2 Copyright (C) 2008-2023 EDF R&D
4 This file is part of SALOME ADAO module.
6 This library is free software; you can redistribute it and/or
7 modify it under the terms of the GNU Lesser General Public
8 License as published by the Free Software Foundation; either
9 version 2.1 of the License, or (at your option) any later version.
11 This library is distributed in the hope that it will be useful,
12 but WITHOUT ANY WARRANTY; without even the implied warranty of
13 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14 Lesser General Public License for more details.
16 You should have received a copy of the GNU Lesser General Public
17 License along with this library; if not, write to the Free Software
18 Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
20 See http://www.salome-platform.org/ or email : webmaster.salome@opencascade.com
22 Author: Jean-Philippe Argaud, jean-philippe.argaud@edf.fr, EDF R&D
24 .. index:: single: UnscentedKalmanFilter
25 .. _section_ref_algorithm_UnscentedKalmanFilter:
27 Calculation algorithm "*UnscentedKalmanFilter*"
28 -----------------------------------------------
30 .. ------------------------------------ ..
31 .. include:: snippets/Header2Algo01.rst
33 This algorithm realizes an estimation of the state of a dynamic system by a
34 "unscented" Kalman Filter, avoiding to have to perform the tangent and adjoint
35 operators for the observation and evolution operators, as in the simple or
36 extended Kalman filter.
38 It applies to non-linear observation and incremental evolution (process)
39 operators with excellent robustness and performance qualities. It can be
40 compared to the :ref:`section_ref_algorithm_EnsembleKalmanFilter`, whose
41 qualities are similar for non-linear systems.
43 We notice that there is no analysis performed at the initial time step
44 (numbered 0 in the time indexing) because there is no forecast at this time
45 (the background is stored as a pseudo analysis at the initial time step). If
46 the observations are provided in series by the user, the first one is therefore
49 In case of linear of "slightly" non-linear operators, one can easily use the
50 :ref:`section_ref_algorithm_ExtendedKalmanFilter` or even the
51 :ref:`section_ref_algorithm_KalmanFilter`, which are often far less expensive
52 to evaluate on small systems. One can verify the linearity of the operators
53 with the help of the :ref:`section_ref_algorithm_LinearityTest`.
59 A difference is made between the "unscented" Kalman filter taking into account
60 bounds on the states (the variant named "2UKF", which is recommended and used
61 by default), and the canonical "unscented" Kalman filter conducted without any
62 constraint (the variant named "UKF", which is not recommended).
64 .. ------------------------------------ ..
65 .. include:: snippets/Header2Algo02.rst
67 .. include:: snippets/Background.rst
69 .. include:: snippets/BackgroundError.rst
71 .. include:: snippets/EvolutionError.rst
73 .. include:: snippets/EvolutionModel.rst
75 .. include:: snippets/Observation.rst
77 .. include:: snippets/ObservationError.rst
79 .. include:: snippets/ObservationOperator.rst
81 .. ------------------------------------ ..
82 .. include:: snippets/Header2Algo03AdOp.rst
84 .. include:: snippets/BoundsWithNone.rst
86 .. include:: snippets/ConstrainedBy.rst
88 .. include:: snippets/EstimationOf_State.rst
90 .. include:: snippets/AlphaBeta.rst
92 StoreSupplementaryCalculations
93 .. index:: single: StoreSupplementaryCalculations
95 *List of names*. This list indicates the names of the supplementary
96 variables, that can be available during or at the end of the algorithm, if
97 they are initially required by the user. Their avalability involves,
98 potentially, costly calculations or memory consumptions. The default is then
99 a void list, none of these variables being calculated and stored by default
100 (excepted the unconditionnal variables). The possible names are in the
101 following list (the detailed description of each named variable is given in
102 the following part of this specific algorithmic documentation, in the
103 sub-section "*Information and variables available at the end of the
106 "APosterioriCorrelations",
107 "APosterioriCovariance",
108 "APosterioriStandardDeviations",
109 "APosterioriVariances",
112 "CostFunctionJAtCurrentOptimum",
114 "CostFunctionJbAtCurrentOptimum",
116 "CostFunctionJoAtCurrentOptimum",
119 "ForecastCovariance",
122 "InnovationAtCurrentAnalysis",
123 "InnovationAtCurrentState",
124 "SimulatedObservationAtCurrentAnalysis",
125 "SimulatedObservationAtCurrentOptimum",
126 "SimulatedObservationAtCurrentState",
130 ``{"StoreSupplementaryCalculations":["CurrentState", "Residu"]}``
132 .. include:: snippets/Variant_UKF.rst
134 .. ------------------------------------ ..
135 .. include:: snippets/Header2Algo04.rst
137 .. include:: snippets/Analysis.rst
139 .. ------------------------------------ ..
140 .. include:: snippets/Header2Algo05.rst
142 .. include:: snippets/Analysis.rst
144 .. include:: snippets/APosterioriCorrelations.rst
146 .. include:: snippets/APosterioriCovariance.rst
148 .. include:: snippets/APosterioriStandardDeviations.rst
150 .. include:: snippets/APosterioriVariances.rst
152 .. include:: snippets/BMA.rst
154 .. include:: snippets/CostFunctionJ.rst
156 .. include:: snippets/CostFunctionJAtCurrentOptimum.rst
158 .. include:: snippets/CostFunctionJb.rst
160 .. include:: snippets/CostFunctionJbAtCurrentOptimum.rst
162 .. include:: snippets/CostFunctionJo.rst
164 .. include:: snippets/CostFunctionJoAtCurrentOptimum.rst
166 .. include:: snippets/CurrentOptimum.rst
168 .. include:: snippets/CurrentState.rst
170 .. include:: snippets/ForecastCovariance.rst
172 .. include:: snippets/ForecastState.rst
174 .. include:: snippets/IndexOfOptimum.rst
176 .. include:: snippets/InnovationAtCurrentAnalysis.rst
178 .. include:: snippets/InnovationAtCurrentState.rst
180 .. include:: snippets/SimulatedObservationAtCurrentAnalysis.rst
182 .. include:: snippets/SimulatedObservationAtCurrentOptimum.rst
184 .. include:: snippets/SimulatedObservationAtCurrentState.rst
186 .. ------------------------------------ ..
187 .. _section_ref_algorithm_UnscentedKalmanFilter_examples:
188 .. include:: snippets/Header2Algo06.rst
190 - :ref:`section_ref_algorithm_KalmanFilter`
191 - :ref:`section_ref_algorithm_ExtendedKalmanFilter`
192 - :ref:`section_ref_algorithm_EnsembleKalmanFilter`
194 .. ------------------------------------ ..
195 .. include:: snippets/Header2Algo07.rst