Applications of artificial intelligence to condition-based maintenance

In this paper we discuss interesting developments of expert systems for machine diagnosis and condition-based maintenance. We review some elements of condition-based maintenance and its applications, expert systems for machine diagnosis, and an example of machine diagnosis. In the last section we note some problems to be resolved so that expert systems for machine diagnosis may gain wider acceptance in the future.

Predicting chick body mass by artificial intelligence-based models

The objective of this work was to develop, validate, and compare 190 artificial intelligence-based models for predicting the body mass of chicks from 2 to 21 days of age subjected to different duration and intensities of thermal challenge. The experiment was conducted inside four climate-controlled wind tunnels using 210 chicks. A database containing 840 datasets (from 2 to 21-day-old chicks) - with the variables dry-bulb air temperature, duration of thermal stress (days), chick age (days), and the daily body mass of chicks - was used for network training, validation, and tests of models based on artificial neural networks (ANNs) and neuro-fuzzy networks (NFNs). The ANNs were most accurate in predicting the body mass of chicks from 2 to 21 days of age after they were subjected to the input variables, and they showed an R² of 0.9993 and a standard error of 4.62 g. The ANNs enable the simulation of different scenarios, which can assist in managerial decision-making, and they can be embedded in the heating control systems.

Monomer conversion of composite dental resins photoactivated by a halogen lamp and a LED: a FT-Raman spectroscopy study

Eighteen circular blocks of resins cured either by a LED or a halogen lamp (20, 40 and 60 s), had their top (T) and bottom (B) surfaces studied using a FT-Raman spectrometer. Systematic changes in the intensity of the methacrylate C=C stretching mode at 1638 cm-1 as a function of exposure duration were observed. The calculated degree of conversion (DC) ranged from 45.0% (B) to 52.0% (T) and from 49.0% (B) to 55.0% (T) for the LED and halogen lamp, respectively. LED and halogen light produced similar DC values with 40 and 60 s of irradiation.

Um fotômetro multi-led microcontrolado, portátil e de baixo custo

A microcontrolled, portable and inexpensive photometer is described. It uses six light-emitting diodes (LEDs) as radiation sources and a phototransistor as detector, as well as a microcontroller (PIC - Programmable Controller of Interruption). This device provided total autonomy to the proposed photometer, which was successfully applied to determination of Fe2+ in ferrous syrups and of seven clinical biochemical parameters. As the components are cheap (~U$30.00) and easy to find, the proposed photometer is an economical alternative for routine chemical analyses in small laboratories, for research and teaching. Being portable and microcontrolled, it allows doing field chemical analyses.

Light emitting diode (LED) use in artificial lighting for broiler chicken production

Light emitting diode (LED) has been used in commercial poultry industry by presenting superior energy savings and providing feasibility on production process. The objective of this research was to evaluate performance and carcass yield of broiler chickens exposed to different LED colors compared with fluorescent lamps. For that, two experiments (E1 and E2) were performed and 2,646 Cobb® chickens were used. In experiment E1, male birds were exposed to 20 lux artificial lighting with red, yellow, blue, and white LED bulbs; and fluorescent bulb. In experiment E2, male and female birds were exposed to 15 lux artificial lighting with red and blue LED bulbs; and fluorescent bulb. Cumulative weight gain (kg), feed intake (kg), feed conversion, hot carcass weight (kg), carcass yield (%), and breast and thigh + drumstick yield (%) were used as response variables. Results showed no difference (p > 0.05) among treatments for performance, carcass yield, and cut yield in experiment E1. In experiment E2 there was only difference between genders (p < 0.05) and males showed higher total weight gain, feed intake, hot carcass weight and thigh + drumstick yield. Different LED color use had same effect as fluorescent lights on broiler performance and carcass yield.

Finance-Led Growth Regime no Brasil: estatuto teórico, evidências empíricas e consequências macroeconômicas

This paper analyzes the Brazilian growth pattern during the post-liberalization period, emphasizing the structural links between finance and productive capital accumulation. The results indicate a finance-led growth regime in the period 2004-2008, under a very specific financialization process. The first part is a survey of the international literature, which defines the financialization concept and its relevance for understanding Brazilian economic problems. The next part provides a historical overview on the structural changes that made possible the development of financial-led regimes. The paper also applies an empirical analysis of some selected Brazilian macroeconomic indicators.