A decision-making system for construction site layout planning

A decision-making system, which consists of input, design, evaluation and selection, and output stages, is proposed to solve dynamic, multi-objective and unequal-area construction site layout planning (CSLP) problem. In the input stage, the multiple objectives, schedule planning and site condition are determined. In the design stage, two mathematical optimization models max-min ant system (MMAS) and modified Pareto-based ant colony optimization (ACO) algorithm are employed to solve single objective optimization (SOO) and multi-objective optimization (MOO) problem respectively. In the evaluation and selection stage, the intuitionistic fuzzy TOPSIS method is used to evaluate and select the best layout plan among the generated layout alternatives from the design stage. The performance of the proposed decision-making system, which was verified by a residential building project, shall assist the practitioners in the construction industry to deliver construction projects in a more efficient and effective manner, and thus construction costs could be reduced significantly.     

Cost–safety trade-off in unequal-area construction site layout planning

Cost and safety are two key elements when designing a good construction site layout planning (CSLP). Previous research works always considered CSLP from the aspect of reducing cost and treated SCLP as a single objective optimization problem. In the paper, CSLP was designed by a multi-objective optimization (MOO) model using modified Pareto-based ant colony optimization (ACO) algorithm, which could find a Pareto solution (trade-off layout) to fulfill the requirement of reducing cost and improve the site safety level simultaneously. Furthermore, in order to apply MOO model to solve unequal-area problem, the random grids-recognition strategy was employed in the proposed MOO model to solve the unequal-area site layout problems without increasing the computational complexities. A case study of a residential building project is used to validate the proposed MOO model and the results are very positive.     

A tri-objective ant colony optimization based model for planning safe construction site layout

Realizing safety improvements in construction site layout planning (CSLP) is vitally important to construction project safety management. Unlike previous studies in which the safety objective is built without detailed risk factors analysis, this study transforms CSLP into a multi-objective optimization (MOO) problem with designing two safety objective functions due to facility safety relationships (potential risks arising from interaction flows) and geographic safety relationship (potential risks arising from hazardous sources) from the holistic interpretation of interaction relationship connecting temporary facilities. Besides, a supplementary cost reduction objective function was also derived as cost is a critical barrier against safety improvement. Subsequently, a tri-objective ant colony optimization based model was developed to solve MOO problem. Finally, a case study is used to verify the proposed model. The study enriches safety implications by considering onsite safety issues from interaction relationship and enhances site safety of CSLP in the pre-construction stage.     

蚁群算法及其在硐群施工优化中的应用

为解决复杂的组合优化问题，近来提出了一种新的模拟进化算法－－蚁群算法。从原理，算法实现等方面详细介绍了该算法，并针对有序组合优化问题，改进了原算法。把改进算法应用于地下工程中的一类组合优化问题－硐群施工顺序优化。一个大型地下硐室群工程的施工顺序优化结果表明，蚁群算法的应用效果良好，是解决岩土工程中的组合优化问题的一种好方法。     

Multi-objective optimal design of braced frames using hybrid genetic and ant colony optimization

In this article, multi-objective optimization of braced frames is investigated using a novel hybrid algorithm. Initially, the applied evolutionary algorithms, ant colony optimization (ACO) and genetic algorithm (GA) are reviewed, followed by developing the hybrid method. A dynamic hybridization of GA and ACO is proposed as a novel hybrid method which does not appear in the literature for optimal design of steel braced frames. Not only the cross section of the beams, columns and braces are considered to be the design variables, but also the topologies of the braces are taken into account as additional design variables. The hybrid algorithm explores the whole design space for optimum solutions. Weight and maximum displacement of the structure are employed as the objective functions for multi-objective optimal design. Subsequently, using the weighted sum method (WSM), the two objective problem are converted to a single objective optimization problem and the proposed hybrid genetic ant colony algorithm (HGAC) is developed for optimal design. Assuming different combination for weight coefficients, a trade-off between the two objectives are obtained in the numerical example section. To make the final decision easier for designers, related constraint is applied to obtain practical topologies. The achieved results show the capability of HGAC to find optimal topologies and sections for the elements.     

资源有限下的公共建设项目进度优化研究--基于改进的蚁群优化算法

进度优化是施工项目计划的一个重要方面,文章提出了运用改进的蚁群优化算法来解决资源有限下的公共建设项目的进度优化问题,通过对西安北客站的实例的分析,进一步验证了蚁群优化算法对进度优化问题的求解具有普遍适用性。     

