Overview
Comment: | No longer delay the simulated data. |
---|---|
Downloads: | Tarball | ZIP archive | SQL archive |
Timelines: | family | ancestors | descendants | both | origin/master | trunk |
Files: | files | file ages | folders |
SHA3-256: |
ecd25de36843cddb1ff95832bf5bab8f |
User & Date: | gawthrop@users.sourceforge.net on 2002-06-11 11:25:25 |
Other Links: | branch diff | manifest | tags |
Context
2002-06-17
| ||
08:50:00 | Changed pattern to prevent 'max(' from being translated to 'mamttx('. check-in: 623234b6c9 user: geraint@users.sourceforge.net tags: origin/master, trunk | |
2002-06-11
| ||
11:25:25 | No longer delay the simulated data. check-in: ecd25de368 user: gawthrop@users.sourceforge.net tags: origin/master, trunk | |
2002-06-10
| ||
23:22:16 | Fixed problem with Matlab fsolve failing because of "user function returned Inf or Nan" (fsolve.m, line 245). check-in: 718f8cde73 user: geraint@users.sourceforge.net tags: origin/master, trunk | |
Changes
Modified mttroot/mtt/lib/control/PPP/ppp_optimise.m from [d6b999b722] to [d54b2723b3].
︙ | ︙ | |||
25 26 27 28 29 30 31 32 33 34 35 36 37 38 | ###################################### ############################################################### ## Version control history ############################################################### ## $Id$ ## $Log$ ## Revision 1.10 2002/05/13 16:01:09 gawthrop ## Addes Q weighting matrix ## ## Revision 1.9 2002/05/08 10:14:21 gawthrop ## Idetification now OK (Moved data range in ppp_optimise by one sample interval) ## ## Revision 1.8 2002/04/23 17:50:39 gawthrop | > > > | 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 | ###################################### ############################################################### ## Version control history ############################################################### ## $Id$ ## $Log$ ## Revision 1.11 2002/05/20 13:32:36 gawthrop ## Sanity check on y_0 ## ## Revision 1.10 2002/05/13 16:01:09 gawthrop ## Addes Q weighting matrix ## ## Revision 1.9 2002/05/08 10:14:21 gawthrop ## Idetification now OK (Moved data range in ppp_optimise by one sample interval) ## ## Revision 1.8 2002/04/23 17:50:39 gawthrop |
︙ | ︙ | |||
116 117 118 119 120 121 122 | printf("\n"); endif while (abs(reduction)>extras.criterion)&&\ (abs(err)>extras.criterion)&&\ (iterations<extras.max_iterations) | | | > > | | | < < | | > > > > > > | 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 | printf("\n"); endif while (abs(reduction)>extras.criterion)&&\ (abs(err)>extras.criterion)&&\ (iterations<extras.max_iterations) iterations = iterations + 1 # Increment iteration counter [y,y_par,x] = eval(sim_command); # Simulate [N_data,N_y] = size(y) if (N_y!=n_y) mess = sprintf("n_y (%i) in data not same as n_y (%i) in model", n_y,N_y); error(mess); endif ## Use the last part of the simulation to compare with data ## ### Removed #### And shift back by one data point # if ( (N_data-n_data)<1 ) # error(sprintf("y_0 (%i) must be shorter than y (%i)", n_data, N_data)); # endif y = y(N_data-n_data+1:N_data,:); y_par = y_par(N_data-n_data+1:N_data,:); if extras.visual==1 ## Plot title("Optimisation data"); plot([y y_0]) endif ##Evaluate error, cost derivative J and cost second derivative JJ err = 0; J = zeros(n_th,1); JJ = zeros(n_th,n_th); for i = 1:n_y E = y(:,i) - y_0(:,i); # Error in ith output |
︙ | ︙ |