Towards a Distributed Multiagent Learning-Based Design Optimization Method

2017 ◽  
Author(s):  
Daniel Hulse ◽  
Brandon Gigous ◽  
Kagan Tumer ◽  
Christopher Hoyle ◽  
Irem Y. Tumer
Keyword(s):  
Multiagent System ◽  
Design Method ◽  
Systems Design ◽  
Optimization Method ◽  
Computational Time ◽  
Selection Strategy ◽  
Similar Amount ◽  
Optimization Framework ◽  
Complex Engineered Systems ◽  
Probabilistic Action

Complex engineered systems create many design challenges for engineers and organizations because of the interactions between subsystems and desire for optimality. In some conceptual-level optimizations, the design problem is simplified to consider the most important variables in an all-in-one optimization framework. This work introduces a stochastic optimization method which uses a distributed multiagent design method in which action-value based learning agents make individual design choices for each component. These agents use a probabilistic action-selection strategy based on the learned objective values of each action. This distributed multiagent system is applied to a simple quadrotor optimization problem in an all-in-one optimization framework, and compared with the performance of centralized methods. Results show the multiagent system is capable of finding comparable designs to centralized methods in a similar amount of computational time. This demonstrates the potential merit of a multiagent approach for complex systems design.

scholarly journals Modeling multidisciplinary design with multiagent learning

2018 ◽  
Vol 33 (1) ◽  
pp. 85-99 ◽  
Author(s):  
Daniel Hulse ◽  
Kagan Tumer ◽  
Christopher Hoyle ◽  
Irem Tumer
Keyword(s):  
Complex Systems ◽  
Multiagent System ◽  
Systems Design ◽  
Organizational Outcomes ◽  
Learning System ◽  
Multidisciplinary Teams ◽  
Design Teams ◽  
Multiagent Learning ◽  
Complex Engineered Systems ◽  
Design Variables

AbstractComplex engineered systems design is a collaborative activity. To design a system, experts from the relevant disciplines must work together to create the best overall system from their individual components. This situation is analogous to a multiagent system in which agents solve individual parts of a larger problem in a coordinated way. Current multiagent models of design teams, however, do not capture this distributed aspect of design teams – instead either representing designers as agents which control all variables, measuring organizational outcomes instead of design outcomes, or representing different aspects of distributed design, such as negotiation. This paper presents a new model which captures the distributed nature of complex systems design by decomposing the ability to control design variables to individual computational designers acting on a problem with shared constraints. These designers are represented as a multiagent learning system which is shown to perform similarly to a centralized optimization algorithm on the same domain. When used as a model, this multiagent system is shown to perform better when the level of designer exploration is not decayed but is instead controlled based on the increase of design knowledge, suggesting that designers in multidisciplinary teams should not simply reduce the scope of design exploration over time, but should adapt based on changes in their collective knowledge of the design space. This multiagent system is further shown to produce better-performing designs when computational designers design collaboratively as opposed to independently, confirming the importance of collaboration in complex systems design.

scholarly journals Lightweight and maintainable rotary-wing UAV frame from configurable design to detailed design

2021 ◽  
Vol 13 (7) ◽  
pp. 168781402110349
Author(s):  
Huiqiang Guo ◽  
Mingzhe Li ◽  
Pengfei Sun ◽  
Changfeng Zhao ◽  
Wenjie Zuo ◽  
...  
Keyword(s):  
Design Method ◽  
Geometric Model ◽  
Optimization Method ◽  
Frame Structure ◽  
Manufacturing Cost ◽  
Detailed Design ◽  
High Manufacturing Cost ◽  
The Military ◽  
Rotary Wing ◽  
Novel Design

Rotary-wing unmanned aerial vehicles (UAVs) are widespread in both the military and civilian applications. However, there are still some problems for the UAV design such as the long design period, high manufacturing cost, and difficulty in maintenance. Therefore, this paper proposes a novel design method to obtain a lightweight and maintainable UAV frame from configurable design to detailed design. First, configurable design is implemented to determine the initial design domain of the UAV frame. Second, topology optimization method based on inertia relief theory is used to transform the initial geometric model into the UAV frame structure. Third, process design is considered to improve the manufacturability and maintainability of the UAV frame. Finally, dynamic drop test is used to validate the crashworthiness of the UAV frame. Therefore, a lightweight UAV frame structure composed of thin-walled parts can be obtained and the design period can be greatly reduced via the proposed method.

