Interval finite difference method for steady-state temperature field prediction with interval parameters

A new numerical technique named interval finite difference method is proposed for the steady-state temperature field prediction with uncertainties in both physical parameters and boundary conditions. Interval variables are used to quantitatively describe the uncertain parameters with limited information. Based on different Taylor and Neumann series, two kinds of parameter perturbation methods are presented to approximately yield the ranges of the uncertain temperature field. By comparing the results with traditional Monte Carlo simulation, a numerical example is given to demonstrate the feasibility and effectiveness of the proposed method for solving steady-state heat conduction problem with uncertain-but-bounded parameters.

Prediction of Superconductivity for Oxides Based on Structural Parameters and Artificial Neural Network Method

Superconductive properties for oxides were predicted by artificial neural network (ANN) method with structural and chemical parameters as inputs. The predicted properties include superconductivity for oxides, distributed ranges of the superconductive transition temperature (Tc) for complex oxides, and Tc values for cuprate superconductors. The calculated results indicated that the adjusted ANN can be used to predict superconductive properties for unknown oxides.

BAYESIAN PREDICTION FOR THE TWO-PARAMETER EXPONENTIAL DISTRIBUTION BASED ON TYPE Ⅱ DOUBLY CENSORING

The two-parameter exponential distribution is proposed to be an underlying model,and prediction bounds for future observations are obtained by using Bayesian approach.Prediction intervals are derived for unobserved lifetimes in one-sample prediction and two-sample prediction based on type Ⅱ doubly censored samples.A numerical example is given to illustrate the procedures,prediction intervals are investigated via Monte Carlo method,and the accuracy of prediction intervals is presented.

Predictive Modeling and Parameter Optimization of Cutting Forces During Orbital Drilling

To optimize cutting control parameters and provide scientific evidence for controlling cutting forces,cutting force modeling and cutting control parameter optimization are researched with one tool adopted to orbital drill holes in aluminum alloy 6061.Firstly,four cutting control parameters(tool rotation speed,tool revolution speed,axial feeding pitch and tool revolution radius)and affecting cutting forces are identified after orbital drilling kinematics analysis.Secondly,hybrid level orthogonal experiment method is utilized in modeling experiment.By nonlinear regression analysis,two quadratic prediction models for axial and radial forces are established,where the above four control parameters are used as input variables.Then,model accuracy and cutting control parameters are analyzed.Upon axial and radial forces models,two optimal combinations of cutting control parameters are obtained for processing a13mm hole,corresponding to the minimum axial force and the radial force respectively.Finally,each optimal combination is applied in verification experiment.The verification experiment results of cutting force are in good agreement with prediction model,which confirms accracy of the research method in practical production.

Evaluation of Some Weibull Parameter Estimation Methods for Characterizing Stem Diameter Distribution in a Tropical Mixed Forest of Southern Nigeria

Stem diameter distribution information is useful in forest management planning. Weibull function is flexible, and has been used in characterising diameter distributions, especially in single-species planted stands, the world over. We evaluated some Weibull parameter estimation methods for stem diameter characterisation in （Oban） multi-species Forest in southern Nigeria. Four study sites （Aking, Ekang, Erokut and Ekuri） were selected. Four 2 km-long transects situated at 600 m apart were laid in each location. Five 50m x 50m plots were alternately laid along each transect at 400 m apart （20 plots/location） using systematic sampling technique. Tree growth variables： diameter at breast height （Dbh）, diameters at the base, middle and merchantable limit, total height, merchantable height, stem straightness, crown length and crown diameter were measured on all trees 〉 10 cm to compute model response variables such as mean diameters, basal area and stem volume. Weibull parameters estimation methods used were： moment-based, percentile-based, hybrid and maximum-likelihood （ML）. Data were analysed using descriptive statistics, regression models and ANOVA at α0.05. Percentile-based method was the best for Weibull [location （a）, scale （b） and shape （c）] parameters estimations with mLogL = 116.66±21.89, while hybrid method was least-suitable （mLogL = 690.14±128.81） for Weibull parameters estimations. Quadratic mean diameter （Dq） was the only suitable predictor of Weibull parameters in Oban Forest.

