1 # -*- coding: utf-8 -*-
3 # Copyright (C) 2008-2019 EDF R&D
5 # This library is free software; you can redistribute it and/or
6 # modify it under the terms of the GNU Lesser General Public
7 # License as published by the Free Software Foundation; either
8 # version 2.1 of the License.
10 # This library is distributed in the hope that it will be useful,
11 # but WITHOUT ANY WARRANTY; without even the implied warranty of
12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13 # Lesser General Public License for more details.
15 # You should have received a copy of the GNU Lesser General Public
16 # License along with this library; if not, write to the Free Software
17 # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
19 # See http://www.salome-platform.org/ or email : webmaster.salome@opencascade.com
21 # Author: Jean-Philippe Argaud, jean-philippe.argaud@edf.fr, EDF R&D
24 from daCore import BasicObjects
27 # ==============================================================================
28 class ElementaryAlgorithm(BasicObjects.Algorithm):
30 BasicObjects.Algorithm.__init__(self, "UNSCENTEDKALMANFILTER")
31 self.defineRequiredParameter(
32 name = "ConstrainedBy",
33 default = "EstimateProjection",
35 message = "Prise en compte des contraintes",
36 listval = ["EstimateProjection"],
38 self.defineRequiredParameter(
39 name = "EstimationOf",
42 message = "Estimation d'etat ou de parametres",
43 listval = ["State", "Parameters"],
45 self.defineRequiredParameter(
53 self.defineRequiredParameter(
59 self.defineRequiredParameter(
66 self.defineRequiredParameter(
67 name = "Reconditioner",
74 self.defineRequiredParameter(
75 name = "StoreInternalVariables",
78 message = "Stockage des variables internes ou intermédiaires du calcul",
80 self.defineRequiredParameter(
81 name = "StoreSupplementaryCalculations",
84 message = "Liste de calculs supplémentaires à stocker et/ou effectuer",
86 "APosterioriCorrelations",
87 "APosterioriCovariance",
88 "APosterioriStandardDeviations",
89 "APosterioriVariances",
98 self.defineRequiredParameter( # Pas de type
100 message = "Liste des valeurs de bornes",
102 self.requireInputArguments(
103 mandatory= ("Xb", "Y", "HO", "R", "B" ),
104 optional = ("U", "EM", "CM", "Q"),
107 def run(self, Xb=None, Y=None, U=None, HO=None, EM=None, CM=None, R=None, B=None, Q=None, Parameters=None):
108 self._pre_run(Parameters, Xb, Y, R, B, Q)
110 if self._parameters["EstimationOf"] == "Parameters":
111 self._parameters["StoreInternalVariables"] = True
114 Alpha = self._parameters["Alpha"]
115 Beta = self._parameters["Beta"]
116 if self._parameters["Kappa"] == 0:
117 if self._parameters["EstimationOf"] == "State":
119 elif self._parameters["EstimationOf"] == "Parameters":
122 Kappa = self._parameters["Kappa"]
123 Lambda = float( Alpha**2 ) * ( L + Kappa ) - L
124 Gamma = math.sqrt( L + Lambda )
129 Ww.append( 1. / (2.*(L + Lambda)) )
131 Wm = numpy.array( Ww )
132 Wm[0] = Lambda / (L + Lambda)
133 Wc = numpy.array( Ww )
134 Wc[0] = Lambda / (L + Lambda) + (1. - Alpha**2 + Beta)
138 Hm = HO["Direct"].appliedControledFormTo