scholarly journals Surrogate-Based Optimization of Horizontal Axis Hydrokinetic Turbine Rotor Blades

Energies ◽  
2021 ◽  
Vol 14 (13) ◽  
pp. 4045
Author(s):  
David Menéndez Arán ◽  
Ángel Menéndez
Keyword(s):  
Turbine Blade ◽  
Design Method ◽  
Optimization Method ◽  
Turbine Rotor ◽  
Computational Effort ◽  
Rotor Blades ◽  
Linear Functions ◽  
Cavitation Inception ◽  
Hydrokinetic Turbine ◽  
Blade Geometry

A design method was developed for automated, systematic design of hydrokinetic turbine rotor blades. The method coupled a Computational Fluid Dynamics (CFD) solver to estimate the power output of a given turbine with a surrogate-based constrained optimization method. This allowed the characterization of the design space while minimizing the number of analyzed blade geometries and the associated computational effort. An initial blade geometry developed using a lifting line optimization method was selected as the base geometry to generate a turbine blade family by multiplying a series of geometric parameters with corresponding linear functions. A performance database was constructed for the turbine blade family with the CFD solver and used to build the surrogate function. The linear functions were then incorporated into a constrained nonlinear optimization algorithm to solve for the blade geometry with the highest efficiency. A constraint on the minimum pressure on the blade could be set to prevent cavitation inception.

A Mathematical Principle and Application on Design of Planar Six-Bar Mechanism with unto Three-Ordered Intermission at Limit Position(s)

2010 ◽  
Vol 37-38 ◽  
pp. 9-13
Author(s):  
Hong Xin Wang ◽  
Ning Dai
Keyword(s):  
Design Method ◽  
Optimization Method ◽  
Basic Function ◽  
Mathematical Principle ◽  
Transmission Characteristics ◽  
Basic Functions ◽  
Combined Mechanism ◽  
Limit Position ◽  
Derivatives Of ◽  
Better Than

A non-iterative design method about high order intermittent mechanisms is presented. The mathematical principle is that a compound function produced by two basic functions, and then one to three order derivatives of the compound function are all zeroes when one order derivative of each basic function is zero at the same moment. The design method is that a combined mechanism is constructed by six bars; the displacement functions of the front four-bar and back four-bar mechanisms are separately built, let one order derivatives of two displacement functions separately be zero at the same moment, and then get geometrical relationships and solution on the intermittent mechanism. A design example shows that this method is simpler and transmission characteristics are better than optimization method.

Comprehensive Design Method for Open or Ducted Propellers for Underwater Vehicles

2021 ◽  
Author(s):  
Spyros A. Kinnas ◽  
Kyungjung Cha ◽  
Seungnam Kim
Keyword(s):  
Design Method ◽  
A Priori ◽  
Optimization Method ◽  
Underwater Vehicles ◽  
Current Approach ◽  
Lattice Method ◽  
B Spline ◽  
Effective Wake ◽  
Propeller Thrust ◽  
Ducted Propellers

A comprehensive method which determines the most efficient propeller blade shapes for a given axisymmetric hull to travel at a desired speed, is presented. A nonlinear optimization method is used to design the blade, the shape of which is defined by a 3-D B-spline polygon, with the coordinates of the B-spline control points being the parameters to be optimized for maximum propeller efficiency, for given effective wake and propeller thrust. The performance of the propeller within the optimization scheme is assessed by a vortex-lattice method (VLM). To account fully for the hull/propeller interaction, the effective wake to the propeller and the hull resistance are determined by analyzing the designed propeller geometry by the VLM, coupled with a Reynolds-Averaged Navier-Stokes (RANS) solver. The optimization method re-designs the optimum blade with the updated effective wake and propeller thrust (taken to be equal to the updated hull resistance), and the procedure continues until convergence of the propeller performance. The current approach does not require knowledge of the wake fraction or the thrust deduction factor, both of which must be estimated a priori in traditional propeller design. The method is applied for a given hull to travel at a desired speed, and the optimum blades are designed for various combinations of propeller diameter and RPM, in the case of open and ducted propellers with provided duct shapes. The effects of the propeller diameter and RPM on the designed propeller thrust, torque, propeller efficiency, and required power are presented and compared with each other in the case of open and ducted propellers. The present approach is shown to provide guidance on the design of propulsors for underwater vehicles, and is applicable to the design of propulsors for surface ships.

