scholarly journals ANN-Based Stop Criteria for a Genetic Algorithm Applied to Air Impingement Design

Energies ◽  
2019 ◽  
Vol 13 (1) ◽  
pp. 16
Author(s):  
Ander Sánchez-Chica ◽  
Ekaitz Zulueta ◽  
Daniel Teso-Fz-Betoño ◽  
Pablo Martínez-Filgueira ◽  
Unai Fernandez-Gamiz
Keyword(s):  
Genetic Algorithm ◽  
Jet Impingement ◽  
Optimization Process ◽  
Second Step ◽  
Flower Pollination Algorithm ◽  
Training Process ◽  
Air Jet ◽  
Stop Criterion ◽  
Air Impingement ◽  
The Cost

Artificial Neural Networks (ANNs) have proven to be a powerful tool in many fields of knowledge. At the same time, evolutionary algorithms show a very efficient technique in optimization tasks. Historically, ANNs are used in the training process of supervising networks by decreasing the error between the output and the target. However, we propose another approach in order to improve these two techniques together. The ANN is trained with the points obtained during an optimization process by a genetic algorithm and a flower pollination algorithm. The performance of this ANN is used as a stop criterion for the optimization process. This new configuration aims to reduce the number of iterations executed by the genetic optimizer when learning the cost function by an ANN. As a first step, this approach is tested with eight benchmark functions. As a second step, the authors apply it to an air jet impingement design process, optimizing the surface temperature and the fan efficiency. Finally, a comparison between the results of a regular optimization and the results obtained in the present study is presented.

scholarly journals Air jet impingement to reduce hot strip wave on a run-out table

2018 ◽  
Vol 19 (6) ◽  
pp. 601 ◽  
Author(s):  
Young Yun Woo ◽  
Sang Wook Han ◽  
Jin Rae Cho ◽  
Young Hoon Moon
Keyword(s):  
Jet Impingement ◽  
Pilot Scale ◽  
Process Efficiency ◽  
Rolled Strip ◽  
Pressure Distributions ◽  
Air Jet ◽  
Hot Strip ◽  
Air Impingement ◽  
Moving Strip ◽  
Moving Direction

Traveling stability is necessary for a hot rolled strip on a run-out table before coiling in steel mills because it affects the process efficiency and the quality of the rolled products. This study proposes an air jet impingement system to reduce the hot strip wave that occurs during tensionless travel in a run-out table before the top end of the strip reaches the coiler mandrel. The finite element method was used to examine the pressure distributions on the moving strip associated with the parameters in the air jet systems. Experiments were carried out on a pilot-scale air jet impingement system to investigate the performance. The results show that the air impingement in the moving direction effectively reduces the strip wave, and the simulated results agree with the actual measurements and observations.

scholarly journals Experimental Air Impingement Crossflow Comparison and Theoretical Application to Photovoltaic Efficiency Improvement

2020 ◽  
Vol 12 (14) ◽  
pp. 5577
Author(s):  
Pablo Martínez-Filgueira ◽  
Ekaitz Zulueta ◽  
Ander Sánchez-Chica ◽  
Gustavo García ◽  
Unai Fernandez-Gamiz ◽  
...  
Keyword(s):  
Jet Impingement ◽  
Photovoltaic Cell ◽  
High Heat ◽  
Experimental Comparison ◽  
Back Surface ◽  
Rate System ◽  
Air Jet ◽  
High Heat Transfer ◽  
Solar Energy Harvesting ◽  
Air Impingement

The photovoltaic cell temperature is a key factor in solar energy harvesting. Solar radiation raises temperature on the cell, lowering its peak efficiency. Air jet impingement is a high heat transfer rate system and has been previously used to cool the back surface of photovoltaic modules and cells. In this work, an experimental comparison of the cooling performance of two different air jet impingement crossflow schemes was performed. Crossflow is defined as the air mass interacting with a certain jet modifying its movement. This leads to a change in its heat exchange capabilities and is related with the inlet-outlet arrangement of the fluid. In this work, zero and minimum crossflow schemes were compared. The main contribution of this work considered the consumption of the flow supplying devices to determine the most suitable system. The best configuration increased the net power output of the cell by 6.60%. These results show that air impingement cooling can play a role in increasing photovoltaic profitability. In terms of uniformity, on small impingement plates with a low number of nozzles, the advantages expected from the zero crossflow configuration did not stand out.

scholarly journals Inclusion of Hydraulic Controls in Rehabilitation Models of Drainage Networks to Control Floods

Water ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 514
Author(s):  
Leonardo Bayas-Jiménez ◽  
F. Javier Martínez-Solano ◽  
Pedro L. Iglesias-Rey ◽  
Daniel Mora-Melia ◽  
Vicente S. Fuertes-Miquel
Keyword(s):  
Genetic Algorithm ◽  
Drainage System ◽  
Optimal Solution ◽  
Hydraulic Control ◽  
Drainage Systems ◽  
Storm Water Management Model ◽  
Drainage Networks ◽  
Extreme Rain ◽  
Rain Events ◽  
The Cost

