Piotr Wolszczak

MONITORING OF CUTTING CONDITIONS WITH THE EMPIRICAL MODE DECOMPOSITION

In this paper, we apply empirical mode decomposition by Huang and Hilbert to transform signals recorded during a milling process. Vibroacoustic sensors recorded vibrations of a tool-workpiece system while milling with the end mill of a special shape of “Hi-Feed”. The results of Huang-Hilbert analysis provide the information about amplitudes and frequencies of empirical modal components. Application of HuangHilbert transform to cutting conditions monitoring allows the separation of various vibration components caused by phenomena associated with the drive system and the machine components. Therefore, the analysis highlights vibrations caused by known sources of vibration, such as spindle speed, the number of teeth of the cutting tool or the frequency of vibration tools. Furthermore, signal components generated in the cutting zone were identified. The resulting information helps to assess the working conditions of cutting tools, selection of cutting parameters and tool wear monitoring.

Appling of Neural Networks to Classification of Brain-Computer Interface Data

The paper presents application of neural networks to the construction of a brain-computer interface (BCI) based on the Motor Imagery paradigm. The BCI was constructed for ten electroencephalographic (EEG) signals collected and analysed in real time.The filtered signals were divided into three groups corresponding to the information displayed to users on the screen during the experiments. ANOVA analysis and automatic construction of a neural network (NN) classification were also performed. Results of the ANOVA analysis were confirmed by the neural networks efficiency analysis. The efficiency of NN classification of the left and right hemisphere activities reached almost 70 %.

On Parameterization of the Reinforcement Phase Distribution in Continuous Fiber-Reinforced Composites

This chapter discusses a problem of parameterization of irregular reinforcement distribution in uniaxial fiber-reinforced composites (CFRC) expressed as an area ratio of the matrix surrounding a single fiber to its perimeter. The distribution parameter, GAB, was applied in the analysis of possible relationships between the microgeometry and mechanical properties of glass-epoxy composites with random distribution of continuous fibers. Test specimens were made in a repeatable process production of the girders of helicopter blades and were tested in bending during the short beam shear tests (SBST), as well as their basic mechanical properties (e.g., the flexural modulus Ef, taking into account shear effects) were determined. The relationship between the SBST results and the theoretical topology of regular CFRC structures was presented: the square (K) and the hexagonal (H) type. The K theoretical model of fiber distribution corresponded with experimental results. It was concluded that the measure of irregular reinforcement distribution (GAB) could be used to estimate the flexural elastic modulus Ef of unidirectional CFRC composites.

Construction of neural nets in brain-computer interface for robot arm steering

The paper presents an attempt to construct a direct brain-to-machine interface (BCI) that could be used to control movements of a robotic arm. A series of experiments was performed to collect data from subjects, train and validate an effective neural network and search for a generalized solution. The ERD/ERS imagery paradigm was chosen to extract valid data from the EEG signal. Since categorizing between two opposite states (like Left-Right) proved to be the most reliable, a control structure containing multiple neural networks was proposed. New research concerns the method of development and the use of neural networks classifiers. An automated procedure was used to select the best bipolar classifiers from the set of machine-generated neural networks. The chosen classifiers were used in a hierarchical structure responsible for signal interpretation. Adoption of this method was motivated mainly by the complexity of arm movement. The movement consisted of several phases, such as the initiation, continuation, change of direction, change of speed. It was observed that simple bipolar classifiers produced better output than classifiers designed to recognize complex decisions.

Kinematic Design of Parallel Delta System in Matlab

The paper presents the problem of modelling the parallel kinematic delta system using specialized software Simmechanics constituting the extension of the Matlab environment. Parameterized model of the parallel delta robot was developed and kinematic analysis was performed. The results of the model was used to correction of design and real construction. Designed robot is intended to direct a tool according to the program recorded by machine commands (G-code).