Nonlinear Identification with Local Model Networks Using GTLS Techniques and Equality Constraints

Institute of Mechanics and Mechatronics, Division of Control and Process Automation, Vienna University of Technology, Vienna, Austria.
IEEE Transactions on Neural Networks (Impact Factor: 2.95). 07/2011; 22(9):1406-18. DOI: 10.1109/TNN.2011.2159309
Source: PubMed

ABSTRACT Local model networks approximate a nonlinear system through multiple local models fitted within a partition space. The main advantage of this approach is that the identification of complex nonlinear processes is alleviated by the integration of structured knowledge about the process. This paper extends these concepts by the integration of quantitative process knowledge into the identification procedure. Quantitative knowledge describes explicit dependences between inputs and outputs and is integrated in the parameter estimation process by means of equality constraints. For this purpose, a constrained generalized total least squares algorithm for local parameter estimation is presented. Furthermore, the problem of proper integration of constraints in the partitioning process is treated where an expectation-maximization procedure is combined with constrained parameter estimation. The benefits and the applicability of the proposed concepts are demonstrated by means of two illustrative examples and a practical application using real measurement data.

  • [Show abstract] [Hide abstract]
    ABSTRACT: Battery emulation with a controllable high-power dc supply enables repeatable hardware-in-the-loop testing of powertrains for hybrid and electric vehicles. For this purpose, not only the power flow but also the nonlinear characteristic and dynamic impedance of batteries need to be emulated. In this paper, nonlinear local model networks are used to obtain dynamic battery models with high fidelity that can be computed in real time. This approach also allows the extraction of local linear impedance models for high-bandwidth impedance emulation, leading to a tighter coupling between the test bed and simulation model with predictable closed-loop dynamics. A model predictive controller that achieves optimal control with adherence to system constraints is extended to impedance control and robustness against constant power loads. This results not only in superior dynamic performance but also in stable dc-bus voltage control even for testing of tightly controlled electric motor inverters with negative differential input resistance. Since the controller design is based on a model of the test bed setup including the virtual battery model, emulator hardware, and input characteristics of the powertrain under test, it is possible to systematically analyze stability.
    IEEE Transactions on Industrial Electronics 02/2014; 61(2):943-955. DOI:10.1109/TIE.2013.2253070 · 6.50 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Local modeling approaches, owing to their ability to model different operating regimes of nonlinear systems and processes by independent local models, seem appealing for modeling, identification, and prediction applications. In this paper, we propose a local neuro-fuzzy (LNF) approach based on the least-squares support vector machines (LSSVMs). The proposed LNF approach employs LSSVMs, which are powerful in modeling and predicting time series, as local models and uses hierarchical binary tree (HBT) learning algorithm for fast and efficient estimation of its parameters. The HBT algorithm heuristically partitions the input space into smaller subdomains by axis-orthogonal splits. In each partitioning, the validity functions automatically form a unity partition and therefore normalization side effects, e.g., reactivation, are prevented. Integration of LSSVMs into the LNF network as local models, along with the HBT learning algorithm, yield a high-performance approach for modeling and prediction of complex nonlinear time series. The proposed approach is applied to modeling and predictions of different nonlinear and chaotic real-world and hand-designed systems and time series. Analysis of the prediction results and comparisons with recent and old studies demonstrate the promising performance of the proposed LNF approach with the HBT learning algorithm for modeling and prediction of nonlinear and chaotic systems and time series.
    IEEE transactions on neural networks and learning systems 02/2013; 24(2):207-218. DOI:10.1109/TNNLS.2012.2227148 · 4.37 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Takagi–Sugeno (TS) fuzzy models are developed for a moving grate biomass furnace for the purpose of simulating and predicting the main process output variables, which are heat output, oxygen concentration of flue gas, and temperature of flue gas. Numerous approaches to modelling biomass furnaces have been proposed in the literature. Usually their objective is to simulate the furnace as accurately as possible. Hence, very complex model architectures are utilized which are not suited for applications like model predictive control. TS fuzzy models are able to approximate the global non-linear behaviour of a moving grate biomass furnace by interpolating between local linear, time-invariant models. The fuzzy partitions of the individual TS fuzzy models are constructed by an axis-orthogonal, incremental partitioning scheme. Validation results with measured process data demonstrate the excellent performance of the developed fuzzy models.
    Mathematical and Computer Modelling of Dynamical Systems 03/2014; 20(2). DOI:10.1080/13873954.2013.821495 · 0.98 Impact Factor