检索结果-内蒙古大学图书馆

Modeling and identification of uncertain-input systems

AUTOMATICA 2019年 105卷 130-141页

作者： Risuleo, Riccardo Sven Bottegal, Giulio Hjalmarsson, Hakan KTH Royal Inst Technol ACCESS Linnaeus Ctr Stockholm Sweden Eindhoven Univ Technol Dept Elect Engn Eindhoven Netherlands

We present a new class of models, called uncertain-input models, that allows us to treat system identification problems in which a linear system is subject to a partially unknown input signal. To encode prior information about the input or the linear system, we use Gaussian-process models. We estimate the model from data using the empirical Bayes approach: the hyperparameters that characterize the Gaussian-process models are estimated from the marginal likelihood of the data. We propose an iterative algorithm to find the hyperparameters that relies on the EM method and results in decoupled update steps. Because in the uncertain-input setting neither the marginal likelihood nor the posterior distribution of the unknowns is tractable, we develop an approximation approach based on variational Bayes. As part of the contribution of the paper, we show that this model structure encompasses many classical problems in system identification such as Hammerstein models, blind system identification, and cascaded linear systems. This connection allows us to build a systematic procedure that applies effectively to all the aforementioned problems, as shown in the numerical simulations presented in the paper. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： System identification estimation algorithms Nonlinear models Nonparametric identification Gaussian processes

来源：评论

学校读者我要写书评

暂无评论

Closed-loop diesel engine combustion phasing control based on crankshaft torque measurements

引用

CONTROL ENGINEERING PRACTICE 2014年 33卷 115-124页

作者： Thor, Mikael Egardt, Bo McKelvey, Tomas Andersson, Ingemar Chalmers Univ Technol Dept Signals & Syst SE-41296 Gothenburg Sweden

Methods for closed-loop combustion phasing control in a diesel engine, based on measurements of crankshaft torque, are developed and evaluated. A model-based method for estimation of cylinder individual torque contributions from the crankshaft torque measurements is explained and a novel approach for identification of crankshaft dynamics is proposed. The use of the combustion net torque concept for combustion phasing estimation in the torque domain is also described. Two different control schemes, one for individual cylinder control and one for average cylinder control, are studied. The proposed methods are experimentally evaluated using a light-duty diesel engine equipped with a crankshaft integrated torque sensor. The results indicate that it is possible to estimate and control on a cylinder individual basis using the measurements from the crankshaft torque sensor. Combustion phasing is estimated with bias levels of less than 0.5 crank angle degrees (CAD) and cycle-to-cycle standard deviations of less than 0.7 CAD for all cylinders and the implemented combustion phasing controllers manage to accurately counteract disturbances in both fuel injection timing and EGR fraction. (C) 2014 Elsevier Ltd. All rights reserved.

关键词： Internal combustion engines Engine control Engine management estimation algorithms

来源：评论

学校读者我要写书评

暂无评论

A GES attitude observer with single vector observations

引用

AUTOMATICA 2012年第2期48卷 388-395页

作者： Batista, Pedro Silvestre, Carlos Oliveira, Paulo Univ Tecn Lisboa Inst Syst & Robot Inst Super Tecn P-1049001 Lisbon Portugal Univ Macau Fac Sci & Technol Taipa Peoples R China

This paper proposes a globally exponentially stable (GES) observer for attitude estimation based on a single time-varying reference vector, in inertial coordinates, and corresponding vector, in body-fixed coordinates, in addition to angular velocity readings. The proposed solution is computationally efficient and, in spite of the fact that the observer does not evolve on the Special Orthogonal Group SO(3), an explicit solution on SO(3) is also provided, whose error is shown to converge exponentially fast to zero for all initial conditions. The distinct roles of the inertial and the corresponding body-fixed vectors on the observability of the system are also examined and simulation results are shown that illustrate the performance of the proposed attitude observer in the presence of low-grade sensor specifications. (C) 2011 Elsevier Ltd. All rights reserved.

关键词： Attitude algorithms State observers Time-varying systems estimation algorithms Navigation systems

来源：评论

学校读者我要写书评

暂无评论

INTELLIGENT KNOWLEDGE-BASED SYSTEM FOR DYNAMIC SYSTEM-IDENTIFICATION

引用

IEE PROCEEDINGS-D CONTROL THEORY AND APPLICATIONS 1990年第1期137卷 1-12页

作者： BETTA, A LINKENS, DA Department of Control Engineering University of Sheffield Sheffield UK

The development and evaluation of an expert advisor for system identification (EASI) is described. The principles behind a suitable knowledge representation paradigm for a system which includes both intelligent tutoring and software package front-end concepts are outlined. The system has been constructed using an expert system ‘text-animation’ shell with linkage into Prolog-2 to provide enhancements. These extensions have included an online dictionary and bibliographic material. The identification domain aspects covered include experimental design, model structure determination, estimation algorithms, with applications to SISO and MIMO linear systems, and SISO nonlinear dynamics. Different levels of user-model are provided, and the advisor acts as a front-end to a number of in-house identification packages.

