改进人工蜂群算法优化的LSSVM在混合气体定量分析中的应用

针对在易燃易爆混合气体定量分析中因交叉敏感易产生测量误差以及最小二乘支持向量机（least squares support vector machine,LSSVM）参数难以确定的问题,提出一种改进人工蜂群（improved artificial bee colony,IABC）算法优化的最小二乘支持向量机。首先,在标准人工蜂群（artificial bee colony, ABC）算法中引入自适应递减因子以更新步长,并结合轮盘赌和反向轮盘赌改进待工蜂跟随概率公式,从而提高收敛精度;然后,利用改进后的人工蜂群算法对最小二乘支持向量机的惩罚参数C和核参数σ²进行优化;最后,利用优化后的参数重建最小二乘支持向量机定量分析模型,并与利用常用的混合气体定量分析方法——粒子群优化（particle swarm optimization,PSO）算法优化的最小二乘支持向量机定量分析模型进行对比。实验结果表明,在交叉敏感状态下,采用改进人工蜂群算法优化的最小二乘支持向量机时的建模总时间和各组分气体浓度测量的平均相对误差均低于采用粒子群算法优化的,有效提高了混合气体的浓度测量精度。研究表明,改进人工蜂群算法优化的最小二乘支持向量机可为混合气体定量分析提供理论支撑,具有一定的工程应用价值。     

A hybrid Tabu sample-sort simulated annealing approach for solving distributed scheduling problem

The distributed scheduling problem has been considered as the allocation of a task to various machines in such a way that these machines are situated in different factories and these factories are geographically distributed. Therefore distributed scheduling has fulfilled various objectives, such as allocation of task to the factories and machines in such a manner that it can utilise the maximum resources. The objective of this paper is to minimise the makespan in each factory by considering the transportation time between the factories. In this paper, to address such a problem of scheduling in distributed manufacturing environment, a novel algorithm has been developed. The proposed algorithm gleans the ideas both from Tabu search and sample sort simulated annealing. A new algorithm known as hybrid Tabu sample-sort simulated annealing (HTSSA) has been developed and it has been tested on the numerical example. To reveal the supremacy of the proposed algorithm over simple SSA and Tabu search, more computational experiments have also been performed on 10 randomly generated datasets.     

Bi-objective scheduling on uniform parallel machines considering electricity cost

This article investigates a bi-objective scheduling problem on uniform parallel machines considering electricity cost under time-dependent or time-of-use electricity tariffs, where electricity price changes with the hours within a day. The aim is to minimize simultaneously the total electricity cost and the number of machines actually used. A bi-objective mixed-integer linear programming model is first formulated for the problem. An insertion algorithm is then proposed for the single-objective scheduling problem of minimizing the total electricity cost for a given number of machines. To obtain the whole Pareto front of the problem, an iterative search framework is developed based on the proposed insertion algorithm. Computational results on real-life and randomly generated instances demonstrate that the proposed approach is quite efficient and can find high-quality Pareto fronts for large-size problems with up to 5000 jobs.     

Models and optimisation approaches for scheduling steelmaking–refining–continuous casting production under variable electricity price

This paper studies the steelmaking–refining–continuous casting (SRCC) scheduling problem with considering variable electricity price (SRCCSPVEP). SRCC is one of the critical production processes for steel manufacturing and energy intensive. Combining the technical rules used in iron-steel production practice, time-dependent electricity price is considered to reduce the electricity cost and the associate production cost. A decomposition approach is proposed for the SRCCSPVEP. Without considering the electrical factor, the first phase applies the mathematical programming method to determine the relative schedule plan for each cast. In the second phase, we formulate a scheduling problem of all casts subject to resource constraint and time-dependent electricity price. A heuristic algorithm combined with the constraint propagation is developed to solve this scheduling problem. To investigate and measure the performance of the proposed approach, numerous instances are randomly generated according to the collective data from a well-known iron-steel plant in China. Computational results demonstrate that our algorithm is very efficient and effective in providing high-quality scheduling plans, and the electricity cost can be reduced for the iron-steel plant.     

Nonlinear model order reduction based on local reduced‐order bases

A new approach for the dimensional reduction via projection of nonlinear computational models based on the concept of local reduced‐order bases is presented. It is particularly suited for problems characterized by different physical regimes, parameter variations, or moving features such as discontinuities and fronts. Instead of approximating the solution of interest in a fixed lower‐dimensional subspace of global basis vectors, the proposed model order reduction method approximates this solution in a lower‐dimensional subspace generated by most appropriate local basis vectors. To this effect, the solution space is partitioned into subregions, and a local reduced‐order basis is constructed and assigned to each subregion offline. During the incremental solution online of the reduced problem, a local basis is chosen according to the subregion of the solution space where the current high‐dimensional solution lies. This is achievable in real time because the computational complexity of the selection algorithm scales with the dimension of the lower‐dimensional solution space. Because it is also applicable to the process of hyper reduction, the proposed method for nonlinear model order reduction is computationally efficient. Its potential for achieving large speedups while maintaining good accuracy is demonstrated for two nonlinear computational fluid and fluid‐structure‐electric interaction problems. Copyright © 2012 John Wiley & Sons, Ltd.     