Research on Optimize Prediction Model and Algorithm about Chaotic Time Series

We put forward a chaotic estimating model, by using the parameter of the chaotic system, sensitivity of the parameter to inching and control the disturbance of the system, and estimated the parameter of the model by using the best update option. In the end, we forecast the intending series value in its mutually space. The example shows that it can increase the precision in the estimated process by selecting the best model steps. It not only conquer the abuse of using detention inlay technology alone, but also decrease blindness of using forecast error to decide the input model directly, and the result of it is better than the method of statistics and other series means. Key words chaotic time series - parameter identification - optimal prediction model - improved change ruler method CLC number TP 273 Foundation item: Supported by the National Natural Science Foundation of China (60373062)Biography: JIANG Wei-jin (1964-), male, Professor, research direction: intelligent compute and the theory methods of distributed data processing in complex system, and the theory of software.

Average Life Prediction Based on Incomplete Data

The two-parameter exponential distribution can often be used to describe the lifetime of products for example, electronic components, engines and so on. This paper considers a prediction problem arising in the life test of key parts in high speed trains. Employing the Bayes method, a joint prior is used to describe the variability of the parameters but the form of the prior is not specified and only several moment conditions are assumed. Under the condition that the observed samples are randomly right censored, we define a statistic to predict a set of future samples which describes the average life of the second-round samples, firstly, under the condition that the censoring distribution is known and secondly, that it is unknown. For several different priors and life data sets, we demonstrate the coverage frequencies of the proposed prediction intervals as the sample size of the observed and the censoring proportion change. The numerical results show that the prediction intervals are efficient and applicable.

Aircraft parameter estimation using a stacked long short-term memory network and Levenberg-Marquardt method

To effectively estimate the unknown aerodynamic parameters from the aircraft’s flight data,this paper proposes a novel aerodynamic parameter estimation method incorporating a stacked Long Short-Term Memory(LSTM)network model and the Levenberg-Marquardt(LM)method.The stacked LSTM network model was designed to realize the aircraft dynamics modeling by utilizing a frame of nonlinear functional mapping based entirely on the measured input-output data of the aircraft system without requiring explicit postulation of the dynamics.The LM method combines the already-trained LSTM network model to optimize the unknown aerodynamic parameters.The proposed method is applied by using the real flight data,generated by ATTAS aircraft and a bio-inspired morphing Unmanned Aerial Vehicle(UAV).The investigation reveals that for the two different flight data,the designed stacked LSTM network structure can maintain the efficacy of the network prediction capability only by appropriately adjusting the dropout rates of its hidden layers without changing other network parameters(i.e.,the initial weights,initial biases,number of hidden cells,time-steps,learning rate,and number of training iterations).Besides,the proposed method’s effectiveness and potential are demonstrated by comparing the estimated results of the ATTAS aircraft or the bio-inspired morphing UAV with the corresponding reference values or wind-tunnel results.

Recursive Parameter Method for Computing the Predicting Function of the Multivariable ARMAX Model

New method for computing the predicting function of the ARMAX model is proposed. The proposed method constructs a set of schemes for recursively computing the parameters in predicting function of the ARMAX model. In contrast to the existing method, that only gives results for the special case of the ARX model, the method presented is suitable not only for an SISO system, but also for an MIMO system. For the SISO system, the method presented here is even more convenient than the exisiting ones.

UCM-PPM:基于用户分级的多参量Web预测模型

Web在过去数十年飞速发展,其低延迟和快响应的特性已经变得越来越重要.面对这样的需求,通常会预取用户即将访问的文件到缓存中,利用代理服务器缓存来获取数据,避免网络堵塞,提高Web访问效率.可见,在预取技术中,一个有效的预测模型是非常有必要的.针对目前缓存预取工作对用户差异关注度不足和度量指标单一化的薄弱环节,提出一个基于用户分级化的Web预测模型,并且能够随着Web请求进行多参数动态调整.该模型通过对代理服务器上用户访问情况分布的变化趋势分析,将用户集分为重要性不同的若干等级,并适当利用序列相似度来聚类低贡献用户产生的会话,之后在部分匹配预测模型的基础上,结合缓存替换策略为预测树结点构造包含多个参量的目标函数,并使构建好的模型能够进行自适应调整.最后通过实验证明该模型可以有效提高缓存的预取性能.

