Active adaptation of a distributed multi-sensor filtering system

I. V. Semushin ; J. V. Tsyganova

Journal of Samara State Technical University, Ser. Physical and Mathematical Sciences, Tome 23 (2019) no. 4, pp. 724-743.

Résumé

A multi-sensor filtering system is characterized mathematically as a result of the solution to the problem of synthesizing the multi-dimensional discrete system of filtering a single signal from heterogeneous data sources. The stationary problem statement has three variants of its solution: by Kolmogorov–Wiener, Kalman covariance, and Kalman information forms. In the body of the paper, we actualize a problem of these solutions under uncertainty conditions. Aimed at the Active Principle of Adaptation, we have found a method to form an instrumental performance index to substitute the inaccessible original performance index (filtering error mean square) by that criterion functional we created. This substitution makes it possible to apply for system adaptation all apparatus and tools of practical optimization methods, first of all, the gradient and Newton-like methods. Our findings follow: – Stretching one-step prediction and measurement update operations are wise to perform at the Decision Making Center; computation operations aimed to minimize the instrumental performance index are to be done in this place, too. – Uncompounded procedures of adaptive data scaling are advisable to complete at the sensors' location in the network. – Adaptation algorithms may be implemented based for filter structures taken in different forms: Kolmogorov–Wiener, Kalman covariance, or Kalman information forms. – Computational operations for minimizing the instrumental performance index would be beneficial to develop as versions to implement the modern practical optimization methods of different levels of complexity.

Détail

Mots-clés : active adaptation
Keywords: multi-sensor system, distributed Kalman filtering, instrumental optimization performance criterion.

Bibliographie

[1] Katkovnik V. Ya., Poluektov R. A., Mnogomernye diskretnye sistemy upravleniia [Multidimensional Discrete Control Systems], Nauka, Moscow, 1966, 416 pp. (In Russian)

[2] Balakrishnan A., Kalman filtering theory, Optimization Software, Inc., Publications Division, New York, 1984, xii+222 pp. | Zbl

[3] Maybeck P. S., Stochastic Models, Estimation, and Control, v. 1, Mathematics in Science and Engineering, 141, Academic Press, Inc, New York, 1979, xix+423 pp. | Zbl

[4] Fomin V. N., Rekurrentnoe otsenivanie i adaptivnaia fil'tratsiia [Recurrent Estimation and Adaptive Filtering], Nauka, Moscow, 1984, 288 pp. (In Russian)

[5] Speyer J., “Computation and transmission requirements for a decentralized linear-quadratic-Gaussian control problem”, IEEE Trans. Automatic Control, 24:2 (1979), 266–269 | DOI | Zbl

[6] Rao B. S., Durrant-Whyte H. F., “Fully decentralised algorithm for multisensor Kalman filtering”, IEE Proc.–Control Theory Appl., 138:5 (1991), 413–420 | DOI

[7] Olfati-Saber R., “Distributed Kalman filtering and sensor fusion in sensor networks”, Networked Embedded Sensing and Control, Lecture Notes in Control and Information Science, 331, eds. P. J. Antsaklis, P. Tabuada, Springer, Berlin, Heidelberg, 2006, 157–167 | DOI | Zbl

[8] Alriksson P., Rantzer A., “Model based information fusion in sensor networks”, IFAC Proceedings Volumes, 41:2 (2008), 4150–4155 | DOI

[9] Rao B. S. Y., Durrant-Whyte H. F., Sheen J. A., “A fully decentralized multi-sensor system for tracking and surveillance”, Int. J. Robot. Res., 12:1 (1993), 20–44 | DOI

[10] Mahmoud M. S., Khalid H. M., “Distributed Kalman filtering: a bibliographic review”, IET Control Theory and Applications, 7:4 (2013), 483–501 | DOI

[11] Marelli D., Zamani M., Fu M., Ninness B., “Distributed Kalman filter in a network of linear systems”, Systems Control Letters, 116:6 (2018), 71–77 | DOI | Zbl

[12] Wu Z., Fu M., Xu Yo., Lu R., “A distributed Kalman filtering algorithm with fast finite-time convergence for sensor networks”, Automatica, 95:9 (2018), 63–72 | DOI | Zbl

[13] Dormann K., Noack B., Hanebeck U. D., “Optimally distributed Kalman filtering with data-driven communication”, Sensors, 18:4 (2018), 1034 | DOI

[14] Badyn M. H., Mesbahi M., “Large-scale distributed Kalman filtering via an optimization approach”, IFAC PapersOnLine, 50:1 (2017), 10742–10747 | DOI

[15] Govaers F., “Distributed Kalman filter (Chapter 13)”, Kalman Filters – Theory for Advanced Applications, eds. Ginalber Luiz de Oliveira Serra, IntechOpen, London, 2018, 253–272 | DOI

[16] Semushin I. V., “The APA based time-variant system identification”, 53rd IEEE Conference on Decision and Control (15–17 December 2014, Los Angeles, CA, USA), 2014, 4137–4141 | DOI

[17] Fletcher R., Practical Methods of Optimization, John Wiley Sons Ltd, Chichester, Great Britain, xiv+436 pp. | DOI

[18] Semushin I. V., “Adaptation in stochastic dynamic systems — Survey and new results II”, Int. J. Communications, Network, and System Sciences, 4:4 (2011), 266–285 | DOI

[19] Tsyganova Yu. V., Othogonalized array methods for parametric identification of linear stochastic systems, Doct. Phys.-Math. Sci. Thesis: 05.13.18, Ulyanovsk State University, Ulyanovsk, 2017, 400 pp. (In Russian)