Mass air flow control of common-rail diesel engines using an artificial neural network

2012 ◽  
Vol 227 (3) ◽  
pp. 299-310 ◽  
Author(s):  
Byounggul Oh ◽  
Minkwang Lee ◽  
Yeongseop Park ◽  
Jongseob Won ◽  
Myoungho Sunwoo
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Flow Control ◽  
Diesel Engines ◽  
Air Flow ◽  
Common Rail ◽  
Artificial Neural ◽  
Air Flow Control

scholarly journals Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control

2019 ◽  
Vol 865 ◽  
pp. 281-302 ◽  
Author(s):  
Jean Rabault ◽  
Miroslav Kuchta ◽  
Atle Jensen ◽  
Ulysse Réglade ◽  
Nicolas Cerardi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Reinforcement Learning ◽  
Flow Control ◽  
Mass Flow ◽  
Active Flow Control ◽  
Flow Rates ◽  
Mass Flow Rates ◽  
Artificial Neural ◽  
Active Flow

We present the first application of an artificial neural network trained through a deep reinforcement learning agent to perform active flow control. It is shown that, in a two-dimensional simulation of the Kármán vortex street at moderate Reynolds number ($Re=100$), our artificial neural network is able to learn an active control strategy from experimenting with the mass flow rates of two jets on the sides of a cylinder. By interacting with the unsteady wake, the artificial neural network successfully stabilizes the vortex alley and reduces drag by approximately 8 %. This is performed while using small mass flow rates for the actuation, of the order of 0.5 % of the mass flow rate intersecting the cylinder cross-section once a new pseudo-periodic shedding regime is found. This opens the way to a new class of methods for performing active flow control.

Application of Artificial Neural Network for Modeling of Mechanical Cooling Tower

2011 ◽  
Vol 383-390 ◽  
pp. 7746-7749 ◽  
Author(s):  
Wei Shun Huang ◽  
Ching Wei Chen ◽  
Cheng Wen Lee ◽  
Ching Liang Chen ◽  
Tien Shuen Jan ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Water Flow ◽  
Cooling Tower ◽  
Air Flow ◽  
Cooling Water ◽  
Computation Method ◽  
Cooling Load ◽  
Artificial Neural ◽  
Tower Model

The objective of the study is to focus on the application of the artificial neural network to configure a heat-radiating model for cooling towers within the parameters of fluctuating in air flow or cooling water flow. To achieve the objective, a cooling tower heat balancing equation have been used to instill the correlations between a cooling tower cooling load to the four predefined parameters. Based on the premise established, the parameters of a cooling tower’s air flow and cooling water flow in a modulated process are utilized in an experimental system for collecting relevant operating data. Lastly, the artificial neural network tool derived from the Matlab software is utilized to define the input parameters being – the cooling water temperature, ambient web-bulb temperature, cooling tower air flow, and cooling water flow, with an objective set to instilling a cooling tower model for defining a cooling tower cooling load. In addition, the tested figures are compared to the simulated figures for verifying the cooling tower model. By utilizing the method derived from the model, the mean error of between 0.72 and 2.13% is obtained, with R2 value rated at between 0.97 and 0.99. The experiment findings show a relatively high reliability that can be achieved for configuring a model by using the artificial neural network. With the support of an optimized computation method, the model can be applied as an optimization operating strategy for an air-conditioning system’s cooling water loop.

Sign in / Sign up

Export Citation Format

Share Document