Batch Execution

The simulation and evaluation of a romAI model can be also done via batch in the Compose OML editor without the need to deploy the trained romAI model into a Twin Activate block, using the romAI_execute function.

The function is particularly useful when you want to access the results of a romAI simulation using a script.

Syntax

[x, inputData, outputData] = romAI_execute(dataset_file, romAI_folder)

Inputs

dataset_file
A string specifying the full path of the dataset .CSV or .MAT file containing the inputs on which the model is going to be evaluated.
Type: string
romAI_folder
A string specifying the folder to save the romAI models.
Type: string

Outputs

x
A vector of time or instances depending on whether the model is dynamic or static.
Type: vector
inputData
A matrix of inputs to the romAI model.
Type: matrix
outputData
A matrix of outputs of the romAI model.
Type: matrix

Examples

A practical example on how to call the function is shown below.

%Define dataset full path
dataset_file = fullfile(romAIdirector_dir(),'demos','romAI','linear',...
						'mkclinear','TrainingDataset.csv');
%Define trained romAI model folder
romAI_folder = fullfile(romAIdirector_dir(),'demos','romAI','linear',...
						'mkclinear','mkc_linear');
[x, inputData, outputData] = romAI_execute(dataset_file , romAI_folder);