CFD and Neural Network-Based Predicting for Oil Delivery Performance of Oil Pump in Engines

2011 ◽  
Vol 230-232 ◽  
pp. 784-788
Author(s):  
Bao Hong Tong ◽  
Jun Yin ◽  
Yin Liu
Keyword(s):  
Neural Network ◽  
Cfd Simulation ◽  
Fluid Dynamic ◽  
Prediction Method ◽  
Operating Conditions ◽  
Ann Model ◽  
Delivery Performance ◽  
Oil Pump ◽  
Oil Flow ◽  
Simulation Results

Oil delivery pefromance of oil pump in engines are investigated by a new prediction method based on computational fluid dynamic (CFD) and artificial neural network (ANN). CFD analysis was done by using Fluent commercial code and distribution of velocity of pump’s internal flow field was achieved by the solving of pump’s CFD model. Infromation data about oil pump’s rotate speed, supplying pressure, oil temperature and oil flow rate were obtained by CFD simulation analyzing. ANN model that used to describe the delivery performance of oil pump was employed, and the model was trained by learning samples from those CFD simulation results. Predicting for the delivery performance of oil pump under various operating conditions were carried out by this model. Experimental results were also used to validate the obtained simulation results. The studies show that the ANN(trained by CFD learning samples) predictions are in very close agreement with the oil flow obtained experimentally or predicted by CFD. The method introduced here can give useful supports for optimization designing of oil pump’s dimension.

CFD Simulation of a Co-rotating Twin-screw Extruder: Validation of a Rheological Model for a Starch-Based Dough for Snack Food

2017 ◽  
Vol 14 (2) ◽  
Author(s):  
Giorgia Tagliavini ◽  
Federico Solari ◽  
Roberto Montanari
Keyword(s):  
Cfd Simulation ◽  
Fluid Dynamic ◽  
Operating Conditions ◽  
Second Phase ◽  
Snack Food ◽  
Suitable Model ◽  
Twin Screw Extruder ◽  
Parallel Plates ◽  
Screw Extruder ◽  
Twin Screw

AbstractThe extrusion of starch-based products has been a matter of interest, especially for the pasta and the snack food production. In recent years, twin-screw extruders for snack food have been studied from both structural and fluid dynamics viewpoints. This project started from the rheological characterization of a starch-based dough (corn 34 wt%, tapioca 32 wt%), comparing viscosity values acquired in laboratory with different theoretical models found in literature. A computational fluid dynamic (CFD) simulation recreating the simple case of a fluid flow between two parallel plates was carried out to validate the former comparison. After the rheological validation was completed, the second phase of this work covered a 3D CFD simulation of the first part of the twin-screw extruder (feeding zone). The objective was to find a suitable model for describing the dough rheological behavior and the operating conditions of a co-rotating intermeshing twin-screw extruder. Once the model would be defined, it would allow to investigate several working conditions and different screws geometries of the machine, predicting the evolution of the product rheological properties.

Numerical Simulation and Stereo PIV Test of Inner Flow in a Double Blades Pump

2011 ◽  
Author(s):  
Kai Wang ◽  
Houlin Liu ◽  
Shouqi Yuan ◽  
Minggao Tan ◽  
Yong Wang ◽  
...  
Keyword(s):  
Numerical Simulation ◽  
Velocity Field ◽  
Cfd Simulation ◽  
Research Work ◽  
Three Dimensional ◽  
Operating Conditions ◽  
Absolute Velocity ◽  
Operation Condition ◽  
Test Technique ◽  
Simulation Results

A double blades pump is widely used in sewage treatment industry, while at present the research on the internal flow characteristics of the double blades pump is very few. So, the CFD technology and the stereo PIV test technique are applied to study the inner flow in a double blades pump whose specific speed is 110.9. The commercial code FLUENT is used to simulate the inner flow in the double blades pump at 0.6Qd, 0.8Qd, 1.0Qd, 1.2Qd and 1.4Qd. The RNG k-ε turbulence model and SIMPLEC algorithm are used in FLUENT. According to the results of the three-dimensional steady numerical simulation, the distributions of velocity field in the impeller are obtained at the five different operating conditions. The analysis of the numerical simulation results shows that there is an obvious vortex in the impeller passage at off-design conditions. But the number, location and area of the vortex are different from each operation condition. In order to validate CFD simulation results, the stereo PIV is used to test the absolute velocity distribution in the double blades pump at Jiangsu University. The distributions of three-dimensional absolute velocity field at the above five different operating conditions are obtained by the PIV test, and the measured results are compared with the CFD simulation results. The comparison indicates that there are vortexes in impeller passages of the double blades pump under the five operating conditions. But as to the area of the vortex and the relative velocity values of the vortex core, there are some differences between the experiment results and the numerical simulation results. The research work can be applied to instruct the hydraulic design of double blades pumps.