关键词： text animation shell online dictionary SISO systems Simulation, modelling and identification system identification multivariable control systems Multivariable control systems multi-input-multi-output systems dynamic system intelligent tutoring knowledge based systems experimental design expert advisor identification Expert systems and other AI software and techniques nonlinear dynamics estimation algorithms Prolog-2 Control engineering computing MIMO systems linear systems user-model software packages control engineering computing single input-single output systems expert system bibliographic material model structure determination

来源：评论

学校读者我要写书评

暂无评论

Disaggregated Daylight-Artificial Light Sensing

引用

IEEE SENSORS JOURNAL 2012年第12期12卷 3438-3445页

作者： Yang, Hongming Pandharipande, Ashish Philips Res Labs NL-5656 AE Eindhoven Netherlands

Control of lighting systems that adapt to daylight is known to be energy efficient. An underlying challenge in such control is the estimation of daylight level. We consider the problem of disaggregated estimation of the daylight and artificial light levels in a lighting system. To facilitate this disaggregation, the light output from each light source is modulated and the system operates under a carrier sense multiple access with collision avoidance protocol. At the light sensor, the received electrical signal is a superposition of the light contributions from daylight and artificial light sources. We present algorithms to process the sensor signal to estimate the daylight and artificial light levels. An optimum joint least-squares estimator is analyzed and, subsequently, two practical successive estimation algorithms are proposed. The performance of these algorithms is evaluated analytically and validated via experimental results.

关键词： estimation algorithms light sensing lighting control systems

来源：评论

学校读者我要写书评

暂无评论

Impact of Algorithm Selection on Modeling Ozone Pollution: A Perspective on Box and Tiao (1975)

引用

FORESTS 2020年第12期11卷 1311页

作者： Paun, Mihaela Gunaime, Nevine Strimbu, Bogdan M. Univ Bucharest Res Inst Univ Bucharest ICUB Fac Adm & Business Bucharest 050663 Romania Saudi Elect Univ Coll Sci & Theoret Studies Jeddah 23442 Saudi Arabia Oregon State Univ Coll Forestry Corvallis OR 97331 USA Transilvania Univ Fac Silviculture & Forest Engn Brasov 500123 Romania

estimation using a suboptimal method can lead to imprecise models, with cascading effects in complex models, such as climate change or pollution. The goal of this study is to compare the solutions supplied by different algorithms used to model ozone pollution. Using Box and Tiao (1975) study, we have predicted ozone concentration in Los Angeles with an ARIMA and an autoregressive process. We have solved the ARIMA process with three algorithms (i.e., maximum likelihood, like Box and Tiao, conditional least square and unconditional least square) and the autoregressive process with four algorithms (i.e., Yule-Walker, iterative Yule-Walker, maximum likelihood, and unconditional least square). Our study shows that Box and Tiao chose the appropriate algorithm according to the AIC but not according to the mean square error. Furthermore, Yule-Walker, which is the default algorithm in many software, has the least reliable results, suggesting that the method of solving complex models could alter the findings. Finally, the model selection depends on the technical details and on the applicability of the model, as the ARIMA model is suitable from the AIC perspective but an autoregressive model could be preferred from the mean square error viewpoint. Our study shows that time series analysis should consider not only the model shape but also the model estimation, to ensure valid results.

关键词： ARIMA autoregressive process estimation algorithms maximum likelihood unconditional least square

来源：评论

学校读者我要写书评

暂无评论

Estimating model mismatch overbounds for the robust autotuning of industrial regulators

引用

AUTOMATICA 2000年第12期36卷 1855-1861页

作者： Leva, A Colombo, AM Politecn Milan Dipartimento Elettron & Informat I-20133 Milan Italy

This paper presents a method which, on the basis of a parametric model of a stable process and of a record of the process response to a convenient input signal, provides a nonparametric overbound of the model error magnitude. The results obtained in no sense depend on the model complexity. Simulation examples are reported to show the method's effectiveness in improving the performance of model-based autotuners. (C) 2000 Elsevier Science Ltd. All rights reserved.

关键词： estimation algorithms autotuners model-based control process control

来源：评论

学校读者我要写书评

暂无评论

Ranging-Free UHF-RFID Robot Positioning Through Phase Measurements of Passive Tags

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2020年第5期69卷 2408-2418页

作者： Magnago, Valerio Palopoli, Luigi Buffi, Alice Tellini, Bernardo Motroni, Andrea Nepa, Paolo Macii, David Fontanelli, Daniele Univ Trento Dept Informat Engn & Comp Sci I-38123 Trento Italy Univ Pisa Dept Energy Syst Terr & Construct Engn I-56122 Pisa Italy Univ Pisa Dept Informat Engn I-56122 Pisa Italy Univ Trento Dept Ind Engn I-38123 Trento Italy

