Pump Bearing Fault Detection Based on EMD and SVM

2018 ◽  
Author(s):  
Yi Feng ◽  
Xianling Li ◽  
Zhiwu Ke ◽  
Zhaoxu Chen ◽  
Mo Tao
Keyword(s):  
Heat Transfer ◽  
Correlation Coefficient ◽  
Operating Conditions ◽  
Heat Transfer Fluid ◽  
Support Vector ◽  
Stable Operation ◽  
Feed Water ◽  
Intrinsic Mode Functions ◽  
Coolant Pump ◽  
Term Operation

In nuclear power plant system, pump is the key equipment to maintain the flow of the primary loop coolant and the secondary loop heat transfer fluid. The main coolant pump and the feed water pump are in long-term operation status. Bearings are the key components to ensure stable operation of the pump, and which could be damaged in abnormal conditions. Once the failure occurred in the bearings, pumps would exhibit periodic vibration, which might cause the flow pulsations of coolant and heat transfer fluid; gradually, these situations could reduce the control accuracy and the stability of pump. Therefore, the detection and diagnosis of pump bearings are significant to improve the safety and stability of reactor system. We proposed an approach combined with signal processing and machine learning to extract the signal features and recognize the signal samples automatically. The proposed approach consists of three main steps: firstly, empirical mode decomposition (EMD) is applied to decompose the signals into several intrinsic mode functions (IMFs) which are corresponding to the different components of the original signals; secondly, calculating the correlation coefficient between each IMF and the original signal, the correlation coefficient sequence imply the components distribution of the signal which can be applied to recognize the signal samples; finally, extracting a part of correlation coefficient sequences to train the support vector machine (SVM), and then an classifier can be obtained and use to recognize the other signal samples automatically. Experimental results show that this method can effectively detect the pump bearing operating conditions and failures, and can provide a reference for the safe and stable operation of reactor pumps.

KNT-artificial neural network model for flux prediction of ultrafiltration membrane producing drinking water

2004 ◽  
Vol 50 (8) ◽  
pp. 103-110 ◽  
Author(s):  
H.K. Oh ◽  
M.J. Yu ◽  
E.M. Gwon ◽  
J.Y. Koo ◽  
S.G. Kim ◽  
...  
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Artificial Neural Network ◽  
Correlation Coefficient ◽  
Network Model ◽  
Operating Conditions ◽  
Transmembrane Pressure ◽  
Feed Water ◽  
Permeate Flux ◽  
Artificial Neural

This paper describes the prediction of flux behavior in an ultrafiltration (UF) membrane system using a Kalman neuro training (KNT) network model. The experimental data was obtained from operating a pilot plant of hollow fiber UF membrane with groundwater for 7 months. The network was trained using operating conditions such as inlet pressure, filtration duration, and feed water quality parameters including turbidity, temperature and UV254. Pre-processing of raw data allowed the normalized input data to be used in sigmoid activation functions. A neural network architecture was structured by modifying the number of hidden layers, neurons and learning iterations. The structure of KNT-neural network with 3 layers and 5 neurons allowed a good prediction of permeate flux by 0.997 of correlation coefficient during the learning phase. Also the validity of the designed model was evaluated with other experimental data not used during the training phase and nonlinear flux behavior was accurately estimated with 0.999 of correlation coefficient and a lower error of prediction in the testing phase. This good flux prediction can provide preliminary criteria in membrane design and set up the proper cleaning cycle in membrane operation. The KNT-artificial neural network is also expected to predict the variation of transmembrane pressure during filtration cycles and can be applied to automation and control of full scale treatment plants.

Numerical Investigation of Heat Transfer, Fluid Flow and Formation of Emissions in Diesel Engines

2013 ◽  
Author(s):  
Müjdat Firat
Keyword(s):  
Heat Transfer ◽  
Fluid Flow ◽  
Combustion Engine ◽  
Operating Conditions ◽  
Heat Transfer Fluid ◽  
Nox Emissions ◽  
Combustion Pressure ◽  
Crank Angle ◽  
The Relationship ◽  
Hole Number

The present study has been performed on heat transfer, fluid flow and formation of emissions in a diesel engine by different engine parameters. The analysis aims at an investigation of flow field, heat transfer, combustion pressure and formation of emission by means of numerical simulation which is using as parameter; hole number of injector and crank angle. Numerical simulations are performed using the AVL-FIRE commercial software depending on the crank angle. This software is successfully used in internal combustion engine applications, and its validity has been accepted. In this paper, k-zeta-f is preferred as turbulence model and SIMPLE/PISO used as algorithms. Thus, results are presented with pressure traces, temperature curves and NOx and soot levels for engine operating conditions. In addition, the relationship between the spray behaviors and combustion characteristics including NOx emissions, soot emissions, combustion pressure and temperature were illustrated through this analysis.

