The Experts below are selected from a list of 327 Experts worldwide ranked by ideXlab platform
Chengliang Liu - One of the best experts on this subject based on the ideXlab platform.
-
particle swarm optimization based support vector machine for forecasting Dissolved Gases content in power transformer oil
Energy Conversion and Management, 2009Co-Authors: Shengwei Fei, Mingjun Wang, Yubin Miao, Chengliang LiuAbstract:Abstract Forecasting of Dissolved Gases content in power transformer oil is a complicated problem due to its nonlinearity and the small quantity of training data. Support vector machine (SVM) has been successfully employed to solve regression problem of nonlinearity and small sample. However, the practicability of SVM is effected due to the difficulty of selecting appropriate SVM parameters. Particle swarm optimization (PSO) is a new optimization method, which is motivated by social behaviour of organisms such as bird flocking and fish schooling. The method not only has strong global search capability, but also is very easy to implement. Thus, the proposed PSO–SVM model is applied to forecast Dissolved Gases content in power transformer oil in this paper, among which PSO is used to determine free parameters of support vector machine. The experimental data from several electric power companies in China is used to illustrate the performance of proposed PSO–SVM model. The experimental results indicate that the PSO–SVM method can achieve greater forecasting accuracy than grey model, artificial neural network under the circumstances of small sample.
Shengwei Fei - One of the best experts on this subject based on the ideXlab platform.
-
particle swarm optimization based support vector machine for forecasting Dissolved Gases content in power transformer oil
Energy Conversion and Management, 2009Co-Authors: Shengwei Fei, Mingjun Wang, Yubin Miao, Chengliang LiuAbstract:Abstract Forecasting of Dissolved Gases content in power transformer oil is a complicated problem due to its nonlinearity and the small quantity of training data. Support vector machine (SVM) has been successfully employed to solve regression problem of nonlinearity and small sample. However, the practicability of SVM is effected due to the difficulty of selecting appropriate SVM parameters. Particle swarm optimization (PSO) is a new optimization method, which is motivated by social behaviour of organisms such as bird flocking and fish schooling. The method not only has strong global search capability, but also is very easy to implement. Thus, the proposed PSO–SVM model is applied to forecast Dissolved Gases content in power transformer oil in this paper, among which PSO is used to determine free parameters of support vector machine. The experimental data from several electric power companies in China is used to illustrate the performance of proposed PSO–SVM model. The experimental results indicate that the PSO–SVM method can achieve greater forecasting accuracy than grey model, artificial neural network under the circumstances of small sample.
-
forecasting Dissolved Gases content in power transformer oil based on support vector machine with genetic algorithm
Electric Power Systems Research, 2008Co-Authors: Shengwei Fei, Yu SunAbstract:Forecasting of Dissolved Gases content in power transformer oil is very significant to detect incipient failures of transformer early and ensure hassle free operation of entire power system. Forecasting of Dissolved Gases content in power transformer oil is a complicated problem due to its nonlinearity and the small quantity of training data. Support vector machine (SVM) has been successfully employed to solve regression problem of nonlinearity and small sample. However, SVM has rarely been applied to forecast Dissolved Gases content in power transformer oil. In this study, support vector machine with genetic algorithm (SVMG) is proposed to forecast Dissolved Gases content in power transformer oil, among which genetic algorithm (GA) is used to determine free parameters of support vector machine. The experimental data from several electric power companies in China is used to illustrate the performance of proposed SVMG model. The experimental results indicate that the proposed SVMG model can achieve greater forecasting accuracy than grey model (GM) under the circumstances of small sample. Consequently, the SVMG model is a proper alternative for forecasting Dissolved Gases content in power transformer oil.
G K Shagieva - One of the best experts on this subject based on the ideXlab platform.
