An adaptive system based on artificial neural networks for NPK fluid fertilizer application

The application process of fluid fertilizers through variable rates implemented by classical techniques with feedback and conventional equipments can be inefficient or unstable. This paper proposes an open-loop control system based on artificial neural network of the type multilayer perceptron for the identification and control of the fertilizer flow rate. The network training is made by the algorithm of Levenberg-Marquardt with training data obtained from measurements. Preliminary results indicate a fast, stable and low cost control system for precision fanning. Copyright (C) 2000 IFAC.

Biomass production and secretion of hydrolytic enzymes are influenced by the structural complexity of the nitrogen source in Fusarium oxysporum and Aspergillus nidulans

The structural complexity of the nitrogen sources strongly affects biomass production and secretion of hydrolytic enzymes in filamentous fungi. Fusarium oxysporum and Aspergillus nidulans were grown in media containing glucose or starch, and supplemented with a nitrogen source varying from a single ammonium salt (ammonium sulfate) to free amino acids (casamino acids), peptides (peptone) and protein (gelatin). In glucose, when the initial pH was adjusted to 5.0, for both microorganisms, higher biomass production occurred upon supplementation with a nitrogen source in the peptide form (peptone and gelatin). With a close to neutrality pH, biomass accumulation was lower only in the presence of the ammonium salt. When grown in starch, biomass accumulation and secretion of hydrolytic enzymes (amylolytic and proteolytic) by Fusarium also depended on the nature of the nitrogen supplement and the pH. When the initial pH was adjusted to 5.0, higher growth and higher amylolytic activities were detected in the media supplemented with peptone, gelatin and casamino acids. However, at pH 7.0, higher biomass accumulation and higher amylolytic activities were observed upon supplementation with peptone or gelatin. Ammonium sulfate and casamino acids induced a lower production of biomass, and a different level of amylolytic enzyme secretion: high in ammonium sulfate and low in casamino acids. Secretion of proteolytic activity was always higher in the media supplemented with peptone and gelatin. Aspergillus, when grown in starch, was not as dependent as Fusarium on the nature of nitrogen source or the pH. The results described in this work indicate that the metabolism of fungi is regulated not only by pH, but also by the level of structural complexity of the nitrogen source in correlation to the carbon source.

Load torque estimation in induction motors using artificial neural networks

The induction motors are largely used in several industry sectors. The dimensioning of an induction motor has still been inaccurate because in most of the cases the load behavior in its shaft is completely unknown. The proposal of this paper is to use artificial neural networks as tool for dimensioning of induction motors rather than conventional methods, which use classical identification techniques and mechanical load modeling. Simulation results are also presented to validate the proposed approach.

Prediction of occurrences of diverse chemical classes in the Asteraceae through artificial neural networks

The training and the application of a neural network system for the prediction of occurrences of secondary metabolites belonging to diverse chemical classes in the Asteraceae is described. From a database containing about 604 genera and 28,000 occurrences of secondary metabolites in the plant family, information was collected encompassing nine chemical classes and their respective occurrences for training of a multi-layer net using the back-propagation algorithm. The net supplied as output the presence or absence of the chemical classes as well as the number of compounds isolated from each taxon. The results provided by the net from the presence or absence of a chemical class showed a 89% hit rate; by excluding triterpenes from the analysis, only 5% of the genera studied exhibited errors greater than 10%. Copyright (C) 2004 John Wiley Sons, Ltd.

Smart structures health monitoring using artificial neural network

This paper presents a non-model based technique to detect and locate structural damage with the use of artificial neural networks. This method utilizes high frequency structural excitation (typically greater than 30 kHz) through a surface-bonded piezoelectric sensor/actuator to detect changes in structural point impedance due to the presence of damage. Two sets of artificial neural networks were developed in order to detect, locate and characterize structural damage by examining changes in the measured impedance curves. A simulation beam model was developed to verify the proposed method. An experiment was successfully performed in detecting damage on a 4-bay structure with bolted-joints, where the bolts were progressively released.

Influência do intervalo entre a inseminação artificial com sêmen diluído resfriado e transportado e a ovulação sobre a fertilidade de éguas

One hundred forty seven cycles of mares were allocated in a completely randomized experiment, with different number of replications and divided in four treatments (T1 = 24 hours preovulation; T2 = 48 hours preovulation; T3 = 48 hours preovulation and in tbe same day of ovulation; T4 = 72 hours preovulation and in the same day of ovulation), in order to study the effect of AI/ovulation interval on mare fertility. The mares were inseminated three times for wek (monday, wednesday and friday), with semen of only one stallion diluted in extender skim milk-glucose, using a volume of 15ml, with 400 x 10(6) sptz viable, cooled at 14 degrees C/3.6 hours, and transported in modified container Celle. Conception rates were not different according to the treatments. So, observed spermatic survival for 60 hours showed the practicability of the inseminations on monday, wednesday and friday.

