遗传算法和高斯牛顿法联合反演地下水渗流模型参数

充分利用遗传算法善于进行全局搜索和高斯牛顿法善于进行局部搜索的优点,克服了两种方法各自的不足,用改进的遗传算法和高斯牛顿法联合反演地下水数值模型参数,首先用遗传算法求出地下水模型参数的初值,然后利用这组初值用高斯牛顿法进行数值模型参数的反演,并以非均质各向同性承压二维非稳定流动模型,结合有限元法讨论了用遗传算法和高斯牛顿法联合反演地下水数值模型参数的过程。计算结果表明,联合参数反演方法,具有收敛速度快、解的精度高的特点。     

工业建筑创作对建筑设计学科创新的意义

面对在建筑设计创新领域中工业建筑设计领衔意识的弱化与消解,剖析了建筑设计创作方面的困惑,通过追溯工业建筑创作对建筑设计创新发展的历史性贡献;提出工业建筑创作是解决“建筑基本问题”的原探索命题,并阐释回归工业建筑创作对设计创新技术的原动力、环境的原生态、美学的原表现现实和未来的意义。     

A Meta‐Heuristic Algorithm for Multi‐Objective Optimal Design of Hybrid Laminate Composite Structures

Abstract: In this article, we propose a meta‐heuristic algorithm for solving multi‐objective combinatorial optimization problems. The proposed multi‐objective combinatorial optimization algorithm is developed by combining the good features of popular guided local search algorithms like simulated annealing (SA) and tabu search (TS). It has been organized as a multiple start algorithm to maintain a good balance between intensification and diversification. The proposed meta‐heuristic algorithm is evaluated by solving the stacking sequence optimization of hybrid fiber‐reinforced composite plate, cylindrical shell, and pressure vessel problems. The standard performance metrics for evaluating multi‐objective optimization algorithms are used to demonstrate the effectiveness of the proposed algorithm over other popular evolutionary algorithms like Nondominated Sorting Genetic Algorithms (NSGA‐II), Pareto Archived Evolutionary Strategy (PAES), micro‐GA, and Multi‐Objective Particle Swarm Optimization (MOPSO).     

Optimal design of double-layer barrel vaults using genetic and pattern search algorithms and optimized neural network as surrogate model

This paper presents a combined method based on optimized neural networks and optimization algorithms to solve structural optimization problems. The main idea is to utilize an optimized artificial neural network (OANN) as a surrogate model to reduce the number of computations for structural analysis. First, the OANN is trained appropriately. Subsequently, the main optimization problem is solved using the OANN and a population-based algorithm. The algorithms considered in this step are the arithmetic optimization algorithm (AOA) and genetic algorithm (GA). Finally, the abovementioned problem is solved using the optimal point obtained from the previous step and the pattern search (PS) algorithm. To evaluate the performance of the proposed method, two numerical examples are considered. In the first example, the performance of two algorithms, OANN + AOA + PS and OANN + GA + PS, is investigated. Using the GA reduces the elapsed time by approximately 50% compared with using the AOA. Results show that both the OANN + GA + PS and OANN + AOA + PS algorithms perform well in solving structural optimization problems and achieve the same optimal design. However, the OANN + GA + PS algorithm requires significantly fewer function evaluations to achieve the same accuracy as the OANN + AOA + PS algorithm.     

Interactive design computation—a case study on quantum design paradigm

The ever-increasing complexity of design processes fosters novel design computation models to be employed in architectural research and design in order to facilitate accurate data processing and refined decision making. These computation models have enabled designers to work with complex geometry and numeric design constraints to explore a whole new design field that is impossible to explore without computation techniques. However, most current design computation models follow an automation-oriented paradigm that only deal with strictly defined problem solving and optimization, but fail in establishing an intuitive and interactive communication with designers. This lack of interaction leads to an unconscious rejection ofnon-parameterizable design factors, which, reduces design computation models to specific design problem solving tools instead of operating as active design partners. This paper presents a non-deterministic design computation modeling approach derived from a discussion on quantum design paradigm, which employs real-time user interaction as the co-driver to evolve user+computation driven informed design outputs. A case study of such a design computation model; QPC Toolset, developed and applied in a QuantumPointCloud workshop, will be illustrated in this paper. Expanded discussions on fabrication optimization and constructiontechniques from the QPC workshop will be addressed to conclude a comprehensive report.     