Geothermal Power Cycle Analysis for Commercial Applicability Using Sequestered Supercritical CO2 as a Heat Transfer or Working Fluid

2011 ◽  
Author(s):  
Brian Janke ◽  
Thomas Kuehn
Keyword(s):  
Heat Transfer ◽  
Binary System ◽  
Power Plants ◽  
Power Production ◽  
Operating Conditions ◽  
Heat Transfer Fluid ◽  
Working Fluid ◽  
Direct System ◽  
Geothermal Power ◽  
The Impact

Thermodynamic analysis has been conducted for geothermal power cycles using a portion of deep ground sequestered CO2 as the working fluid. This allows energy production from much shallower depths and in geologic areas with much lower temperature gradients than those of current geothermal systems. Two different system designs were analyzed for power production with varying reservoir parameters, including reservoir depth, temperature, and CO2 mass flow rate. The first design is a direct single-loop system with the CO2 run directly through the turbine. This system was found to provide higher system efficiency and power production, however design complications such as the need for high pressure turbines, two-phase flow through the turbine and the potential for water-CO2 brine mixtures, could require the use of numerous custom components, driving up the cost. The second design is a binary system using CO2 as the heat transfer fluid to supply thermal energy to an Organic Rankine Cycle (ORC). While this system was found to have slightly less power production and efficiency than the direct system, it significantly reduces the impact of design complications associated with the direct system. This in turn reduces the necessity for certain custom components, thereby reducing system cost. While performance of these two systems is largely dependent on location and operating conditions, the binary system is likely applicable to a larger number of sites and will be more cost effective when used in combination with current off-the-shelf ORC power plants.

scholarly journals Numerical Performance Investigation of Parabolic Dish Solar-Assisted Cogeneration Plant Using Different Heat Transfer Fluids

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Muhammad Sajid Khan ◽  
Muhammad Abid ◽  
Khuram Pervez Amber ◽  
Hafiz Muhammad Ali ◽  
Mi Yan ◽  
...  
Keyword(s):  
Heat Transfer ◽  
Solar Collector ◽  
Integrated System ◽  
Operating Conditions ◽  
Heat Transfer Fluid ◽  
Working Fluid ◽  
Inlet Temperature ◽  
Pressurized Water ◽  
Parabolic Dish ◽  
Process Heating

Parabolic dish solar collectors gain higher solar to thermal conversion efficiency due to their maximum concentration ratio. The present research focuses by integrating the parabolic dish solar collector to the steam cycle producing power and rate of process heating. Pressurized water, therminol VP1, and supercritical carbon dioxide are the examined working fluids in the parabolic dish solar collector. The aim of the current research is to observe the optimal operating conditions for each heat transfer fluid by varying inlet temperature and flow rate of the working fluid in the parabolic dish solar collector, and combination of these parameters is predicted to lead to the maximum energy and exergy efficiencies of the collector. The operating parameters are varied to investigate the overall system efficiencies, work output, and process heating rate. Findings of the study declare that water is an efficient heat transfer fluid at low temperature levels, whereas therminol VP1 is effective for a higher temperature range. The integrated system efficiencies are higher at maximum flow rates and low inlet temperatures. The efficiency map of solar collector is located at the end of study, and it shows that maximum exergy efficiency gains at inlet temperature of 750 K and it is observed to be 37.75%.

Implementation of an Integrated Solar Combined Cycle on an Existing Coal Fired Power Plant

2010 ◽  
Author(s):  
Eric Reitze ◽  
Hank Price
Keyword(s):  
Heat Transfer ◽  
Control System ◽  
Power Plant ◽  
Thermal Energy ◽  
Combined Cycle ◽  
Heat Transfer Fluid ◽  
Feed Water ◽  
Water Heater ◽  
Solar Field ◽  
Steam Cycle

This paper presents the implementation of an integrated solar combined cycle (ISCC) on the existing 44 MW Cameo Power Generating Station, located in Palisade, Colorado. The plant was originally built in 1957 as a coal fired power plant, to serve the Grand Junction community. This plant has been chosen to demonstrate the viability of the ISCC because of its time line to decommissioning and the availability of additional power from nearby stations to fulfill the community’s needs. The solar system at Cameo utilizes 8 aluminum parabolic trough collectors arranged in 4 loops. Each of these collectors is approximately 150 meters long and 5.77 meters wide. The hot heat transfer fluid used in the solar field is sent to a solar feed water heater, located in between two of the existing feed water heaters, to supplement the thermal energy required by the steam cycle. At design conditions, the solar field will provide 4 MW of thermal energy to the power plant. The development of this ISCC has faced several design and construction challenges not common in traditional power plant and solar power plant design. When first constructed, the Cameo station had no provisions made regarding solar field location, heat transfer fluid piping runs, heat transfer fluid pumping station, thermal expansion vessels, the addition of solar thermal energy to the feed water system, and the integration of a solar field control system into the existing plant distributed control system. Also unaccounted for are the affects the integration of a solar feed water heater has on the thermodynamic efficiency of the steam cycle. This paper discusses these challenges, as well as their resolution, as seen during the engineering, procurement, construction, and commissioning phases of this project. The Cameo Power Generating Station is located in the DeBeque Canyon, 4 miles east of Palisade, Colorado along the Colorado River and Interstate 70. The solar feed water heating demonstration will be in operation for 1 to 2 years, at the discretion of Xcel Energy, to test and develop operating and maintenance methods for large scale application. After such time, both the plant and the solar field will be decommissioned. After decommissioning all applicable solar field equipment shall be refurbished and utilized at additional testing facilities.