-
efficiency of water purification from Dissolved Gases under weak and strong phase interaction in film degassers
Thermal Engineering, 2018Co-Authors: A. G. Laptev, E A Lapteva, G K ShagievaAbstract:Water purification processes in film decarbonizers and thermal deaerators with different contact arrangements in the modes of weak and strong interaction between phases are considered. Weak interaction is characterized by a separate movement of phases, wherein a gas or vapor flow hardly affects the hydrodynamics of a liquid film. Such a mode is most often implemented in the case of countercurrent phases. At a gas or vapor velocity greater than 8 m/s and an atmospheric pressure, the gas flow carries the liquid film in an ascending or descending flow. In this mode, mass and heat transfer processes are greatly intensified. The modes are considered by the example of removal of aggressive corrosive Gases at TPPs and industrial enterprises. Expressions are given for the calculation of the mass exchange characteristics of degassers and for the efficiency of water purification from oxygen and carbon dioxide. It is shown that a strong interaction occurs in the tubes with discrete-rough walls and a ribbon swirler, whereas a weak one takes place in irregular (chaotic) packed beds and regular corrugated packed beds with a rough surface. To calculate the efficiency of mass transfer (the extraction of Dissolved Gases from water), we used such flow structure models as a diffusion model and a cell model with bulk mass sources. Expressions for the calculation of model parameters—dispersion coefficients, number of cells, mass transfer coefficients in the liquid phase—are presented. The results of calculations of the mass transfer efficiency in packed columns and channels with discrete-rough walls and swirling flows are given. An example for mounting a packed bed in a DSA-300 deaerator is presented. Conclusions are drawn concerning the most rational designs and operating modes of thermal deaerators and decarbonizers.
-
Improving the efficiency of water purification from Dissolved Gases at TPP
Thermal Engineering, 2017Co-Authors: A. G. Laptev, E A Lapteva, G K ShagievaAbstract:The method for increasing the efficiency of thermal deaerators and calciners of a TPP is considered; it consists of the use of a turbulent mass transfer device with random small packing. Before entering the packed bed in water, air (decarbonization) or water vapor (deaeration) is supplied. Chaotic nozzle creates intense turbulent interaction mode of air (vapor) with water and splitting it into small bubbles; thus the specific surface area of the contact of phases significantly increases, and high efficiency of mass transfer (extraction of Dissolved Gases) is ensured. A turbulent mass transfer device is a circular channel with connections for connecting of the source water to a pipeline. Inzhekhim chaotic nozzle is used with large free volume (95%) and the specific surface area of 150–300 m^2/m^3. The nozzle is made of a thin metal strip that may have a rough surface and is retained in the channel by means of two grids. For the calculation of turbulent mixer, mathematical model of the flow structure is presented, which is built with the use of a one-parameter diffusion model and a semiempirical reverse mixing ratio. Accounting of interphase transfer of Dissolved Gases is carried out via volume source of weight. The equation to determine the weight source and calculation of its parameters is presented. In the particular case, transition to the cell model is made and an expression for calculating the profile of concentrations of Dissolved gas is obtained along the channel with a nozzle. An example of calculating the efficiency of turbulent mixer upon removing Dissolved carbon dioxide from water at a TPP is shown. Recommendations on the use of the considered technical device are given.
H. Gumilang - One of the best experts on this subject based on the ideXlab platform.
-
transformer paper expected life estimation using anfis based on oil characteristics and Dissolved Gases case study indonesian transformers
Energies, 2017Co-Authors: Rahman A. Prasojo, K. Diwyacitta, H. GumilangAbstract:This article presents an algorithm for modelling an Adaptive Neuro Fuzzy Inference System (ANFIS) for power transformer paper conditions in order to estimate the transformer’s expected life. The dielectric characteristics, Dissolved gasses, and furfural of 108 running transformers were collected, which were divided into 76 training datasets and another 32 testing datasets. The degree of polymerization (DP) of the transformer paper was predicted using the ANFIS model based on using the dielectric characteristics and Dissolved Gases as input. These inputs were analyzed, and the best combination was selected, whereas CO + CO2, acidity, interfacial tension, and color were correlated with the paper’s deterioration condition and were chosen as the input variables. The best combination of input variables and membership function was selected to build the optimal ANFIS model, which was then compared and evaluated. The proposed ANFIS model has 89.07% training accuracy and 85.75% testing accuracy and was applied to a transformer paper insulation assessment and an estimation of the expected life of four Indonesian transformers for which furfural data is unavailable. This proposed algorithm can be used as a furfural alternative for the general assessment of transformer paper conditions and the estimation of expected life and provides a helpful assistance for experts in transformer condition assessment.