Structural topology optimization of bridge girders in cable supported bridges

2018 ◽  
Author(s):  
Mads Baandrup ◽  
Ole Sigmund ◽  
Niels Aage
Keyword(s):  
Topology Optimization ◽  
Large Scale ◽  
Design Method ◽  
Optimization Method ◽  
Bridge Girders ◽  
Structural Topology ◽  
Box Girders ◽  
Box Girder ◽  
Fine Mesh ◽  
Further Development

<p>This work applies a ultra large scale topology optimization method to study the optimal structure of bridge girders in cable supported bridges.</p><p>The current classic orthotropic box girder designs are limited in further development and optimiza­ tion, and suffer from substantial fatigue issues. A great disadvantage of the orthotropic girder is the loads being carried one direction at a time, thus creating stress hot spots and fatigue problems. Hence, a new design concept has the potential to solve many of the limitations in the current state­ of-the-art.</p><p>We present a design method based on ultra large scale topology optimization. The highly detailed structures and fine mesh-discretization permitted by ultra large scale topology optimization reveal new design features and previously unseen eff ects. The results demonstrate the potential of gener­ ating completely different design solutions for bridge girders in cable supported bridges, which dif­ fer significantly from the classic orthotropic box girders.</p><p>The overall goal of the presented work is to identify new and innovative, but at the same time con­ structible and economically reasonable, solutions tobe implemented into the design of future cable supported bridges.</p>

Performance Evaluation of Coating Materials Containing Perlite-Volcanic Lava Stone-Carrot Pulp Ternary System

2021 ◽  
Vol 43 (6) ◽  
pp. 635-635
Author(s):  
Bilge elik and Nil Acaral Bilge elik and Nil Acaral
Keyword(s):  
Design Method ◽  
Optimization Method ◽  
Natural Polymer ◽  
Organic Additives ◽  
Coating Materials ◽  
Pumice Stone ◽  
Design Expert ◽  
Experimental Design Method ◽  
Volcanic Lava ◽  
Suitable Process

Cellulose in the fibrous structure, which is the main structural component in the cell wall of plants, was formed by the combination of three thousand or more glucose molecules and was a natural polymer synthesized by many living microorganisms. In this study, it was aimed to observe the performance of carrot pulp physically added to water-based coating to increase the viscosity of the coatings. In addition, volcanic lava stone (red pumice stone) and perlite stone were added to the coating to improve its properties that heat transfer, adhesion, hydrophobicity, corrosion resistance. The effect of cellulose-based material on the viscosity of the coating was determined using the Design Expert Optimization Method. In this experimental design method, the experimental set was created to be “carrot pulp, volcanic lava stone, and perlite stone” and additives was added as 0-6% by weight of the coating. By using this method, the most suitable process parameters were determined, and the effects of the additives added to the coating were examined, comparatively. As a result, it was found that cellulose derived organic additives and other additives improved the various properties of coating and could be evaluated for industrial coatings.

