scholarly journals NWTOPT – A hyperparameter optimization approach for selection of environmental model solver settings

2021 ◽  
pp. 105250
Author(s):  
Max W. Newcomer ◽  
Randall J. Hunt
Keyword(s):  
Optimization Approach ◽  
Environmental Model ◽  
Hyperparameter Optimization ◽  
Selection Of

Life Augmentation of Turbine Exhaust System Compensators Through Integrated MADM Optimization Approach of Stress Based Fatigue Cycles

2021 ◽  
Author(s):  
Nitin D. Pagar ◽  
Amit R. Patil
Keyword(s):  
Exhaust System ◽  
Optimization Methods ◽  
Fractional Factorial ◽  
Design Parameters ◽  
Optimization Approach ◽  
Auxiliary Equipment ◽  
Maximum Expansion ◽  
Optimal Configurations ◽  
Selection Of ◽  
Turbine Exhaust

Abstract Exhaust expansion joints, also known as compensators, are found in a variety of applications such as gas turbine exhaust pipes, generators, marine propulsion systems, OEM engines, power units, and auxiliary equipment. The motion compensators employed must have accomplished the maximum expansion-contraction cycle life while imposing the least amount of stress. Discrepancies in the selecting of bellows expansion joint design parameters are corrected by evaluating stress-based fatigue life, which is challenging owing to the complicated form of convolutions. Meridional and circumferential convolution stress equations that influencing fatigue cycles are evaluated and verified with FEA. Fractional factorial Taguchi L25 matrix is used for finding the optimal configurations. The discrete design parameters for the selection of the suitable configuration of the compensators are analysed with the help of the MADM decision making techniques. The multi-response optimization methods GRA, AHP, and TOPSIS are used to determine the parametric selection on a priority basis. It is seen that weighing distribution among the responses plays an important role in these methods and GRA method integrated with principal components shows best optimal configurations. Multiple regression technique applied to these methods also shows that PCA-GRA gives better alternate solutions for the designer unlike the AHP and TOPSIS method. However, higher ranked Taguchi run obtained in these methods may enhance the suitable selection of different design configurations. Obtained PCA-GRG values by Taguchi, Regression and DOE are well matched and verified for the all alternate solutions. Further, it also shows that stress based fatigue cycles obtained in this analysis for the L25 run indicates the range varying from 1.13 × 104 cycles to 9.08 × 105 cycles, which is within 106 cycles. This work will assist the design engineer for selecting the discrete parameters of stiff compensators utilized in power plant thermal appliances.

Optimal Offloading Configuration of Spread-Moored FPSOs

2009 ◽  
Vol 131 (2) ◽  
Author(s):  
Steven M. Wilkerson ◽  
Satish Nagarajaiah
Keyword(s):  
Environmental Conditions ◽  
Main Tool ◽  
Design Parameters ◽  
Optimization Approach ◽  
Analysis Model ◽  
Simple Analysis ◽  
Formal Approach ◽  
Fine Tune ◽  
Formal Optimization ◽  
Selection Of

As the oil offloading operations of floating production storage and offloading (FPSO) units become more routine, the desire grows to increase the availability for offloading and thus decrease production downtime. Experience with these operations is the main tool available to increase the efficiency of this aspect of deepwater production. However, it is clear that a formal optimization approach can help to fine tune design parameters so that not only is availability increased but the significance of each design parameter can be better understood. The key issue is to define the environmental conditions under which the vessels involved in offloading are able to maintain position. By this, we reduce the notion of availability to a set of operating criteria, which can or cannot be met for a particular set of environmental conditions. The actual operating criteria such as relative vessel heading depend on selection of design parameters, such as the direction and magnitude of external force applied by thrusters or tugs. In the earliest offloading operations, engineering judgment was used to determine the feasibility of offloading at a particular time. For example, if wind and current were not expected to exceed a 1year return period, offloading may be considered safe. This approach can be both conservative and unconservative, depending on the nuances of the particular environmental conditions. This study will propose a formal approach to choosing the design parameters that optimize the availability of a FPSO for offloading. A simple analysis model will be employed so that optimization can be performed quickly using a robust second order method. The proposed analysis model will be compared to model test data to demonstrate its agreement with the more complex system.

