- مبلغ: ۸۶,۰۰۰ تومان
- مبلغ: ۹۱,۰۰۰ تومان
An approach based on self-organizing models is presented for identification of piecewise linear switching systems, whose dynamics switch between a number of modes. The proposed method is based on a formulation of the identification problem as a generalized plane-clustering problem, which is solved using self-organizing maps. The method does not assume that the system modes depend on the state, but the mode switches may occur in an arbitrary and unknown manner. The procedure does not require knowledge of the number of modes or system orders, and it can be used for both on-line and off-line identification. Numerical examples illustrate that the procedure identifies switching systems correctly. The identification method is also applied to data from an industrial blast furnace for modeling and prediction of the silicon content of the hot metal. A switched linear model is demonstrated to capture different dynamics of the process and an analysis of the results reveals how mode switching models gradual and rapid changes in the output. The resulting models are finally shown to provide insight into factors that govern the silicon content in the blast furnace in different states.
An identification method for switching systems has been presented. Themethoddoesnot assume thatthe systemmodedepends on the state, but may change in an arbitrary way. In the proposed procedure the identification problem is formulated as a generalized plane clustering problem. The resulting problem is solved using a method which can be considered as a modification of selforganizing maps. One advantage of the proposed identification method is that in analogy with standard self-organizing maps, it is simple to implement, and it can be applied both off line or recursively to on-line identification. Numerical simulations show that the proposed technique efficiently identifies the correct modes and parameters. On a set of industrial data taken from an ironmaking blast furnace, the method was illustrated to provide reasonable predictions of the output variable, the hot metal silicon content, thus demonstrating the potential of the technique for real-time applications. Furthermore,the switching between themodes was analyzed and the interpretation provided by the modes was discussed. The results of the analysis with multiple models demonstrated that the modes describe different dynamics and also different operationlevels of the silicon content, further revealing interesting findings on the way in which the input variables affected the output in different states. Despite the black-box nature of the model, a detailed analysis of the arising modes can provide additional information about the factors governing the silicon content in the hot metal. These findings may prove useful, e.g., in the design of strategies for automatic control of the silicon content.