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.

Ichthyometry and electrical bioimpedance analysis to estimate the body composition of tambatinga

Body composition analysis is relevant to characterize the nutritional requirements and finishing phase of fish. The aim of this study was to investigate the relationship between ichthyometric (weight, total and standard length, density and yields), bromatological (fat, protein, ash and water content) and bioelectrical-impedance-analysis (BIA) (resistance, reactance, phase angle and composition indexes) variables in the hybrid tambatinga (Colossoma macropomum × Piaractus brachypomus). In a non-fertilized vivarium, 520 juveniles were housed and fed commercial rations. Then, 136 days after hatching (DAH), 15 fish with an average weight of 37.69 g and average total length of 12.96 cm were randomly chosen, anesthetized (eugenol) and subjected to the first of fourteen fortnightly assessments (BIA and biometry). After euthanasia, the following parts were weighed: whole carcass with the head, fillet, and skin (WC); fillet with skin (FS); and the remainder of the carcass with the head (CH). Together, FS and CH were ground and homogenized for the bromatological analyses. Estimates of the body composition and yields of tambatinga, with models including ichthyometric and BIA variables, showed correlation coefficients ranging from 0.81 (for the FS yield) to 1,00 (for the total ash). Similarly, models that included only BIA variables had correlation coefficients ranging from 0.81 (FS and CH yields) to 0.98 (for the total ash). Therefore, in tambatinga, the BIA technique allows the estimation of the yield of the fillet with skin and the body composition (water content, fat, ash, and protein). The best models combine ichthyometric and BIA variables.

Transmission immunity in malaria: reflections on the underlying immune mechanisms during natural infections and following artificial immunization

Malaria transmission-blocking immunity has been studied in natural malaria infections in man, during infections in animals and following artificial immunization of animals with sexual stage malaria parasites. Effective immunity, which prevents infectivity of a malarial infection to mosquitoes, has been observed under all of these circumstances. Two general types of effector mechanism have been identified. One is an antibody mediated mechanism which acts against the extracellular sexual stages of the parasite within the midgut of a blood feeding mosquito. The other is a cytokine mediated mechanism which inactivates the gametocytes of the parasites while in the circulation of the vertebrate host. Both effects have been observed during natural infections and following artificial immunization. The basis of induction of transmission-blocking immunity, including the nature of the memory for such immunity, however, may be very different in different host/parasite systems and during natural infection of following artificial immunization. Following artificial immunization a strong immune memory for transmission blocking immunity has been observed in animal systems. By contrast, following natural infections in man immune memory for transmission blocking immunity has been found to be weak and short lived if it occurs at all. It is suggested that the immunogens which induce natural transmission blocking immunity may be CD4+ independent.

Rearing the southern green stink bug using an artificial dry diet and an artificial plant

Laboratory and greenhouse studies were conducted with an artificial dry diet to rear nymphs, and with an artificial plant as substrate for egg laying by the southern green stink bug, Nezara viridula (L.). The artificial diet was composed of: soybean protein (15 g); potato starch (7.5 g); dextrose (7.5 g); sucrose (2.5 g); cellulose (12.5 g); vitamin mixture (niacinamide 1 g, calcium pantothenate 1 g, thiamine 0.25 g, riboflavin 0.5 g, pyridoxine 0.25 g, folic acid 0.25 g, biotin 0.02 mL, vitamin B12 1 g - added to 1,000 mL of distilled water) (5.0 mL); soybean oil (20 mL); wheat germ (17.9 g); and water (30 mL). Nymphs showed normal feeding behavior when fed on the artificial diet. Nymphal development time was longer than or similar to that of nymphs fed on soybean pods. Total nymphal mortality was low (ca. 30%), both for nymphs reared on the artificial diet, and for nymphs fed on soybean pods. At adult emergence, fresh body weights were significantly (P<0.01) less on the artificial diet than on soybean pods. Despite the lower adult survivorship and fecundity on artificial plants than on soybean plants, it was demonstrated for the first time that a model simulating a natural plant, can be used as a substrate for egg mass laying, in conjunction with the artificial diet.

