基于组合优化方法的平面叶栅优化设计

采用奇点分布法与贝塞尔(Bezier)曲线参数化方法相结合的平面叶栅设计方法进行叶栅的初步设计与参数化表达。该方法在完成设计的同时为基于现代优化算法的叶栅粘性流动最优化设计提供设计变量,以实现叶栅翼型的变形控制。然后结合N-S方程流场数值模拟,采用多目标遗传算法(NCGA)和序列二次规划法(NLPQL)组合的优化算法,通过调节叶栅翼型的形状控制参数对叶栅的总压损失和空化性能进行了优化。结果表明,优化效果良好。     

基于MOGA/SOS的互连缓冲及线型优化算法

将互连延时、信号响应波形、布线面积作为互连优化的3个目标函数,把推导出的串扰下边界作为优化参量的限制条件,采用分布式RLC模型作为互连系统的近似解析模型,提出了一种基于单目标排序非支配集构造算法的多目标遗传算法,用于解决互连优化中的缓冲及线型优化问题.算法所得解为满足串扰限制条件且对信号延时、信号波形以及布线面积进行优化的折中解.测试结果表明所提算法对互连优化问题规模的适应性强,所得解的优化结果明显优于基于Elmore模型的优化结果,布线面积减少了30%,信号延时与串扰性能分别提高了25%和25.73%.     

Scenario-Based Multi-Objective Genetic Algorithm Optimization of Closed Ball-Milling Circuit of Esfordi Phosphate Plant

The main goal of this article is to demonstrate an approach based on integration of process simulation and Multi-Objective Genetic Algorithm (MOGA) concepts to solve a real grinding circuit optimization problem by finding the best operating condition under which process objectives can be achieved. Esfordi phosphate plant is located near city of Bafgh at Yazd province of Iran and produces 5 Mt of phosphate annually. The fine particles (nearly ?20 µm) in hydrocyclone underflow which contain a high grade of iron are subjected to over grinding. In addition to electrical energy loss, this causes problems in the downstream process, i.e., flotation stage. The main goals of this study were to solve this problem by adjusting operating condition so that (a) hydrocyclone overflow particle size can be increased from 94.2 µm to 100 µm and (b) increase hydrocyclone underflow particle size from 205 to 500 µm. The second process objective will decrease fine particles in hydrocyclone underflow stream. First, plant sampling campaigns were carried out to calibrate ball mill and hydrocyclone models to be used for performing simulation trials. Then, full circuit simulations were done and optimized by MOGA search process to find the best operating condition that produces hydrocyclone overflow and underflow streams with predefined particle sizes simultaneously. The results indicate that there are various solutions that can be recommended for plant testing and performance improvements. The results of plant implementation of one solution for scenario No. 4 showed improved circuit performance and also validated simulator predictions.     

考虑运输代价的制造工作流调度算法

在云制造环境下,因制造服务资源所在地域的差异性,多目标制造工作流调度不仅考虑制造服务所需时间、费用,还需考虑产品运输所需时间、费用,原有工作流调度算法无法有效优化运输代价.针对此问题,结合遗传算法全局搜索能力强与粒子群算法收敛速度快的特点,提出多目标混合遗传粒子群(MOGA - PSO)算法.仿真结果表明混合算法能够有效降低运输代价,使得工作流调度得到进一步优化,可适用于云制造环境.     

Multi-objective optimization of linear multi-state multiple sliding window system

This paper considers the optimal element sequencing in a linear multi-state multiple sliding window system that consists of n linearly ordered multi-state elements. Each multi-state element can have different states: from complete failure up to perfect functioning. A performance rate is associated with each state. The failure of type i in the system occurs if for any i (1≤i≤I) the cumulative performance of any r_i consecutive elements is lower than w_i. The element sequence strongly affects the probability of any type of system failure. The sequence that minimizes the probability of certain type of failure can provide high probability of other types of failures. Therefore the optimization problem for the multiple sliding window system is essentially multi-objective. The paper formulates and solves the multi-objective optimization problem for the multiple sliding window systems. A multi-objective Genetic Algorithm is used as the optimization engine. Illustrative examples are presented.     