A new jig-shape optimization method for the high aspect ratio wing

2018 ◽  
Vol 91 (1) ◽  
pp. 124-133
Author(s):  
Zhe Yuan ◽  
Shihui Huo ◽  
Jianting Ren
Keyword(s):  
Aspect Ratio ◽  
Shape Optimization ◽  
High Aspect Ratio ◽  
Optimization Design ◽  
Design Method ◽  
Aircraft Design ◽  
Optimization Method ◽  
Attack Angle ◽  
Structural Deformation ◽  
Content Type

Purpose Computational efficiency is always the major concern in aircraft design. The purpose of this research is to investigate an efficient jig-shape optimization design method. A new jig-shape optimization method is presented in the current study and its application on the high aspect ratio wing is discussed. Design/methodology/approach First, the effects of bending and torsion on aerodynamic distribution were discussed. The effect of bending deformation was equivalent to the change of attack angle through a new equivalent method. The equivalent attack angle showed a linear dependence on the quadratic function of bending. Then, a new jig-shape optimization method taking integrated structural deformation into account was proposed. The method was realized by four substeps: object decomposition, optimization design, inversion and evaluation. Findings After the new jig-shape optimization design, both aerodynamic distribution and structural configuration have satisfactory results. Meanwhile, the method takes both bending and torsion deformation into account. Practical implications The new jig-shape optimization method can be well used for the high aspect ratio wing. Originality/value The new method is an innovation based on the traditional single parameter design method. It is suitable for engineering application.

scholarly journals Multiscale, thermomechanical topology optimization of self-supporting cellular structures for porous injection molds

2019 ◽  
Vol 25 (9) ◽  
pp. 1482-1492
Author(s):  
Tong Wu ◽  
Andres Tovar
Keyword(s):  
Topology Optimization ◽  
Mechanical Performance ◽  
Mechanical Load ◽  
Design Method ◽  
Three Dimensional ◽  
Optimization Method ◽  
Cellular Structures ◽  
Injection Mold ◽  
Computationally Efficient ◽  
Content Type

Purpose This paper aims to establish a multiscale topology optimization method for the optimal design of non-periodic, self-supporting cellular structures subjected to thermo-mechanical loads. The result is a hierarchically complex design that is thermally efficient, mechanically stable and suitable for additive manufacturing (AM). Design/methodology/approach The proposed method seeks to maximize thermo-mechanical performance at the macroscale in a conceptual design while obtaining maximum shear modulus for each unit cell at the mesoscale. Then, the macroscale performance is re-estimated, and the mesoscale design is updated until the macroscale performance is satisfied. Findings A two-dimensional Messerschmitt Bolkow Bolhm (MBB) beam withstanding thermo-mechanical load is presented to illustrate the proposed design method. Furthermore, the method is implemented to optimize a three-dimensional injection mold, which is successfully prototyped using 420 stainless steel infiltrated with bronze. Originality/value By developing a computationally efficient and manufacturing friendly inverse homogenization approach, the novel multiscale design could generate porous molds which can save up to 30 per cent material compared to their solid counterpart without decreasing thermo-mechanical performance. Practical implications This study is a useful tool for the designer in molding industries to reduce the cost of the injection mold and take full advantage of AM.

Research on the Facilities Layout Planning in MTO Manufacturing Industry Based on Genetic Algorithm

2013 ◽  
Vol 842 ◽  
pp. 695-702
Author(s):  
Ying Wang ◽  
You Rong Li ◽  
Yu Qiong Zhou
Keyword(s):  
Genetic Algorithm ◽  
Manufacturing Industry ◽  
Design Method ◽  
Facility Layout ◽  
Optimization Method ◽  
Market Demand ◽  
Layout Planning ◽  
Manufacturing Enterprises ◽  
Make To Order ◽  
Systematic Layout Planning

To enlarge production to meet the market demand, its nessasery to improve the present facility layout for MTO (Make-To-Order) manufacturing enterprises. This paper tries to design a optimization method based on genetic algorithm for the facility layout of MTO enterprises. Firstly, SLP (systematic layout planning) was applied to analyze the material and non-material flow interrelation of the workshop. Secondly, a relatively optimum layout was determined after using fuzzy hierarchy estimation to evaluate the schemes. Then the scheme was optimized with genetic algorithm. The result shows that the optimized logistics transport load is obviously less than before. This design method based on genetic algorithm (GA) is proved feasible and effective in the optimization of facility layout.

Sign in / Sign up

Export Citation Format

Share Document