A problem for drainage systems managers is the increase in extreme rain events that are increasing in various parts of the world. Their occurrence produces hydraulic overload in the drainage system and consequently floods. Adapting the existing infrastructure to be able to receive extreme rains without generating consequences for cities’ inhabitants has become a necessity. This research shows a new way to improve drainage systems with minimal investment costs, using for this purpose a novel methodology that considers the inclusion of hydraulic control elements in the network, the installation of storm tanks and the replacement of pipes. The presented methodology uses the Storm Water Management Model for the hydraulic analysis of the network and a modified Genetic Algorithm to optimize the network. In this algorithm, called the Pseudo-Genetic Algorithm, the coding of the chromosomes is integral and has been used in previous studies of hydraulic optimization. This work evaluates the cost of the required infrastructure and the damage caused by floods to find the optimal solution. The main conclusion of this study is that the inclusion of hydraulic controls can reduce the cost of network rehabilitation and decrease flood levels.

Heat transfer of multi-slot nozzle air jet impingement with different Reynolds number

2020 ◽  
pp. 116470
Author(s):  
Jinqi Zhu ◽  
Ruifeng Dou ◽  
Ye Hu ◽  
Shixing Zhang ◽  
Xuyun Wang
Keyword(s):  
Heat Transfer ◽  
Reynolds Number ◽  
Jet Impingement ◽  
Slot Nozzle ◽  
Air Jet

scholarly journals Carbon Emission Reduction of Apparel Material Distribution Based on Multi-Objective Genetic Algorithm (NSGA-II)

2019 ◽  
Vol 11 (9) ◽  
pp. 2571
Author(s):  
Xujing Zhang ◽  
Lichuan Wang ◽  
Yan Chen
Keyword(s):  
Genetic Algorithm ◽  
Carbon Emissions ◽  
Optimal Solution ◽  
Material Distribution ◽  
Low Carbon ◽  
Nsga Ii ◽  
Management Objectives ◽  
Multi Objective Genetic Algorithm ◽  
Distribution Process ◽  
The Cost

Low-carbon production has become one of the top management objectives for every industry. In garment manufacturing, the material distribution process always generates high carbon emissions. In order to reduce carbon emissions and the number of operators to meet enterprises’ requirements to control the cost of production and protect the environment, the paths of material distribution were analyzed to find the optimal solution. In this paper, the model of material distribution to obtain minimum carbon emissions and vehicles (operators) was established to optimize the multi-target management in three different production lines (multi-line, U-shape two-line, and U-shape three-line), while the workstations were organized in three ways: in the order of processes, in the type of machines, and in the components of garment. The NSGA-II algorithm (non-dominated sorting genetic algorithm-II) was applied to obtain the results of this model. The feasibility of the model and algorithm was verified by the practice of men’s shirts manufacture. It could be found that material distribution of multi-line layout produced the least carbon emissions when the machines were arranged in the group of type.

Experimental Measurements of the Flow and Heat Transfer of a Square Jet Impinging on an Array of Square Pin Fins

2002 ◽  
Author(s):  
Johnny S. Issa ◽  
Alfonso Ortega
Keyword(s):  
Heat Transfer ◽  
Thermal Resistance ◽  
Flow Behavior ◽  
Jet Impingement ◽  
Tip Clearance ◽  
Heat Sinks ◽  
Clearance Ratio ◽  
Cross Sectional ◽  
Pressure Loss Coefficient ◽  
Air Jet

An experimental investigation was conducted to explore the flow behavior, pressure drop, and heat transfer due to free air jet impingement on square in-line pin fin heat sinks (PFHS) mounted on a plane horizontal surface. A parametrically consistent set of aluminum heat sinks with fixed base dimension of 25 × 25 mm was used, with pin heights varying between 12.5 mm and 22.5 mm, and fin thickness between 1.5 mm and 2.5 mm. A 6:1 contracting nozzle having a square outlet cross sectional area of 25 × 25 mm was used to blow air at ambient temperature on the top of the heat sinks with velocities varying from 2 to 20 m/s. The ratio of the gap between the jet exit and the pin tips to the pin height, the so-called tip clearance ratio, was varied from 0 (no tip clearance) to 1. The stagnation pressure recovered at the center of the heat sink was higher for tall pins than short pins. The pressure loss coefficient showed a little dependence on Re, increased with increasing pin density, and pin diameter, and decreased with increasing pin height and clearance ratio. The overall base-to-ambient thermal resistance decreased with increasing Re number, pin density and pin diameter. Surprisingly, the dependence of the thermal resistance on the pin height and clearance ratio was shown to be mild at low Re, and to vanish at high Re number.