Use of multiple objective evolutionary algorithms in optimizing surveillance requirements

This paper presents the development and application of a double-loop Multiple Objective Evolutionary Algorithm that uses a Multiple Objective Genetic Algorithm to perform the simultaneous optimization of periodic Test Intervals (TI) and Test Planning (TP). It takes into account the time-dependent effect of TP performed on stand-by safety-related equipment. TI and TP are part of the Surveillance Requirements within Technical Specifications at Nuclear Power Plants. It addresses the problem of multi-objective optimization in the space of dependable variables, i.e. TI and TP, using a novel flexible structure of the optimization algorithm. Lessons learnt from the cases of application of the methodology to optimize TI and TP for the High-Pressure Injection System are given. The results show that the double-loop Multiple Objective Evolutionary Algorithm is able to find the Pareto set of solutions that represents a surface of non-dominated solutions that satisfy all the constraints imposed on the objective functions and decision variables. Decision makers can adopt then the best solution found depending on their particular preference, e.g. minimum cost, minimum unavailability.     

Thermodynamic and multi-objective optimisation of solar-driven Organic Rankine Cycle using zeotropic mixtures

This paper communicates the performance of low-grade solar heat source powered Organic Rankine Cycle (ORC). To investigate the system performance, first law and exergetic efficiencies, power output are evaluated and compared for zeotropic mixtures of (iso)butane/(iso)pentane and cyclohexane/R123. The results indicate that there exists an optimal mass fraction for which energy and exergetic efficiencies, and power output are maximum corresponding to a given value of expander inlet temperature compared with pure fluids. However, the specific volume flow ratio of the expander is higher for zeotropic mixtures; which results in a lower economy of mixtures than pure fluids. The use of an internal heat exchanger in the system improves cycle performance. Moreover, the multi-objective genetic algorithm further improves the performance of ORC and exhibits better exergetic efficiency 51–57% and 0–14.09% reduction in lower expander-specific volume flow ratio (v ₆/v ₅) than thermodynamically optimised ORC.     

Ensemble component selection for improving ICA based microarray data prediction models

Independent component analysis (ICA) has been widely used to tackle the microarray dataset classification problem, but there still exists an unsolved problem that the independent component (IC) sets may not be reproducible after different ICA transformations. Inspired by the idea of ensemble feature selection, we design an ICA based ensemble learning system to fully utilize the difference among different IC sets. In this system, some IC sets are generated by different ICA transformations firstly. A multi-objective genetic algorithm (MOGA) is designed to select different biologically significant IC subsets from these IC sets, which are then applied to build base classifiers. Three schemes are used to fuse these base classifiers. The first fusion scheme is to combine all individuals in the final generation of the MOGA. In addition, in the evolution, we design a global-recording technique to record the best IC subsets of each IC set in a global-recording list. Then the IC subsets in the list are deployed to build base classifier so as to implement the second fusion scheme. Furthermore, by pruning about half of less accurate base classifiers obtained by the second scheme, a compact and more accurate ensemble system is built, which is regarded as the third fusion scheme. Three microarray datasets are used to test the ensemble systems, and the corresponding results demonstrate that these ensemble schemes can further improve the performance of the ICA based classification model, and the third fusion scheme leads to the most accurate ensemble system with the smallest ensemble size.     

基于MOGA和SVM的发酵过程建模

针对微生物发酵过程，使用多目标遗传算法（multi-objective genetic algorithm, MOGA）确定最优参数．MOGA和SVM回归相结合形成一种新的建模方法，该方法利用现场生产数据建立了青霉素效价预估模型．仿真结果表明此方法具有很强的拟合和泛化能力．MOGA方法的有效性也得到了验证，它也能够自动选择最优参数．     

基于Kriging模型与MOGA算法的风力机主轴轻量化设计

为了实现风力机主轴轻量化设计,首先根据有限元结果,以质量为目标函数,应力、变形为约束条件建立数学模型。然后利用实验设计方法（DOE）获得初始样本点,并应用Kriging模型建立响应面,得到各设计变量对应力、变形和质量的影响程度和变化趋势,同时获得局部最优解。最后利用多目标遗传算法（MOGA）进行优化,通过1100次迭代,获得全局最优解。实现主轴减重10.71%,可为风力机其他零部件轻量化设计提供参考性优化设计方法。