-
Correlation of transformer paper deterioration to oil characteristics and Dissolved Gases
2017 International Conference on High Voltage Engineering and Power Systems (ICHVEPS), 2017Co-Authors: Rahman A. Prasojo, K. Diwyacitta, H. GumilangAbstract:Dissolved Gases and Oil Characteristics are widely available data for detecting faults and evaluating condition of oil-impregnated power transformers. This paper presents the statistical insights of the effect of transformer paper deterioration to oil insulation. The oil characteristics, Dissolved Gases, and 2FAL data of 108 Indonesian transformers are collected. 2FAL is used as paper condition parameter and then directly linked to the degree of polymerization estimated (DPest). The correlation analysis is done using simple linear regression to find several most correlated parameters to transformer paper deterioration. The result is CO and CO2 is the most correlated Dissolved Gases to transformer paper condition. CO and CO2 have long been recognized as one of the cellulose degradation products. The oil characteristics data shows high correlation of interfacial tension (IFT), acidity, and color to the transformer paper aging condition. Finally, the result is compared to the standard.
Francesco Italiano - One of the best experts on this subject based on the ideXlab platform.
-
Insights into mantle-type volatiles contribution from Dissolved Gases in artesian waters of the Great Artesian Basin, Australia
Chemical Geology, 2014Co-Authors: Francesco Italiano, Galip Yuce, I. T. Uysal, Massimo Gasparon, Guia MorelliAbstract:Abstract The geochemical features of the volatiles Dissolved in artesian thermal waters discharged over three basins (Millungera, Galilee and Cooper basin) of the Australian Great Artesian Basin (GAB) consistently indicate the presence of fluids from multiple gas sources located in the crust (e.g. sediments, oil reservoirs, granites) as well as minor but detectable contributions of mantle/magma-derived fluids. The Gases extracted from 19 water samples and analyzed for their chemical and isotopic composition exhibit amounts of CO2 up to about 340 mlSTP/LH2O marked by a δ13CTDC (Total Dissolved Carbon) ranging from − 16.9 to + 0.18‰ vs PDB, while CH4 concentrations vary from 4.4 × 10− 5 to 4.9 mlSTP/LH2O. Helium contents were between 9 and > 2800 times higher than equilibrium with Air Saturated Water (ASW), with a maximum value of 0.12 mlSTP/LH2O. Helium isotopic composition was in the 0.02–0.21 Ra range (Ra = air-normalized 3He/4He ratio). The three investigated basins differ from each other in terms of both chemical composition and isotopic signatures of the Dissolved Gases whose origin is attributed to both mantle and crustal volatiles. Mantle He is present in the west-central and hottest part of the GAB despite no evidence of recent volcanism. We found that the partial pressure of helium, significantly higher in crustal fluids than in mantle-type volatiles, enhances the crustal He signature in the Dissolved Gases, thus masking the original mantle contribution. Neotectonic activity involving deep lithospheric structures and magma intrusions, highlighted by recent geophysical investigations, is considered to be the drivers of mantle/magmatic volatiles towards the surface. The results, although pertaining to artesian waters from a vast area of > 542,000 km2, provide new constraints on volatile injection, and show that fluids' geochemistry can provide additional and independent information on the geo-tectonic settings of the Great Artesian Basin and its geothermal potential.
