Multivariate Prediction of Airflow and Temperature Distributions Using Artificial Neural Networks

2011 ◽  
Author(s):  
Zhihang Song ◽  
Bruce T. Murray ◽  
Bahgat Sammakia
Keyword(s):  
Real Time ◽  
Thermal Management ◽  
Data Centers ◽  
Design Tool ◽  
Operating Conditions ◽  
Ann Model ◽  
Predictive Tool ◽  
Temperature Distributions ◽  
Design Variables ◽  
Artificial Neural

Thermal Management optimization for data centers, including prediction of airflow and temperature distributions, is generally an extremely time-consuming process using full-scale CFD analysis. Reduced order models are necessary in order to provide real-time assessment of cooling requirements for data centers. The use of a simulation-based Artificial Neural Network (ANN) is being investigated as a predictive tool. A model for a basic hot aisle/cold aisle data center configuration was built and analyzed using the commercial software FloTHERM. The flow field and temperature distributions were obtained for 100 representative sets of operating conditions using the CFD package. The Latin Hypercube Sampling technique was employed to select values for three design variables: plenum height, percentage open area of the perforated tiles and air leakage fraction. The FloTHERM results were used to generate a database for the ANN training. The CFD results from 85 cases were used for training and 16 cases were used for validation. A multivariate mapping between the input design variables and output variables (individual tile flow rates and maximum rack temperatures) was obtained. Good agreement (0.5% average relative error) was obtained between the ANN model predictions and the CFD results. These preliminary results are promising and show that an ANN based model may yield an effective real-time thermal management design tool for data centers.

scholarly journals Modeling Fused Filament Fabrication using Artificial Neural Networks

2021 ◽  
Author(s):  
Paul Oehlmann ◽  
Paul Osswald ◽  
Juan Camilo Blanco ◽  
Martin Friedrich ◽  
Dominik Rietzel ◽  
...  
Keyword(s):  
Real Time ◽  
Large Scale ◽  
Cost Effective ◽  
Print Quality ◽  
Ann Model ◽  
Production Environment ◽  
Fused Filament Fabrication ◽  
Artificial Neural ◽  
Using Data ◽  
Artificial Neural Network Ann

AbstractWith industries pushing towards digitalized production, adaption to expectations and increasing requirements for modern applications, has brought additive manufacturing (AM) to the forefront of Industry 4.0. In fact, AM is a main accelerator for digital production with its possibilities in structural design, such as topology optimization, production flexibility, customization, product development, to name a few. Fused Filament Fabrication (FFF) is a widespread and practical tool for rapid prototyping that also demonstrates the importance of AM technologies through its accessibility to the general public by creating cost effective desktop solutions. An increasing integration of systems in an intelligent production environment also enables the generation of large-scale data to be used for process monitoring and process control. Deep learning as a form of artificial intelligence (AI) and more specifically, a method of machine learning (ML) is ideal for handling big data. This study uses a trained artificial neural network (ANN) model as a digital shadow to predict the force within the nozzle of an FFF printer using filament speed and nozzle temperatures as input data. After the ANN model was tested using data from a theoretical model it was implemented to predict the behavior using real-time printer data. For this purpose, an FFF printer was equipped with sensors that collect real time printer data during the printing process. The ANN model reflected the kinematics of melting and flow predicted by models currently available for various speeds of printing. The model allows for a deeper understanding of the influencing process parameters which ultimately results in the determination of the optimum combination of process speed and print quality.

Prediction of Hot Aisle Partition Airflow Boundary Conditions

2013 ◽  
Author(s):  
Zhihang Song ◽  
Bruce T. Murray ◽  
Bahgat Sammakia
Keyword(s):  
Boundary Conditions ◽  
Data Center ◽  
Computation Time ◽  
Design Tool ◽  
Operating Conditions ◽  
Ann Model ◽  
Flow Rates ◽  
Level Model ◽  
Optimization Methodology ◽  
Artificial Neural Network Ann

The integration of a simulation-based Artificial Neural Network (ANN) with a Genetic Algorithm (GA) has been explored as a real-time design tool for data center thermal management. The computation time for the ANN-GA approach is significantly smaller compared to a fully CFD-based optimization methodology for predicting data center operating conditions. However, difficulties remain when applying the ANN model for predicting operating conditions for configurations outside of the geometry used for the training set. One potential remedy is to partition the room layout into a finite number of characteristic zones, for which the ANN-GA model readily applies. Here, a multiple hot aisle/cold aisle data center configuration was analyzed using the commercial software FloTHERM. The CFD results are used to characterize the flow rates at the inter-zonal partitions. Based on specific reduced subsets of desired treatment quantities from the CFD results, such as CRAC and server rack air flow rates, the approach was applied for two different CRAC configurations and various levels of CRAC and server rack flow rates. Utilizing the compact inter-zonal boundary conditions, good agreement for the airflow and temperature distributions is achieved between predictions from the CFD computations for the entire room configuration and the reduced order zone-level model for different operating conditions and room layouts.

