Identification of the Optimal Conditions of a Pneumatic Drill

This paper presents a multidisciplinary study that identifies and applies unsupervised connectionist models in conjunction with modelling systems, in order to determine optimal conditions to perform automated drilling tasks. This industrial problem is defined by a data set relayed through sensors situated on a robotic drill that is used to build industrial warehouses. The results of the study and the application of the connectionist architectures allow the identification, in a second phase, of a model for a drilling robot based on low-order models such as Black Box, which are capable of approximating the optimal form of the model. Finally, it is shown that the most appropriate model to control these industrial tasks is the Box-Jenkins algorithm, which calculates the function of a linear system from its input and output samples.