基于先验信息的供水管网阻力系数识别

供水管网阻力系数识别是指通过调整管网水力模型中管道阻力系数,使模型计算值与监测值相符的过程。由于实际中监测点数量有限,管网阻力系数识别为欠定的优化问题。现行方法通常采用管道分组这一参数化方法将欠定问题转换为超定,应用遗传算法或其它随机搜索算法求解。提出了基于先验信息的供水管网阻力系数识别算法,所提出算法根据管道管材、管龄等先验信息对管道阻力系数进行估计,并将估计值作为伪观测值引入目标函数将欠定优化问题转换为超定,采用高斯-牛顿算法进行求解。与现有方法相比,所提出算法避免了管道分组不唯一的问题;再者,推导了供水管网阻力系数雅克比矩阵解析式用于搜索向量构造,提高了参数识别计算效率。采用小型管网阐明了雅克比矩阵计算及搜索向量构造,利用大型管网验证了算法的实用性。     

Stochastic time-cost optimization using non-dominated archiving ant colony approach

This article employs a non-dominated archiving ant colony approach to solve the stochastic time-cost trade-off optimization problem. The model searches for non-dominated solutions considering total duration and total cost of the project as two objectives. In order to expect more realistic outcomes for the time-cost trade-off problem, uncertainties in time and cost of the project should be taken into account. Fuzzy sets theory is used to answer for uncertainties in time and cost of the project. The model embeds the α-cut approach to account for accepted risk level of the project manager. Left and right dominance ranking method is used for finding non-dominated solutions. The ranking method employs decision maker's optimism using β concept. The performance of the model is tested according to performance metrics for multi-objective evolutionary algorithms proposed in the literature. The results show that the algorithm is adequately reliable. A case study is solved to show the application of the proposed model for the uncertain time-cost trade-off problem.     

Optimisation of total water coverage in a network with priority using max-min ant system algorithm

A general mathematical programming algorithm is presented to optimise the total cost for the whole water network achieving total water coverage to all demand points in a water network with priority considering penalties associated with failure to meet the demand of two classes of consumers. The algorithm accommodates water leakages and pressure-driven demand and their effects on allocating water. Max-min ant system (MMAS) is used to solve the model using MIDACO 3.0 after interfacing MATLAB 7.0.4 and GAMS 23.9.4. The model is first solved using a particle swarm optimisation (PSO) algorithm. MMAS proved to be an effective water network optimisation tool with priority evidenced in an analysis of the Bulawayo water network by a lower total cost, inclusive of penalties for failure to meet demand for senior priority water users, which is reduced by 25.4%.     

遗传算法在约束优化问题中的应用

介绍了利用遗传算法求解约束优化问题的一般方法,在分析传统方法的基础上提出一种遗传算法求解约束优化问题的新方法,还对该方法在不同问题下作了分析,证明了该方法对求解有约束优化问题有良好性能。     

Antithetic Method‐Based Particle Swarm Optimization for a Queuing Network Problem with Fuzzy Data in Concrete Transportation Systems

The aim of this article is to develop an antithetic method‐based particle swarm optimization to solve a queuing network problem with fuzzy data for concrete transportation systems. The concrete transportation system at the Jinping‐I Hydropower Project is considered the prototype and is extended to a generalized queuing network problem. The decision maker needs to allocate a limited number of vehicles and unloading equipment in multiple stages to the different queuing network transportation paths to improve construction efficiency by minimizing both the total operational costs and the construction duration. A multiple objective decision‐making model is established which takes into account the constraints and the fuzzy data. To deal with the fuzzy variables in the model, a fuzzy expected value operator, which uses an optimistic–pessimistic index, is introduced to reflect the decision maker's attitude. The particular nature of this model requires the development of an antithetic method‐based particle swarm optimization algorithm. Instead of using a traditional updating method, an antithetic particle‐updating mechanism is designed to automatically control the particle‐updating in the feasible solution space. Results and a sensitivity analysis for the Jinping‐I Hydropower Project are presented to demonstrate the performance of our optimization method, which was proved to be very effective and efficient compared to the actual data from the project and other metaheuristic algorithms.     

Dynamic Optimal Traffic Assignment and Signal Time Optimization Using Genetic Algorithms

Abstract:   In this article a dynamic system-optimal traffic assignment model is formulated for a congested urban road network with a number of signalized intersections. A simulation-based approach is employed for the case of multiple-origin-multiple-destination traffic flows. The artificial intelligence technique of genetic algorithms (GAs) is used to minimize the overall travel cost in the network with fixed signal timings and optimization of signal timings. The proposed method is applied to the example network and results are discussed. It is concluded that GAs allow the relaxation of many of the assumptions that may be needed to solve the problem analytically by traditional methods.     

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.     

