Effects of oxygen concentration on the macroscopic characteristic indexes of high-temperature oxidation of coal

To explore the macroscopic characteristic indexes for oxidation of coal under high-temperature conditions, an XKGW-1-type high-temperature-programmed heating experimental system was constructed. Tests on high-temperature oxidation of coal under high-temperature conditions at five oxygen concentrations of 21, 17, 13, 8, and 3 vol% were independently conducted. Laws of variation in high-temperature oxidation of coal indices, such as the coal temperature, gas ratios, rate of oxygen consumption, and exothermic strength from indoor temperature to 500 °C, were investigated at those oxygen concentrations. The results showed that the variation tendencies of characteristic indices for high-temperature oxidation of coal at different oxygen concentrations were extremely intricate. At the five oxygen concentrations, the rate of oxygen consumption increased rapidly with an increase in coal temperature and eventually remained at a higher range. The rate of oxygen consumption increased with temperature with an approximate exponential trend at the five oxygen concentrations tested. For the same coal temperature, the rate of oxygen consumption decreased with the oxygen concentration. The variation tendencies of the CO and CO₂ production rates were similar, both increased rapidly with an increase in coal temperature in the early stages and reached a maximum at a coal temperature of 380 °C. They decreased slightly with an increase in coal temperature at first and increased promptly thereafter. The concentrations of CH₄, C₂H₄, and C₂H₆ first increased with an increase in the coal temperature and markedly decreased after the maximal value. The temperatures for the extreme points were 480, 410, and 420 °C for CH₄, C₂H₄, and C₂H₆, respectively. The trends of the macroscopic characteristic indexes throughout the process of high-temperature oxidation of coal in a certain temperature range at various oxygen concentrations can be used for temperature prediction and fire prevention during coal mining.     

Comparison of the fatigue behaviors of FRP bridge decks and reinforced concrete conventional decks under extreme environmental conditions

This paper summarizes the results of the fatigue test of four composite bridge decks in extreme temperatures (-30°C and 50°C). The work was performed as part of a research program to evaluate and install multiple FRP bridge deck systems in Dayton, Ohio. A two-span continuous concrete deck was also built on three steel girders for the benchmark tests. Simulated wheel loads were applied simultaneously at two points by two servo-controlled hydraulic actuators specially designed and fabricated to perform under extreme temperatures. Each deck was initially subjected to one million wheel load cycles at low temperature and another one million cycles at high temperature. The results presented in this paper correspond to the fatigue response of each deck for four million load cycles at low temperature and another four million cycles at high temperature. Thus, the deck was subjected to a total of ten million cycles. Quasi-static load-deflection and load-strain responses were determined at predetermined fatigue cycle levels. Except for the progressive reduction in stiffness, no significant distress was observed in any of the composite deck prototypes during ten million load cycles. The effects of extreme temperatures and accumulated load cycles on the load-deflection and load-strain response of FRP composite and FRP-concrete hybrid bridge decks are discussed based on the experimental results.     

极小刻划间隙下的衍射光强度变化规律分析

讨论了极小刻划间隙下的衍射场光强度分布规律,并以单缝为例分析了当缝宽与波长改变时,相对光强度变化规律,补充和完善了使用普通平行光照明系统时的接近式光刻衍射场理论。     

新型高效磷系极压剂的研究

根据分子设计原理,合成了一种磷系极压抗磨剂,试验结果表明,含磷添加剂具有优异的摩擦磨损性能,其PB、PD值有较大提高,已超过硫化异丁烯的极压抗磨性能.     

Comparative Study of ELM and SVM in Hyperspectral Image Supervision Classification

Combining the spatial features and spectral feature of hyperspectral remote sensing image in supervised classification can effectively improve the classification time and accuracy.In this study,the spatial information extraction method,named watershed transform,was combined with the Extreme Learning Machine(ELM)and Support Vector Machine(SVM)methods.The classification results of the datasets with the spatial features and without the spatial features were synthetically evaluated and compared.Two hyperspectral datasets,the ROSIS data of Pavia university and the Hyperion data of Okavango Delta(Botswana),were selected to test the methods.After preprocessing,the training samples were selected from the images as the reference areas for each type,and the spectral features of each type were analyzed.The two classification methods were utilized to classify the hyperspectral datasets and relevant classification results were obtained.based on the validation samples selected from the images,the classification results were evaluated using the confusion matrix and the execution times.After that,the spectral features and spatial features were combined to classify the data.The results show that the Extreme Learning Machine(ELM) is superior to the Support Vector Machine(SVM)in the classification time and precision,and the spatial features are introduced in the classification process,which can effectively improve the classification accuracy.     