Thrust Throttling of Large Liquid Propellant Rocket Engines

1964 ◽  
Vol 68 (647) ◽  
pp. 751-758
Author(s):  
I. E. Smith
Keyword(s):  
Heat Transfer ◽  
Rocket Engine ◽  
Engine Performance ◽  
Pressure Change ◽  
Relative Effect ◽  
Operating Conditions ◽  
Stable Operation ◽  
Rocket Engines ◽  
Gas Generator ◽  
Thrust Chamber

SummaryThe paper concerns rocket engines of the type currently employed in ballistic missiles and satellite booster vehicles, outlining some advantages to be gained from a reduction in thrust towards the end of the burning period. Several methods of throttling a rocket engine are then examined.Low frequency combustion instability which can arise when an engine is operated below its normal thrust level is considered in some detail, including the effect of such instability on engine performance. Means of ensuring stable operation both in the main thrust chamber and the turbine gas generator are described and compared.The mechanism of heat transfer to the main injector has been studied and the modifications to the injection pattern necessary to maintain this at a safe level are described. Also, changes in the overall heat transfer rate to the thrust chamber walls are discussed with special reference to the formation of an insulating layer which occurs with carbon-bearing propellants.The discrepancy between the inlet heads of the propellants at high vehicle accelerations is noted and the relative effect of this on engine operating conditions for the throttled and unthrottled cases described.Finally, the effect of pressure change on the thrust chamber performance is considered with reference to studies made on the Rolls-Royce RZ.2 engine.

scholarly journals Numerical Modeling Prediction of Thermal Storage during Discharging Phase, PV- Thermal Solar and with Nanofluids

2021 ◽  
Vol 10 ◽  
pp. 1-18
Author(s):  
Samuel Sami Howard ◽  
Keyword(s):  
Heat Transfer ◽  
Hybrid System ◽  
Phase Change Materials ◽  
Thermal Storage ◽  
Operating Conditions ◽  
Heat Transfer Fluid ◽  
Melting Time ◽  
Discharge Process ◽  
Fluid Temperature ◽  
System Efficiency

This study is intended to present a numerical model that was established after the energy conservation equations coupled with the heat transfer equations to predict the discharge behavior of different phase change materials, paraffin under the effect of different operating conditions such as solar radiation, heat transfer fluid, using nanofluids; AI2O3, CuO, Fe304 and SiO2, at different concentrations, and heat transfer fluid temperatures. Besides, the effect of the aforementioned operating conditions on the thermal storage process using PV-Thermal hybrid system and the thermal energy conversion efficiency is presented and discussed. It has been observed in this study that the nanofluid AI2O3 has the longest discharge duration elapse compared to other nanofluids and water as base heat transfer fluid. The nanofluid Ai2O3 as heat transfer fluid exhibited the longest time compared to other nanofluids and water as base heat transfer fluid. It was also shown that the higher the nanofluid volumetric concentrations, the longer the discharge process duration elapses. The data showed that nanofluid Al2O3 has the highest discharge time at different concentrations compared to the other nanofluids during the three regions solid, mushy, and liquid. The results clearly showed that by adding 5 % Fe304 nanoparticles, the melting time of paraffin could be saved by 16.5% over the water. It is also evident that the higher the heat transfer fluid temperature, the higher the hybrid system efficiency, and nanofluids CuO and SiO2 have the highest hybrid system efficiency compared to other nanofluids and water as heat transfer fluid. Finally, a good agreement has been obtained between the model and experimental data published in the literature.

scholarly journals Study of the impact of NPP rated thermal power uprate on process behavior at different transient conditions

2018 ◽  
pp. 9-13 ◽  
Author(s):  
A. G. Nikulenkov ◽  
D. V. Samoilenko ◽  
T. V. Nikulenkova
Keyword(s):  
Power Unit ◽  
Thermal Power ◽  
Operating Conditions ◽  
Life Assessment ◽  
Feed Water ◽  
Dimensional System ◽  
Residual Service Life ◽  
Safety Level ◽  
Coolant Pump ◽  
The Impact