An improved harmony search minimization algorithm using different slip surface generation methods for slope stability analysis

An improved harmony search algorithm is proposed which is found to be more efficient than the original harmony search algorithm for slope stability analysis. The effectiveness of the proposed algorithm is examined by considering several published cases. The improved harmony search method is applied to slope stability problems with five types of procedure for generating trial slip surfaces. It is demonstrated that the improved harmony search algorithm is efficient and effective for the minimization of factors of safety for various difficult problems, and the method of generating the trial failure surfaces can be important in the minimization process.     

基于佳点集粒子群算法的SVM参数优化方法

针对传统的粒子群算法（PSO）初始种群随机生成而导致的算法稳定性差和易出现早熟等问题,提出了基于佳点集改进的粒子群算法（GSPSO）,并将其优化支持向量机（SVM）,构建一种高效的预测评估模型（GSPSO-SVM）。首先采用佳点集方法使PSO中初始粒子均匀分布,然后利用GSPSO优化SVM的惩罚因子C和径向基核函数参数g以获取最佳参数值,提高SVM分类性和稳定性,最后将模型应用于旱情数据的评估预测。仿真实验结果表明：本模型在平均准确率和方差方面的准确都取得了很好的效果;对比分别用PSO和遗传算法（GA）优化的SVM模型,本模型的性能更好。     

Application of genetic algorithms with dominant genes in a distributed scheduling problem in flexible manufacturing systems

Multi-factory production networks have increased in recent years. With the factories located in different geographic areas, companies can benefit from various advantages, such as closeness to their customers, and can respond faster to market changes. Products (jobs) in the network can usually be produced in more than one factory. However, each factory has its operations efficiency, capacity, and utilization level. Allocation of jobs inappropriately in a factory will produce high cost, long lead time, overloading or idling resources, etc. This makes distributed scheduling more complicated than classical production scheduling problems because it has to determine how to allocate the jobs into suitable factories, and simultaneously determine the production scheduling in each factory as well. The problem is even more complicated when alternative production routing is allowed in the factories. This paper proposed a genetic algorithm with dominant genes to deal with distributed scheduling problems, especially in a flexible manufacturing system (FMS) environment. The idea of dominant genes is to identify and record the critical genes in the chromosome and to enhance the performance of genetic search. To testify and benchmark the optimization reliability, the proposed algorithm has been compared with other approaches on several distributed scheduling problems. These comparisons demonstrate the importance of distributed scheduling and indicate the optimization reliability of the proposed algorithm.     

Three‐dimensional numerical modelling by XFEM of spring‐layer imperfect curved interfaces with applications to linearly elastic composite materials

The spring‐layer interface model is widely used in describing some imperfect interfaces frequently involved in materials and structures. Typically, it is appropriate for modelling a thin soft interphase layer between two relatively stiff bulk media. According to the spring‐layer interface model, the displacement vector suffers a jump across an interface whereas the traction vector is continuous across the same interface and is, in the linear case, proportional to the displacement vector jump. In the present work, an efficient three‐dimensional numerical approach based on the extended finite element method is first proposed to model linear spring‐layer curved imperfect interfaces and then applied to predict the effective elastic moduli of composites in which such imperfect interfaces intervene. In particular, a rigorous derivation of the linear spring‐layer interface model is provided to clarify its domain of validity. The accuracy and convergence rate of the elaborated numerical approach are assessed via benchmark tests for which exact analytical solutions are available. The computated effective elastic moduli of composites are compared with the relevant analytical lower and upper bounds. Copyright © 2011 John Wiley & Sons, Ltd.     

Stability assessment of earth slope using modified particle swarm optimization

This paper has proposed an effective method to determine the minimum factor of safety (FS) and associated critical failure surface in slope stability analysis. The search for the minimum FS based on limit equilibrium methods is a complex optimization problem as the objective function is non-smooth and non-convex. Recently, particle swarm optimization (PSO) as a meta-heuristic optimization algorithm has been developed with success in treating various types of problems. In the current study, a new approach of PSO is proposed to calculate the safety factor of earth slopes. The safety factors of the general slip surfaces are calculated using Spencer method of slices, and each new slip surface is randomly generated by straight line technique. The reliability and efficiency of the proposed algorithm are examined by considering a number of published cases. The results indicate that the new method can predict a more critical failure mechanism with a lower FS and can outperform the other methods in the literature as well as standard PSO. Finally, the proposed method will be validated by considering an existing slope failure in Ulu Klang, Malaysia.     

