Abstract
System identification has been a major advancement in the evolution of engineering. As it is by default the first step towards a significant set of adaptive control techniques, it is imperative for engineers to apply it in order to practice control. Given that system identification could be useful in creating a digital twin, this work focuses on the initial stage of the procedure by discussing simplistic system order identification. Through specific numerical examples, this study constitutes an investigation on the most “natural” method for estimating the order from responses in a convenient and seamless way in time-domain. The method itself, originally proposed by Ho and Kalman and utilizing linear algebra, is an intuitive tool retrieving information out of the data themselves. Finally, with the help of the limitations of the methods, the potential future outlook is discussed, under the prism of forming a digital twin.
Highlights
Adaptive control has been quite popular over the last fifty years [1,2], with a variety of methodologies available [3]
With Industry 4.0-like movements across the Globe being the main streams of digitalization trends in industry [5,6], the cognitive functionalities of automation have been integrated to a great extent and the use of adaptive control techniques has been spread even more
The set of Bayesian information criterion (BIC)/Akaike information criterion (AIC)/generalized information criterion (GIC) methodologies is another set of methods [18,19] highly utilized; in the literature there has been a practical comparison between residual sum of squares (RSS) and BIC [20]
Summary
Adaptive control has been quite popular over the last fifty years [1,2], with a variety of methodologies available [3]. The set of Bayesian information criterion (BIC)/Akaike information criterion (AIC)/generalized information criterion (GIC) methodologies is another set of methods [18,19] highly utilized; in the literature there has been a practical comparison between residual sum of squares (RSS) and BIC [20]. What seems to be missing, is a numerical illustration on the simplest, intuitive way to extract such information (meaning the order of the system) from data (the responses themselves) To this end, this work attempts to investigate numerically a simple method for the estimation of the system order, in time domain, utilizing the linear dependence between the sampled data. Conclusions are extracted on the significance and the usability of the algorithm
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
