The experiment progress of bracket brazing to SSMIC for the ITER ELM prototype coil

The first Edge Localized Modes (ELMs) prototype coil for International Thermonuclear Experimental Reactor (ITER) has been manufactured in the Institute of Plasma Physics, CAS (ASIPP) at 2014. The all 19 brackets need to braze to the stainless steel jacketed, Mineral Insulated Conductor (SSMIC) for transporting the nuclear heating in the brackets to the water-cooled SSMIC. Silver-based alloy is the only candidate brazing filler for the bracket brazing due to the limitation from melting point temperature and strength. In this paper, firstly, the experimental study for controlling the fluidity of silver-based brazing alloy is developed. And then, the brazing experiment of prototype bracket is introduced to develop the brazing process and some cracks in the Inconel 625 jackets surface appeared unexpectedly. The microstructures and tensile performance study of the cracked Inconel 625 jacket were made to explore the reason for cracks and the improved brazing technologies to suppress the cracks are developed. Finally, the bracket brazing experiment for the first ELM prototype coil is carried out, In spite of this, some cracks also appear in the Inconel 625 jackets.     

考虑风电-光伏功率相关性的因子分析-极限学习机聚合方法

针对风电和光伏时序数据单独聚合改变风电-光伏序列相关性的问题,提出因子分析-极限学习机聚合方法.首先,将z-score标准化的风电-光伏原始日场景集分解为水平分量日场景集和波动分量日场景集.其次,对水平分量日场景集进行近邻传播聚类,得到K类场景簇,再通过分层抽样获取2n天的水平分量日场景集.在标准化的风电-光伏原始日场景集中选取对应2n天的原始日场景集,分别得到n天的训练集和n天的测试集.然后,通过极限学习机获取水平分量日场景集和原始日场景集之间的映射关系,输出拟合功率日场景集.最后,通过反标准化,分别得到n天的风电和光伏功率的聚合序列,并通过概率统计指标、相关系数、仿真计算结果验证所提方法的准确性和可行性.     

因子分析和ELM在模拟电路故障诊断的应用

针对非线性模拟电路故障诊断中参数型故障元件定位的难题,提出采用因子分析优化的小波包能量谱和极限学习机的模拟电路故障诊断的方法。该方法首先对采集到的模拟故障数据进行小波包分解并提取不同频带的能量谱,然后利用因子分析对能量谱进行降维以提取故障特征,最后将提取的故障特征输入极限学习机进行故障诊断。仿真结果表明,该方法具有良好的区分能力,提高了故障诊断的效果。     

Selection of Most Relevant Input Parameters Using Principle Component Analysis for Extreme Learning Machine Based Power Transformer Fault Diagnosis Model

The dissolved gas-in-oil analysis is a prevailing methodology being extensively utilized to diagnose incipient faults in oil-immersed power transformers. However distinct approaches have been implemented to find out dissolved gas analysis (DGA) results, they may sometimes fail to diagnose precisely. The incipient fault identification accuracy of various artificial intelligence (AI)-based methodology is assorted with change of input parameters. Thus, selection of input variable to an AI model is major research area. In this paper, principle component analysis algorithm using RapidMiner is applied to 360 experimental datasets, imitated in lab to identify most pertinent input variables for incipient fault classification. Thereafter, multi-class Extreme Learning Machine (ELM) technique is implemented to classify the incipient faults of power transformer and its performance is compared with artificial neural network, gene expression programming, fuzzy-logic, and support vector machine. The compared result shows that ELM provides better diagnosis results up to 100% accuracy at proposed input variable in short of time period which is helpful in on-line condition monitoring.     

Automatic segmentation of hippocampal subfields based on multi-atlas image segmentation techniques

The volume of hippocampal subfields is closely related with early diagnosis of Alzheimer＇s disease. Due to the anatomical complexity of hippocampal subfields, automatic segmentation merely on the content of MR images is extremely difficult. We presented a method which combines multi-atlas image segmentation with extreme learning machine based bias detection and correction technique to achieve a fully automatic segmentation of hippocampal subfields. Symmetric diffeomorphic registration driven by symmetric mutual information energy was implemented in atlas registration, which allows multi-modal image registration and accelerates execution time. An exponential function based label fusion strategy was proposed for the normalized similarity measure case in segmentation combination, which yields better combination accuracy. The test results show that this method is effective, especially for the larger subfields with an overlap of more than 80%, which is competitive with the current methods and is of potential clinical significance.     

