System identification : a survey

By Eykhoff K .J . ström P. 1994

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Model-based reinforcement learning with parametrized physical models and optimism-driven exploration (2015, methodology): “One way to tackle this challenge is to first perform model identification, and then use the identified model to control the system [16], [20].”
Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems (2018, background): “The answer to this question pertains to the well-established field of systems identification [5].”
EPOpt: Learning Robust Neural Network Policies Using Model Ensembles (2016, methodology): “Standard model-based control methods typically operate by finding a maximum-likelihood estimate of the target model (Ljung, 1998; Ross & Bagnell, 2012; Deisenroth et al., 2013), followed by policy optimization.”
A new kernel-based approach for linear system identification (2010, background): “When identification is motivated by robust-control design purposes model order has to be relatively low [23,37,41].”
Robust identification of continuous-time models with arbitrary time-delay from irregularly sampled data (2015, background): “Introduction Although dynamic systems in the physical world are naturally described in the continuous-time (CT) domain, most system identification schemes have been based on discrete-time (DT) models [1, 2].”
A Broader View on Bias in Automated Decision-Making: Reflecting on Epistemology and Dynamics (2018, methodology): “…the field of System Identification uses statistical methods to build mathematical models of dynamical systems from measured data, often to be employed to control dynamical systems with strict safety requirements, such as airplanes or electric power systems (Ljung, 1998; Åström & Murray, 2010).”
A comprehensive review of digital twin — part 1: modeling and twinning enabling technologies (2022, methodology): “• Statistical models for dynamic system identification (P2V) System identification is the process of learning a mathematical representation of a dynamic system based on pairs of measured input/output data (Ljung 1998).”
Visual Grounding of Learned Physical Models (2020, methodology): “Prior works on system identi-ﬁcation for robotics usually make strong assumptions on the structure of the underlying system (Ljung, 2001), or require a lot of data to train a forward model (Finn & Levine, 2017), and therefore have a hard time modeling complex de-formable objects like ﬂuids and…”
Learning GP-BayesFilters via Gaussian process latent variable models (2009, methodology): “The system identification community has developed various subspace identification techniques (Ljung 1987; Van Overschee and De Moor 1996).”
A sensitivity matrix based methodology for inverse problem formulation (2020, background): “The question of parameter identifiability/estimation in the context of parameter determination from system observations or output is at least forty years old and received much attention in the zenith years of linear system and control theory in the investigation of observability, controllability and”
Time-domain fitting of battery electrochemical impedance models (2015, background): “Recently, there has been significant interest in the practical identifiability analysis of battery models (see for instance [41] and references therein), which are mainly based on the Fisher information matrix [42, 43].”
MIMO Transceiver Design via Majorization Theory (2007, background): “Matrix Inversion Lemma The general expression of the matrix inversion lemma is [66, 83, 133, 143] (A + BCD)−1 = A−1 − A−1B(DA−1B + C−1)−1DA−1.”
NoRML: No-Reward Meta Learning (2019, unknown): “Separate from the meta learning literature, many other works have considered the problem of adapting to varying dynamics through,e.g. adaptiveinversecontrol[34],self-modeling[2],Bayesian optimization[6],oronlinesystemidentification[18,35].”
Nonlinear System Identification: A User-Oriented Road Map (2019, methodology): “is estimated on the ’tail’ experiment using the prediction error framework [6], [7].”
Engineering Self-Adaptive Systems through Feedback Loops (2009, background): “Feedback loops of this sort are used in many engineered devices to bring about desired behavior despite undesired disturbances [24,27,28,29].”