Advanced energy‐based analyses of trusses employing hybrid metaheuristics

Total potential optimization using metaheuristic algorithm (TPO/MA) is an alternative method in structural analyses, and it is a black‐box application for nonlinear analyses. In the study, an advanced TPO/MA using hybridization of several metaheuristic algorithms is investigated to solve large‐scale structural analyses problems. The new generation algorithms considered in the study are flower pollination algorithm (FPA), teaching learning‐based optimization, and Jaya algorithm (JA). Also, the proposed methods are compared with methodologies using classic and previously used algorithms such as differential evaluation, particle swarm optimization, and harmony search. Numerical investigations were carried out for structures with four to 150 degrees of freedoms (design variables). It has been seen that in several runs, JA gets trapped into local solutions. For that reason, four different hybrid algorithms using fundamentals of JA and phases of other algorithms, namely, JA using Lévy flights, JA using Lévy flights and linear distribution, JA with consequent student phase, and JA with probabilistic student phase (JA1SP), are developed. It is observed that among the variants tried, JA1SP is seen to be more effective on approaching to the global optimum without getting trapped in a local solution.     

Handling construction pollutions using multi‐objective optimization

Quantitative assessment of emissions associated with construction projects should be carried out during the planning phase of the projects. This is important to detect and highlight any excesses of residuals during the construction phase. A newly developed framework is proposed to handle construction pollution using multi‐objective optimization. The approach, utilized by the proposed framework, is based on calculating the generated pollution for each activity involved in the project, as a result of dust, harmful gases and noise. The results of the quantitative assessment are integrated in a utility function that expresses the amount of total pollution. Then, evolutionary genetic algorithms (GAs) are used to carry multi‐objective optimization, considering three objective functions (project duration, project cost and total pollution). The proposed application considers the dynamic nature of construction activities including different types of relationships and the change of activities' criticality. An actual case study is worked out to demonstrate the practical use of the proposed framework and to investigate the sensitivity of its parameters.     

粒子群优化算法在桁架优化设计中的应用

粒子群优化（PSO）算法是近年来发展起来的一种基于群智能的随机优化算法,具有概念简单、易于实现、占用资源低等优点。为了解决有应力约束和位移约束的桁架的尺寸优化问题,将PSO算法应用于桁架结构的尺寸优化设计。首先介绍了原始的PSO算法的基本原理,然后引入压缩因子改进了PSO算法,并提出合理的参数设置值。对几个经典问题进行了求解,并与传统的优化算法和遗传算法进行了比较。数值结果表明,改进的PSO算法具有良好的收敛性和稳定性,可以有效地进行桁架结构的尺寸优化设计。     

A particle swarm ant colony optimization for truss structures with discrete variables

In this paper, a particle swarm optimizer with passive congregation (PSOPC), ant colony optimization (ACO) and harmony search scheme (HS) are combined to reach to an efficient algorithm, called discrete heuristic particle swarm ant colony optimization (DHPSACO). This method is then employed to optimize truss structures with discrete variables. The DHPSACO applies a PSOPC for global optimization and the ant colony approach for local search, similar to its continuous version. The problem-specific constraints are handled using a modified feasible-based mechanism, and the harmony search scheme is employed to deal with variable constraints. Some design examples are tested using the new method and their results are compared to those of PSO, PSOPC and HPSO algorithms to demonstrate the effectiveness of the present method.     

基于改进蚁群算法的室内疏散路径优化

针对传统蚁群算法在解决室内疏散问题时存在收敛速度慢、容易陷入局部最优的缺陷问题,将火场的动态参数引入到蚁群算法中,对其路径选择策略、启发函数和信息素更新策略进行改进,为整个疏散群体求解更优的疏散路径。运用改进的蚁群算法对室内人员的疏散路径进行动态规划,考虑了路径的实时拥挤度,避免了疏散人员局部实现路径优化的瓶颈效应。将分析结果与基本蚁群算法的规划结果进行比较验证,研究结果显示,优化算法缩短了疏散时间和规划路径,提高了疏散效率和搜索速度。     

Optimal Layout of Bridge Trusses by Genetic Algorithms

In this paper we present an approach to the layout and shape-optimization problem of bridge truss structures using genetic algorithms. The objective is to find an optimal layout design that will have minimum weight or material volume, subject to performance constraints related to member stresses, joint displacements, and member buckling. An automated two-stage optimization search process, which integrates structural analysis by finite-element method, genetic algorithms, and cognitive topology patterns (domain knowledge), is developed to solve the optimal problem. Two examples concerning bridge truss structure are investigated to demonstrate the effectiveness of the proposed method in solving these layout-optimization problems.     

基于粒子群算法的工程项目多目标优化问题研究

为了更有效地解决工程项目的工期—成本—质量优化问题,从施工单位的角度出发,基于工期、质量、成本间的对立统一关系,以双代号网络图中每项工作的持续时间为自变量,建立工期—成本—质量优化模型,采用标准粒子群算法来优化求解。为了消除量纲对评价标准的影响,对 3 个目标适应值采取了标准化的处理方法。利用 Matlab 软件,对一个工程案例进行多目标优化,通过与蒙特卡罗方法进行对比,分析了粒子群算法的计算效率,优化结果验证了粒子群算法求解工程项目多目标优化模型的可行性和适用性。