online adaptation, where the model is trained in a self-supervised manner during testing, seems a promising technique to alleviate the drop. However, continuous online adaptation may cause the model to over-adapt and miss the optimal parameters, resulting in oscillation or even degradation of the model performance, in addition to wasting computational resources. Therefore, this paper proposes an adaptive online adaptation framework to make model adaptively trigger online adaptation when encountering novel environments and stop adaptation when model has adapted to the current environment. In detail, we design a trigger to detect the familiarity of model to the current scenario based on image similarity and then launch online adaptation when the scenario is novel. Besides, we elaborate a stopper to monitor the error between prediction and depth input and convert online adaptation to inference when online adaptation does not bring improvement for model. Experimental results demonstrate that our method improves the accuracy of model prediction and increases average running speed of the model on each frame in online adaptation. © 2023 ACM.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Valve Stiction Compensation Based on Equivalent-Input-Disturbance Approach 29

Valve Stiction Compensation Based on Equivalent-Input-Distur...

引用

第29届中国控制与决策会议

作者： Qi Lei Xi Lei Min Wu School of Information Science and Engineering Central South University School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

ISBN: (纸本)9781509046584

The presence of stiction in a control valve causes loop oscillation,and limits the control loop *** address this problem,the paper proposes a method based on equivalent-input-disturbance（EID） to control valve *** this method,a classic two-parameter stiction model is ***,an EID estimator is utilized to estimate the effects of valve stiction in control *** the controller is designed in the spirit of repetitive *** simulation control results are compared with the traditional *** results demonstrate that the proposed EID method can effectively improve the control performance of valve stiction and eliminate the stiction-induced oscillations.

关键词： Valve Stiction EID Repetitive control Compensation

来源：评论

学校读者我要写书评

暂无评论

Adaptive Augmented Kalman Filter-Based control for Electronic Throttle systems with Disturbances and Noises 42

Adaptive Augmented Kalman Filter-Based Control for Electroni...

引用

42nd Chinese control Conference, CCC 2023

作者： Li, Wen Su, Jinya Li, Shihua School of Automation Southeast University Nanjing210096 China Ministry of Education Key Laboratory of Measurement and Control of Complex Systems of Engineering Southeast University Nanjing210096 China

ISBN: (纸本)9789887581543

In this study, we investigate the control problem of electronic throttle systems in the presence of practical challenges such as disturbances and measurement noises. To address these challenges, we propose an adaptive augmented Kalman filter (AAKF) based control approach that combines the strengths of extended state observer in disturbance estimation and adaptive Kalman fil-ter in adaptive noise filtering. The outputs of AAKF are integrated into the Backstepping control design, resulting in a composite control that concurrently achieves fast disturbance rejection and noise suppression. We conduct a comparative simulation study against conventional methods without adaptive filtering to validate the effectiveness of the proposed AAKF-based control strat-egy, which exhibits superior position control accuracy and disturbance attenuation performance. We envision that our proposed control strategy will contribute to improving vehicle power, fuel economy, and emission performance. © 2023 Technical Committee on control Theory, Chinese Association of automation.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

Driving behaviour recognition from still images by using multi-stream fusion CNN

Driving behaviour recognition from still images by using mul...

引用

作者： Hu, Yaocong Lu, Mingqi Lu, Xiaobo School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

Abnormal driving behaviour is a leading cause of serious traffic accidents threatening human life and public property globally. In this paper, we investigate the use of a deep learning approach to automatically recognize driving behaviour (such as normal driving, driving with hands off the wheel, calling, playing mobile phone, smoking and talking with passengers) in a single image. The task of driving behaviour recognition can be regarded as a multi-class classification problem, and we resolve this problem from two aspects in our study: (1) Employ multi-stream CNN to extract multi-scale features by filtering images with receptive fields of different kernel sizes and (2) investigate different fusion strategies to combine the multi-scale information and generate the final decision for driving behaviour recognition. The effectiveness of our proposed method is validated by extensive experiments carried out on our self-created simulated driving behaviour dataset, as well as a real driving behaviour dataset, and the experiment results demonstrate that the proposed multi-stream CNN-based method achieves the significant performance improvements compared to the state of the art. © 2018, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Smoke vehicle detection based on multi-feature fusion and hidden Markov model

Smoke vehicle detection based on multi-feature fusion and hi...

引用

作者： Tao, Huanjie Lu, Xiaobo School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

Existing smoke vehicle detection methods and vision-based smoke detection methods are vulnerable to false alarms. This paper presents an automatic smoke vehicle detection method based on multi-feature fusion and hidden Markov model (HMM). In this method, we first detect moving objects using an improved visual background extractor (ViBe) algorithm and obtain smoke-colored blocks using color histogram features in the HSI (hue, saturation, and intensity) color space. The adaptive scale local binary pattern (AS-LBP) and the discriminative edge orientation histogram (disEOH) are proposed and combined to characterize the smoke-colored blocks. More specifically, the proposed AS-LBP, a texture feature descriptor, is based on the quadratic fitting of our labelled data to obtain the best scale. The proposed disEOH, a gradient-based feature descriptor, is robust to noise by extracting discriminative edge information using Gaussian filters and principal component analysis (PCA). The discrete cosine transform (DCT) is employed to extract frequency domain information from the region fused by smoke blocks. To utilize the dynamic features, the HMMs are employed to analyze and classify the smoke-colored block sequences and region sequences in continuous frames. The experimental results show that the proposed method achieves better performances than existing smoke detection methods, especially achieves lower false alarms. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Smoke

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：