System identification : theory for the user / Lennart Ljung

SERBIULA (sistema Librum 2.0) 01/1989;
Source: OAI


Incluye bibliografía e índice

401 Reads
  • Source
    • "Fig. 1. SID model development procedure Details about how to use the training data to obtain a SID model is described in [8] [9] and is briefly summarized in Fig. 1. In this figure, U is training inputs, Y is training outputs data, PSD is power spectral density model for inputs, and CPSD is cross power spectral density model for input and output. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Buildings, consuming over 70% of the electricity in the U.S., play significant roles in smart grid infrastructure. The automatic operation of buildings and their subsystems in responding to signals from a smart grid is essential to reduce energy consumption and demand, as well as improve the resilience to power disruptions. In order to achieve such automatic operation, high fidelity and computationally efficiency building energy forecasting models under different weather and operation conditions are needed. Currently, data-driven (black box) models and hybrid (grey box) models are commonly used in model based building control operation. However, typical black box models often require long training period and are bounded to weather and operation conditions during the training period. On the other hand, creating a grey box model often requires long calculation time due to parameter optimization process and expert knowledge during the model structure determining and simplification process. An earlier study by the authors proposed a system identification approach to develop computationally efficient and accurate building energy forecasting models. This paper attempts to extend this early study and to quantitatively evaluate how the most important characteristics of a building energy system: its nonlinearity and response time, affect the system identification process and model accuracy. Two commercial building: a small-size and a medium-size commercial building, with varying chiller nonlinearity, are simulated using EnergyPlus in lieu of real buildings for model development and validation. The system identification method proposed in the early study is applied to these two buildings that have varying nonlinearity and response time. Adaption of the proposed system identification method based on systems??? nonlinearity and response time is proposed in this study. The energy forecasting results demonstrate that the adaption is capable of significantly improve the performan- e of the system identification model.
    2015 Workshop on Modeling and Simulation of Cyber-Physical Energy Systems (MSCPES), Seattle, WA; 04/2015
  • Source
    • "(C) and (D) Learning the dimensionality and dynamics, via subspace identification [45] of a linear neural network of size N = 5000 from spontaneous noise driven activity. The low-rank connectivity of the network forces the system to lie in a K = 6 dimensional subspace. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Technological advances have dramatically expanded our ability to probe multi-neuronal dynamics and connectivity in the brain. However, our ability to extract a simple conceptual understanding from complex data is increasingly hampered by the lack of theoretically principled data analytic procedures, as well as theoretical frameworks for how circuit connectivity and dynamics can conspire to generate emergent behavioral and cognitive functions. We review and outline potential avenues for progress, including new theories of high dimensional data analysis, the need to analyze complex artificial networks, and methods for analyzing entire spaces of circuit models, rather than one model at a time. Such interplay between experiments, data analysis and theory will be indispensable in catalyzing conceptual advances in the age of large-scale neuroscience. Copyright © 2015. Published by Elsevier Ltd.
    Current opinion in neurobiology 03/2015; 32. DOI:10.1016/j.conb.2015.04.003 · 6.63 Impact Factor
  • Source
    • "The problem of going from data to models is the usual system identification problem. Several approaches have been proposed in the literature ranging from standard prediction error methods [20], to iterative solutions based on EM [9], to the more recent subspace methods [25]. For the case of dynamic textures, due to the dimension of the signal (76,800 for video at half-resolution), one cannot apply standard identification algorithms. "
    [Show abstract] [Hide abstract]
    ABSTRACT: In this expository paper we illustrate the use of filtering and identification-theoretic techniques in a number of problems in computer vision. We first demonstrate how linear system identification techniques combined with distances for linear systems can be used for modeling, synthesis, classification and recognition of dynamic textures and human gaits. We then show how hybrid system identification techniques can be used for segmentation of dynamic textures. We also highlight some open problems in system identification that are motivated by extensions of the research described in this paper.
Show more