Wear Particle Classifier System Based on an Artificial Neural Network

This paper describes a method of identifying morphological attributes that classify wear particles in relation to the wear process from which they originate and permit the automatic identification without human expertise. The method is based on the use of Multi Layer Perceptron (MLP) for analysis of specific types of microscopic wear particles. The classification of the wear particles was performed according to their morphological attributes of size and aspect ratio, among others. (C) 2010 Journal of Mechanical Engineering. All rights reserved.

A mechatronic system applied to wear particle analysis

This paper describes the development of a mechatronic system for a predictive maintenance grounded on wear particle analysis. The reckoning of wear particles containing in lubricating industrial oils brings the image acquisition system into being. The ISO 4406:1999 standard is a guide to establish the counting and evaluation processes of particles. The system applied to the acquisition and analysis of the data consists of a digital camera, a monocular microscope and an oil filtering system. A computational program was developed with the application of Visual Microsoft C++ in a way to detain the oil sample image from the microscope slide to the computer screen. Quantitative analyses of the wear debris particles bulk are exploited applying a graphical interface that was developed to render the image processing of the sample test. The implemented system has a reachable cost thus it can be applied for schooling goals and for bolstering laboratories of minor industries and medium size companies.

Manutenção de redutores de velocidade pela integração das técnicas preditivas de análise de vibrações e análise de óleo lubrificante

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Redes neurais artificiais aplicadas à manutenção baseada na condição

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Lixamento do Pinus elliotti com carbeto de silício e óxido de aluminio

The Sanding is a complex process involving many variables that affect the quality of the part produced, working mainly in the timber industry in the production of panels (MDF, MDP, HDF, etc...) and furniture. However, these industries use the sanding process empirically, not optimizing it. The aim of this study was to compare the behavior of sandpaper white aluminum oxide (OA-white) and Black silicon carbide (SiC-black), analyzing variables in the process as: strength, power, emission, vibration, wear particle size of sanding, and its consequences on the surface finish of the workpiece. Made the process of plane grinding samples of Pinus elliottii, processed in parallel to the fibers, which were sanded with sandpaper grain OA white and black 3-SiC abrasive conditions (new, moderately eroded and severely eroded) grain sizes in 3 (80, 100, and 120 mesh). 6 replicates was performed for each condition tested. Each trial was captured output variables of the sanding process: strength, power, emission and vibration. With two stages totaling 108 trials. After the sanded samples, it has the same surface quality by raising the surface roughness Ra. Through experiment, it can be concluded that abrasives OA-white tended to have higher strength, power, emissions and less vibration in the sanding process, compared to the SiC-black. However, surface finish exhibited similar to the particle size of 80 to 100 mesh, worn abrasive conditions. However, the particle size of 120 mesh, obtained by the roughness of sandpaper OA-bank was higher compared to SiC-black to all conditions of sandpaper due to its toughness

Corrosion and Wear Studies of Cr3C2NiCr-HVOF Coatings Sprayed on AA7050 T7 Under Cooling

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)