A soft computing system used to optimize deep drilling operations under high-speed conditions in the manufacture of steel components is presented. The input data includes cutting parameters and axial cutting force obtained from the power consumption of the feed motor of the milling centres. Two different coolant strategies are tested: traditional working fluid and Minimum Quantity Lubrication (MQL). The model is constructed in three phases. First, a new strategy is proposed to evaluate and complete the set of available measurements. The primary objective of this phase is to decide whether further drilling experiments are required to develop an accurate roughness prediction model. An important aspect of the proposed strategy is the imputation of missing data, which is used to fully exploit both complete and incomplete measurements. The proposed imputation algorithm is based on a genetic algorithm and aims to improve prediction accuracy. In the second phase, a bag of multilayer perceptrons is used to model the impact of deep drilling settings on borehole roughness. Finally, this model is supplied with the borehole dimensions, coolant option and expected axial force to develop a 3D surface showing the expected borehole roughness as a function of drilling process settings. This plot is the necessary output of the model for its use under real workshop conditions. The proposed system is capable of approximating the optimal model used to control deep drilling tasks on steel components for industrial use.
As a response to the increasing number of cyber threats, novel detection and prevention methods are constantly being developed. One of the main obstacles hindering the development and evaluation of such methods is the shortage of reference data sets. What is proposed in this work is a way of testing methods detecting network threats. It includes a procedure for creating realistic reference data sets describing network threats and the processing and use of these data sets in testing environments. The proposed approach is illustrated and validated on the basis of the problem of spam detection. Reference data sets for spam detection are developed, analysed and used to both generate the requested volume of simulated traffic and analyse it using machine learning algorithms. The tests take into account both the accuracy and performance of threat detection methods under real load and constrained computing resources.