scholarly journals Layout Optimization of Two Autonomous Underwater Vehicles for Drag Reduction with a Combined CFD and Neural Network Method

Complexity ◽  
2017 ◽  
Vol 2017 ◽  
pp. 1-15 ◽  
Author(s):  
Wenlong Tian ◽  
Zhaoyong Mao ◽  
Fuliang Zhao ◽  
Zhicao Zhao
Keyword(s):  
Neural Network ◽  
Autonomous Underwater Vehicles ◽  
Back Propagation ◽  
Three Dimensional ◽  
Optimization Method ◽  
Back Propagation Neural Network ◽  
Underwater Vehicles ◽  
Minimum Drag ◽  
Computational Fluid Dynamics Cfd ◽  
The Relationship

This paper presents an optimization method for the design of the layout of an autonomous underwater vehicles (AUV) fleet to minimize the drag force. The layout of the AUV fleet is defined by two nondimensional parameters. Firstly, three-dimensional computational fluid dynamics (CFD) simulations are performed on the fleets with different layout parameters and detailed information on the hydrodynamic forces and flow structures around the AUVs is obtained. Then, based on the CFD data, a back-propagation neural network (BPNN) method is used to describe the relationship between the layout parameters and the drag of the fleet. Finally, a genetic algorithm (GA) is chosen to obtain the optimal layout parameters which correspond to the minimum drag. The optimization results show that (1) the total drag of the AUV fleet can be reduced by 12% when the follower AUV is located directly behind the leader AUV and (2) the drag of the follower AUV can be reduced by 66% when it is by the side of the leader AUV.

scholarly journals Layout Effect of Two Autonomous Underwater Vehicles on the Hydrodynamics Performances

2020 ◽  
Vol 19 ◽  
Keyword(s):  
Fluid Dynamics ◽  
Computational Fluid Dynamics ◽  
Autonomous Underwater Vehicles ◽  
Three Dimensional ◽  
Pressure Change ◽  
Underwater Vehicles ◽  
Optimal Layout ◽  
Minimum Drag ◽  
Computational Fluid Dynamics Cfd ◽  
Two Parameters

Three-dimensional computational fluid dynamics (CFD) is used for the design optimization of the layout of an autonomous underwater vehicles (AUV) containing three torpedo-shaped hulls. The AUV layout is defined by two parameters a and b present the stance following YY and XX respectively. several simulations are carried on the AUV with different positions of the torpedo in order to define the optimal layout which designates the minimum drag. the numerical results approve that the variation in the drag coefficient of the AUV is the to the interaction of the flow rate and the pressure change between the both hulls. in addition, an optimal layout for the minimum AUV drag with two torpedoes is found which provides a drag reduce of about 11.4% lower than a single UV with a single torpedo.

Optimization of the Hot Pressing Parameters of Nanocomposite Ceramic Tool and Die Materials: I. with BP Neural Network Method

2010 ◽  
Vol 154-155 ◽  
pp. 1114-1118
Author(s):  
Jing Jie Zhang ◽  
Chong Hai Xu ◽  
Ming Dong Yi ◽  
Hui Fa Zhang ◽  
Xing Hai Wang
Keyword(s):  
Neural Network ◽  
Hot Pressing ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Ceramic Tool ◽  
Network Method ◽  
Die Materials ◽  
Die Material ◽  
Set Up ◽  
The Relationship

In this paper, back propagation neural network was used in the optimum design of the hot pressing parameters of an advanced ZrO2/TiB2/Al2O3 nanocomposite ceramic tool and die material. The BP algorithm could set up the relationship well between the hot pressing parameters and mechanical property of nanocomposite ceramic tool and die materials. After analyzed the predicted results, the best predicted results were the sintering temperature was 1420°C and the holding time was 60min. Under these hot pressing parameters, the best flexural strength and the best fracture toughness of the material could be obtained.

Risk Assessment for Remanufacturing System Based on Neural Network

2011 ◽  
Vol 204-210 ◽  
pp. 1382-1385 ◽  
Author(s):  
Qiu Lian Wang ◽  
Cong Bo Li
Keyword(s):  
Neural Network ◽  
Risk Assessment ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Assessment Model ◽  
The Internet ◽  
Risk Assessment Model ◽  
Key Indicators ◽  
The Relationship ◽  
Evaluating Method

To provide referenced risk assessment model for implementing remanufacturing program in enterprise, a set of evaluating indicators was proposed according to the characteristics of the remanufacturing program’s life cycle, which includes acquisition, assessment, disassembly, reproducing and reprocessing phases; And Back Propagation neural network (BPNN) was applied to measure the risk of the remanufacturing system as evaluating method; In addition, the influence of the evaluating indicators on the output was calculated by the Relationship Function between the networked weights, so the key indicators can be found out. The risk assessment model is trained by five samples obtained from the Internet, and is verified by the case of one machining tools company.

