Genetic Algorithm for Injection Mould Design and Moulding

Obtaining the optimal values of the parameters for th e design of a required mould and the operation of the moulding process are diffi cult, this is due to the complexity of product geometry and the variation of pla stic material properties. The typical parameters for the mould design and mouldi ng process are melt flow length, injection pressure, holding pressure, back pres sure, injection speed, melt temperature, mould temperature, clamping force, inje ction time, holding time and cooling time. This paper discusses the difficulties of using the current computer aided optimization methods to acquire the values of the parameters. A method that is based on the concept of genetic algorithm is proposed to overcome the difficulties. The proposed method describes in details on how to attain the optimal values of the parameters form a given product geom etry.

Satellite constellation design with genetic algorithms based on system performance

Satellite constellation design for space optical systems is essentially a multiple-objective optimization problem. In this work, to tackle this challenge, we first categorize the performance metrics of the space optical system by taking into account the system tasks（i.e., target detection and tracking）. We then propose a new non-dominated sorting genetic algorithm（NSGA） to maximize the system surveillance performance. Pareto optimal sets are employed to deal with the conflicts due to the presence of multiple cost functions. Simulation results verify the validity and the improved performance of the proposed technique over benchmark methods.

MODIFIED GENETIC ALGORITHM APPLIED TO SOLVE PRODUCT FAMILY OPTIMIZATION PROBLEM

The product family design problem solved by evolutionary algorithms is discussed. A successful product family design method should achieve an optimal tradeoff among a set of competing objectives, which involves maximizing commonality across the family of products and optimizing the performances of each product in the family. A 2-level chromosome structured genetic algorithm （2LCGA） is proposed to solve this class of problems and its performance is analyzed in comparing its results with those obtained with other methods. By interpreting the chromosome as a 2-level linear structure, the variable commonality genetic algorithm （GA） is constructed to vary the amount of platform commonality and automatically searches across varying levels of commonality for the platform while trying to resolve the tradeoff between commonality and individual product performance within the product family during optimization process. By incorporating a commonality assessing index to the problem formulation, the 2LCGA optimize the product platform and its corresponding family of products in a single stage, which can yield improvements in the overall performance of the product family compared with two-stage approaches （the first stage involves determining the best settings for the platform variables and values of unique variables are found for each product in the second stage）. The scope of the algorithm is also expanded by introducing a classification mechanism to allow mul- tiple platforms to be considered during product family optimization, offering opportunities for superior overall design by more efficacious tradeoffs between commonality and performance. The effectiveness of 2LCGA is demonstrated through the design of a family of universal electric motors and comparison against previous results.

MODELING, VALIDATION AND OPTIMAL DESIGN OF THE CLAMPING FORCE CONTROL VALVE USED IN CONTINUOUSLY VARIABLE TRANSMISSION

Associated dynamic performance of the clamping force control valve used in continuously variable transmission （CVT） is optimized. Firstly, the structure and working principle of the valve are analyzed, and then a dynamic model is set up by means of mechanism analysis. For the purpose of checking the validity of the modeling method, a prototype workpiece of the valve is manufactured for comparison test, and its simulation result follows the experimental result quite well. An associated performance index is founded considering the response time, overshoot and saving energy, and five structural parameters are selected to adjust for deriving the optimal associated performance index. The optimization problem is solved by the genetic algorithm （GA） with necessary constraints. Finally, the properties of the optimized valve are compared with those of the prototype workpiece, and the results prove that the dynamic performance indexes of the optimized valve are much better than those of the prototype workpiece.

Optimized Design for the Plow of a Submarine Plowing Trencher

The plow of the submarine plowing trencher is one of the main functional mechanisms, and its optimization is very important. The design parameters play a very significant role in determining the requirements of the towing force of a vessel. A multi-objective genetic algorithm based on analytical models of the plow surface has been examined and applied in efforts to obtain optimal design of the plow. For a specific soil condition, the draft force and moldboard surface area which are the key parameters in the working process of the plow are optimized by finding the corresponding optimal values of the plow blade penetration angle and two surface angles of the main cutting blade of the plow. Parameters such as the moldboard side angle of deviation, moldboard lift angle, angular variation of the tangent line, and the spanning length are also analyzed with respect to the force of the moldboard surface along soil flow direction. Results show that the optimized plow has an improved plow performance. The draft forces of the main cutting blade and the moldboard are 10.6% and 7%, respectively, less than the original design. The standard deviation of Gaussian curvature of moldboard is lowered by 64.5%, which implies that the smoothness of the optimized moldboard surface is much greater than the original.

