how to create NARX nn from my data

load('date.txt')    %date from inverted pendulum (first column - input, 2 and 3 - output)
inputDATE=date(:,1);       %input
outputDATE=date(:,[2,3]);   %output

%%from generete Simple Script:

% Solve an Autoregression Problem with External Input with a NARX Neural Network
% Script generated by NTSTOOL
% Created Wed Oct 02 22:26:03 CEST 2013
%
% This script assumes these variables are defined:
%
%   inputDATE - input time series.
%   outputDATE - feedback time series.

inputSeries = tonndata(inputDATE,false,false);
targetSeries = tonndata(outputDATE,false,false);

% Create a Nonlinear Autoregressive Network with External Input
inputDelays = 1:2;
feedbackDelays = 1:2;
hiddenLayerSize = 10;
net = narxnet(inputDelays,feedbackDelays,hiddenLayerSize);

% Prepare the Data for Training and Simulation
% The function PREPARETS prepares timeseries data for a particular network,
% shifting time by the minimum amount to fill input states and layer states.
% Using PREPARETS allows you to keep your original time series data unchanged, while
% easily customizing it for networks with differing numbers of delays, with
% open loop or closed loop feedback modes.
[inputs,inputStates,layerStates,targets] = preparets(net,inputSeries,{},targetSeries);

% Setup Division of Data for Training, Validation, Testing
net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 15/100;
net.divideParam.testRatio = 15/100;

% Train the Network
[net,tr] = train(net,inputs,targets,inputStates,layerStates);

% Test the Network
outputs = net(inputs,inputStates,layerStates);
errors = gsubtract(targets,outputs);
performance = perform(net,targets,outputs)

% View the Network
view(net)

% Plots
% Uncomment these lines to enable various plots.
%figure, plotperform(tr)
%figure, plottrainstate(tr)
%figure, plotregression(targets,outputs)
%figure, plotresponse(targets,outputs)
%figure, ploterrcorr(errors)
%figure, plotinerrcorr(inputs,errors)

% Closed Loop Network
% Use this network to do multi-step prediction.
% The function CLOSELOOP replaces the feedback input with a direct
% connection from the outout layer.
netc = closeloop(net);
netc.name = [net.name ' - Closed Loop'];
view(netc)
[xc,xic,aic,tc] = preparets(netc,inputSeries,{},targetSeries);
yc = netc(xc,xic,aic);
closedLoopPerformance = perform(netc,tc,yc)

% Early Prediction Network
% For some applications it helps to get the prediction a timestep early.
% The original network returns predicted y(t+1) at the same time it is given y(t+1).
% For some applications such as decision making, it would help to have predicted
% y(t+1) once y(t) is available, but before the actual y(t+1) occurs.
% The network can be made to return its output a timestep early by removing one delay
% so that its minimal tap delay is now 0 instead of 1.  The new network returns the
% same outputs as the original network, but outputs are shifted left one timestep.
nets = removedelay(net);
nets.name = [net.name ' - Predict One Step Ahead'];
view(nets)
[xs,xis,ais,ts] = preparets(nets,inputSeries,{},targetSeries);
ys = nets(xs,xis,ais);
earlyPredictPerformance = perform(nets,ts,ys)

%%create closeloop system in simulink:
[sysNameC,netNameC] = gensim(netc,'SampleTime',0.001,'InputMode','Workspace');
setsiminit(sysNameC,netNameC,netc,xic,aic,1);
x1 = nndata2sim(inputSeries,1,1);
x1.time=x1.time/1000; %original sample time was 0.001s

Results:

performance =   2.4806e-08 
closedLoopPerformance =    8.3127        !!! <- why?
earlyPredictPerformance =   2.4806e-08

I can't create nn closeloop in simulink who can model my input to output. What can I do to do this?

EDIT: I created a new data (as in the previous post: 1 column: input to the system, 2 and 3 - output) shorter and better. But it is * impossible * to create a neural network in simulink with a (closed feedback) edit: OPEN loop, which would operate in the same way as the original ... Why? How to do it?

Answer 1

[Greg Heath]

If you plot the data, you will see three distinct regions with different statistics.

 ind1 ~ 1:10000;
 ind2 ~ 10001:20000;
 ind3 ~ 20001:35001;

Region 2 displays the response to a huge doublet like input.

I would investigate the auto and cross-correlation functions in the three separate regions before going any further.

There is so much data that it is not necessary to use most of it to characterize the I/O relationships.

Hope this helps.

Thank you for formally accepting my answer

Greg