-
helium and carbon isotopes in the Dissolved Gases of friuli region ne italy geochemical evidence of co2 production and degassing over a seismically active area
Chemical Geology, 2009Co-Authors: Francesco Italiano, Pietro Bonfanti, Manuela Ditta, Riccardo Petrini, Francesca SlejkoAbstract:Abstract The first geochemical data showing the existence of an active degassing activity over a large seismically active sector of the Southern Alps (Friuli Region, NE Italy) are presented. The Dissolved Gases, helium and carbon isotopic systematics of 46 water samples taken from 13 sites running along E–W and NE–SW faults besides the natural degassing of a 5000 km 2 wide area are investigated. The chemical composition of the Dissolved Gases revealed that a CO 2 -rich gas phase feeds the local groundwaters. 3 He/ 4 He ratios ( R ) normalized to the atmospheric 3 He/ 4 He ratio (Ra = 1.39 × 10 − 6 ) and corrected for the atmospheric contamination ( R /Ra c ), range from 0.29 to 1 as a result of a two component (radiogenic and atmospheric) mixing. The δ 13 C values of total Dissolved inorganic carbon (TDIC) ranging from − 15.28 to − 0.75‰ vs. PDB, show the occurrence of multiple gas–water interactions. The mixing between the atmospheric air and a crustal source and the gas–water interactions occurring at various extents appears to be the main control on the observed He–C systematics. The natural CO 2 degassing was evaluated by a soil gas survey carried out by a grid of about 100 measuring sites located over the area that generated destructive seismic sequences (e.g. the Gemona sequence of 1976; main shocks M6.4 of 6th May and M6.1 of 11th and 15th September). The results obtained show that a significant amount of crustal-originated Gases are released over the continental area of Eastern Southern Alps. The evidence that carbon dioxide is associated with radiogenic-type helium denotes the lack of the mantle as primary energy and degassing source, highlighting the possibility that CO 2 is produced by thermo-mechanical processes occurring at seismogenic depth. The information provided here may be used to start up a long-term geochemical monitoring of this seismically active area and could be able to detect the modifications occurring to the circulating fluids to gain a better insight on the relationships between the fluids' geochemistry and the activity of the local seismogenic faults.
-
Geochemical evidence of seismogenic‐induced anomalies in the Dissolved Gases of thermal waters: A case study of Umbria (Central Apennines, Italy) both during and after the 1997–1998 seismic swarm
Geochemistry Geophysics Geosystems, 2004Co-Authors: Francesco Italiano, Giovanni Martinelli, Andrea Luca RizzoAbstract:[1] In this paper we present the first geochemical data set regarding long-term monitoring of Dissolved Gases in thermal waters from a seismic area. Three sites in Umbria (Central Apennines, Italy) were studied both for the chemical and for the helium isotopic composition of the Dissolved Gases. Data were collected during and after the seismic crisis that struck the region in 1997–1998. The chemical composition of the Dissolved Gases revealed that a CO2-rich gas phase was always mixed with an atmospheric-derived component dominated by N2. A normal faulting marked the beginning of the seismic activity enhancing the release of CO2 on a regional scale. Variations in both the chemical and isotopic compositions of the Dissolved Gases were also observed as preseismic, synseismic, and postseismic phenomena related to the seismic shock of March 1998. Those geochemical modifications were interpreted as being the consequence of a drop in the CO2 degassing rate, in good agreement with the compressive focal mechanism of that seismic event. Furthermore, this interpretation was also consistent with the geologic and tectonic setting of the study area and induced us to postulate that changes in the local rock permeability, due to crustal deformations (i.e., coseismic deformation and postseismic release), were responsible for the geochemical modifications observed. On the basis of the foregoing, we have concluded that the geochemistry of Dissolved Gases in groundwaters represents a useful tool for the investigation of the relationships between circulating fluids and seismic activity.