Automated system of seedling image analysis (SVIS) and electrical conductivity to assess sun hemp seed vigor

The development of new procedures for quickly obtaining accurate information on the physiological potential of seed lots is essential for developing quality control programs for the seed industry. In this study, the effectiveness of an automated system of seedling image analysis (Seed Vigor Imaging System - SVIS) in determining the physiological potential of sun hemp seeds and its relationship with electrical conductivity tests, were evaluated. SVIS evaluations were performed three and four days after sowing and data on the vigor index and the length and uniformity of seedling growth were collected. The electrical conductivity test was made on 50 seed replicates placed in containers with 75 mL of deionised water at 25 ºC and readings were taken after 1, 2, 4, 8 and 16 hours of imbibition. Electrical conductivity measurements at 4 or 8 hours and the use of the SVIS on 3-day old seedlings can effectively detect differences in vigor between different sun hemp seed lots.

Avaliação do uso de métodos quimiométricos em análise de solos

One of the major interests in soil analysis is the evaluation of its chemical, physical and biological parameters, which are indicators of soil quality (the most important is the organic matter). Besides there is a great interest in the study of humic substances and on the assessment of pollutants, such as pesticides and heavy metals, in soils. Chemometrics is a powerful tool to deal with these problems and can help soil researchers to extract much more information from their data. In spite of this, the presence of these kinds of strategies in the literature has obtained projection only recently. The utilization of chemometric methods in soil analysis is evaluated in this article. The applications will be divided in four parts (with emphasis in the first two): (i) descriptive and exploratory methods based on Principal Component Analysis (PCA); (ii) multivariate calibration methods (MLR, PCR and PLS); (iii) methods such as Evolving Factor Analysis and SIMPLISMA; and (iv) artificial intelligence methods, such as Artificial Neural Networks.

Protein recovery, separation and purification: selection of optimal techniques using an expert system

The paper discusses the utilization of new techniques ot select processes for protein recovery, separation and purification. It describesa rational approach that uses fundamental databases of proteins molecules to simplify the complex problem of choosing high resolution separation methods for multi component mixtures. It examines the role of modern computer techniques to help solving these questions.

Comparing the artificial neural network with parcial least squares for prediction of soil organic carbon and pH at different moisture content levels using visible and near-infrared spectroscopy

Visible and near infrared (vis-NIR) spectroscopy is widely used to detect soil properties. The objective of this study is to evaluate the combined effect of moisture content (MC) and the modeling algorithm on prediction of soil organic carbon (SOC) and pH. Partial least squares (PLS) and the Artificial neural network (ANN) for modeling of SOC and pH at different MC levels were compared in terms of efficiency in prediction of regression. A total of 270 soil samples were used. Before spectral measurement, dry soil samples were weighed to determine the amount of water to be added by weight to achieve the specified gravimetric MC levels of 5, 10, 15, 20, and 25 %. A fiber-optic vis-NIR spectrophotometer (350-2500 nm) was used to measure spectra of soil samples in the diffuse reflectance mode. Spectra preprocessing and PLS regression were carried using Unscrambler® software. Statistica® software was used for ANN modeling. The best prediction result for SOC was obtained using the ANN (RMSEP = 0.82 % and RPD = 4.23) for soil samples with 25 % MC. The best prediction results for pH were obtained with PLS for dry soil samples (RMSEP = 0.65 % and RPD = 1.68) and soil samples with 10 % MC (RMSEP = 0.61 % and RPD = 1.71). Whereas the ANN showed better performance for SOC prediction at all MC levels, PLS showed better predictive accuracy of pH at all MC levels except for 25 % MC. Therefore, based on the data set used in the current study, the ANN is recommended for the analyses of SOC at all MC levels, whereas PLS is recommended for the analysis of pH at MC levels below 20 %.

HETEROTIC GROUP FORMATION IN PSIDIUM GUAJAVA L. BY ARTIFICIAL NEURAL NETWORK AND DISCRIMINANT ANALYSIS

ABSTRACT The present study aimed at evaluating the heterotic group formation in guava based on quantitative descriptors and using artificial neural network (ANN). For such, we evaluated eight quantitative descriptors. Large genetic variability was found for the eight quantitative traits in the 138 genotypes of guava. The artificial neural network technique determined that the optimal number of groups was three. The grouping consistency was determined by linear discriminant analysis, which obtained classification percentage of the groups, with a value of 86 %. It was concluded that the artificial neural network method is effective to detect genetic divergence and heterotic group formation.