140 if self._parameters["EstimationOf"] == "State":
141 Mm = EM["Direct"].appliedControledFormTo
143 if CM is not None and "Tangent" in CM and U is not None:
144 Cm = CM["Tangent"].asMatrix(Xb)
148 # Nombre de pas identique au nombre de pas d'observations
149 # -------------------------------------------------------
150 if hasattr(Y,"stepnumber"):
151 duration = Y.stepnumber()
155 # Précalcul des inversions de B et R
156 # ----------------------------------
157 if self._parameters["StoreInternalVariables"] \
158 or self._toStore("CostFunctionJ") \
159 or self._toStore("CostFunctionJb") \
160 or self._toStore("CostFunctionJo"):
167 if hasattr(B,"asfullmatrix"):
168 Pn = B.asfullmatrix(Xn.size)
172 self.StoredVariables["Analysis"].store( Xn.A1 )
173 if self._toStore("APosterioriCovariance"):
174 self.StoredVariables["APosterioriCovariance"].store( Pn )
177 previousJMinimum = numpy.finfo(float).max
179 for step in range(duration-1):
180 if hasattr(Y,"store"):
181 Ynpu = numpy.asmatrix(numpy.ravel( Y[step+1] )).T
183 Ynpu = numpy.asmatrix(numpy.ravel( Y )).T
186 if hasattr(U,"store") and len(U)>1:
187 Un = numpy.asmatrix(numpy.ravel( U[step] )).T
188 elif hasattr(U,"store") and len(U)==1:
189 Un = numpy.asmatrix(numpy.ravel( U[0] )).T
191 Un = numpy.asmatrix(numpy.ravel( U )).T
195 Pndemi = numpy.linalg.cholesky(Pn)
196 Xnp = numpy.hstack([Xn, Xn+Gamma*Pndemi, Xn-Gamma*Pndemi])
199 if self._parameters["Bounds"] is not None and self._parameters["ConstrainedBy"] == "EstimateProjection":
200 for point in range(nbSpts):
201 Xnp[:,point] = numpy.max(numpy.hstack((Xnp[:,point],numpy.asmatrix(self._parameters["Bounds"])[:,0])),axis=1)
202 Xnp[:,point] = numpy.min(numpy.hstack((Xnp[:,point],numpy.asmatrix(self._parameters["Bounds"])[:,1])),axis=1)
205 for point in range(nbSpts):
206 if self._parameters["EstimationOf"] == "State":
207 XEtnnpi = numpy.asmatrix(numpy.ravel( Mm( (Xnp[:,point], Un) ) )).T
208 if Cm is not None and Un is not None: # Attention : si Cm est aussi dans M, doublon !
209 Cm = Cm.reshape(Xn.size,Un.size) # ADAO & check shape
210 XEtnnpi = XEtnnpi + Cm * Un
211 if self._parameters["Bounds"] is not None and self._parameters["ConstrainedBy"] == "EstimateProjection":
212 XEtnnpi = numpy.max(numpy.hstack((XEtnnpi,numpy.asmatrix(self._parameters["Bounds"])[:,0])),axis=1)
213 XEtnnpi = numpy.min(numpy.hstack((XEtnnpi,numpy.asmatrix(self._parameters["Bounds"])[:,1])),axis=1)
214 elif self._parameters["EstimationOf"] == "Parameters":
215 # --- > Par principe, M = Id, Q = 0
216 XEtnnpi = Xnp[:,point]
217 XEtnnp.append( XEtnnpi )
218 XEtnnp = numpy.hstack( XEtnnp )
220 Xncm = numpy.matrix( XEtnnp.getA()*numpy.array(Wm) ).sum(axis=1)
222 if self._parameters["Bounds"] is not None and self._parameters["ConstrainedBy"] == "EstimateProjection":
223 Xncm = numpy.max(numpy.hstack((Xncm,numpy.asmatrix(self._parameters["Bounds"])[:,0])),axis=1)
224 Xncm = numpy.min(numpy.hstack((Xncm,numpy.asmatrix(self._parameters["Bounds"])[:,1])),axis=1)
226 if self._parameters["EstimationOf"] == "State": Pnm = Q
227 elif self._parameters["EstimationOf"] == "Parameters": Pnm = 0.