Today, objective preconditions have been formed to find the ways on how to increase cost-effectiveness of NPPs operation, while providing the required safety level. One of such ways to increase thermal nominal power of power unit. The paper provides for the results of reactor behavior analysis at increased thermal power above nominal received using a one-dimensional system computer code RELAP5/MOD3.2 and relevant model of VVER-1000 (V-320) power unit. Calculation analyses are performed for quasi-static reactor operating conditions and transients using realistic approach in terms of initial performance parameters of reactor installation. In researches, representative initial events for transients have been selected according to the principle described further. For an abnormal operation, an event has been selected based on its high frequency and consequences, which require decreasing reactor power down to 50 % of nominal thermal power. For emergency conditions an event has been selected which is caused by external extreme impacts typical for Ukrainian NPP sites resulting in the worst consequences. Thus, the transients are represented by events associated with failure of a single turbine-driven feed water pump and total station blackout unit. To analyze emergency conditions caused by long-term blackout, they were additionally accompanied by a leakage through reactor coolant pump seals. Given that increase of steam flow in a turbine at increased thermal power above nominal requires additional studies on residual service life assessment of its critical components, a 3-D model of high-pressure rotor of a full speed turbine is proposed for further studies. Based on the calculations a comparative analysis of major parameters of the reactor at rated and increased thermal power is performed with assessment of significant factors to be considered in further studies on increase of installed thermal output of NPP unit.

Development of Molten Salt Heat Transfer Fluid With Low Melting Point and High Thermal Stability

2011 ◽  
Vol 133 (3) ◽  
Author(s):  
Justin W. Raade ◽  
David Padowitz
Keyword(s):  
Heat Transfer ◽  
Thermal Stability ◽  
Melting Point ◽  
Molten Salt ◽  
Solar Power ◽  
Stability Limit ◽  
High Thermal Stability ◽  
Operating Conditions ◽  
Heat Transfer Fluid ◽  
Concentrating Solar Power

This paper describes an advanced heat transfer fluid (HTF) consisting of a novel mixture of inorganic salts with a low melting point and high thermal stability. These properties produce a broad operating range molten salt and enable effective thermal storage for parabolic trough concentrating solar power plants. Previous commercially available molten salt heat transfer fluids have a high melting point, typically 140 °C or higher, which limits their commercial use due to the risk of freezing. The advanced HTF embodies a novel composition of materials, consisting of a mixture of nitrate salts of lithium, sodium, potassium, cesium, and calcium. This unique mixture exploits eutectic behavior resulting in a low melting point of 65 °C and a thermal stability limit over 500 °C. The advanced HTF described in this work was developed using advanced experiment design and data analysis methods combined with a powerful high throughput experimental workflow. Over 5000 unique mixtures of inorganic salt were tested during the development process. Additional work is ongoing to fully characterize the relevant thermophysical properties of the HTF and to assess its long term performance in realistic operating conditions for concentrating solar power applications or other high temperature processes.

scholarly journals Mental Task Classification Scheme Utilizing Correlation Coefficient Extracted from Interchannel Intrinsic Mode Function

2017 ◽  
Vol 2017 ◽  
pp. 1-11 ◽  
Author(s):  
Md. Mostafizur Rahman ◽  
Shaikh Anowarul Fattah
Keyword(s):  
Correlation Coefficient ◽  
Classification Performance ◽  
Support Vector ◽  
Svm Classifier ◽  
Eeg Signal ◽  
Statistical Features ◽  
Intrinsic Mode Functions ◽  
Mode Decomposition ◽  
High Level ◽  
Mental Tasks

In view of recent increase of brain computer interface (BCI) based applications, the importance of efficient classification of various mental tasks has increased prodigiously nowadays. In order to obtain effective classification, efficient feature extraction scheme is necessary, for which, in the proposed method, the interchannel relationship among electroencephalogram (EEG) data is utilized. It is expected that the correlation obtained from different combination of channels will be different for different mental tasks, which can be exploited to extract distinctive feature. The empirical mode decomposition (EMD) technique is employed on a test EEG signal obtained from a channel, which provides a number of intrinsic mode functions (IMFs), and correlation coefficient is extracted from interchannel IMF data. Simultaneously, different statistical features are also obtained from each IMF. Finally, the feature matrix is formed utilizing interchannel correlation features and intrachannel statistical features of the selected IMFs of EEG signal. Different kernels of the support vector machine (SVM) classifier are used to carry out the classification task. An EEG dataset containing ten different combinations of five different mental tasks is utilized to demonstrate the classification performance and a very high level of accuracy is achieved by the proposed scheme compared to existing methods.

Sign in / Sign up

Export Citation Format

Share Document