Multilayer perceptron neural networks training through charged system search and its Application for non-technical losses detection

The non-technical loss is not a problem with trivial solution or regional character and its minimization represents the guarantee of investments in product quality and maintenance of power systems, introduced by a competitive environment after the period of privatization in the national scene. In this paper, we show how to improve the training phase of a neural network-based classifier using a recently proposed meta-heuristic technique called Charged System Search, which is based on the interactions between electrically charged particles. The experiments were carried out in the context of non-technical loss in power distribution systems in a dataset obtained from a Brazilian electrical power company, and have demonstrated the robustness of the proposed technique against with several others nature-inspired optimization techniques for training neural networks. Thus, it is possible to improve some applications on Smart Grids. © 2013 IEEE.

Using baseline methods to identify non-technical losses in the context of smart grids

Demand response has gained increasing importance in the context of competitive electricity markets and smart grid environments. In addition to the importance that has been given to the development of business models for integrating demand response, several methods have been developed to evaluate the consumers' performance after the participation in a demand response event. The present paper uses those performance evaluation methods, namely customer baseline load calculation methods, to determine the expected consumption in each period of the consumer historic data. In the cases in which there is a certain difference between the actual consumption and the estimated consumption, the consumer is identified as a potential cause of non-technical losses. A case study demonstrates the application of the proposed method to real consumption data. © 2013 IEEE.

Soil and crop residue CO2-C emission under tillage systems in sugarcane-producing areas of southern Brazil

Appropriate management of agricultural crop residues could result in increases on soil organic carbon (SOC) and help to mitigate gas effect. To distinguish the contributions of SOC and sugarcane (Saccharum spp.) residues to the short-term CO2-C loss, we studied the infl uence of several tillage systems: heavy offset disk harrow (HO), chisel plow (CP), rotary tiller (RT), and sugarcane mill tiller (SM) in 2008, and CP, RT, SM, moldboard (MP), and subsoiler (SUB) in 2009, with and without sugarcane residues relative to no-till (NT) in the sugarcane producing region of Brazil. Soil CO2-C emissions were measured daily for two weeks after tillage using portable soil respiration systems. Daily CO2-C emissions declined after tillage regardless of tillage system. In 2008, total CO2-C from SOC and/or residue decomposition was greater for RT and lowest for CP. In 2009, emission was greatest for MP and CP with residues, and smallest for NT. SOC and residue contributed 47% and 41%, respectively, to total CO2-C emissions. Regarding the estimated emissions from sugarcane residue and SOC decomposition within the measurement period, CO2-C factor was similar to sugarcane residue and soil organic carbon decomposition, depending on the tillage system applied. Our approach may define new emission factors that are associated to tillage operations on bare or sugarcane-residue-covered soils to estimate the total carbon loss.

Soil organic matter and physical attributes affected by crop rotation under no-till

Growing cover crops in systems under no tillage affects different pools of soil organic matter, and eventually soil physical attributes are modified. The objective of this study was to evaluate changes in soil organic matter and their relationship with soil physical attributes as affected by plant species grown in rotation with soybean [Glycine max (L.) Merr.] under no-till for 3 yr. Crop rotations included grain sorghum [Sorghum bicolor (L.) Moench], ruzigrass [Urochloa ruziziensis (R. Germ, and CM. Evard) Crins] and sorghum mixed with ruzigrass, all grown in fall/winter, followed by pearl millet [Pennisetum americanum (L.) Leeke], sunn hemp (Crotalaria juncea L.) and sorghum-sudangrass [S. bicolor × S. sudanense (Piper) Stapf] grown during the spring, plus a fallow check plot. Soybean was grown as the summer crop. Millet and sorghum-sudangrass cropped in spring showed higher root and shoot production as spring cropping. In fall/winter, sorghum mixed with ruzigrass yielded higher phytomass compared with sole cropping. Soil physical attributes and organic matter fractioning were positively affected by cropping millet and sorghum-sudangrass whereas intermediate effects were observed after sunn hemp. Maintaining fallow in spring had negative effects on soil organic matter and physical properties. Ruzigrass and sorghum mixed with ruzigrass cropped in fall/winter resulted in better soil quality. Spring cover crops were more efficient in changing soil bulk density, porosity, and aggregates down to 0 to 10 cm; on the other hand, fall/winter cropping showed significant effects on bulk density in the uppermost soil layer. Total C levels in soil were increased after a 3-yr rotation period due to poor initial physical conditions. Fractions of particulate organic C, microbial C, and C in macroaggregates were the most affected by crop rotations, and showed high relation with improved soil physical attributes (porosity, density, and aggregates larger than 2 mm). © Soil Science Society of America, All rights reserved.

Cover crop termination timing on rice crop production in a no-till system

Measuring shikimic acid accumulation in response to glyphosate applications can be a rapid and accurate way to quantify and predict glyphosate-induced damage to sensitive plants. The objective of this paper was to evaluate the effect of cover crop termination timing by glyphosate application on rice (Oryza sativa L.) yield in a no-till system. A factorial experiment, arranged in a split-plot design, was conducted for 2 yr. Treatments consisted of cover crops (main plots) and timed herbicide applications (subplots) to these cover crops (30, 20, 10, and 0 d before rice planting). There was a decrease in rice yield from 2866 kg ha-1 to 2322 kg ha-1 when the herbicide was applied closer to the rice planting day. Glyphosate application on cover crops increased shikimate concentrations in rice seedlings cultivated under palisade grass (Brachiaria brizantha), signal grass (B. ruziziensis), guinea grass (Panicum maximum), and weedy fallow (spontaneous vegetation) but not under millet (Pennisetum glaucum), which behaved similarly to the control (clean fallow, no glyphosate application). Glyphosate applications in the timing intervals used were associated with stress in the rice plants, and this association increased if cover crops took longer to completely dry and if higher amounts of biomass were produced. Millet, as a cover crop, allowed the highest seedling dry matter for upland rice and the highest rice yield. Our results suggest that using millet as a cover crop, with glyphosate application far from upland rice planting day (10 d or more), was the best option for upland rice under a no-tillage system. © Crop Science Society of America.

Teor de clorofila, danos oxidativos e qualidade de sementes de soja

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Uso do clorofilômetro portátil na determinação da adubação nitrogenada de cobertura em cultivares de feijoeiro

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Nitrogênio no sistema solo-planta após a dessecação de brachiarias

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Períodos de interferência de uma comunidade infestante na cultura do milho em primeira e segunda safras

Pós-graduação em Agronomia (Agricultura) - FCA

Sistemática molecular de Atta laevigata (Smith 1858) e Acromyrmex balzani (Emery 1890)

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

Desempenho de máquinas para a semeadura e o arranquio mecanizado na cultura do amendoim em latossolo vermelho

Pós-graduação em Agronomia (Ciência do Solo) - FCAV

Doses, épocas e modos de aplicação da uréia comum e revestida na cultura do milho

Pós-graduação em Agronomia (Ciência do Solo) - FCAV

Uso do lodo biológico de indústria de gelatina para adubação de cana-de-açúcar

Pós-graduação em Agronomia (Ciência do Solo) - FCAV

Perdas de nutrientes e matéria orgânica por erosão em entressulcos em argissolo com resíduos de cana-de-açúcar

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Isolamento, purificação e caracterização da peroxidase de yacon (Smallanthus sonchifolius)

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)