How to find the optimum parameters from a trained network?

We have done an experiment and fitted the data using NN toolbox. The experiment involves three parameters. The size of input is 3x79 and the size of output is 1x79. Using these data we have created a feedforward backpropogation with 10 neurons(1 hidden layer). As our problem doesnt have an objective function we need this trained network to act as an input function in Genetic Algorithm for optimisation within the specified range.

The experiment(Welding) inputs: Welding speed, heat input, clamping location

Outputs: Residual stress

I want to find the input parameters that give the least residual stress using genetic algorithm. How can I do this?