Experimental Studies on Cooling Effectiveness of the Double-Decker Air Jet Impingement With Film Outflow

2007 ◽  
Author(s):  
Junkui Mao ◽  
Wen Guo ◽  
Zhenxiong Liu ◽  
Jun Zeng
Keyword(s):  
Infrared Radiation ◽  
Experimental Studies ◽  
Jet Impingement ◽  
Experimental Results ◽  
Thermal Camera ◽  
Local Cooling ◽  
Cooling Effectiveness ◽  
Air Jet ◽  
Double Decker ◽  
Wide Range

Experiments were carried out to investigate the cooling effectiveness of a lamellar double-decker impingement/effusion structure. Infrared radiation (I.R.) thermal camera was used to measure the temperature on the outside surface of the lamellar double-decker. Experimental results were obtained for a wide range of governing parameters (blowing rate M (0.0017∼0.0066), the ratio of the jet impingement distance to the diameter of film hole H/D (0.5∼1.25), the ratio of the distance between the jet hole and film hole to the diameter of the film hole P/D (0, 3, 4), and the material of double-decker (Steel and Copper)). It was observed that the local cooling effectiveness η varies with all these parameters in a complicated way. All the results show that higher cooling effectiveness η is achieved in larger blowing rate cases. A certain range of H/D and P/D can be designed to result in the maximum cooling effectiveness η. And η is less sensitive to the material type compared with those parameters such as H/D, M and P/D.

scholarly journals A Heuristics-Based Parthenogenetic Algorithm for the VRP with Potential Demands and Time Windows

2016 ◽  
Vol 2016 ◽  
pp. 1-12
Author(s):  
Chenghua Shi ◽  
Tonglei Li ◽  
Yu Bai ◽  
Fei Zhao
Keyword(s):  
Genetic Algorithm ◽  
Time Windows ◽  
Computation Time ◽  
Routing Problem ◽  
Split Delivery ◽  
Soft Time Windows ◽  
Comparison Results ◽  
Potential Demand ◽  
The Cost

We present the vehicle routing problem with potential demands and time windows (VRP-PDTW), which is a variation of the classical VRP. A homogenous fleet of vehicles originated in a central depot serves customers with soft time windows and deliveries from/to their locations, and split delivery is considered. Also, besides the initial demand in the order contract, the potential demand caused by conformity consuming behavior is also integrated and modeled in our problem. The objective of minimizing the cost traveled by the vehicles and penalized cost due to violating time windows is then constructed. We propose a heuristics-based parthenogenetic algorithm (HPGA) for successfully solving optimal solutions to the problem, in which heuristics is introduced to generate the initial solution. Computational experiments are reported for instances and the proposed algorithm is compared with genetic algorithm (GA) and heuristics-based genetic algorithm (HGA) from the literature. The comparison results show that our algorithm is quite competitive by considering the quality of solutions and computation time.

A Hybrid Method Based on Semi-Supervised Learning for Relation Extraction in Chinese EMRs (Preprint)

2021 ◽  
Author(s):  
ChunMing Yang
Keyword(s):  
Supervised Learning ◽  
Learning Algorithm ◽  
Medical Knowledge ◽  
Relation Extraction ◽  
Small Scale ◽  
Semantic Features ◽  
Training Process ◽  
Network Layers ◽  
Relation Prediction ◽  
The Cost

BACKGROUND Extracting relations between the entities from Chinese electronic medical records(EMRs) is the key to automatically constructing medical knowledge graphs. Due to the less available labeled corpus, most of the current researches are based on shallow networks, which cannot fully capture the complex semantic features in the text of Chinese EMRs. OBJECTIVE In this study, a hybrid deep learning method based on semi-supervised learning is proposed to extract the entity relations from small-scale complex Chinese EMRs. METHODS The semantic features of sentences are extracted by residual network (ResNet) and the long dependent information is captured by bidirectional GRU (Gated Recurrent Unit). Then the attention mechanism is used to assign weights to the extracted features respectively, and the output of the two attention mechanisms is integrated for relation prediction. We adjusted the training process with manually annotated small-scale relational corpus and bootstrapping semi-supervised learning algorithm, and continuously expanded the datasets during the training process. RESULTS The experimental results show that the best F1-score of the proposed method on the overall relation categories reaches 89.78%, which is 13.07% higher than the baseline CNN model. The F1-score on DAP, SAP, SNAP, TeRD, TeAP, TeCP, TeRS, TeAS, TrAD, TrRD and TrAP 11 relation categories reaches 80.95%, 93.91%, 92.96%, 88.43%, 86.54%, 85.58%, 87.96%, 94.74%, 93.01%, 87.58% and 95.48%, respectively. CONCLUSIONS The hybrid neural network method strengthens the feature transfer and reuse between different network layers and reduces the cost of manual tagging relations. The results demonstrate that our proposed method is effective for the relation extraction in Chinese EMRs.

Sign in / Sign up

Export Citation Format

Share Document