棒材轧制椭圆孔型的多种群遗传优化

 针对目前棒材连轧孔型全域优化问题,提出了多种群遗传算法,可以解决标准遗传算法存在的全域收敛差问题,并结合某钢厂连轧棒材椭圆孔的几何参数进行了多种群遗传算法优化分析。采用刚塑性有限元法模拟优化前后的两道次连轧过程,并分析了连轧过程轧制力的变化情况。结合Matlab曲线拟合和符号积分方法,计算优化前后的轧制能耗并进行比较。同时,借助实际铅件轧制过程的轧制力测试结果,较好地验证了模拟结果的可靠性。结果表明：优化后的孔型可以有效地降低轧制能耗和轧辊的轧制压力。     

焊丝钢ER70S-6的成分优化及工艺研究

介绍TER70S--6焊丝钢盘条的化学成分要求、特点及残余元素的控制,结合重钢生产实际,通过优化炼钢、轧钢工艺,改善了ER70S--6焊丝钢盘条的综合性能,基本解决了严重影响焊丝焊接质量问题。     

Q345C钢的开发与工艺优化

天钢联合特钢炼钢厂为满足高级别角钢的市场需求,进行了Q345C钢的开发.该钢种要求钢中铝含量较高(A1≥0.020％),试生产时连铸塞棒水口结瘤严重,造成铸机连续2个浇次非计划停浇.对关键工序生产工艺进行优化后,再次生产时钢水浇铸性良好,铸坯性能完全满足C级钢的要求,成功开发了Q345C高级别角钢.     

基于改进的遗传算法优化电梯群控

针对乘客候梯时间,乘梯时间,拥挤度和电梯系统运行能耗等多个目标优化的电梯群问题,给出一个改进的遗传算法.该算法在选择,交叉,变异操作时,采用首位存在最优个体,在生成初始种群时采用模糊生成其中一个解的方法.并把改进的遗传算法应用到实际电梯群控中,数值结果表示该方法是有效的,可行的.     

基于遗传算法的自动控制系统数学模型优化

采用遗传算法对控制系统的数学模型进行优化，由实验数据可以得出遗传算法是适合于控制系统模型寻优的。     

LF炉生产焊丝钢精炼工艺优化

本介绍了酒钢60t直流钢包精炼炉生产焊丝钢(ER70S-6X)的精炼工艺优化情况及其取得的冶金效果。实践表明，经30min的精炼，LF炉脱硫率达3l.3％，脱氧率达32％，钢中显微夹杂物去除率为24．26％，大型夹杂物去除率为20．32％。     

LD-LF-CC流程生产45钢的工艺优化

从理论方面探讨了优化工艺的理论基础和工艺要点.在此基础上,通过工业试验对上述理论进行验证,取得了比较好的试验效果.基本做到钢中全氧控制在30×10-6以下,连铸中间包连浇时水口不"结瘤".     

高炉转炉流程生产洁净钢工艺优化研究

简述了洁净钢生产的基本概念，重点论述了高炉转炉流程生产洁净钢的工艺优化问题，提出了该流程大规模，低成本生产洁净钢的基本思路。     

基于遗传算法的无钟高炉布料工艺优化

 面对现代炼铁生产节能减排的迫切需求,优化无钟高炉布料是保证高炉稳产顺行、提高资源利用率和减少污染排放的有效途径。结合无钟炉顶的设备结构与布料工艺特点,提出了使用料面形状误差评价布料操作的准确性,设计了针对多环布料操作优化的遗传算法,并应用该优化算法分析了溜槽倾角档位数量以及布料总周数等参数对无钟布料工艺的影响。结果表明：基于遗传算法的组合优化模型能够有效制定布料矩阵,溜槽倾角档位数量和布料总周数的增多以及单次布料体积的减少有利于实现高炉精准布料,溜槽倾角档位数量无穷大时与螺旋布料的料面构造能力相当,布料总周数和单次布料体积受设备和工艺多方面限制,需合理设定。     

基于遗传算法的冷连轧机轧制策略优化

轧制策略是冷连轧机进行过程控制参数设定的基础。给出了基于遗传算法的轧制策略自动寻优系统,实验数据对比分析结果表明,该系统能够大幅度提高轧制策略的优化性能指标,在实际生产中具有推广应用价值。     

Simulated Annealing–Genetic Algorithm for Transit Network Optimization

This paper presents a mathematical stochastic methodology for transit route network optimization. The goal is to provide an effective computational tool for the optimization of a large-scale transit route network to minimize transfers with reasonable route directness while maximizing service coverage. The methodology includes representation of transit route network solution search spaces, representation of transit route and network constraints, and a stochastic search scheme based on an integrated simulated annealing and genetic algorithm solution search method. The methodology has been implemented as a computer program, tested using previously published results, and applied to a large-scale realistic network optimization problem.     

