基于遗传算法提高计算机连续语音识别率的研究

为提高计算机连续语音识别准确率,应用遗传算法人工智能控制技术具有的高效全局启发式搜索特点,探讨了提高计算机连续语音识别准确率的优化方法,通过提取语音特征参数,作为初始语音群体的生成,把语音识别内核程序中语言焦点作为遗传算法中操作算子,以高效全局启发式适配语音类型,连续语音识别准确率提高7％,为实现真正意义上计算机“人一机对话”进行了大胆的尝试。     

根据遗传算法的拉深模试冲缺陷智能诊断

总结了拉深模试冲时的缺陷及原因，建立原因表，应用遗传算法技术对拉深模试冲时的缺陷进行智能诊断，探讨了提高拉深模试冲时的缺陷诊断准确率的优化方法，描述了遗传算法的诊断过程。     

An equilibrium multi-objective optimum design for non-circular clearance hole of disk with discrete variables

An Equilibrium Multi-objective Optimization Model(EMOM) with self-regulated weighting factors has been proposed for the optimum design of non-circular clearance hole on the front flange of turbine disk. In the ‘‘equilibrium design", both the stress decrease around the hole and the least hole's profile variation are considered, which balances two ambivalent design goals. Specific discrete variables are applied to realize the standardization design in the optimization process, in which a Surrogate Genetic Coding Algorithm(SGCA) is introduced, and a special check module is used to get rid of repeated fitness evaluation of the samples. The method offers an equilibrium design for the non-circular clearance hole of the turbine disk with great accuracy and efficiency.     

Genetic differentiation induced by spaceflight treatment of Cistanche deserticola and identification of inter-simple sequence repeat markers associated with its medicinal constituent contents

The dried, fleshy stems of Cistanche deserticola (Orobanchaceae) are popular tonics in Traditional Chinese Medicine (TCM) to treat the inability of kidney in expelling extra fluid in the body, causing fluid retention, and reform reproductive system. However, the wild plants of C. deserticola have become endangered due to habitat downsizing and over-harvesting for its medicinal usages. The present research was carried out for the following purposes: (1) promoting the space-breeding research; (2) providing molecular evidence for agricultural selective breeding; and (3) protecting this endangered herbal medicine and conserving its genetic resources.     

电机控制系统PID参数的遗传算法优化

近年来,遗传算法的研究十分引人注目,作为一种新型的、模拟生物进化过程的随机化搜索和优化方法。其算法简单通用,鲁棒性强,在组合优化、机器学习、自适应控制和规划设计等领域的应用中已展现了其特色和魅力。该方法是一种不需要任何初始信息并可以寻求全局最优解的、高效的优化组合方法。文章就是利用遗传算法对某一电机控制系统的PID参数进行优化,以提高控制系统的性能指标。     

一种新的蚁群算法及其在飞行器设计中的应用

尝试将蚁群算法引入飞行器优化设计领域,为此建立了适用于高维、多目标、多约束优化问题的连续空间蚁群算法,并以高超声速飞行器气动布局的多目标优化设计为例进行了验证.优化设计结果与采用遗传算法得到的优化结果进行了对比,指出了蚁群算法的优点.该研究可为蚁群算法应用于复杂、高维的大规模飞行器设计问题提供参考.      

1种发动机自适应模型的修正方法

为解决由于工艺落后和性能衰退所导致的发动机模型与实际发动机失配的问题,从而达到视情维修的目的,建立了1种基于遗传算法的自适应模型修正方法.利用遗传算法高效率的全局搜索能力,以发动机性能参数为目标,优化部件参数,实现了模型的修正,并通过分析发动机性能参数对部件参数的敏感性,研究了选取不同组合的待修正部件参数对模型修正精度的影响.结果表明:采用该修正方法所建立的发动机模型准确性高、鲁棒性强,且具有良好的通用性,为发动机的健康管理和故障诊断提供了重要依据,具有很好的军事和工程应用价值.     

原位自生TiB2/Al复合材料车削参数多目标优化方法

原位自生TiB2/Al复合材料具有密度小、比强度高、高耐磨等特点,在航空航天领域具有广泛的应用前景.主要针对TiB2/Al复合材料车削参数对表面粗糙度的影响进行探索性研究.首先,以车削速度、进给速度、车削深度为对象,基于单因素试验研究了车削参数控制域.进一步在控制域内设计正交试验,并基于试验结果研究了表面粗糙度与车削参数的映射关系,推导了材料去除率模型.最后,以表面粗糙度和材料去除率为优化目标,提出并研究了基于GA-Pareto的车削参数多目标优化方法,并通过试验验证了该方法的可行性和有效性.     

Optimization of communication network topology for navigation sharing among distributed satellites

Navigation sharing among distributed satellites is quite important for coordinated motion and collision avoidance. This paper proposes optimization methods of the communication network topology to achieve navigation sharing. The whole communication network constructing by inter-satellite links are considered as a topology graph. The aim of this paper is to find the communication network topology with minimum communication connections’ number (MCCN) in different conditions. It has found that the communication capacity and the number of channels are two key parameters affecting the results. The model of MCCN topology for navigation sharing is established and corresponding method is designed. Two main scenarios, viz., homogeneous case and heterogeneous case, are considered. For the homogeneous case where each member has the same communication capacity, it designs a construction method (Algorithm 1) to find the MCCN topology. For the heterogeneous case, it introduces a modified genetic algorithm (Algorithm 2) to find the MCCN topology. When considering the fact that the number of channels is limited, the Algorithm 2 is further modified by adding a penalized term in the fitness function. The effectiveness of these algorithms is all proved in theoretical. Three examples are further tested to illustrate the methods developed in this paper.     

月球精确软着陆最优标称轨迹在轨制导方法

为实现在月球表面期望的着陆点进行精确软着陆（PPL）,且满足燃耗最优性要求,基于提出的LIDAR目标点在轨自主选定的月球精确软着陆方案,对月球PPL最优标称轨迹在轨快速规划制导方法进行研究。首先针对月球PPL三维球体非线性轨道动力学模型,采用Legendre Gauss Lobatto伪光谱方法将轨迹优化的最优控制问题转化为非线性规划问题（NLP）,再利用SQP优化算法求解月球PPL最优标称轨迹,最后通过遗传算法对优化结果进行验证,并提出应用遗传算法提供SQP在轨规划初值数据库的方案。仿真结果表明了最优标称轨迹在轨规划方法的快速性和有效性。