In transforming the predictor the predictor covariances also need to be transformed. In this example, four direct measurements of the furnace slot size, sizeMeasured, and furnace current-power ratio, ySizeMeasured, are used to estimate. Specifically, transform the predictor state,, to, so that where the measured current-power ratio, and is the furnace slot size. This is not uncommon in practice where the cost of taking direct measurements is high and only be done periodically (such as when the component is being replaced). How do we transform the state coordinates so that the model's state corresponds to the (time dependent) slot size? The solution is to rely on actual, direct measurements of the slot size taken intermittently. The model est is a 1-step ahead predictor expressed in the same state coordinates as the original model sys. Use "idssdata", "getpvec", "getcov" for parameters and their uncertainties.Ĭreated by direct construction or transformation. % translate the identified model covariance to the predictor.ĭiscrete-time identified state-space model: % |TimeSeriedPredictionExample| and the |translatecov()| command to % Create a 1-step ahead predictor model sys for the specified model mdl %CREATEPREDICTOR Return 1-step ahead predictor. Function pred = createPredictor(mdl,data)
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. Archives
December 2022
Categories |