Trihalomethane Species Forecast Using Optimization Methods: Genetic Algorithms and Simulated Annealing

Chlorination is an effective method for disinfection of drinking water. Yet chlorine is a strong oxidizing agent and easily reacts with both organic and inorganic materials. Trihalomethanes (THMs), formed as a by-product of chlorination, are carcinogenic to humans. Models can be derived from linear and nonlinear multiregression analyses to predict the THM species concentration of empirical reaction kinetic equations. The main objective of this study is to predict the concentrations of THM species by minimizing the nonlinear function, representing the errors between the measured and calculated THM concentrations, using the genetic algorithm (GA) and simulated annealing (SA). Additionally, two modifications of SA are employed. The solutions obtained from GA and SA are compared with the measured values and those obtained from a generalized reduced gradient method (GRG2). The results indicate that the proposed heuristic methods are capable of optimizing the nonlinear problem. The predicted concentrations may provide useful information for controlling the chlorination dosage necessary to assure the safety of water drinking.     

Upgrade Rolling Based on Ultra Fast Cooling Technology for C-Mn Steel

By measuring the expansion curves of a C-Mn steel at different cooling rates by using an MMS-300 thermo- mechanical simulator, continuous cooling transformation curves were obtained. The new process ＂ultra fast cooling＋ laminar cooling＂ was simulated and the effects of ultra fast cooling ending temperature on microstructure had also been investigated. The hot rolling experiment was done by adopting ＂high temperature rolling-[-forepart ultra fast cooling＂ technologies at laboratory scale. The results revealed that ultra fast cooling can delay the decrease of disloca- tion density and refine ferrite grains. Diversity control of the microstructure and phase transformation strengthening can be realized by changing the ultra fast cooling ending temperature. With the decrease of ultra fast cooling ending temperature, the strength and toughness increase, but plasticity does not decrease obviously. The new technique can improve the yield strength by over 50 MPa. Therefore, the upgrade of mechanical properties of C-Mn steel can be realized by using ＂high temperature rolling＋ ultra fast cooling＋laminar cooling＂ technique. Compared with ＂low temperature rolling with large deformation degree＂ technique, this new technology can decrease the roiling force and in- crease the production efficiency.     

Parameters Optimization of Plasma Hardening Process Using Genetic Algorithm and Neural Network

 Plasma surface hardening process was performed to improve the performance of the AISI 1045 carbon steel. Experiments were carried out to characterize the hardening qualities. A predicting and optimizing model using genetic algorithm-back propagation neural network (GA-BP) was developed based on the experimental results. The non-linear relationship between properties of hardening layers and process parameters was established. The results show that the GA-BP predicting model is reliable since prediction results are in rather good agreement with measured results. The optimal properties of the hardened layer were deduced from GA. And through multi optimizations, the optimum comprehensive performances of the hardened layer were as follows: plasma arc current is 90 A, hardening speed is 22 m/min, plasma gas flow rate is 60 L/min and hardening distance is 43 mm. It concludes that GA-BP mode developed in this study provides a promising method for plasma hardening parameters prediction and optimization.     

Optimization of Open-Pit Mine Depressurization System Using Simulated Annealing Technique

Opencast mines operating in an area with dominant groundwater features may face hydrology-related problems such as heaving and bursting of the mine floor due to excessive uplift pressure. A proper groundwater control system has to be implemented to solve these problems. But the groundwater control system, which includes dewatering and depressurization wells may also create impacts on local groundwater flows. Therefore, an optimization-based development of the groundwater control system is required to ensure that local and regional hydrogeological impacts are within acceptable limits. This note presents a case study where an optimization program based on the simulated annealing technique was developed and applied to a three-dimensional seven-layer groundwater model. The calibrated groundwater flow model, which is based on MODFLOW, was used as the simulation component in the linked simulation-optimization model. The combined model was then used to identify the optimum depressurization strategy. The results show that this combined simulation and optimization methodology is a viable approach for solving large-scale groundwater management problems.     

自适应遗传算法在冷连轧负荷优化中的应用

利用自适应遗传交叉变异策略,设计了一种冷连轧轧制负荷优化方法。以各机架相对压下率为自变量,以各机架轧制力相对均衡为优化目标,建立目标函数。通过与在某1370冷连轧机的负荷优化方法进行比较,仿真结果表明,自适应遗传算法具有搜索速度更快、收敛精度更高等优点,更适合在实际生产中应用。     

基于遗传算法的烧结配料综合优化研究

运用遗传算法和逐步回归分析的方法建立烧结配料优化模型,对重钢烧结配料优化,并进行了实验验证和分析.结果表明:优化配料后的烧结矿化学成分和物理性能均满足生产的要求,在稳定各项指标的前提下,每吨烧结矿原料成本降低14.7元.应用遗传算法,可以解决线性规划等方法所不能处理的问题,实现更快、更全面的优化烧结配料.     

基于遗传算法的武钢电网无功优化分析与计算

应用基于遗传算法的无功电压优化模型,结合武钢电网实际开发无功电压优化和有功潮流调控的分析软件,并在该软件的基础上,实现了武钢电网无功的优化计算,形成一套行之有效的无功调控方案应用于生产实际,有效地减少了系统的网络损耗,产生较好的社会和经济效益。     

一种改进的遗传算法用于PI控制器的参数寻优

以武钢1700mm精轧机主传动系统中控制对象特性参数的改变后系统动态响应品质变差为背景,利用遗传送代算法研究了双闭环控制系统中转速PI调节器参数的优化问题.数字仿真结果证明了该算法的有效性和合理性.