Design optimization of transonic compressor stage using CFD and response surface model

In order to shorten the design period, the paper describes a new optimization strategy for computationally expensive design optimization of turbomachinery, combined with design of experiment (DOE), response surface models (RSM), genetic algorithm (GA) and a 3-D Navier-Stokes solver(Numeca Fine). Data points for response evaluations were selected by improved distributed hypercube sampling (IHS) and the 3-D Navier-Stokes analysis was carried out at these sample points. The quadratic response surface model was used to approximate the relationships between the design variables and flow parameters. To maximize the adiabatic efficiency, the genetic algorithm was applied to the response surface model to perform global optimization to achieve the optimum design of NASA Stage 35. An optimum leading edge line was found, which produced a new 3-D rotor blade combined with sweep and lean, and a new stator one with skew. It is concluded that the proposed strategy can provide a reliable method for design optimization of turbomachinery blades at reasonable computing cost.

Optimizing the Double Inverted Pendulum′s Performance via the Uniform Neuro Multiobjective Genetic Algorithm

An inverted pendulum is a sensitive system of highly coupled parameters, in laboratories, it is popular for modelling nonlinear systems such as mechanisms and control systems, and also for optimizing programmes before those programmes are applied in real situations. This study aims to find the optimum input setting for a double inverted pendulum（DIP）, which requires an appropriate input to be able to stand and to achieve robust stability even when the system model is unknown. Such a DIP input could be widely applied in engineering fields for optimizing unknown systems with a limited budget. Previous studies have used various mathematical approaches to optimize settings for DIP, then have designed control algorithms or physical mathematical models.This study did not adopt a mathematical approach for the DIP controller because our DIP has five input parameters within its nondeterministic system model. This paper proposes a novel algorithm, named Uni Neuro, that integrates neural networks（NNs） and a uniform design（UD） in a model formed by input and response to the experimental data（metamodel）. We employed a hybrid UD multiobjective genetic algorithm（HUDMOGA） for obtaining the optimized setting input parameters. The UD was also embedded in the HUDMOGA for enriching the solution set, whereas each chromosome used for crossover, mutation, and generation of the UD was determined through a selection procedure and derived individually. Subsequently, we combined the Euclidean distance and Pareto front to improve the performance of the algorithm. Finally, DIP equipment was used to confirm the settings. The proposed algorithm can produce 9 alternative configured input parameter values to swing-up then standing in robust stability of the DIP from only 25 training data items and 20 optimized simulation results. In comparison to the full factorial design, this design can save considerable experiment time because the metamodel can be formed by only 25 experiments using the UD. Furthermore, the proposed algorithm can be applied to nonlinear systems with multiple constraints.

Variable-fidelity optimization with design space reduction

Advanced engineering systems, like aircraft, are defined by tens or even hundreds of design variables. Building an accurate surrogate model for use in such high-dimensional optimization problems is a difficult task owing to the curse of dimensionality. This paper presents a new algorithm to reduce the size of a design space to a smaller region of interest allowing a more accurate surrogate model to be generated. The framework requires a set of models of different physical or numerical fidelities. The low-fidelity （LF） model provides physics-based approximation of the high-fidelity （HF） model at a fraction of the computational cost. It is also instrumental in identifying the small region of interest in the design space that encloses the high-fidelity optimum. A surrogate model is then constructed to match the low-fidelity model to the high-fidelity model in the identified region of interest. The optimization process is managed by an update strategy to prevent convergence to false optima. The algorithm is applied on mathematical problems and a two-dimen-sional aerodynamic shape optimization problem in a variable-fidelity context. Results obtained are in excellent agreement with high-fidelity results, even with lower-fidelity flow solvers, while showing up to 39% time savings.