Lakhdar Laouar

Genetic Optimization of Decision Tree Choice for Fault Diagnosis in an Industrial Ventilator

Fault diagnosis and condition monitoring of industrial machines have known significant progress in recent years, particularly with the introduction of pattern recognition and data-mining techniques for their development. The decision trees are among the most suitable techniques for the diagnosis and have several algorithms for their construction. Each building algorithm has its advantages and drawbacks which make the optimal choice of adapted method to the desired application difficult. In this paper we propose the diagnosis accomplishment of an industrial ventilator based on the combination vibration analysis-decision trees. For the choice of the adapted decision tree building algorithm a method based on genetic algorithms was used. Its results were commented and discussed

Decision tree selection in an industrial machine fault diagnostics

Decision trees are widely used technique in data mining and classification fields. This method classifies objects following succession tests on their attributes. Its principal disadvantage is the choice of optimal model among the various existing trees types (Chaid, Cart,Id3..). Each tree has its specificities which make the choice justification difficult. In this work, decision tree choice validation is studied and the use of genetic algorithms is proposed. To pull out best tree, all models are generated and their performances measured on distinct training and validation sets. After that, various statistical tests are made. In this paper we propose the diagnosis accomplishment of an industrial ventilator(Fan) based an analysis-decision trees.

Improvement of surface finish by ball burnishing: approach by fractal dimension

The surface roughness significantly affects the quality of parts and their functional properties such as contact surface, as well as coating adhesion. The machined surface quality is evaluated by arithmetic deviation Ra which does not suffice to describe the surface irregularities. In order to apprehend these deficiencies a new technique based on fractal geometry was introduced. To apply this concept an experimental work was carried out to characterise surface quality by fractal dimension ‘D’. The operations of burnishing ball were performed according to plans of experiments of ‘Box–Behnken’, an optimal regime was obtained and a mathematical model was cleared for predicting the fractal dimension ‘D’ as a function of treatment regime parameters. Furthermore, the application of optimal regime under several passes ‘i’ has enabled to examine the evolution of ‘D’. The results confirm that fractal dimension ‘D’ has impact on surface quality and tribological parameters.

Combining RBF-PCA-ReliefF Filter for a Better Diagnosis Performance in Rotating Machines

Condition monitoring and faults diagnosis in rotating machinery is a current research field. In this direction the use of pattern recognition combined with non-destructive testing techniques such as’ vibration analysis and signal processing can be very helpful. In this paper is proposed, a diagnosis method of rotating machinery using vibration signatures using a Radial Basis Function classifier. Recorded signals were preprocessed with a Wavelet Decomposition and indicators were extracted both in temporal and frequency domains. To improve diagnosis performance, two techniques for dimension reduction of indicators space were combined; Principal Component Analysis and the ReliefF filter. The method was tested on real signatures from a vibration test rig, operating under several conditions, the results showed the interest to look closely at the choice of indicators in order to obtain best diagnosis performances.