A novel wind speed forecasting model for wind farms of Northwest China

Wind resources are becoming increasingly significant due to their clean and renewable characteristics, and the integration of wind power into existing electricity systems is imminent. To maintain a stable power supply system that takes into account the stochastic nature of wind speed, accurate wind speed forecasting is pivotal. However, no single model can be applied to all cases. Recent studies show that wind speed forecasting errors are approximately 25% to 40% in Chinese wind farms. Presently, hybrid wind speed forecasting models are widely used and have been verified to perform better than conventional single forecasting models, not only in short-term wind speed forecasting but also in long-term forecasting. In this paper, a hybrid forecasting model is developed, the Similar Coefficient Sum (SCS) and Hermite Interpolation are exploited to process the original wind speed data, and the SVM model whose parameters are tuned by an artificial intelligence model is built to make forecast. The results of case studies show that the MAPE value of the hybrid model varies from 22.96% to 28.87 %, and the MAE value varies from 0.47 m/s to 1.30 m/s. Generally, Sign test, Wilcoxon’s Signed-Rank test, and Morgan--Granger--Newbold test tell us that the proposed model is different from the compared models.     

BP模型的改进及其在大气污染预报中的应用

针对传统BP模型存在着训练速度较慢、局部极值以及最佳网络结构无法准确确定的不足，进行了改进，应用于城市空气污染预报，建立大气污染浓度的神经网络预测模型。计算结果表明，应用改进的BP模型进行大气污染预报能够得到更好的预测结果，具有很强的实用性。     

人工智能技术集成方法以及在塑性加工中的应用研究

论述了海洋工程所面临的严重挑战。阐述了舰船行业中舰船材料、构件的海洋环境腐蚀防护试验概况以及舰船机电设备环境试验、舰船海洋(含湖水)环境物理性能(电磁、水声、水压等)测试和海洋风、浪、流等海洋环境观测和试验发展概况。     

t分布受控遗传算法优化BP神经网络的PM2.5质量浓度预测

根据齐齐哈尔大学监测点2014年3—5月PM2?5质量浓度及其对应的每小时的气象因素、气体污染物浓度,建立基于t分布受控遗传算法的BP神经网络模型（ BPM?TCG）,对PM2?5质量浓度进行模拟预测。并将其与BP神经网络模型、遗传算法优化BP神经网络模型（ BP?GA）进行对比分析。3种模型预测结果表明：BPM?TCG模型预测精度最高,泛化能力最好。 BPM?TCG模型对PM2?5质量浓度的准确预测为预防和控制PM2?5提供依据。     

Deep Ethology, Animal Rights, and the Great Ape/Animal Project: Resisting Speciesism and Expanding the Community of Equals

In this essay I argue that the evolutionary and comparative study of nonhuman animal (hereafter animal) cognition in a wide range of taxa by cognitive ethologists can readily inform discussions about animal protection and animal rights. However, while it is clear that there is a link between animal cognitive abilities and animal pain and suffering, I agree with Jeremy Bentham who claimed long ago the real question does not deal with whether individuals can think or reason but rather with whether or not individuals can suffer. One of my major goals will be to make the case that the time has come to expand. The Great Ape Project (GAP) to The Great Ape/Animal Project (GA/AP) and to take seriously the moral status and rights of all animals by presupposing that all individuals should be admitted into the Community of Equals. I also argue that individuals count and that it is essential to avoid being speciesist cognitivists; it really doesn't matter whether ‘dogs ape’ or whether ‘apes dog’ when taking into account the worlds of different individual animals. Narrow-minded primatocentrism and speciesism must be resisted in our studies of animal cognition and animal protection and rights. Line-drawing into ‘lower’ and ‘higher’ species is a misleading speciesist practice that should be vigorously resisted because not only is line-drawing bad biology but also because it can have disastrous consequences for how animals are viewed and treated. Speciesist line-drawing also ignores within species individual differences. This revised version was published online in July 2006 with corrections to the Cover Date.     

基于遗传神经网络的入侵检测研究

入侵检测技术是计算机网络信息安全检测的重要手段之一,入侵检测作为一种动态的安全防护技术,提供了对内部攻击、外部攻击和误操作的实时保护,在网络系统受到危害之前拦截和响应入侵。对计算机网络数据进行特征提取,提出了采用遗传算法和神经网络相结合入侵检测技术。遗传算法具有计算简单、优化效果好的特点。利用遗传算法来避免BP算法的局部极小点,从而达到均方根误差全局最小点,也解决了BP算法的收敛慢的问题;同时也解决了单独利用GA往往不能在短时间内寻找到接近最优解的这一问题。通过计算机实验验证了入侵检测的效果,提高了识别率,使得误报率和漏报率降低。     

基于混合遗传算法的模拟电路自动设计研究

模拟电路在电子系统设计中具有重要意义．模拟电路设计包括电路拓扑结构设计和元件值设计，这两个方面对计算机辅助模拟电路设计都很重要．但是，传统的遗传算法在不断进化电路元件值时效率低．因此，本文提出一种具有超突变和精英策略的混合遗传算法HME-GA．该方法不仅可以用来设计电路的拓扑结构，而且可用于设计电路的元件值．实验结果表明，HEM-GA算法优于简单遗传算法GA，可作为计算机辅助模拟电路设计的有效方法，在模拟电路自动化设计中具有非常重要的意义和巨大的应用潜力．     

基于运行安全的停机位分配问题研究

随着民航运输业的发展,航班密度不断增加,相邻停机位间推出冲突概率不断增加。为合理分配大型繁忙机场停机位,兼顾安全与效率,建立基于运行安全的停机位分配问题优化模型。在模型中加入约束条件以避免潜在的推出冲突,以及考虑将重要航班优先分配到指定的旅客行走距离较短的停机位,来提高旅客的整体满意度。通过分析机位分配特点,选择性能比较优越的遗传算法进行求解。最后用实际算例进行验证,得到停机位分配甘特图以及算法收敛曲线。从结果中可以看到,停机位分配比较合理,算法收敛性能良好。就整体而言,达到了预期的要求。     

基于改进支持向量机的石煤提钒行业清洁生产评价研究

采用遗传算法(GA)对支持向量机(SVM)进行改进,并将其应用于石煤提钒行业清洁生产评价.在系统研究石煤提钒工艺类型的基础上,根据前期已建立的石煤提钒行业清洁生产评价指标体系,提出GA改进SVM的应用思路,通过对3种工艺类型企业的现场数据采集,形成训练和测试样本,并利用GA算法确定出各类参数(惩罚参数C和核函数参数g),分别为强酸浸工艺C=2.1049,g=5.2184;弱酸浸工艺C=0.0035286,g=1.9947;水浸工艺C=0.39587,g=1.4105.GA-SVM模型测试结果表明,分类精度达到100%.通过与其他评价方法对比表明,训练好的GA-SVM方法针对小样本数据在分类精度和可操作性上都较其他方法有明显优势,实现了对石煤提钒行业清洁生产水平的定量评价.