scholarly journals An artificial neural network model for rainfall forecasting in Bangkok, Thailand

2009 ◽  
Vol 13 (8) ◽  
pp. 1413-1425 ◽  
Author(s):  
N. Q. Hung ◽  
M. S. Babel ◽  
S. Weesakul ◽  
N. K. Tripathi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Real Time ◽  
Input Parameter ◽  
Rain Gauge ◽  
Ann Model ◽  
Rainfall Forecasting ◽  
Forecast Performance ◽  
Hourly Data ◽  
Artificial Neural

Abstract. This paper presents a new approach using an Artificial Neural Network technique to improve rainfall forecast performance. A real world case study was set up in Bangkok; 4 years of hourly data from 75 rain gauge stations in the area were used to develop the ANN model. The developed ANN model is being applied for real time rainfall forecasting and flood management in Bangkok, Thailand. Aimed at providing forecasts in a near real time schedule, different network types were tested with different kinds of input information. Preliminary tests showed that a generalized feedforward ANN model using hyperbolic tangent transfer function achieved the best generalization of rainfall. Especially, the use of a combination of meteorological parameters (relative humidity, air pressure, wet bulb temperature and cloudiness), the rainfall at the point of forecasting and rainfall at the surrounding stations, as an input data, advanced ANN model to apply with continuous data containing rainy and non-rainy period, allowed model to issue forecast at any moment. Additionally, forecasts by ANN model were compared to the convenient approach namely simple persistent method. Results show that ANN forecasts have superiority over the ones obtained by the persistent model. Rainfall forecasts for Bangkok from 1 to 3 h ahead were highly satisfactory. Sensitivity analysis indicated that the most important input parameter besides rainfall itself is the wet bulb temperature in forecasting rainfall.

Modeling of surface temperature distributions on powered e-textile structures using an artificial neural network

2017 ◽  
Vol 89 (3) ◽  
pp. 311-321 ◽  
Author(s):  
Senem Kursun Bahadir ◽  
Umut Kivanc Sahin ◽  
Alper Kiraz
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Surface Temperature ◽  
Electric Power ◽  
Cold Weather ◽  
Sample Type ◽  
Ann Model ◽  
Temperature Distributions ◽  
Different Types ◽  
Artificial Neural

An artificial neural network (ANN) model is constructed to derive the surface temperature of e-textile structures developed for cold weather clothing. A series of textile transmission lines made of different types of conductive yarns, insulated by using different types of seam tapes, were enclosed in a thermoplastic textile structure via hot air welding technology, and then they were powered with different levels of specific voltages in order to obtain different heating levels. The surface temperatures of the powered e-textile structures were measured using a thermal camera. The experimental input variables, sample type, temperature, feeding speed, resistance of samples, applied voltage and current were used to construct an ANN model and the outputs of surface temperature and electric power dissipated were used to test the prediction performance of the developed model. It was concluded that the ANN provided substantial predictive performance. Simulations based on the developed ANN model can estimate the surface temperature distributions of powered e-textile structures under different conditions. The ANN model developed for prediction of electric power dissipated was very successful and can be useful for e-textile product designers as well as textile manufacturers, particularly for cold weather protection products such as jackets, gloves and outdoor sleeping mats.

scholarly journals Real-time temperature calculation and temperature prediction of wet multi-plate clutches

2021 ◽  
Author(s):  
D. Groetsch ◽  
K. Voelkel ◽  
H. Pflaum ◽  
K. Stahl
Keyword(s):  
Real Time ◽  
Operation Mode ◽  
Time Estimation ◽  
Design Tool ◽  
Operating Conditions ◽  
Temperature Prediction ◽  
Temperature Calculation ◽  
Component Design ◽  
Component Test ◽  
Real Time Estimation

AbstractMany applications of wet multi-plate clutches are within safety-critical areas since malfunction or failure of the clutch is often equivalent to “loss of drive”.The main criterion for the estimation of damage and endurance of wet multi-plate clutches is the temperature on the friction interface. Owing to the thin, rotating geometry of the plates, determination of relevant temperatures in operation mode is almost impossible. State of the art is that there is no general applicable model for real-time estimation of clutch temperatures during operation.This contribution presents a validated parametric real-time temperature model that is applicable to various use cases and operating conditions. The model enables the calculation of the actual clutch temperature during operation and the prediction of temperature for future shifting operations.The model is validated by comparing temperature measurements from a component test rig and from the KUPSIM thermal clutch design tool with the developed real-time temperature calculation. The validity of the model for serial parts from industry and automotive applications under various load cases (clutch mode, continuous slip, non-steady slip) is demonstrated. The deviation between measurement and calculation are typically very small (< 5 K). The temperature prediction allows a highly accurate (deviations typically < 5 K) conservative prediction of the thermal load for future shifting operations.The model can thus contribute to the increase of operational safety of wet multi-plate clutches while at the same time facilitating optimal component design by reducing thermal over-dimensioning of clutches.