High-Pressure Water Spray Research Based on Neural Network

2010 ◽  
Vol 29-32 ◽  
pp. 138-142
Author(s):  
Rui Li ◽  
Zi Ming Kou
Keyword(s):  
Neural Network ◽  
High Pressure ◽  
Influencing Factors ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Industrial Processes ◽  
Water Spray ◽  
Key Factors ◽  
Pressure Water ◽  
The Relationship

The spray cleaning method is important and universal in many industrial processes and other occasion. Because the size of the waterdrop is one of key factors for cleaning, this paper not only studied the relationship between the size of waterdrop and other influencing factors, but also researched the forecasted method for the size of waterdrop. In lab, by measuring the size of the waterdrop, jetted by one kind of nozzle, data were acquired and were used to train the Back Propagation Neural Network ( BPNN ). Through comparing those diameters, between measured in lab and calculated by BPNN after trained. It was acquired that the maximum errors was smaller than 1.62%, between the computed results and the factual measured ones. The experimental results showed that BPNN is an effective tool to predict the variation of the non-linear waterdrop diameter.

Three-dimensional MRI segmentation based on back-propagation neural network with robust supervised training

2000 ◽  
Author(s):  
Jorge U. Garcia ◽  
Leopoldo Gonzalez-Santos ◽  
Rafael Favila ◽  
Rafael Rojas ◽  
Fernando A. Barrios
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Three Dimensional ◽  
Back Propagation Neural Network ◽  
Mri Segmentation ◽  
Supervised Training

Setting Speed Limits on Kansas Two-Lane Highways: Neuronet Approach

2000 ◽  
Vol 1708 (1) ◽  
pp. 20-27 ◽  
Author(s):  
Yacoub M. Najjar ◽  
Robert W. Stokes ◽  
Eugene R. Russell
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Field Studies ◽  
Back Propagation Neural Network ◽  
Speed Limit ◽  
Speed Limits ◽  
Rural Highways ◽  
Resource Limitations ◽  
Traffic Volumes ◽  
The Relationship

Recent federal legislation allowing states to set their own speed limits on highways, as well as increases in the number of requests from citizens and neighborhood groups to implement actions to reduce “excessive” speeding on their streets and highways, has created considerable debate about and scrutiny of the appropriate speed limits that should be posted on state highways. Various speed studies have indicated that sensible and cautious drivers will most likely drive at the speed dictated by roadway and traffic conditions rather than relying on a posted speed limit. To incorporate roadway characteristics and traffic volumes into the selection of the most appropriate (i.e., comfortable, safe, and efficient) speed limit, actual engineering field speed studies are carried out. Generally, the 85th percentile speed at which the drivers surveyed are driving is selected as a primary factor in determining the posted speed limit. Carrying out such field studies for all highway sections is a costly and time-consuming process. Therefore, characterizing the relationship between the 85th percentile speed and the roadway characteristics will assist in selecting the most appropriate posted speed limit on highway sections where field surveying is difficult due to resource limitations. A back-propagation neural network is used to extract the relationship between roadway characteristics and 85th percentile speed. The developed neural-network-based speed model was found to perform satisfactorily for characterization of speed on Kansas two-lane, uninterrupted-flow rural highways and for quantifying the influence of prevailing roadway characteristics on the anticipated 85th percentile speed.

scholarly journals COMPARISON OF HYBRID METHODS WITH DIFFERENT META MODEL USED IN BRIDGE MODEL-UPDATING

2017 ◽  
Vol 12 (3) ◽  
pp. 193-202 ◽  
Author(s):  
Zhiyuan Xia ◽  
Aiqun Li ◽  
Jianhui Li ◽  
Maojun Duan
Keyword(s):  
Neural Network ◽  
Model Updating ◽  
Hybrid Methods ◽  
Back Propagation ◽  
Element Model ◽  
Optimization Method ◽  
Back Propagation Neural Network ◽  
Meta Model ◽  
The One ◽  
Two Hybrid

Two hybrid model updating methods by integration of Gaussian mutation particle swarm optimization method, Latin Hypercube Sampling technique and meta models of Kriging and Back-Propagation Neural Network respectively were proposed, and the methods make the convergence speed of the model updating process faster and the Finite Element Model more adequate. Through the application of the hybrid methods to model updating process of a self-anchored suspension bridge in-service with extra-width, which showed great necessity considering the ambient vibration test results, the comparison of the two proposed methods was made. The results indicate that frequency differences between test and modified model were narrowed compared to results between test and original model after model updating using both methods as all the values are less than 6%, which is 25%−40% initially. Furthermore, the Model Assurance Criteria increase a little illustrating that more agreeable mode shapes are obtained as all of the Model Assurance Criteria are over 0.86. The particular advancements indicate that a relatively more adequate Finite Element Model is yielded with high efficiency without losing accuracy by both methods. However, the comparison among the two hybrid methods shows that the one with Back-Propagation Neural Network meta model is better than the one with Kriging meta model as the frequency differences of the former are mostly under 5%, but the latter ones are not. Furthermore, the former has higher efficiency than the other as the convergence speed of the former is faster. Thus, the hybrid method, within Gaussian mutation particle swarm optimization method and Back-Propagation Neural Network meta model, is more suitable for model updating of engineering applications with large-scale, multi-dimensional parameter structures involving implicit performance functions.

Sign in / Sign up

Export Citation Format

Share Document