No abstract

No abstract

No abstract

A method for detecting and classifying faults in an aluminum cantilever beam is proposed in this paper. The method uses features based on second-, third-and fourthorder statistics, which are extracted from the vibration signals generated by the cantilever beam. Fisher's discriminant ratio (FDR) is used for feature selection, and an artificial neural network is used for fault detection and classification. Three different degrees of faults (low, medium and high) were applied to the cantilever beam, and the proposed pattern recognition system was able to classify the faults, reaching performances ranging from 88 to 100 %. Moreover, the use of higher-order statistics-based features combined with FDR led to a compact feature space and provided satisfactory results.

Stress concentration and large displacements are usual problems in the components of the structure of agricultural machinery such harvesters coffee, and that finite element method (FEM) can be a tool to minimize its effects. The goal of this paper is to get results of stresses and displacements of a coffee harvester structure by using FEM for static simulation. The main parts of the coffee harvester analyzed were: engine frame, body right and left sides, front and rear end, main beam, coffee reservoir, wheels and fuel tank. Two different design concepts of a coffee harvester machine were analyzed (structure with rear wheels aligned and misaligned) and the results were compared. It was observed that the model with rear wheels misaligned showed maximum displacement lower than the model with rear wheels aligned. Although higher stress was found in the rear wheels misaligned, it was observed that average stresses for the misaligned wheels design were lower in most structural components analyzed. Based on FEM results, the coffee harvester machine with misaligned rear wheels was built and subjected to operational tests without showing any structural failure.