Meta-cognitive Recurrent Recursive Kernel OS-ELM for concept drift handling

In this paper, a Meta-cognitive Recurrent Recursive Kernel Online Sequential Extreme Learning Machine with Drift Detector Mechanism (meta-RRKOS-ELM-DDM) is proposed. It combines the strengths of Recurrent Kernel Online Sequential Extreme Learning Machine with a new modified Drift Detector Mechanism (DDM) and Approximate Linear Dependency Kernel Filter (ALD) in solving concept drift problems and reducing complex computations in the learning. The recursive kernel method successfully replaces the normal kernel method in Recurrent Kernel Online Sequential Extreme Learning Machine with DDM (RKOS-ELM-DDM) and generates a fixed reservoir with optimized information in enhancing the forecasting performance. Meta-cognitive learning strategy decides when the incoming data needs to be updated, retrained, or discarded during learning and automatically finding ALD threshold that reduces the learning time of prediction model. In the experiment, six synthetic and three real-world time series datasets are used to evaluate the ability of recursive kernel method, the performance of concept drift detectors, and meta-cognitive learning strategy in time series prediction. Experimental results indicate the meta-RRKOS-ELM with DDM has superior prediction ability in the different predicting horizons as compared with other algorithms.     

Forecasting reservoir monthly runoff via ensemble empirical mode decomposition and extreme learning machine optimized by an improved gravitational search algorithm

Monthly streamflow prediction plays a significant role in reservoir operation and water resource management. Hence, this research tries to develop a hybrid model for accurate monthly streamflow prediction, where the ensemble empirical mode decomposition (EEMD) is firstly used to decompose the original streamflow data into a finite amount of intrinsic mode functions (IMFs) and a residue; and then the extreme learning machine (ELM) is employed to forecast each IMFs and the residue, while an improved gravitational search algorithm (IGSA) based on elitist-guide evolution strategies, selection operator and mutation operator is used to select the parameters of all the ELM models; finally, the summarized predicated results for all the subcomponents are treated as the final forecasting result. The hybrid method is applied to forecast the monthly runoff of Three Gorges in China, while four quantitative indexes are used to test the performances of the developed forecasting models. The results show that EEMD can effectively separate the internal characteristics of the original monthly runoff, and the hybrid model is able to make an obvious improvement over other models in hydrological time series prediction.     

PCA和PSO-ELM在高炉铁水硅含量中的预测仿真

炉温的实时预测技术对高炉运转具有重要意义。在高炉炼铁过程中,通常以铁水硅含量来表征高炉热状态。针对硅含量预测效率和精度不足的问题,提出主成分分析和粒子群改进的极限学习机相结合的方法对高炉铁水硅含量进行预测。由于影响铁水硅含量的因素众多,且各因素之间相互影响,通过主成分分析对影响硅含量的输入变量进行降维处理。利用粒子群算法来优化极限学习机的权值和阈值,并以均方根误差作为适应度函数建立预测模型。将提取出的主成分作为模型输入,铁水硅含量作为模型输出。最后比较了极限学习机算法和粒子群改进的极限学习机,实验结果表明改进后的预测模型提高了硅含量预测的准确度,上述方法可为高炉的生产操作提供参考。     

基于KLLDA和ELM的新型模拟电路故障诊断方法

模拟电路是工业设备中最重要的元器件,其故障可能造成重大的人员伤亡,甚至造成巨大的经济损失。针对这一问题,提出一种基于核局部线性判别分析(Kernel Local Linear Discriminant Analysis,KLLDA)的故障诊断方案。利用小波分析和统计分析对原始信号进行预处理,得到原始特征集;利用KLLDA方法进行降维,并与核主成分分析(Kernel Principal Component Analysis,KPCA)和核线性判别分析(Kernel Linear Discriminant Analysis,KLDA)方法进行比较;采用极限学习机(Extreme Learning Machine,ELM)对测试电路的故障进行定位。对两个故障诊断案例的实验结果表明了该方法的有效性,并表明KLLDA在降维方面总体上优于KPCA和KLDA。     

基于Tri-DE-ELM的半监督模式分类方法研究

针对极限学习机（ELM）未充分利用未标注样本、训练精度受网络权值初值影响的问题,提出一种基于协同训练与差分进化的改进ELM算法（Tri-DE-ELM）。考虑到传统的ELM模式分类技术只利用了少量标注样本而忽视大量未标注样本的问题,首先应用基于Tri-Training算法的协同训练机制构建Tri-ELM半监督分类算法,利用少量的标记样本训练三个基分类器实现对未标记样本的标注。进一步针对基分类器训练中ELM网络输入层权值随机初始化影响分类效果的问题,采用差分进化（DE）算法对网络初值进行优化,优化目标及过程同时包括网络权值和分类误差两方面的因素,以避免网络的过拟合现象。在标准数据集上的实验结果表明,Tri-DE-ELM算法能有效地利用未标注数据,具有比传统ELM更高的分类精度。