228 for point in range(nbSpts):
229 Pnm += Wc[i] * (XEtnnp[:,point]-Xncm) * (XEtnnp[:,point]-Xncm).T
231 if self._parameters["EstimationOf"] == "Parameters" and self._parameters["Bounds"] is not None:
232 Pnmdemi = self._parameters["Reconditioner"] * numpy.linalg.cholesky(Pnm)
234 Pnmdemi = numpy.linalg.cholesky(Pnm)
236 Xnnp = numpy.hstack([Xncm, Xncm+Gamma*Pnmdemi, Xncm-Gamma*Pnmdemi])
238 if self._parameters["Bounds"] is not None and self._parameters["ConstrainedBy"] == "EstimateProjection":
239 for point in range(nbSpts):
240 Xnnp[:,point] = numpy.max(numpy.hstack((Xnnp[:,point],numpy.asmatrix(self._parameters["Bounds"])[:,0])),axis=1)
241 Xnnp[:,point] = numpy.min(numpy.hstack((Xnnp[:,point],numpy.asmatrix(self._parameters["Bounds"])[:,1])),axis=1)
244 for point in range(nbSpts):
245 if self._parameters["EstimationOf"] == "State":
246 Ynnpi = numpy.asmatrix(numpy.ravel( Hm( (Xnnp[:,point], None) ) )).T
247 elif self._parameters["EstimationOf"] == "Parameters":
248 Ynnpi = numpy.asmatrix(numpy.ravel( Hm( (Xnnp[:,point], Un) ) )).T
250 Ynnp = numpy.hstack( Ynnp )
252 Yncm = numpy.matrix( Ynnp.getA()*numpy.array(Wm) ).sum(axis=1)
256 for point in range(nbSpts):
257 Pyyn += Wc[i] * (Ynnp[:,point]-Yncm) * (Ynnp[:,point]-Yncm).T
258 Pxyn += Wc[i] * (Xnnp[:,point]-Xncm) * (Ynnp[:,point]-Yncm).T
261 if self._parameters["EstimationOf"] == "Parameters":
262 if Cm is not None and Un is not None: # Attention : si Cm est aussi dans H, doublon !
267 Pn = Pnm - Kn * Pyyn * Kn.T
269 if self._parameters["Bounds"] is not None and self._parameters["ConstrainedBy"] == "EstimateProjection":
270 Xn = numpy.max(numpy.hstack((Xn,numpy.asmatrix(self._parameters["Bounds"])[:,0])),axis=1)
271 Xn = numpy.min(numpy.hstack((Xn,numpy.asmatrix(self._parameters["Bounds"])[:,1])),axis=1)
273 self.StoredVariables["Analysis"].store( Xn.A1 )
274 if self._toStore("APosterioriCovariance"):
275 self.StoredVariables["APosterioriCovariance"].store( Pn )
276 if self._toStore("Innovation"):
277 self.StoredVariables["Innovation"].store( numpy.ravel( d.A1 ) )
278 if self._parameters["StoreInternalVariables"] \
279 or self._toStore("CurrentState"):
280 self.StoredVariables["CurrentState"].store( Xn )
281 if self._parameters["StoreInternalVariables"] \
282 or self._toStore("CostFunctionJ") \
283 or self._toStore("CostFunctionJb") \
284 or self._toStore("CostFunctionJo"):
285 Jb = 0.5 * (Xn - Xb).T * BI * (Xn - Xb)
286 Jo = 0.5 * d.T * RI * d
287 J = float( Jb ) + float( Jo )
288 self.StoredVariables["CostFunctionJb"].store( Jb )
289 self.StoredVariables["CostFunctionJo"].store( Jo )
290 self.StoredVariables["CostFunctionJ" ].store( J )
291 if J < previousJMinimum:
294 if self._toStore("APosterioriCovariance"):
300 # Stockage supplementaire de l'optimum en estimation de parametres
301 # ----------------------------------------------------------------
302 if self._parameters["EstimationOf"] == "Parameters":
303 self.StoredVariables["Analysis"].store( Xa.A1 )
304 if self._toStore("APosterioriCovariance"):
305 self.StoredVariables["APosterioriCovariance"].store( covarianceXa )
307 if self._toStore("BMA"):
308 self.StoredVariables["BMA"].store( numpy.ravel(Xb) - numpy.ravel(Xa) )
313 # ==============================================================================
314 if __name__ == "__main__":
315 print('\n AUTODIAGNOSTIC \n')