scholarly journals Artificial Neural Network Model for Managing and Forecasting Water Reservoir Discharge (Hemren Reservoir as A Case Study)

2014 ◽  
Vol 7 (4) ◽  
pp. 132-143
Author(s):  
ABBAS M. ABD ◽  
SAAD SH. SAMMEN
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Correlation Coefficient ◽  
Mean Squared Error ◽  
Water Reservoir ◽  
Prediction Method ◽  
Training Data ◽  
Ann Model ◽  
Data Set ◽  
Artificial Neural

The prediction of different hydrological phenomenon (or system) plays an increasing role in the management of water resources. As engineers; it is required to predict the component of natural reservoirs’ inflow for numerous purposes. Resulting prediction techniques vary with the potential purpose, characteristics, and documented data. The best prediction method is of interest of experts to overcome the uncertainty, because the most hydrological parameters are subjected to the uncertainty. Artificial Neural Network (ANN) approach has adopted in this paper to predict Hemren reservoir inflow. Available data including monthly discharge supplied from DerbendiKhan reservoir and rain fall intensity falling on the intermediate catchment area between Hemren-DerbendiKhan dams were used.A Back Propagation (LMBP) algorithm (Levenberg-Marquardt) has been utilized to construct the ANN models. For the developed ANN model, different networks with different numbers of neurons and layers were evaluated. A total of 24 years of historical data for interval from 1980 to 2004 were used to train and test the networks. The optimum ANN network with 3 inputs, 40 neurons in both two hidden layers and one output was selected. Mean Squared Error (MSE) and the Correlation Coefficient (CC) were employed to evaluate the accuracy of the proposed model. The network was trained and converged at MSE = 0.027 by using training data subjected to early stopping approach. The network could forecast the testing data set with the accuracy of MSE = 0.031. Training and testing process showed the correlation coefficient of 0.97 and 0.77 respectively and this is refer to a high precision of that prediction technique.

Supply Air Temperature Prediction in an Air-Handling Unit Using Artificial Neural Network

2018 ◽  
Author(s):  
Nikita Sukthankar ◽  
Abhishek Walekar ◽  
Dereje Agonafer
Keyword(s):  
Neural Network ◽  
Fluid Dynamics ◽  
Computational Fluid Dynamics ◽  
Artificial Neural Network ◽  
Air Temperature ◽  
Data Center ◽  
Operating Conditions ◽  
Cfd Analysis ◽  
Ann Model ◽  
Air Handling Unit

Continuous provision of quality supply air to data center’s IT pod room is a key parameter in ensuring effective data center operation without any down time. Due to number of possible operating conditions and non-linear relations between operating parameters make the working mechanism of data center difficult to optimize energy use. At present industries are using computational fluid dynamics (CFD) to simulate thermal behaviour for all types of operating conditions. The focus of this study is to predict Supply Air Temperature using Artificial Neural Network (ANN) which can overcome limitations of CFD such as high cost, need of an expertise and large computation time. For developing ANN, input parameters, number of neurons and hidden layers, activation function and the period of training data set were studied. A commercial CFD software package 6sigma room is used to develop a modular data center consisting of an IT pod room and an air-handling unit. CFD analysis is carried out for different outside air conditions. Historical weather data of 1 year was considered as an input for CFD analysis. The ANN model is “trained” using data generated from these CFD results. The predictions of ANN model and the results of CFD analysis for a set of example scenarios were compared to measure the agreement between the two. The results show that the prediction of ANN model is much faster than full computational fluid dynamics simulations with good prediction accuracy. This demonstrates that ANN is an effective way for predicting the performance of an air handling unit.

scholarly journals Methodology for Computational Fluid Dynamic Validation for Medical Use: Application to Intracranial Aneurysm

2017 ◽  
Vol 139 (12) ◽  
Author(s):  
Nikhil Paliwal ◽  
Robert J. Damiano ◽  
Nicole A. Varble ◽  
Vincent M. Tutino ◽  
Zhongwang Dou ◽  
...  
Keyword(s):  
Flow Field ◽  
Intracranial Aneurysm ◽  
Cfd Simulation ◽  
Fluid Dynamic ◽  
Model Error ◽  
Patient Specific ◽  
Cfd Validation ◽  
Validation Data ◽  
Promising Tool ◽  
Simulation Results

