A Box-Jenkins Method that is Asymptotically Globally Convergent for Open Loop Data
نویسنده
چکیده
An algorithm for the identification of a multi-input single-output (MISO) Box-Jenkins model is developed. The method consists of several simple steps: first a high order ARX model is estimated; then the process model is calculated using the so-called Steiglitz-McBride iteration on the filtered inputoutput data; and finally the disturbance model is calculated by estimating an ARMA model of the output error residual. It can be proven that the Steiglitz-McBride iteration for the process model part is asymptotically globally convergent. The proposed method outperforms a standard Box-Jenkins method in simulation examples.
منابع مشابه
Center manifold analysis and Hopf bifurcation of within-host virus model
A mathematical model of a within-host viral infection is presented. A local stability analysis of the model is conducted in two ways. At first, the basic reproduction number of the system is calculated. It is shown that when the reproduction number falls below unity, the disease free equilibrium (DFE) is globally asymptotically stable, and when it exceeds unity, the DFE is unstable and there ex...
متن کاملForecasting Milled Rice Production in Ghana Using Box-Jenkins Approach
The increasing demand for rice in Ghana has been a major concern to the government and other stakeholders. Recent concerns by the coalition for African Rice Development (CARD) to double rice production within ten years in Sub-Saharan countries have triggered the to implement strategies to boost rice production in the government. To fulfill this requirement, there is a need to monitor and foreca...
متن کاملPrediction of Stock Price using Particle Swarm Optimization Algorithm and Box-Jenkins Time Series
The purpose of this research is predicting the stock prices using the Particle Swarm Optimization Algorithm and Box-Jenkins method. In this way, the information of 165 corporations is collected from 2001 to 2016. Then, this research considers price to earnings per share and earnings per share as main variables. The relevant regression equation was created using two variables of earnings per sha...
متن کاملMl Identification of Closed-loop Systems in a Specified Frequency Band
In classical time domain Box-Jenkins identification discrete-time plant and noise models are estimated using sampled input/output signals. The frequency content of the input/output samples covers uniformly the whole unit circle in a natural way, even in case of prefiltering. In Ljung (1999) the time domain Box-Jenkins framework has been extended to frequency domain data captured in open loop on...
متن کاملA New Method for Time-Delay Compensation in Control Systems
In this paper a new method is introduced and investigated for removing the destabilizing effects of time-delay parameter in control loops. The concept of the method is taken from the knowledge concerning the dynamic behaviour of irrational transfer functions (Ir-TF), which is discussed and investigated elswhere in frequency response domain and is explained briefly here. Ir-TFs, which are we...
متن کامل