Predicting axial piston pump performance using neural networks

Karkoub, Mansour; Gad, Osama; Rabie, Mahmoud G

doi:10.1016/s0094-114x(98)00086-x

Cited by 31 publications

(14 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The external characteristics could be described as head H, power N and efficiency η. The parameters could be calculated by inlet pressure p in , outlet pressure p out , rotation speed n, and shaft torque M as Equations (2)- (4).…”

Section: Performance Parameter Definitionmentioning

confidence: 99%

See 1 more Smart Citation

Experimental Investigation on Transient Pressure Characteristics in a Helico-Axial Multiphase Pump

Cao

Sano

et al. 2019

Energies

View full text Add to dashboard Cite

In oil and gas exploitation, the multiphase pump is a vital piece of equipment to guarantee production with high efficiency and stable operation. The complicated pattern of multiphase flow in the multiphase pump affects the pump performance; for this reason, the multiphase performance and the inner flow should be sufficiently investigated. In the present work, a liquid-gas multiphase pump is designed and manufactured, and then tested in a specialized test rig to reveal the transient pressure characteristics of the multiphase pump. Results show that the dominant frequency under water and water-air conditions is the blade passing frequency, which is induced by the rotor stator interaction. In the downstream of the impeller, the pressure fluctuation is obviously weakened, because the splitter-blade design could improve the control ability of flow pattern in the downstream region. In comparison with water condition, the pressure fluctuation of water-air condition greatly increases, and the multiples of impeller rotating frequency are stimulated due to the movement and merging of air bubbles. Finally, the correlation of transient pressure and phase distribution in impeller is revealed by using a high-speed camera. With the gradual pressure rise from impeller inlet to outlet, the relative movement and separation of two phases induce violent pressure fluctuations.

show abstract

Section: Performance Parameter Definitionmentioning

confidence: 99%

“…The main difficulty for rotodynamic pumps to transport liquid-gas flow is the separation of two-phase due to the pressure difference. In this field, the fixed displacement pumps have their advantage of pumping mediums with different component and proportion, while keeping the output flowrate constant [4,5].…”

Section: Introductionmentioning

confidence: 99%

Experimental Investigation on Transient Pressure Characteristics in a Helico-Axial Multiphase Pump

Cao

Sano

et al. 2019

Energies

View full text Add to dashboard Cite

show abstract

“…The more detailed information and calculations, formulas, etc. about the method can be found in [18,19,[22][23][24][25][26][27].…”

Section: Ann Approachmentioning

confidence: 99%

Prediction of Performance and Smoke Emission Using Artificial Neural Network in a Diesel Engine

Sekmen

Gölcü

Erduranlı

et al. 2006

MCA

View full text Add to dashboard Cite

The fuel injection pressure is one of the significant operating parameters affects atomization of fuel and mixture formation; therefore, it determines the performance and emissions of a diesel engine. Increasing the fuel injection pressure decrease the particle diameter and caused the diesel fuel spray to vaporize quickly. However, with decreasing fuel particles their inertia will also decrease and for this reason fuel can not penetrate deeply into the combustion chamber. In this study, artificial neural-networks (ANNs) are used to determine the effects of injection pressure on smoke emissions and engine performance in a diesel engine. Experimental studies were used to obtain training and test data. Injection pressure was changed from 100bar to 300bar in experiment (standard injection pressure of test engine is 150bar). Injection pressure and engine speed have been used as the input layer; smoke emission, engine torque and specific fuel consumption have been used as the output layer. Two different training algorithms were studied. The best results were obtained from Levenberg-Marquardt (LM) and Scaled Conjugate gradient (SCG) algorithms with 11 neurons. However, The LM algorithm is faster than the SCG algorithm, and its error values are smaller than those of the SCGs. For the torque with LM algorithm, fraction of variance (R 2 ) and mean absolute percentage error (MAPE) were found to be 0.9927 and 7.2108%, respectively. Similarly, for the specific fuel consumption (SFC), R 2 and MAPE were calculated as 0.9872 and 6.0261%, respectively. For the torque with SCG algorithm, R 2 and MAPE were found to be 0.9879 and 9.0026%, respectively. Similarly, for the specific fuel consumption (SFC), R 2 and MAPE were calculated as 0.9793 and 8.7974%, respectively. So, these ANN predicted results can be considered within acceptable limits and the results show good agreement between predicted and experimental values.

show abstract

“…Many researchers have developed diagnostic methods by using ANNs to detect the problems of march-motors, electric motors (Bayır & Bay, 2004), rotating machine parts (Rajakarunakaran, Venkumar, Devaraj, & Rao, 2008), automobile engines, bearings, hydraulic servo-valves, servomotors, check-valves (Seong et al, 2005), wood sawing machines, metal cutting operations, gears, gearboxes (Chen & Wang, 2000;Samanta, 2004;Wuxing, Tse, Guicai, & Tielin, 2004), hydraulic systems (Demetgul, 2008;Sandt et al, 1997), pumps (Karkoub, Gad, & Rabie, 1999), gas turbines, Fisher Rosemount valves (Karpenko & Sepehri, 2002;Karpenko, Sepehri & Scuse, 2003), and compressors. Some of the commonly used ANN algorithms in fault diagnosis are Bp, ART2, Levenberg Marquart, Neuro-fuzzy (Wang, Golnaraghi, & Ismail, 2004), (Self Organization Feature Maps) SOFM (Jams a-Jounela, Vermasvuori, Enden, & Haavisto, 2003), (Learning Vector Quantisation) LVQ, and (Radial Basis Function) RBF algorithms (Parlos, Kim, & Bharadwaj, 2004).…”

Section: Introductionmentioning

confidence: 99%