热红外与多光谱遥感图像的神经网络回归融合方法研究

为验证神经网络方法用于遥感图像融合的有效性,归纳了利用神经网络对遥感数据进行回归来实现融合的3种途径,并提出了一种结合图像数据回归和多光谱遥感图像锐化技术来实现热红外图像的全色锐化新方法。这种热红外图像的全色锐化方法,利用了极限学习机（ELM）这种新型神经网络算法,快速高效地由训练样本得到遥感图像数据间的回归关系;同时,方法注重图像数据本身的物理含义,以提高热红外图像数据的真实质量为目标,是一种定量化的图像融合方法。经这种方法融合得到的热红外数据也能很好地用于定量遥感的物理模型,为遥感的实际应用提供方便。该方法的有效性通过对ETM+图像进行实验得到了证明,而直接对热红外图像数据和全色图像数据进行回归的融合模式,在实验中则无法得到满意的结果。     

前交叉韧带断裂后足底压力特征的聚类分析

运动过程中,人体的步态特征可以在足底压力图像上有准确的记录,而这也就可以成为判断步态正常与否的一条有效依据.通过一组压力传感器阵列获取人体运动过程的足底压力分布数据,提取步态的运动学和动力学特性.在此基础上,采用极限学习机（Extreme learning machines,ELM）神经网络聚类算法对足底压力数据进行分析,完成正常与异常步态的分类辨识工作.本文从实际临床数据出发,对前交叉韧带断裂患者进行步态分析,并据医生的临床诊断结果进行校验.该方法在步态分析上取得了较为良好的效果,仿真结果表明了其有效性.     

基于因子分析的极限学习机在煤与瓦斯突出等级识别中的应用

煤与瓦斯突出预测是一个非线性、非正态和高维数据处理问题,为了提高预测的准确性和时效性,采用因子分析法将原有的9个判断指标转化为4个综合性指标,再将转化后的指标作为极限学习机(ELM)的输入,充分发挥极限学习机学习速度快、泛化能力强以及容易获得全局唯一最优解的特点,快速准确地进行诊断识别,和BP神经网络、支持向量机SVM比较,极限学习机的建模时间短,对样本数据预测的准确性高,具有借鉴价值。     

Physical design of a new set of high poloidal mode number coils in the EAST tokamak

An external resonant magnetic perturbation (RMP) field, which is an effective method to mitigate or suppress the edge localized mode (ELM), has been planned to be applied on the ELM control issue in ITER. A new set of magnetic perturbation coils, named as high m coils, has been developed for the EAST tokamak. The magnetic perturbation field of the high m coils is localized in the midplane of the low field side, with the spectral characteristic of high m and wide n, where m and n are the poloidal and toroidal mode numbers, respectively. The high m coils generate a strong localized perturbation field. Edge magnetic topology under the application of high m coils should have either a small or no stochastic region. With the combination of the high m coils and the current RMP coils in the EAST, flexible working scenarios of the magnetic perturbation field are available, which is beneficial for ELM control exploration on EAST. Numerical simulations have been carried out to characterize the high m coil system, including the magnetic spectrum and magnetic topology, which shows a great flexibility of magnetic perturbation variation as a tool to investigate the interaction between ELM and external magnetic perturbation.     

Prediction of permafrost changes in Northeastern China under a changing climate

Northeastern China has the second largest expanse of permafrost in China,primarily known as Xing'an-Baikal permafrost.Located on the southeastern edges of the Eurasian cryolithozone,the permafrost is thermally unstable and ecologically sensitive to external changes.The combined impacts of climatic,environmental,and anthropogenic changes cause 3-dimensional degradation of the permafrost.To predict these changes on the southern limit and ground temperature of permafrost in Northeastern China,an equivalent lat...