Search

The problem of estimating parameters of switched affine systems with noisy input-output observations is considered. The switched affine models is transformed into a switched linear one by removing its intersection subspace, which is estimated from observations. A subspace technique is proposed to exploit the observations' permutation structure, which transforms the problem of associating observations with subsystems into one of de-permutating a block diagonal matrix, referred as adjacency matrix. Then a normalized spectral clustering algorithm is presented to recover the block structure of adjacency matrix, from which each observation is related to a particular subsystem. With the labelled observations, parameters of the submodel are estimated via the total least squares (TLS) estimator. The proposed technique is applicable to switched affine systems with arbitrarily shaped domain partitions, and it offers significantly improved performance and lowered computation complexity than existing techniques., Comment: 13 pages, 14 figures. arXiv admin note: text overlap with arXiv:1307.0326

The problem of estimating parameters of a deterministic jump or piecewise linear model is considered. A subspace technique referred to as spectral clustering on subspace (SCS) algorithm is proposed to estimate a set of linear model parameters, the model input, and the set of switching epochs. The SCS algorithm exploits a block diagonal structure of the system input subspace, which partitions the observation space into separate subspaces, each corresponding to one and only one linear submodel. A spectral clustering technique is used to label the noisy observations for each submodel, which generates estimates of switching time epoches. A total least squares technique is used to estimate model parameters and the model input. It is shown that, in the absence of observation noise, the SCS algorithm provides exact parameter identification. At high signal to noise ratios, SCS attains a clairvoyant Cram\'{e}r-Rao bound computed by assuming the labeling of observation samples is perfect., Comment: 11 pages with 11 figures