中国当代城市问题的设计应答

该文从城市出发,浅析建筑师直面当代城市问题的基本态度,探讨建筑实践回应城市问题、调和城市矛盾、发掘城市潜力的有效策略。中国当代城市问题的设计应答可以从"城市消极用地之积极化、城市顽疾之城市诊疗、城市革命之质能转化、城市未来之时代思考"四个方面阐释。希望通过对创作现象的思辨,探寻属于中国当代城市自己的设计语言,找到求解城市问题的可能。     

建筑日照方案优化调整中的工具和思路

随着国内商品住房的发展,建设用地日趋紧张,各地住宅高度不断提高,高层住宅已经成为主要的住宅形式,甚至在某些大城市超高层住宅也已经出现,日照问题成为城市规划和建筑设计中需要重点考虑的一个问题。如何以有限的土地资源,既要保证一定的容积率,又要达到国家和地方关于日照的规范要求,是摆在各级规划和建筑设计部门的一道难题,本文介绍了目前国内日照方案优化中采用的工具,并初步探讨了方案优化中的几个解决思路。     

Fluid transients and pipeline optimization using GA and PSO: the diameter connection

This paper describes the optimal selection of pipe diameters in a network considering steady state and transient analysis in water distribution systems. Two evolutionary approaches, namely genetic algorithms (GA) and particle swarm optimization (PSO), are used as optimization methods to obtain pipe diameters. Both optimization programs, inspired by natural evolution and adaptation, show excellent performance for solving moderately complex real-world problems which are highly nonlinear and demanding. The case study shows that the integration of GA or PSO with a transient analysis technique can improve the search for effective and economical hydraulic protection strategies. This study also shows that not only is the selection of pipe diameters crucially sensitive for the surge protection strategies but also that more global systematic approaches should be involved in water distribution system design, preferably at an early stage in the design process.     

基于蚁群算法的土石坝土体参数反演

介绍了新近为求解复杂组合优化问题而提出的蚁群算法。将蚁群算法运用于土石坝土体参数反演问题的求解:先对反演参数的搜索空间进行离散,将参数反演问题转化成一个组合优化问题;再针对土体参数反演问题的特点,改进蚁群算法,并将其用于土体参数的反演计算。算例表明,改进蚁群算法可有效求解土石坝土体参数反演问题。     

A unified approach to parameter selection in meta-heuristic algorithms for layout optimization

Meta-heuristic optimization algorithms have attracted many researchers in the last decade. Adjustment of different parameters of these algorithms is usually a time consuming task which is mostly done by a trial and error approach. In this study an index, namely convergence factor (CF), is introduced that can show the performance of these algorithms. CF of an algorithm provides an estimate of the suitability of the parameters being set and can also enforce the algorithm to adjust its parameters automatically according to a pre-defined CF.In this study GA, ACO, PSO and BB-BC algorithms are used for layout (topology plus sizing) optimization of steel braced frames. Numerical examples show these algorithms have some similarities in common that should be taken into account in solving optimization problems.     

A comparison of deterministic and probabilistic optimization algorithms for nonsmooth simulation-based optimization

In solving optimization problems for building design and control, the cost function is often evaluated using a detailed building simulation program. These programs contain code features that cause the cost function to be discontinuous. Optimization algorithms that require smoothness can fail on such problems. Evaluating the cost function is often so time-consuming that stochastic optimization algorithms are run using only a few simulations, which decreases the probability of getting close to a minimum. To show how applicable direct search, stochastic, and gradient-based optimization algorithms are for solving such optimization problems, we compare the performance of these algorithms in minimizing cost functions with different smoothness. We also explain what causes the large discontinuities in the cost functions.     

Lattice-Dome Design Using a Knowledge-Based System Approach

In the design of lattice domes, design engineers need expertise in areas such as configuration processing, nonlinear analysis, and optimization. These are extensive numerical, iterative, and time-consuming processes that are prone to error without an integrated design tool. This article presents the application of a knowledge-based system in solving lattice-dome design problems. An operational prototype knowledge-based system, LADOME, has been developed by employing the combined knowledge representation approach, which uses rules, procedural methods, and an object-oriented blackboard concept. The system's objective is to assist engineers in lattice-dome design by integrating all design tasks into a single computer-aided environment with implementation of the knowledge-based system approach. For system verification, results from design examples are presented.     

