Component Layout Optimization Research Articles

Accurate and real-time prediction of umbilical component layout optimization based on convolutional neural network

Umbilicals are an essential piece of control equipment in an underwater production system and are composed of cables, optical cables, steel pipes, and other components. Different component layouts result in umbilicals exhibiting different geometric characteristics and bearing capacities. Considering the geometric characteristics and mechanical properties of the umbilical components, a quantifiable optimization mathematical model for the layout of umbilical components is established in this work. The Differential Evolution-Generalized Lagrange Multiplier (DE-GLM) method is proposed to solve the mathematical model. We demonstrate, using mathematical examples, that the DE-GLM method can avoid the uncertainty of artificial experience layout design. Nevertheless, the increasing types, numbers, and layers of components lead to the time cost of DE-GLM calculation to be higher. To avoid the excessive consumption of time and artificial costs caused by traditional layout algorithms, a novel Efficient Pyramid-Scale Aggregation-U-Net (EPSA-U-Net) convolutional neural network is proposed to achieve real-time accurate prediction of umbilical component layout results. After discussing, in detail, the effects of hyperparameters such as optimization algorithms, learning rates, and loss functions, on the performance of the network, we demonstrate that the method not only automatically obtains an umbilical component layout design form that satisfies the performance requirements in real-time but also achieves an accuracy rate of 93.28% compared with other convolutional neural networks. As such, it could replace complex artificial operations, significantly improving the efficiency of umbilical component layout design within a negligible time frame. Simultaneously, it also provides an intelligent, reliable, and efficient reference for the layout design of other similar structures and equipment for marine engineering.

A bi-population clan-based genetic algorithm for heat pipe-constrained component layout optimization

Component Layout Optimization (CLO) is attracting growing attention as electronic equipment rapidly advances toward integration, miniaturization, and high function. Heat pipe-constrained Component Layout Optimization (HCLO) seeks to maximize the thermal performance of electronic equipment by optimizing its component layout, where heat dissipation relies heavily on heat pipes. HCLO poses its peculiar challenges with Many-dimensions, Many-constraints and Many-optima. Although many approaches have been proposed for various CLO applications, they do not consider heat pipe-related constraints and therefore underperform on HCLO. In this paper, we propose a Bi-population Clan-based Genetic Algorithm (BCGA) tailored for HCLO. BCGA introduces (i) A bi-population strategy to decompose HCLO into two interrelated sub-problems, which alleviates the challenge of Many-dimensions and Many-constraints; (ii) A clan-based framework inspired by human evolution to handle Many-optima, under which improved GA operators are also designed. The performance of BCGA is evaluated on a suite of HCLO benchmark problems of varying complexity. Compared with other algorithms recently proposed for CLO and HCLO, BCGA can deliver much more satisfying layout solutions within only half of the computation time.

Component assignment and layout optimization for multi-module microsatellite considering variable module size

The general satellite component layout optimization problems have always focused on satellites with fixed module size, and each component is limited to a specific module or panel. In actual engineering practice, dimensions of microsatellite are no longer constrained strictly, but adjustable within an allowed range. The assignment of the components and the dimensions of the modules should be considered as variable to get better global performance. In this paper, a TS+DE+AFT hybrid algorithm is proposed to solve this component assignment and layout optimization problem for multi-module microsatellite (CALO-MM) considering variable module size, in which tabu search (TS) is mainly used to assign components to the appropriate module, and differential evolution (DE) is used to optimize the layout of the components in each module. An adaptive fine-tuning (AFT) strategy is applied to dynamically adjust the length and height of modules within a maximum envelope size. Demonstration and engineering cases are studied to verify the effectiveness of proposed hybrid algorithm.

A Surrogate-Assisted Evolutionary Algorithm for Space Component Thermal Layout Optimization

In space engineering, the electronic component layout has a very important impact on the centroid stability and heat dissipation of devices. However, the expensive thermodynamic simulations in the component thermal layout optimization problems bring great challenges to the current optimization algorithms. To reduce the cost, a surrogate-assisted evolutionary algorithm with restart strategy is proposed in this work. The algorithm is consisted of the local search and global search. A restart strategy is designed to make the local search jump out of the local optimum promptly and speed up the population convergence. The proposed algorithm is compared with two state-of-the-art algorithms on the CEC2006, CEC2010, and CEC2017 benchmark problems. The experiment results show that the proposed algorithm has a high convergence speed and excellent ability to find the optimum in the expensive constrained optimization problems under the very limited computation budget. The proposed algorithm is also applied to solve an electronic component layout optimization problem. The final results demonstrate the good performance of the proposed algorithm, which is of great significance to the component layout optimization.

An ILP-Assisted Two-Stage Layout Optimization Method for Satellite Payload Placement

In the satellite overall design phase, it is a crucial step to perform satellite layout design to guarantee that the aggregation of electronic components can operate normally and stably in an appropriate temperature environment. In order to handle the satellite payload placement problem of the DongFangHong 4 (DFH-4) platform, the heat pipe-constrained component layout optimization (HCLO) problem is proposed with the HCLO model formulated. Through careful investigation, it can be divided into two optimization subproblems that can be solved subsequently. Based on the divide-and-conquer strategy, an integer linear programming- (ILP-) assisted two-stage layout optimization method is proposed. In stage one, component-heat pipe distribution optimization is performed using the ILP technique so that specific heat pipes occupied by each component can be determined and the horizontal movement range of components can be reduced. In stage two, the detailed component layout optimization is investigated to obtain the final positions of components. First, the sequence layout sampling (SeqLS) method is used to generate one nonoverlap initial layout. Next, swap operation between components is incorporated to reduce the centroid deviation. Finally, sequential quadratic programming (SQP) search is conducted based on the generated promising initial layout solutions. Therefore, the SeqLS-based heuristic layout search algorithm is proposed in the second stage. Two layout test cases, including 15 components and 90 components, respectively, are investigated to demonstrate the validity and efficacy of the proposed layout design method. Experimental results show that it is promising to apply such a two-stage approach for satellite payload placement in engineering.

