Overview
Comment:Trying to fix parameter identification problem ...
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | origin/master | trunk
Files: files | file ages | folders
SHA3-256: 93079fee467bc64a07a6821d4a3898637e7d8d5c00fb16c50f5d3ba2da451295
User & Date: gawthrop@users.sourceforge.net on 2002-05-07 16:28:26
Other Links: branch diff | manifest | tags
Context
2002-05-07
23:50:34
Preliminary support for Matlab dynamically linked shared objects:
invoke with: mtt -cc sys rep mexglx
ode2odes support is not yet included.
check-in: 2a56bcb441 user: geraint@users.sourceforge.net tags: origin/master, trunk
16:28:26
Trying to fix parameter identification problem ... check-in: 93079fee46 user: gawthrop@users.sourceforge.net tags: origin/master, trunk
13:48:43
Improved clarity of code generated for -cc and -oct (except ode2odes).
Octave DEFUN_DLDs now call (rather than replace) their .cc equivalents.
check-in: 06c3b3d188 user: geraint@users.sourceforge.net tags: origin/master, trunk
Changes

Modified mttroot/mtt/lib/control/PPP/ppp_nlin_run.m from [313a218248] to [3008238ce6].

31
32
33
34
35
36
37
38
39
40
41
42
43



44
45
46
47
48
49
50
  global system_name_sim i_ppp_sim x_0_sim y_sim u_sim A_u_sim simpar_sim

  ## Defaults
  if nargin<7
    extras.alpha = 0.1;
    extras.criterion = 1e-5;
    extras.emulate_timing = 0;
    extras.estimate = 1;
    extras.max_iterations = 10;
    extras.simulate = 1;
    extras.v = 1e-5;
    extras.verbose = 0;
  endif



  
  ## Names
  s_system_name = sprintf("s%s", system_name);

  ## System details -- defines simulation within ol interval
  par = eval(sprintf("%s_numpar;", system_name));
  simpar = eval(sprintf("%s_simpar;", system_name));







<





>
>
>







31
32
33
34
35
36
37

38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
  global system_name_sim i_ppp_sim x_0_sim y_sim u_sim A_u_sim simpar_sim

  ## Defaults
  if nargin<7
    extras.alpha = 0.1;
    extras.criterion = 1e-5;
    extras.emulate_timing = 0;

    extras.max_iterations = 10;
    extras.simulate = 1;
    extras.v = 1e-5;
    extras.verbose = 0;
  endif

  ##Estimate if we have some adjustable parameters
  estimating_parameters = (length(i_par)>0)
  
  ## Names
  s_system_name = sprintf("s%s", system_name);

  ## System details -- defines simulation within ol interval
  par = eval(sprintf("%s_numpar;", system_name));
  simpar = eval(sprintf("%s_simpar;", system_name));
58
59
60
61
62
63
64

65
66
67
68
69
70
71
  x_0_model = x_0;
  [n_x,n_y,n_u] = eval(sprintf("%s_def;", system_name));

  ## Sensitivity system details -- defines moving horizon simulation
  simpars = eval(sprintf("%s_simpar;", s_system_name));
  pars = eval(sprintf("%s_numpar;", s_system_name));
  x_0s = eval(sprintf("%s_state(pars);", s_system_name));


  ## Times
  ## -- within opt horizon
  n_Tau = round(simpars.last/simpars.dt);
  dtau = simpars.dt;
  Tau = [0:n_Tau-1]'*dtau;
  [n_tau,n_w] = size(w_s);







>







60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
  x_0_model = x_0;
  [n_x,n_y,n_u] = eval(sprintf("%s_def;", system_name));

  ## Sensitivity system details -- defines moving horizon simulation
  simpars = eval(sprintf("%s_simpar;", s_system_name));
  pars = eval(sprintf("%s_numpar;", s_system_name));
  x_0s = eval(sprintf("%s_state(pars);", s_system_name));
  x_0_models = x_0s;

  ## Times
  ## -- within opt horizon
  n_Tau = round(simpars.last/simpars.dt);
  dtau = simpars.dt;
  Tau = [0:n_Tau-1]'*dtau;
  [n_tau,n_w] = size(w_s);
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161

162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179

180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
      T_ol = n_ol*dt;		# Length of ol interval
      t_open = [t_open;T_ol];

      ## Generate input to actual system
      u_star_t = ppp_ustar(A_u,1,t_ol',0,0,n_u-n_U);

      ## Tune parameters/states
      if (extras.estimate==1)
	## Save up the estimated parameters
	par_est = pars(i_par(:,1));
	p = [p; par_est'];