Rapid Calculation of the Pressures and Clearances in Rough, Elastohydrodynamically Lubricated Contacts Under Pure Rolling. Part 1: Low Amplitude, Sinusoidal Roughness

2006 ◽  
Vol 220 (6) ◽  
pp. 901-913 ◽  
Author(s):  
C J Hooke ◽  
K Y Li
Keyword(s):  
Surface Roughness ◽  
Real Time ◽  
Design Process ◽  
Design Tool ◽  
Operating Conditions ◽  
Lubricated Contacts ◽  
Pure Rolling ◽  
Rapid Calculation ◽  
Low Amplitude ◽  
Insight Into

Modern elastohydrodynamically lubricated (EHL) solvers allow the calculation of the pressures and clearances in rough EHL contacts. However, the process is time consuming and the results give little insight into the physical behaviour of the system. The length of calculation also makes these methods unsuitable for use as a design tool. The investigation of the behaviour of low amplitude, sinusoidal roughness in EHL contacts provides greater understanding of the processes involved. The results also allow the effects of surface roughness to be examined rapidly. This suggests that it may be possible to develop the approach and create a ‘real-time’ design process for the analysis of different surface roughnesses under a range of operating conditions.

scholarly journals Transient Temperature Distributions on Lithium-Ion Polymer SLI Battery

Vehicles ◽  
2019 ◽  
Vol 1 (1) ◽  
pp. 127-137 ◽  
Author(s):  
Yiqun Liu ◽  
Y. Gene Liao ◽  
Ming-Chia Lai
Keyword(s):  
Thermal Management ◽  
Thermal Model ◽  
Operating Temperature ◽  
Lithium Ion ◽  
Operating Conditions ◽  
Battery Pack ◽  
Transient Temperature ◽  
Temperature Distributions ◽  
Lithium Ion Polymer Battery ◽  
Polymer Battery

Lithium-ion polymer batteries currently are the most popular vehicle onboard electric energy storage systems ranging from the 12 V/24 V starting, lighting, and ignition (SLI) battery to the high-voltage traction battery pack in hybrid and electric vehicles. The operating temperature has a significant impact on the performance, safety, and cycle lifetime of lithium-ion batteries. It is essential to quantify the heat generation and temperature distribution of a battery cell, module, and pack during different operating conditions. In this paper, the transient temperature distributions across a battery module consisting of four series-connected lithium-ion polymer battery cells are measured under various charging and discharging currents. A battery thermal model, correlated with the experimental data, is built in the module-level in the ANSYS/Fluent platform. This validated module thermal model is then extended to a pack thermal model which contains four parallel-connected modules. The temperature distributions on the battery pack model are simulated under 40 A, 60 A, and 80 A constant discharge currents. An air-cool thermal management system is integrated with the battery pack model to ensure the operating temperature and temperature gradient within the optimal range. This paper could provide thermal management design guideline for the lithium-ion polymer battery pack.

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.

Development of Bolted Flange Design Tool Based on Artificial Neural Network

2019 ◽  
Vol 141 (5) ◽  
Author(s):  
Alper Yıldırım ◽  
Ahmet Arda Akay ◽  
Hasan Gülaşık ◽  
Demirkan Çoker ◽  
Ercan Gürses ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Finite Element ◽  
Design Tool ◽  
Finite Element Analyses ◽  
Element Analysis ◽  
Flange Connection ◽  
Design Variables ◽  
Artificial Neural ◽  
Bolted Flange

Finite element analysis (FEA) of bolted flange connections is the common methodology for the analysis of bolted flange connections. However, it requires high computational power for model preparation and nonlinear analysis due to contact definitions used between the mating parts. Design of an optimum bolted flange connection requires many costly finite element analyses to be performed to decide on the optimum bolt configuration and minimum flange and casing thicknesses. In this study, very fast responding and accurate artificial neural network-based bolted flange design tool is developed. Artificial neural network is established using the database which is generated by the results of more than 10,000 nonlinear finite element analyses of the bolted flange connection of a typical aircraft engine. The FEA database is created by taking permutations of the parametric geometric design variables of the bolted flange connection and input load parameters. In order to decrease the number of FEA points, the significance of each design variable is evaluated by performing a parameter correlation study beforehand, and the number of design points between the lower and upper and bounds of the design variables is decided accordingly. The prediction of the artificial neural network based design tool is then compared with the FEA results. The results show excellent agreement between the artificial neural network-based design tool and the nonlinear FEA results within the training limits of the artificial neural network.

Sign in / Sign up

Export Citation Format

Share Document