The classification of technical equipment states, using a neural nets approach

The Maser thesis is devoted to developing a model to technical state of gas turbine engine estimation. The approaches to preparation data, especially to handle unbalanced data were presented in the thesis. In order to efficient estimation of model performance, the special metric was chosen. Goal of the master thesis is analyzing of monitoring parameters data and developing a model of technical state of GTE estimation based on the data.

Handling the Problem of Unbalanced Data Sets in the Classification of Technical Equipment States

Questions of handling unbalanced data considered in this article. As models for classification, PNN and MLP are used. Problem of estimation of model performance in case of unbalanced training set is solved. Several methods (clustering approach and boosting approach) considered as useful to deal with the problem of input data.

Hydraulic conductivity and experiments of sediment beds

In marine environments, sediments from different sources are stirred and dispersed, generating beds that are composed of mixed and layered sediments of differing grain sizes. Traditional engineering formulations used to predict erosion thresholds are however, generally for unimodal sediment distributions, and so may be inadequate for commonly occurring coastal sediments. We tested the transport behavior of deposited and mixed sediment beds consisting of a simplified two-grain fraction (silt (D50 = 55 µm) and sand (D50 = 300 µm)) in a laboratory-based annular flume with the objective of investigating the parameters controlling the stability of a sediment bed. To mimic recent deposition of particles following large storm events and the longer-term result of the incorporation of fines in coarse sediment, we designed two suites of experiments: (1) "the layering experiment": in which a sandy bed was covered by a thin layer of silt of varying thickness (0.2 - 3 mm; 0.5 - 3.7 wt %, dry weight in a layer 10 cm deep); and (2) "the mixing experiment" where the bed was composed of sand homogeneously mixed with small amounts of silt (0.07 - 0.7 wt %, dry weight). To initiate erosion and to detect a possible stabilizing effect in both settings, we increased the flow speeds in increments up to 0.30 m/s. Results showed that the sediment bed (or the underlying sand bed in the case of the layering experiment) stabilized with increasing silt composition. The increasing sediment stability was defined by a shift of the initial threshold conditions towards higher flow speeds, combined with, in the case of the mixed bed, decreasing erosion rates. Our results show that even extremely low concentrations of silt play a stabilizing role (1.4% silt (wt %) on a layered sediment bed of 10 cm thickness). In the case of a mixed sediment bed, 0.18% silt (wt %, in a sample of 10 cm depth) stabilized the bed. Both cases show that the depositional history of the sediment fractions can change the erosion characteristics of the seabed. These observations are summarized in a conceptual model that suggests that, in addition to the effect on surface roughness, silt stabilizes the sand bed by pore-space plugging and reducing the inflow in the bed, and hence increases the bed stability. Measurements of hydraulic conductivity on similar bed assemblages qualitatively supported this conclusion by showing that silt could decrease the permeability by up to 22% in the case of a layered bed and by up to 70% in the case of a mixed bed.

World survey of agricultural machinery and equipment.

[1] Asia.--[2] Europe.--[3] South America.--[4-5] Africa, Australia-Oceania.--[6] North and Central America.