Model development ( methodology)

Phase 1: Data collection: case study

Phase 2: Data pre-processing

Input selection

Normalisation : To cope with different magnitudes in the input and output data, all the data
were scaled to zero mean and unit standard deviation.

Phase 3: Data Division

The data for neural network model building need to be divided into: 1). Training data (for
network training); 2). Testing data (for cross-validation based network structure selection and
early stopping); and 3). Unseen validation data (for evaluation of the final selected model).

Phase 3:Model development

ANN

For ANN model predictions, the process output at time (t), y(t), is used as a model input to
predict the process output at time t, y(t), as follows:

Y(t) = f [ u1(t), u2(t) u3(t),….un(t)]

where u(t) is the process input at time (t), ^y (t ) is the predicted process output at time t, n are
the number of the process input. Y can more that 1 output ( MIMO) for MISO y is only 1.
Check ARX and NARX model ANN model development using time series.

The number of hidden neurons, were determined through cross validation. Single hidden
layer neural networks with different numbers of hidden neurons were trained on the training
data and tested on the testing data. The network with the lowest sum of squared errors (SSE)
on the testing data was considered as having the best network topology.

Phase 4: Model validation

In assessing the developed models, SSE on the unseen validation data is used as the
performance criterion. For dynamic system modelling, multi-step-ahead or long range
predictions should be looked at. In many advanced process control applications, such as
optimal control of batch processes, accurate long range predictions are required.

Figure 3.1 Long range prediction with feedback after the combination of individual networks