Computational fluid dynamics (CFD) is a promising tool to aid in clinical diagnoses of cardiovascular diseases. However, it uses assumptions that simplify the complexities of the real cardiovascular flow. Due to high-stakes in the clinical setting, it is critical to calculate the effect of these assumptions in the CFD simulation results. However, existing CFD validation approaches do not quantify error in the simulation results due to the CFD solver’s modeling assumptions. Instead, they directly compare CFD simulation results against validation data. Thus, to quantify the accuracy of a CFD solver, we developed a validation methodology that calculates the CFD model error (arising from modeling assumptions). Our methodology identifies independent error sources in CFD and validation experiments, and calculates the model error by parsing out other sources of error inherent in simulation and experiments. To demonstrate the method, we simulated the flow field of a patient-specific intracranial aneurysm (IA) in the commercial CFD software star-ccm+. Particle image velocimetry (PIV) provided validation datasets for the flow field on two orthogonal planes. The average model error in the star-ccm+ solver was 5.63 ± 5.49% along the intersecting validation line of the orthogonal planes. Furthermore, we demonstrated that our validation method is superior to existing validation approaches by applying three representative existing validation techniques to our CFD and experimental dataset, and comparing the validation results. Our validation methodology offers a streamlined workflow to extract the “true” accuracy of a CFD solver.

Using Artificial Neural Network (ANN) for Manipulating Energy Gain of Nansulate Coating

2011 ◽  
Vol 2 (1) ◽  
Author(s):  
Hadi Salehi ◽  
Mosayyeb Amiri ◽  
Morteza Esfandyari
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Artificial Neural Network ◽  
Energy Gain ◽  
Operating Conditions ◽  
Maximum Relative Error ◽  
Ann Model ◽  
Wide Range ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

In this work, an extensive experimental data of Nansulate coating from NanoTechInc were applied to develop an artificial neural network (ANN) model. The Levenberg–Marquart algorithm has been used in network training to predict and calculate the energy gain and energy saving of Nansulate coating. By comparing the obtained results from ANN model with experimental data, it was observed that there is more qualitative and quantitative agreement between ANN model values and experimental data results. Furthermore, the developed ANN model shows more accurate prediction over a wide range of operating conditions. Also, maximum relative error of 3% was observed by comparison of experimental and ANN simulation results.

Modeling and Optimization of M-cresol Isopropylation for Obtaining N-thymol: Combining a Hybrid Artificial Neural Network with a Genetic Algorithm

2007 ◽  
Vol 5 (1) ◽  
Author(s):  
Yao Kouassi Benjamin ◽  
Emmanuel Assidjo Nogbou ◽  
Gossan Ado ◽  
Catherine Azzaro-Pantel ◽  
André Davin
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Artificial Neural Network ◽  
Operating Conditions ◽  
Molar Ratio ◽  
Ann Model ◽  
Sequential Method ◽  
Modeling And Optimization ◽  
Artificial Neural ◽  
Better Than

The application of a hybrid framework based on the combination, artificial neural network-genetic algorithm (ANN-GA), for n-thymol synthesis modeling and optimization has been developed. The effects of molar ratio propylene/cresol (X1), catalyst mass (X2) and temperature (X3) on n-thymol selectivity Y1 and m-cresol conversion Y2 were studied. A 3-8-2 ANN model was found to be very suitable for reaction modeling. The multiobjective optimization, led to optimal operating conditions (0.55 ? X1 ? 0.77; 1.773 g ? X2 ? 1.86 g; 289.74 °C ? X3 ? 291.33 °C) representing good solutions for obtaining high n-thymol selectivity and high m-cresol conversion. This optimal zone corresponded to n-thymol selectivity and m-cresol conversion ranging respectively in the interval [79.3; 79.5]% and [13.4 %; 23.7]%. These results were better than those obtained with a sequential method based on experimental design for which, optimum conditions led to n-thymol selectivity and m-cresol conversion values respectively equal to 67% and 11%. The hybrid method ANN-GA showed its ability to solve complex problems with a good fitting.

scholarly journals Analisis Perbedaan Mesh Pada Simulasi Boiler PLTGU Tanjung Priok Berbasis CFD

Jurnal METTEK ◽  
2020 ◽  
Vol 6 (1) ◽  
pp. 46
Author(s):  
I Nyoman Agus Adi Saputra ◽  
I Gusti Bagus Wijaya Kusuma ◽  
I Gusti Ngurah Priambadi
Keyword(s):  
Computational Fluid Dynamic ◽  
Cfd Simulation ◽  
Initial Conditions ◽  
Fluid Dynamic ◽  
Working Fluid ◽  
Process Stage ◽  
Convergence Study ◽  
Simulation Results ◽  
Gas Power Plant ◽  
Meshing Process

