To check the working of NARX neural network for time series prediction

Hi all, i am using NARX neural network to train my model. for the training of neural network, my data train is 31*468 double , data test is 31*168 and target train is 1*468 whereas target test is 1*168 But i am encountering the error as "

>> [inputStates,Xi,Ai,targetStates] = preparets(net,data_train,{},target_train)

Index in position 2 exceeds array bounds (must not exceed 1).

Error in preparets (line 293)

xi = xx(:,FBS+((1-net.numInputDelays):0));

My NARX net configuration is :

trainFcn = 'trainlm';

inputDelays = 1:2;

feedbackDelays = 1:2;

hiddenLayerSize = 10;

net.performFcn = 'mse';

net = narxnet(inputDelays,feedbackDelays,hiddenLayerSize,'open',trainFcn);

[inputStates,Xi,Ai,targetStates] = preparets(net,data_train,{},target_train)

net = train(net,Xs,Ts,Xi,Ai);

view(net)

net.divideFcn = 'divideblock'; % Divide data in blocks

net.divideMode = 'time'; % Divide up every value

net.trainFcn = 'trainlm'; % Levenberg-Marquardt

[net,tr] = train(net,data_train,target_train,inputStates,layerStates)