Uterine leucocyte infiltration after artificial insemination in bitches

In the present study, polymorphonuclear neutrophils (PMN) were enumerated to evaluate acute uterine inflammation after artificial insemination in the bitch. It was concluded that the canine seminal plasma possessed an immunomodulating action. However, the most commonly used extender for freezing canine semen (Tris glucose with egg yolk and glycerol) was a potential inducer of uterine inflammation. (c) 2006 Published by Elsevier B.V.

Kinetic characterization of hypophosphatasia mutations with physiological substrates

We have analyzed 16 missense mutations of the tissue-nonspecific AP (TNAP) gene found in patients with hypophosphatasia. These mutations span the phenotypic spectrum of the disease, from the lethal perinatal/infantile forms to the less severe adult and odontohypophosphatasia. Site-directed mutagenesis was used to introduce a sequence tag into the TNAP cDNA and eliminate the glycosylphosphatidylinositol (GPI)-anchor recognition sequence to produce a secreted epitope-tagged TNAP (setTNAP). The properties of GPI-anchored TNAP (gpiTNAP) and setTNAP were found comparable. After introducing each single hypophosphatasia mutation, the setTNAP and mutant TNAP cDNAs were expressed in COS-1 cells and the recombinant flagged enzymes were affinity purified. We characterized the kinetic behavior, inhibition, and heat stability properties of each mutant using the artificial substrate p-nitrophenylphosphate (pNPP) at pH 9.8. We also determined the ability of the mutants to metabolize two natural substrates of TNAP, that is, pyridoxal-5'-phosphate (PLP) and inorganic pyrophosphate (PPi), at physiological pH. Six of the mutant enzymes were completely devoid of catalytic activity (R54C, R54P, A94T, R206W, G317D, and V365I), and 10 others (A16V, A115V, A160T, A162T, E174K, E174G, D277A, E281K, D361V, and G439R) showed various levels of residual activity. The A160T substitution was found to decrease the catalytic efficiency of the mutant enzyme toward pNPP to retain normal activity toward PPi and to display increased activity toward PLP. The A162T substitution caused a considerable reduction in the pNPPase, PPiase, and PLPase activities of the mutant enzyme. The D277A mutant was found to maintain high catalytic efficiency toward pNPP as substrate but not against PLP or PPi. Three mutations ( E174G, E174K, and E281K) were found to retain normal or slightly subnormal catalytic efficiency toward pNPP and PPi but not against PLP. Because abnormalities in PLP metabolism have been shown to cause epileptic seizures in mice null for the TNAP gene, these kinetic data help explain the variable expressivity of epileptic seizures in hypophosphatasia patients.

Using artificial neural networks for identification of electrical losses in transformers during the manufacturing phase

The paper describes a novel neural model to estimate electrical losses in transformer during the manufacturing phase. The network acts as an identifier of structural features on electrical loss process, so that output parameters can be estimated and generalized from an input parameter set. The model was trained and assessed through experimental data taking into account core losses, copper losses, resistance, current and temperature. The results obtained in the simulations have shown that the developed technique can be used as an alternative tool to make the analysis of electrical losses on distribution transformer more appropriate regarding to manufacturing process. Thus, this research has led to an improvement on the rational use of energy.

Structural health evaluation by optimization techinique and artificial neural network

This paper presents two different approaches to detect, locate, and characterize structural damage. Both techniques utilize electrical impedance in a first stage to locate the damaged area. In the second stage, to quantify the damage severity, one can use neural network, or optimization technique. The electrical impedance-based, which utilizes the electromechanical coupling property of piezoelectric materials, has shown engineering feasibility in a variety of practical field applications. Relying on high frequency structural excitations, this technique is very sensitive to minor structural changes in the near field of the piezoelectric sensors, and therefore, it is able to detect the damage in its early stage. Optimization approaches must be used for the case where a good condensed model is known, while neural network can be also used to estimate the nature of damage without prior knowledge of the model of the structure. The paper concludes with an experimental example in a welded cubic aluminum structure, in order to verify the performance of these two proposed methodologies.