Multi-stage optimization method for air-intake system of hovercraft based on autonomous optimization

An advanced three stage filtration/separation air intake system (Compact II) is introduced in this paper. The system was developed to meet the current and expected future market demands for gas turbine combustion air treatment in a marine environment. Developing and testing of the Compact II are subjects of this paper.

Download Full-text

Application of Box-Behnken Analysis on the Optimisation of Air Intake System for a Naturally Aspirated Engine

International Journal of Automotive and Mechanical Engineering ◽

10.15282/ijame.17.2.2020.21.0602 ◽

2020 ◽

Vol 17 (2) ◽

pp. 8029-8042

Author(s):

N.S. Mustafa ◽

N.H.A. Ngadiman ◽

M.A. Abas ◽

M.Y. Noordin

Keyword(s):

Fuel Consumption ◽

Fuel Efficiency ◽

Engine Performance ◽

Fuel Price ◽

Design Expert ◽

Intake System ◽

Analysis Technique ◽

System Components ◽

Air Intake ◽

High Influence

Fuel price crisis has caused people to demand a car that is having a low fuel consumption without compromising the engine performance. Designing a naturally aspirated engine which can enhance engine performance and fuel efficiency requires optimisation processes on air intake system components. Hence, this study intends to carry out the optimisation process on the air intake system and airbox geometry. The parameters that have high influence on the design of an airbox geometry was determined by using AVL Boost software which simulated the automobile engine. The optimisation of the parameters was done by using Design Expert which adopted the Box-Behnken analysis technique. The result that was obtained from the study are optimised diameter of inlet/snorkel, volume of airbox, diameter of throttle body and length of intake runner are 81.07 mm, 1.04 L, 44.63 mm and 425 mm, respectively. By using these parameters values, the maximum engine performance and minimum fuel consumption are 93.3732 Nm and 21.3695×10-4 kg/s, respectively. This study has fully accomplished its aim to determine the significant parameters that influenced the performance of airbox and optimised the parameters so that a high engine performance and fuel efficiency can be produced. The success of this study can contribute to a better design of an airbox.

Download Full-text

A novel multi-stage ensemble model with fuzzy clustering and optimized classifier composition for corporate bankruptcy prediction

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-200741 ◽

2020 ◽

pp. 1-17

Author(s):

Dongqi Yang ◽

Wenyu Zhang ◽

Xin Wu ◽

Jose H. Ablanedo-Rosas ◽

Lingxiao Yang ◽

...

Keyword(s):

Fuzzy Clustering ◽

Rapid Development ◽

Optimization Method ◽

Selection Method ◽

Bankruptcy Prediction ◽

Ensemble Model ◽

Composition Method ◽

Classifier Selection ◽

Multi Stage ◽

Proposed Model

With the rapid development of commercial credit mechanisms, credit funds have become fundamental in promoting the development of manufacturing corporations. However, large-scale, imbalanced credit application information poses a challenge to accurate bankruptcy predictions. A novel multi-stage ensemble model with fuzzy clustering and optimized classifier composition is proposed herein by combining the fuzzy clustering-based classifier selection method, the random subspace (RS)-based classifier composition method, and the genetic algorithm (GA)-based classifier compositional optimization method to achieve accuracy in predicting bankruptcy among corporates. To overcome the inherent inflexibility of traditional hard clustering methods, a new fuzzy clustering-based classifier selection method is proposed based on the mini-batch k-means algorithm to obtain the best performing base classifiers for generating classifier compositions. The RS-based classifier composition method was applied to enhance the robustness of candidate classifier compositions by randomly selecting several subspaces in the original feature space. The GA-based classifier compositional optimization method was applied to optimize the parameters of the promising classifier composition through the iterative mechanism of the GA. Finally, six datasets collected from the real world were tested with four evaluation indicators to assess the performance of the proposed model. The experimental results showed that the proposed model outperformed the benchmark models with higher predictive accuracy and efficiency.

Download Full-text

Multi-Robot Indoor Environment Map Building Based on Multi-Stage Optimization Method

Complex System Modeling and Simulation ◽

10.23919/csms.2021.0011 ◽

2021 ◽

Vol 1 (2) ◽

pp. 145-161

Author(s):

Hui Lu ◽

Siyi Yang ◽

Meng Zhao ◽

Shi Cheng

Keyword(s):

Indoor Environment ◽

Optimization Method ◽

Map Building ◽

Environment Map ◽

Multi Stage ◽

Multi Robot

Download Full-text

Use of an Eulerian/Lagrangian Framework to Improve the Air Intake System of an Automobile with Respect to Snow Ingress

SAE International Journal of Passenger Cars - Mechanical Systems ◽

10.4271/2017-01-1319 ◽

2017 ◽

Vol 10 (2) ◽

pp. 487-497 ◽

Cited By ~ 1

Author(s):

Christoph Huber ◽

Bernhard Weigand ◽

Heinrich Reister ◽

Thomas Binner

Keyword(s):

Intake System ◽

Lagrangian Framework ◽

Air Intake

Download Full-text

DISTRIBUTION INCENTIVE SYSTEM FOR ELECTRICAL COMPANIES

EKONOMIKA I UPRAVLENIE: PROBLEMY, RESHENIYA ◽

10.36871/ek.up.p.r.2021.05.04.005 ◽

2021 ◽

Vol 4 (5) ◽

pp. 43-48

Author(s):

Yu. V. NIKITOCHKINA ◽

Keyword(s):

Optimization Method ◽

Incentive System ◽

New Model ◽

Incentive Model ◽

Multi Stage ◽

Commercial Enterprise ◽

Product Image

This article proposes a new model for stimulating distributors – a multi-stage scale that compares the distributor's rating with the percentage level of discount for regional coverage and specialization. The list of indicators for calculating discounts by specialization and regional coverage includes a group of indicators to increase the motivation of the distributor to improve the quality of their work and a group of indicators to increase the motivation of the distributor to expand the scope of action. Using the method of index grouping of expert estimates, the weight values of each indicator were found. The task of calculating the evaluation of the results of the distribution was set as a multi-criteria task, in which the additive optimization method was used for the procedure of folding private criteria, which was preceded by checking all private criteria for addi-tive independence. The developed incentive model can be adapted for any commercial enterprise interested in promoting its product through regional coverage, as well as in supporting the product image, which, of course, contributes to stimulating demand and increasing sales.

Download Full-text