scholarly journals Selection of Reserves for Woodland Caribou Using an Optimization Approach

PLoS ONE ◽  
2012 ◽  
Vol 7 (2) ◽  
pp. e31672 ◽  
Author(s):  
Richard R. Schneider ◽  
Grant Hauer ◽  
Kimberly Dawe ◽  
Wiktor Adamowicz ◽  
Stan Boutin
Keyword(s):  
Optimization Approach ◽  
Woodland Caribou ◽  
Selection Of

scholarly journals Reliability optimization on power systems network using genetic algorithm

2020 ◽  
Vol 2 ◽  
pp. 18-29
Author(s):  
A. E. Airoboman ◽  
Emmanuel A. Ogujor
Keyword(s):  
Genetic Algorithm ◽  
Power Systems ◽  
Inequality Constraints ◽  
Optimization Approach ◽  
Reliability Optimization ◽  
Equality And Inequality Constraints ◽  
The Mean ◽  
Mean Time ◽  
Reliability And Availability ◽  
Selection Of

In this study, reliability optimization of a non-linear transmission network using Genetic Algorithm (GA) based optimization approach is presented and proposed. A GA based algorithm was developed for Koko, Guinness, Nekpenekpen, Ikpoba-Dam, Switch station, Etete and GRA 33kV tertiary transmission feeders within Benin Metropolis, Nigeria and was used to determine the optimal performance of the feeders’ reliability and availability through the minimization of downtime and the Mean Time between Failure (MTBF) by the appropriate selection of the objective functions and constraints. The equality and inequality constraints for each feeder on the network were defined, thereafter, codes were written on the Matlab 2016a environment to optimize the selected parameters. The results from the study showed a reduction in downtime of 5.63%, 26.87%, 34.20%, 5.42% 8.37%, 5.18% and 10.97% and an increment increased in MTBF by 4.95%, 19.87%, 4.58%, 3.85%, 4.88%, 5.77% and 13.56% for Guinness, Etete, Nekpenekpen, GRA, Switch station and Ikpoba-Dam feeders respectively. The obtained results, therefore, yielded an average corresponding improvement on the network’s reliability and availability by 1.85% and 2.83% respectively. Conclusively, the desired result reached in this paper validates the robustness of the GA tool in reliability studies. However, conscious effort must be geared concerning the ways and manners the system is operated in order to achieve desired results.

scholarly journals COVID-19 ResNet: Residual neural network for COVID-19 classification with bayesian data augmentation

2021 ◽  
Vol 13 (2) ◽  
pp. 19
Author(s):  
Maria Baldeon calisto ◽  
Javier Sebastián Balseca Zurita ◽  
Martin Alejandro Cruz Patiño
Keyword(s):  
Neural Network ◽  
Medical Image ◽  
Data Augmentation ◽  
Optimization Approach ◽  
Hyperparameter Optimization ◽  
First Case ◽  
Augmentation Strategy ◽  
Medical Image Classification ◽  
Novel Coronavirus ◽  
Insight Into

COVID-19 is an infectious disease caused by a novel coronavirus called SARS-CoV-2. The first case appeared in December 2019, and until now it still represents a significant challenge to many countries in the world. Accurately detecting positive COVID-19 patients is a crucial step to reduce the spread of the disease, which is characterize by a strong transmission capacity. In this work we implement a Residual Convolutional Neural Network (ResNet) for an automated COVID-19 diagnosis. The implemented ResNet can classify a patient´s Chest-Xray image into COVID-19 positive, pneumonia caused from another virus or bacteria, and healthy. Moreover, to increase the accuracy of the model and overcome the data scarcity of COVID-19 images, a personalized data augmentation strategy using a three-step Bayesian hyperparameter optimization approach is applied to enrich the dataset during the training process. The proposed COVID-19 ResNet achieves a 94% accuracy, 95% recall, and 95% F1-score in test set. Furthermore, we also provide an insight into which data augmentation operations are successful in increasing a CNNs performance when doing medical image classification with COVID-19 CXR.

Sign in / Sign up

Export Citation Format

Share Document