Component layout optimization design based on genetic algorithm

When working, electronic equipment is often subjected to a mechanical environment dominated by vibration. The printed circuit board (PCB) in the equipment is prone to deformation and transmits vibration to the components on the board. As the weakest link, the component corner position has a large acceleration, which is one of the important reasons for the failure of components and the entire electronic equipment. Based on the finite element modeling of PCB, the interaction between the finite element analysis software NASTRAN and the programming software MATLAB is realized, and the application of genetic algorithm in component layout optimization becomes possible. The optimization results show that the method adopted in this paper can effectively reduce the acceleration value at the component corner and optimize the mechanical environment when the electronic equipment works.

A collaborative design method for satellite module component assignment and layout optimization

The collaborative design of the multi-module satellite component (equipment) assignment and layout is the key aspect of the overall satellite design, and the two parts are closely related. In the past, satellite module component layout optimization usually adopted fixed component assignments, which remained constant in the layout optimization stage. If the components were improperly distributed in these modules, it would seriously affect the layout optimization. To overcome this disadvantage, a collaborative design method for the component assignment and layout design is presented for the multi-module (or multi-bearing plate) satellite component layout problem, based on a multi-agent system. First, the component assignment agent adopted a multi-objective optimization method (the non-dominated sorting genetic algorithm II, NSGA-II) to obtain the approximate Pareto solution set of the satellite component assignment scheme. Second, it adopted a fuzzy multi-objective decision method to select a high-quality component assignment scheme from the approximate Pareto solution set. Third, the layout agent employed a dual system co-evolutionary method for the layout optimization design. In the process of the layout optimization, the layout result is fed back to the component assignment design, and the component assignment is adjusted according to the result of the layout optimization. Thus, the above process is continually iterated to achieve the optimal collaborative design of the component assignment and the layout. The proposed method is applied to a simplified multi-module satellite component assignment and layout optimization problem and aims to provide a reference and technical support for other similar multi-module equipment assignment and layout optimization problems.

Multi-module satellite component assignment and layout optimization

In previous optimization methods for multi-module satellite equipment (component) layout optimization problem, each component was limited to certain module or supporting surface and could only search its position there. Components could not migrate from one module or supporting surface to another. In this case, the layout design of components within satellite module was seriously hindered from further improvement. In this study a component assignment and layout integration optimization algorithm is presented to deal with this problem, which can assign components to each module of satellite dynamically during optimization procedure. The aim of this paper is to expand the solution space of component layout optimization so as to further improve the component layout design. The proposed component assignment and layout integration optimization algorithm is inspired from the idea of stepwise regression in multiple regression analysis, which allows independent variables to enter or leave regression equation freely. In the proposed algorithm components enter the satellite module one by one in descending order of the product of mass and height. For all supporting surfaces within satellite module, each component will try all of them through layout optimization together with these components have been in the satellite module, and finally select the one with the best fitness as its initial assignment. At the same time, these components have been in the satellite module will be evaluated by their moment of inertia to decide whether they leave the current supporting surfaces and move to another or not. The layout optimization algorithm uses the differential evolution (DE) and random mutation operation to optimize the coordinates and orientations of components, respectively. The performance of the proposed algorithm is finally evaluated on a simplified satellite case. Experimental results show the proposed algorithm outperforms other two algorithms that did not consider component assignment in computational accuracy.

Assignment and layout integration optimization for simplified satellite re-entry module component layout

Previous studies of satellite module component (equipment) layout optimization usually initialized a component assignment in the initialization stage, which kept constant in following optimization process. The invariable component assignment will restrict the further improvement in layout optimization. To overcome this deficiency, an assignment and layout integration optimization method is presented for multi-module or supporting surface satellite module component layout design. The assignment and layout integration optimization model and the component reassignment model are built. The component reassignment model is solved by algorithms with new heuristic rule, and the integration optimization model itself is solved by evolutionary algorithm. The purpose of this article is to improve the computational performance of algorithms for multi-module or supporting surface satellite module component layout optimization. The proposed method is applied to a simplified satellite re-entry module component layout optimization problem to illustrate its effectiveness.

An Extended Pattern Search Algorithm for Three-Dimensional Component Layout

An extended pattern search algorithm is introduced for efficient component layout optimization. The algorithm is applicable to general layout problems, where component geometry can be arbitrary, design goals can be multiple and spatial constraint satisfactions can be of different types. Extensions to pattern search are introduced to help the algorithm to converge to optimal solutions by escaping inferior local minima. The performance on all of the test problems shows that the algorithm runs one-to-two orders of magnitude faster than a robust simulated annealing-based algorithm for results with the same quality. The algorithm is further extended to solve a concurrent layout and routing problem, which demonstrates the ability of the algorithm to apply new pattern strategies in search and to include different objective functions in optimization. [S1050-0472(00)01901-2]