Penelitian Analisis Perbedaan Mesh berbasis Computational Fluid Dynamic (CFD) ini dilakukan Pada Boiler PLTGU Tanjung Priok. Boiler atau reboiler dalam sistem PLTGU dikategorikan sebagai alat penukar kalor karena perpindahan panasnya dilakukan tanpa kontak langsung antara media pemanas dengan media yang dipanaskan. Fluida kerja pada boiler PLTGU Tanjung Priok berupa gas methane dan air. Penelitian ini bertujuan melihat jumlah pembagian elemen terhadap hasil simulasi dengan menggunakan dua model Studi konvergensi grid yaitu dengan grid kasar, dan yang paling optimal melalui hasil simulasi CFD. Metode yang digunakan mulai dari mendesain geometri boiler sesuai kondisi di lapangan menginput initial conditions dan  boundry conditions. Data hasil penelitian yang sudah di lakukan pada simulasi boiler menunjukkan bahwa baik temperatur, tekanan dan kecepatan aliran memiliki nilai yang sama besar dan tidak di pengaruhi oleh pembagian elemen yang di lakukan pada saat proses meshing dari elemen yang paling kasar dengan jumlah total sebanyak 203.363 sampai pada tahap  proses meshing dengan elemen teroptimal yang berjumlah sebanyak 1.491.428 berdasarkan hal tersebut maka proses simulasi yang dilakukan menjadi lebih efisien karena proses perhitungan data dari elemen yang lebih sedikit mendapatkan hasil yang sama dengan elemen yang lebih banyak. The research on Mesh Difference Analysis based on Computational Fluid Dynamic (CFD) was conducted at Tanjung Priok PLTGU Boiler. Boilers or reboilers in PLTGU systems are categorized as heat exchangers because the heat transfer is done without direct contact between the heating media and the heated media. The working fluid in the Tanjung Priok gas power plant boiler is in the form of methane gas and water. This study aims to look at the number of elements divided against the simulation results by using two grid convergence study models, namely with a coarse grid, and the most optimal through CFD simulation results. The method used starts from designing the boiler geometry according to the field conditions, inputting initial conditions and boundry conditions. Data from research that has been done on boiler simulations shows that both temperature, pressure and flow velocity have the same value and are not affected by the division of elements carried out during the meshing process of the most coarse elements with a total number of 203.363 up to the meshing process stage with the optimum elements totaling 1,491,428 based on this, the simulation process carried out becomes more efficient because the process of calculating data from fewer elements gets the same results with more elements.

Management of an Industrial Facility Using an Artificial Neural Network Monitoring System

2007 ◽  
Author(s):  
Rory Hynes ◽  
Babak Seyedan
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Simulation Model ◽  
Direct Method ◽  
Load Capacity ◽  
Operating Conditions ◽  
Good Time ◽  
Ann Model ◽  
Computer Technique ◽  
Artificial Neural

The objective of this paper is to assess the optimum heat load capacity of a real CHP plant and provide recommendations to improve heat utilization and reduce costs using a computerized system. A simulation model based on component actual behaviour has been developed. The simulation model is capable of plant optimization that could lead to significant economic and energy consumption improvements. The general modular structural of the plant component is described together with a discussion of the results and cost analysis. In the second part, feasibility of the Artificial Neural Network (ANN) approach is evaluated. The data from the simulation model of the plant is used to train such an ANN model. Results from the conventional computer technique are compared with that of the direct method based ANN approach. The results indicate it is feasible to use ANN to predict plant-operating conditions. The ANN gives a good time response and performance prediction capability with change of boundary conditions. Significantly shorter computation time is obtained with the ANN compared to the physical model. The accuracy of the ANN output and its suitability for on-line monitoring of a CHP plant are discussed.

scholarly journals Combinatory Finite Element and Artificial Neural Network Model for Predicting Performance of Thermoelectric Generator

Energies ◽  
2018 ◽  
Vol 11 (9) ◽  
pp. 2216 ◽  
Author(s):  
Ravi Kishore ◽  
Roop Mahajan ◽  
Shashank Priya
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Electrical Energy ◽  
Optimization Techniques ◽  
Operating Conditions ◽  
Ann Model ◽  
Predicting Performance ◽  
Ann Models ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Thermoelectric generators (TEGs) are rapidly becoming the mainstream technology for converting thermal energy into electrical energy. The rise in the continuous deployment of TEGs is related to advancements in materials, figure of merit, and methods for module manufacturing. However, rapid optimization techniques for TEGs have not kept pace with these advancements, which presents a challenge regarding tailoring the device architecture for varying operating conditions. Here, we address this challenge by providing artificial neural network (ANN) models that can predict TEG performance on demand. Out of the several ANN models considered for TEGs, the most efficient one consists of two hidden layers with six neurons in each layer. The model predicted TEG power with an accuracy of ±0.1 W, and TEG efficiency with an accuracy of ±0.2%. The trained ANN model required only 26.4 ms per data point for predicting TEG performance against the 6.0 minutes needed for the traditional numerical simulations.

Sign in / Sign up

Export Citation Format

Share Document