The phase of the signals backscattered by the ultrahigh frequency radio-frequency identification (UHF-RFID) tags is generally more insensitive to multipath propagation than the received signal strength indicator (RSSI). However, signal phase measurements are inherently ambiguous and could be further affected by the unknown phase offsets added by the transponders. As a result, the localization of an agent by using only signal phase measurements looks infeasible. In this article, it is shown instead that the design of a dynamic position estimator (e.g., a Kalman filter) based only on the signal phase measurement is actually possible. To this end, the necessary conditions to ensure the theoretical local nonlinear observability are first demonstrated. However, a system that is locally observable guarantees the convergence of the localization algorithm only if the actual initial agent position is approximately known a priori. Therefore, the second part of the analysis covers the global observability, which ensures convergence starting from any initial condition in the state space. It is important to emphasize that complete observability holds only in theory. In fact, measurement uncertainty may greatly affect position estimation convergence. The validity of the analysis and the practicality of this localization approach are further confirmed by numerical simulations based on an unscented Kalman filter (UKF).

关键词： estimation algorithms indoor localization observability analysis radio-frequency identification (RFID) phase-based localization ultrahigh frequency radio-frequency identification (UHF-RFID)

来源：评论

学校读者我要写书评

暂无评论

Modelling the volumetric efficiency of IC engines: Parametric, non-parametric and neural techniques

引用

CONTROL ENGINEERING PRACTICE 1996年第10期4卷 1405-1415页

作者： DeNicolao, G Scattolini, R Siviero, C Dipartimento di Informatica e Sistemistica Universitd di Pavia Via Ferrata 1 27100 Pavia Italy

The volumetric efficiency (eta(v)) represents a measure of the effectiveness of an air pumping system, and is one of the most commonly used parameters in the characterization and control of four-stroke internal combustion engines. Physical models of eta(v) require the knowledge of some quantities usually not available in normal operating conditions, Hence, a purely black-box approach is often used to determine the dependence of eta(v) upon the main engine variables, like the crankshaft speed and the intake manifold pressure. Various black-box approaches for the estimation of eta(v) are reviewed, from parametric (polynomial-type) models, to non-parametric and neural techniques, like additive models, radial basis function neural networks and multi-layer perceptrons. The benefits and limitations of these approaches are examined and compared. The problem considered here can be viewed as a realistic benchmark for different estimation techniques.

关键词： internal combustion engines engine control estimation algorithms parameter identification polynomial models non-parametric identification additive models neural networks

来源：评论

学校读者我要写书评

暂无评论

Highlights of statistical signal and array processing

引用

IEEE SIGNAL PROCESSING MAGAZINE 1998年第5期15卷 21-64页

作者： Chen, TH Hero, A Djuric, PM Messer, H Goldberg, J Thomson, DJ Amin, MG Krim, H Pesquet, JC Giannakis, G Swami, A Tugnait, JK Cardoso, JF Tong, L Krolik, J Carnegie Mellon Univ Pittsburgh PA 15213 USA Univ Michigan Ann Arbor MI 48109 USA Univ Virginia Charlottesville VA 22903 USA Villanova Univ Villanova PA 19085 USA Ecole Natl Super Telecommun Bretagne Paris France Auburn Univ Auburn AL 36849 USA SUNY Stony Brook Stony Brook NY 11794 USA N Carolina State Univ Raleigh NC 27695 USA Duke Univ Durham NC 27706 USA Portland State Univ Portland OR 97207 USA Tel Aviv Univ IL-69978 Tel Aviv Israel Univ Illinois Chicago IL USA Univ Colorado Boulder CO 80309 USA USA Res Lab Washington DC 20310 USA Brigham Young Univ Provo UT 84602 USA Rochester Inst Technol Rochester NY 14623 USA Cornell Univ Ithaca NY 14853 USA Chalmers Univ Technol S-41296 Gothenburg Sweden Univ Texas Austin TX 78712 USA Purdue Univ W Lafayette IN 47907 USA

The Statistical Signal and Array Processing Technical Committee(SSAP-TC) deals with signals that are random and processes an array ofsignals simultaneously. The field of SSAP represents both solid theoryand practical applications. Starting with research in spectrumestimation and statistical modeling, study in this field is always fullof elegant mathematical tools such as statistical analysis and matrixtheory. The area of statistical signal processing expands intoestimation and detection algorithms, time-frequency domain analysis,system identification, and channel modeling and equalization. The areaof array signal processing also extends into multichannel filtering,source localization and separation, and so on. This article representsan endeavor by the members of the SSAT-TC to review all the significantdevelopments in the field of SSAP. To provide readers with pointers forfurther study of the field, this article includes a very impressivebibliography-close to 500 references are cited. This is just one of theindications that the field of statistical signals has been an extremelyactive one in the signal processing community. The article alsointroduces the recent reorganization of three technical committees ofthe Signal Processing Society

关键词： array signal processing parameter estimation reviews signal detection spectral analysis statistical analysis time-frequency analysis channel modeling detection algorithms equalization estimation algorithms matrix theory multichannel filtering random sign signal acquisition Parameter estimation channel modeling Statistical analysis array signal processing Array processing Statistical methods Fields Time frequency analysis Multichannel filter signals Spectrum Analysis Detection algorithms matrix theory Equalization

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：