Guided modes in a uniaxial multilayer

An algorithm is presented for simulation of guided modes in a multilayer uniaxial structure with each layer characterized by its own ellipsoid of refractive indices and direction of optical axis. The proposed approach is based on presenting an electromagnetic field in each layer as a linear combination of ordinary and extraordinary waves coupled through the boundary conditions. The problem is reduced to two dimensions by considering the waves with a given projection of the wave vector on the plane of the waveguide. No a priori assumption about the guided-mode polarization is required in this method. Hybrid polarized modes appear naturally as solutions of a system of linear equations with respect to the amplitudes of the ordinary and extraordinary waves. The proposed approach covers a wide variety of important practical cases including isotropic waveguides, surface waves at the boundary between positive uniaxial crystal and isotropic medium, surface plasmons at metallic interfaces, uniaxial multilayers in a very general form, and leaky modes in such structures.     

An efficient metamodeling approach for uncertainty quantification of complex systems with arbitrary parameter probability distributions

This paper proposes an efficient metamodeling approach for uncertainty quantification of complex system based on Gaussian process model (GPM). The proposed GPM‐based method is able to efficiently and accurately calculate the mean and variance of model outputs with uncertain parameters specified by arbitrary probability distributions. Because of the use of GPM, the closed form expressions of mean and variance can be derived by decomposing high‐dimensional integrals into one‐dimensional integrals. This paper details on how to efficiently compute the one‐dimensional integrals. When the parameters are either uniformly or normally distributed, the one‐dimensional integrals can be analytically evaluated, while when parameters do not follow normal or uniform distributions, this paper adopts the effective Gaussian quadrature technique for the fast computation of the one‐dimensional integrals. As a result, the developed GPM method is able to calculate mean and variance of model outputs in an efficient manner independent of parameter distributions. The proposed GPM method is applied to a collection of examples. And its accuracy and efficiency is compared with Monte Carlo simulation, which is used as benchmark solution. Results show that the proposed GPM method is feasible and reliable for efficient uncertainty quantification of complex systems in terms of the computational accuracy and efficiency. Copyright © 2016 John Wiley & Sons, Ltd.     

Optimal batch ordering policies for assembly systems with guaranteed service

For a supply chain modelled as a multi-echelon inventory system, effective management of its inventory at each stock is critical to reduce inventory costs while assuring a given service level to customers. In our previous work, we used the guaranteed-service approach (GSA) to design optimal echelon batch ordering policies for continuous-review serial systems with Poisson customer demand and fixed order costs. The approach assumes that the final customer demand is bounded and each stock has a guaranteed service time in the sense that the demand of its downstream stock can always be satisfied in the service time. This paper extends this work by considering more general assembly systems. We first derive an analytical expression for the total cost of the system in the long run. The problem of finding optimal echelon batch ordering policies for the system can then be decomposed into two independent sub-problems: order size decision sub-problem and reorder point decision sub-problem. We develop efficient dynamic programming algorithms for the two sub-problems. Numerical experiments on randomly generated instances show the effectiveness of the proposed approach.     

Kinematic modelling of 3D woven fabric deformation for structural scale features

A multi-scale approach to modelling is optimal for computationally intensive problems of a hierarchical nature such as 3D woven composites. In this paper an approach capable of modelling feature/component scale fabric deformations and defects is proposed. The proposed technique starts with a meso-scale model for predicting the as-woven geometry of a single unit cell using a high fidelity digital element method. The unit cell geometry is then converted into a macro-scale fabric model by geometric reduction then tessellation. On the macro-scale, two and three dimensional approaches to yarn geometry representation are proposed, with an accompanying yarn mechanical model. Each approach is evaluated based on solution accuracy and computational efficiency. The proposed approach is then verified against experimental results on the meso- and macro-scales. The applicability of this modelling technique to larger scale compaction problems is then investigated. The proposed algorithm was found to be accurate and computationally efficient.     

An innovative artificial bee colony algorithm and its application to a practical intercell scheduling problem

In this article, an innovative artificial bee colony (IABC) algorithm is proposed, which incorporates two mechanisms. On the one hand, to provide the evolutionary process with a higher starting level, genetic programming (GP) is used to generate heuristic rules by exploiting the elements that constitute the problem. On the other hand, to achieve a better balance between exploration and exploitation, a leading mechanism is proposed to attract individuals towards a promising region. To evaluate the performance of IABC in solving practical and complex problems, it is applied to the intercell scheduling problem with limited transportation capacity. It is observed that the GP-generated rules incorporate the elements of the most competing human-designed rules, and they are more effective than the human-designed ones. Regarding the leading mechanism, the strategies of the ageing leader and multiple challengers make the algorithm less likely to be trapped in local optima.     