基于改进GA-SVR算法的隧道工程三维弹塑性模型参数的智能辨识

将支持向量回归（SVR）算法引入岩土工程数值计算模型参数的辨识中可以充分发挥SVR算法的小样本、泛化性好和全局最优化的优点。但现阶段标准的SVR算法只能解决一维输出变量的回归问题，这就使其在反分析领域的应用受到限制。引入一种改进的SVR算法，这种算法通过将多维输出变量回归转化为多层标准一维输出变量回归来解决这个问题，并与十进制编码的遗传算法相结合，形成改进的GA-SVR算法，用遗传算法搜索最优的SVR模型参数以建立最优的待辨识参数与位移之间的非线性映射关系，然后用遗传算法进行待辨识参数的最优辨识。为对比这种改进GA-SVR算法的效果，将遗传算法与BP神经网络相结合，形成GA-BP算法且编制相应的计算程序。将这两种算法运用于同样的隧道工程三维弹塑性模型参数的智能辨识，数值算例表明改进的GA-SVR算法较GA-BP算法可以取得更高的辨识精度和更好的计算效率，可运用于类似岩土工程计算参数的辨识。     

缺陷石板的计算机优化排样研究

这篇文章提出了一种解决矩形排样问题的新方法。重点是有缺陷的矩形石板的排样问题。由于存在着组合爆炸，求解复杂工程布局问题是很困难的。此问题至今没有很好的解决。文章不同之处在于使用了一种直接比较-比例法（DCPM）来处理约束和解决收敛慢的问题。将遗传算法与DCPM相结合能够达到很好解决问题的目的。     

Genetic Algorithms for Optimal Urban Transit Network Design

This article attempts to highlight the effectiveness of genetic algorithm (GA)–based procedures in solving the urban transit network design problem (UTNDP). The article analyzes why traditional methods have problems in solving the UTNDP. The article also suggests procedures to alleviate these problems using GA–based optimization technique. The thrust of the article is three–fold: (1) to show the effectiveness of GAs in solving the UTNDP, (2) to identify features of the UTNDP that make it a difficult problem for traditional techniques, and (3) to suggest directions, through the presentation of GA–based methodologies for the UTNDP, for the development of GA–based procedures for solving other optimization problems having features similar to the UTNDP.     

Two‐stage profit optimization model for linear scheduling problems considering cash flow

Linear projects with repetitive activity in units are considered for investigation, and a two‐stage profit optimization model for linear scheduling problems using constraint programming (CP) is proposed. To maintain work continuity for repetitive activities, interruption time and crew availability are addressed, and the optimization process is presented as follows: (1) optimizing the primary objective (project profit); (2) minimizing total interruption time, given the optimized value of the primary objective. Repetitive activities incur batches of budget expenditure according to activity implementation time. Cash flow and financial elements are therefore integrated into the optimization model. Owing to flexible CP techniques, contractors’ requirements, such as credit limit and payment conditions, can be integrated simply into the model formulation for practical use. Lastly, a bridge example is adopted, with various constraints such as duration limitation, for scenario analysis. Consequently, the two‐stage optimization process optimizes project profit, and also maximizes work continuity for linear scheduling problems.     

建筑设计中的制约性与创造性--佛山广播电视中心创作回顾

建筑的设计活动可看做是个不断发掘问题，继而又解决问题的过程。从某种意义上说，解决设计制约是建筑创作的源泉之一。通过对佛山广播电视中心创作的回顾，重新审视了整个设计过程，总结了设计中的制约性与创造性。     

建筑生成设计的随机与约束 ——以多智能体地块优化为例

计算机在建筑设计中的功效一方 面体现为辅助制图、场景表现以及指标测算 等;另一方面其强大的计算能力与辅助设计潜 能依然有待发掘。文章以地块演化为例,探索 基于规则与目标函数的地块优化及其自生长 模型,各地块在彼此利益博弈中达到全局优 化。该算法可扩展至建筑学科的其它层面,为 建筑设计提供新的探索方向。     

关于建筑设计教学改革的思考

建筑设计可归纳为一个寻找问题和解决问题的过程，计划是寻找问题，设计是解决问题，我们的建筑设计教育缺乏设计前期工作的内容，学生被动地按给定的任务书做设计，这不利于学生掌握正确的设计方法，如何增加，强化建筑计划方面的训练是建筑设计课程改革的重要内容之一。     

Optimal design method for building energy systems using genetic algorithms

In this paper, a new optimal design method for building energy systems is proposed. This method provides the most efficient energy system, best combination of equipment capacity and best operational planning for cooling, heating, and power simultaneously with respect to certain criteria such as energy consumption, CO₂ emission, etc. Specifically for this paper, the authors apply this method to a sample building as a case study. The “Genetic Algorithms (GA)” optimization method, which can resolve nonlinear optimization problems, is adopted for this optimization analysis. Also its applicability is analyzed in a case study. In order to validate the accuracy of this method, the correct optimum solution based on comprehensive inquiries is also calculated. A comparison of the GA solution with the correct solution demonstrates fairly good agreement. The results show that the proposed method is sufficiently capable of determining the optimal design and has the potential to be applied to very complex energy systems with appropriate modifications.