	## Set up according to interval length
	if (T_ol>T_ol_0) ## Truncate data
	  simpar_est.last = T_ol_0;
	  y_est = y_ol(1:n_t+1,:);
	else
	  simpar_est.last = T_ol;
	  y_est = y_ol;
	endif

	simpar_pred.last = T_ol_0; # Predicted length of next interval
	pars(i_ppp(:,1)) = U_old; # Update the simulation ppp weights
	
	## Optimise
	tick = time;
	[pars,Par,Error,Y,its] = \
	    ppp_optimise(s_system_name,x_0s,pars,simpar_est,u_star_t,y_est,i_par,extras);

	est_time = time-tick;  
	t_est = [t_est;est_time];
	its_est = [its_est; its-1];
      endif

      ## Update internal model
      par(i_ppp(:,3)) = U_old; # Update the simulation ppp weights

      if (extras.estimate==1)
	par(i_par(:,3)) = pars(i_par(:,1)); # Update the simulation params
      endif
      
      simpar_model.last = T_ol;
      [y_model,x_model] = eval(sprintf("%s_sim(x_0_model, par, simpar_model, \
 					       u_star_t);",system_name));

      x_0 = x_model(n_ol+1,:)';	# Initial state of next interval
      x_0_model = x_0;


      ## Compute U by optimisation
      tick = time;

      ## Predict state at start of next interval
      par(i_ppp(:,3)) = U;
      [y_next,x_next] = eval(sprintf("%s_sim(x_0, par, simpar, \
					     u_star_t);",system_name));
      x_next = x_next(n_t+1,:)'; # Initial state for next time
      x_nexts(1:2:(2*n_x)-1) = x_next;
      
      ## Optimize for next interval      
      U_old = U;		# Save previous value
      U = expm(A_u*T_ol)*U;	# Initialise from continuation trajectory
      pars(i_ppp(:,1)) = U;	# Put initial value of U into the parameter vector
      [U, U_all, Error, Y, its] = ppp_nlin(system_name,x_nexts,pars,simpars,u_star_tau,w_s,i_ppp,extras);








|

|

















|
>






|

|
|

|






>









|







137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
      T_ol = n_ol*dt;		# Length of ol interval
      t_open = [t_open;T_ol];

      ## Generate input to actual system
      u_star_t = ppp_ustar(A_u,1,t_ol',0,0,n_u-n_U);

      ## Tune parameters/states
      if (estimating_parameters==1)
	## Save up the estimated parameters
	par_est = pars(i_par(:,1))
	p = [p; par_est'];

	## Set up according to interval length
	if (T_ol>T_ol_0) ## Truncate data
	  simpar_est.last = T_ol_0;
	  y_est = y_ol(1:n_t+1,:);
	else
	  simpar_est.last = T_ol;
	  y_est = y_ol;
	endif

	simpar_pred.last = T_ol_0; # Predicted length of next interval
	pars(i_ppp(:,1)) = U_old; # Update the simulation ppp weights
	
	## Optimise
	tick = time;
	[pars,Par,Error,Y,its] = \
	    ppp_optimise(s_system_name,x_0_models,pars,simpar_est,u_star_t,y_est,i_par,extras);
II = [1:length(y_est)]; plot(II,y_est,"*", II,Y)
	est_time = time-tick;  
	t_est = [t_est;est_time];
	its_est = [its_est; its-1];
      endif

      ## Update internal model
      par(i_ppp(:,3)) = U_old; # Update the internal model ppp weights

      if (estimating_parameters==1)
	par(i_par(:,3)) = pars(i_par(:,1)); # Update the internal model params
      endif

      simpar_model.last = T_ol;
      [y_model,x_model] = eval(sprintf("%s_sim(x_0_model, par, simpar_model, \
 					       u_star_t);",system_name));

      x_0 = x_model(n_ol+1,:)';	# Initial state of next interval
      x_0_model = x_0;
      x_0_models(1:2:(2*n_x)-1) = x_0_model;

      ## Compute U by optimisation
      tick = time;

      ## Predict state at start of next interval
      par(i_ppp(:,3)) = U;
      [y_next,x_next] = eval(sprintf("%s_sim(x_0, par, simpar, \
					     u_star_t);",system_name));
      x_next = x_next(n_t+1,:)'; # Initial state for next time
      x_nexts(1:2:(2*n_x)-1) = x_next; # And for internal sensitivity model
      
      ## Optimize for next interval      
      U_old = U;		# Save previous value
      U = expm(A_u*T_ol)*U;	# Initialise from continuation trajectory
      pars(i_ppp(:,1)) = U;	# Put initial value of U into the parameter vector
      [U, U_all, Error, Y, its] = ppp_nlin(system_name,x_nexts,pars,simpars,u_star_tau,w_s,i_ppp,extras);


MTT: Model Transformation Tools
GitHub | SourceHut | Sourceforge | Fossil RSS ]