Improved variable neighbourhood search for integrated tundish planning in primary steelmaking processes

Production planning (or product design) in the steel industry needs specific, sophisticated procedures in order to guarantee competitive plant performance. This paper describes an integrated tundish planning problem, considering the steelmaking-continuous casting-hot rolling and other downstream integrated technical constraints, and a multi-objective optimisation model is proposed with the objective to optimise the number of tundish, the additional cost of technical operations and the throughput balance to each flow. Also, instead of using traditional metaheuristic algorithm or artificial intelligence (AI)-based heuristic approaches, this paper develops two new approaches, the improved variable neighbourhood descent (IVND) search method and improved reduced variable neighbourhood search (IRVNS) method, by introducing the iterated local search into local search to the problem described above. The performance of IVND and IRVNS are analysed based on changing the number of local iteration and weights of objective function, these two algorithms are also compared with tabu search(TS) and heuristic method based on numeral analysis of the actual data, and the results show that the model and algorithm are feasible and efficient.     

A boundary cohesive grain element formulation for modelling intergranular microfracture in polycrystalline brittle materials

In this paper, a cohesive grain boundary integral formulation is proposed, for simulating intergranular microfracture evolution in polycrystalline brittle materials. Artificially generated polycrystalline microstructures are discretized using the proposed anisotropic boundary element method, considering the random location, morphology and material orientation of each grain. Each grain is assumed as a single crystal with general elastic orthotropic mechanical behaviour. Crack initiation and propagation along the grain boundaries interfaces are modelled using a linear cohesive law, considering mixed mode failure conditions. Furthermore, a non‐linear frictional contact analysis is performed over cracked grain interfaces to encounter cases where crack surfaces come into contact, slide or separate. The effect of randomly located pre‐existing flaws on the overall behaviour and microcracking evolution of a polycrystalline material is also investigated for different Weibull moduli. The stochastic effects of each grain morphology‐orientation, internal friction and randomly distributed pre‐existing flaws, under different loading conditions, are studied probabilistically by simulating various randomly generated microstructures. Copyright © 2006 John Wiley & Sons, Ltd.     

基于粒子群与聚类的多目标优化算法

针对粒子群优化算法容易陷入局部最优的问题,提出了一种基于粒子群优化与分解聚类方法相结合的多目标优化算法。算法基于参考向量分解的方法,通过聚类优选粒子策略来更新全局最优解。首先,通过每条均匀分布的参考向量对粒子进行聚类操作,来促进粒子的多样性。从每个聚类中选择一个具有最小聚合函数适应度值的粒子,以平衡收敛性和多样性。动态更新全局最优解和个体最优解,引导种群均匀分布在帕累托前沿附近。通过仿真实验,与4种粒子群多目标优化算法进行对比。实验结果表明,提出的算法在27个选定的基准测试问题中获得了20个反世代距离(IGD)最优值。     

Analytical solutions of coupled-mode equations for multiwaveguide systems, obtained by use of Chebyshev and generalized Chebyshev polynomials

A novel approach is proposed for obtaining the analytical solutions of the coupled-mode equations (CMEs); the method is applicable for an arbitrary number of coupled waveguides. The mathematical aspects of the CMEs and their solution by use of Chebyshev polynomials are discussed. When mode coupling between only adjacent waveguides is considered (denoted weak coupling), the first and second kinds of the usual Chebyshev polynomials are appropriate for evaluating the CMEs for linearly distributed and circularly distributed multiwaveguide systems, respectively. However, when one is considering the coupling effects between nonadjacent waveguides also (denoted strong coupling), it is necessary to use redefined generalized Chebyshev polynomials to express general solutions in a form similar to those for the weak-coupling case. As concrete examples, analytical solutions for 2 x 2, 3 x 3, and 4 x 4 linearly distributed directional couplers are obtained by the proposed approach, which treats the calculation as a nondegenerate eigenvalue problem. In addition, for the 3 x 3 circularly distributed directional coupler, which gives rise to a degenerate eigenvalue problem, an analytical solution is obtained in an improved way. Also, for comparison and without loss of generality, to clarify the difference between the two coupling cases, analytical solutions for a 5 x 5 circularly distributed directional coupler are obtained by use of the usual and the redefined generalized Chebyshev polynomials.     

Tabu search approach based on a similarity coefficient for cell formation in generalized group technology

Both a similarity coefficient method (SCM)-based algorithm and meta-heuristics have been widely applied to various cell formation problems; however, few studies have explored the combination of the two methods. This paper addresses a hybrid algorithm, in which, based on the initial solution produced by a new SCM-based hierarchical clustering method, a fast and effective tabu search approach is presented to solve cell formation in group technology (GT). The proposed algorithm is applied to several problems from literature and a group of the randomly generated instances with alternative process plans and compared with simulated annealing (SA) and other TS; the results demonstrate that the proposed algorithm is available and efficient for cell formation in generalized GT.