基于鲁棒双参数指数平滑法的BDS卫星钟差预报

为提高北斗(BDS)卫星钟差预报精度与稳定性,基于BDS卫星钟工作原理与数据特征,提出了一种基于鲁棒双参数指数平滑法的BDS卫星钟差预报方法。将双参数指数平滑法引入BDS钟差预报,并通过鲁棒化建模与优化初始值选取方式提升了双参数指数平滑法的抗差与适应能力,减小了数据异常干扰对钟差预报性能的影响。与常用的多项式模型、谱分析模型、灰色预测模型及超快速钟差预报产品进行对比分析,结果表明:所提方法适用于不同BDS轨道与类型的卫星钟差预报,取得了良好的预报精度与稳定性,其对BDS卫星钟的6h平均预报精度分别提升了40.3%、31.7%、63.6%和36.6%,预报稳定性分别提升了43.8%、38.9%、65.4%和33.1%。

纵扭超声振动辅助铣削60%SiC_(p)/Al多目标参数优化研究

针对高体积分数碳化硅颗粒增强型铝基复合材料(SiC_(p)/Al)在铣削过程中加工难度大、表面质量差等问题,提出了纵扭超声振动辅助铣削复合工艺。以超声振幅、切削速度、每齿进给量和切削深度为变量,设计了四因素五水平正交试验。通过响应曲面法和人工神经网络,建立了切削力、切削温度和表面粗糙度的预测模型,分析了4个参数变量中两个指标的交互影响作用,并对预测模型的准确性进行了对比验证。最后,采用遗传算法对切削力、切削温度和表面粗糙度进行了多目标参数优化。结果表明,响应曲面法与人工神经网络建立的模型均有较好的预测能力,但人工神经网络准确性更高。采用遗传算法优选出的最佳参数组合为超声振幅A=1.84μm,切削速度v_(c)=20 m/min,每齿进给量f_(z)=0.015 mm/z,切削深度a_(p)=0.8 mm,经过验证试验后发现,采用优选参数有效降低了切削力、切削温度和表面粗糙度,各值分别为切削力F_(t)=7.23 N,切削温度T=40.18℃,表面粗糙度R_(a)=2.4673μm,预测误差分别为6.91%、6.53%、2.53%,证明了预测模型的准确性与优化参数的有效性。

二氧化氮浓度时空预测:一种区间二型直觉模糊神经网络方法

空气中二氧化氮浓度的高低对环境保护和公共健康具有重要影响。目前二氧化氮浓度预测方法在表征时空关联性方面存在不足。鉴于此,提出了新的使用区间二型直觉模糊神经网络时空预测二氧化氮浓度的方法。首先,阐述了该区间二型直觉模糊神经网络框架,引入可变系数加权其隶属部分和非隶属部分的输出,并采用随机向量泛函链接神经网络作为规则后件;然后,为确定网络结构和参数,采用分层聚类算法得到模糊规则库,并通过最小二乘法优化网络后件的输出权值;最后,使用2018年1月至3月采集的北京市二氧化氮浓度真实数据进行数值验证。实验结果表明,与现有方法相比,该方法在短期和长期时空预测方面均取得了较高的预测精度和效率。

基于软注意力GRU模型的堆芯瞬态热工水力参数预测方法研究

反应堆在各种工况下堆芯瞬态热工水力参数预测的准确性,直接影响到反应堆的安全性。质量流量和温度作为堆芯热工水力的重要参数,二者常被建模为时间序列预测问题。研究旨在解决瞬时条件下堆芯热工水力参数连续预测的精度问题,检验基于注意力机制的门控循环单元在核心参数预测中的可行性。本文采用1/2中国实验快堆(China Experimental Fast Reactor,CEFR)为研究对象,使用快堆子通道程序SUBCHANFLOW生成瞬态堆芯热工水力参数的时间序列,采用基于软注意力的门控循环单元(Gated Recurrent Unit,GRU)模型预测堆芯的质量流量和温度时间序列。结果表明:相较于自适应径向基(Radial Basis Function,RBF)神经网络,本文使用的软注意力的GRU网络模型预测结果更好,温度在步长为3的情况下平均相对误差不超过0.5%,在15 s内预测效果较好;质量流量在步长为10的情况下平均相对误差不超过5%,且在后续12 s内预测效果较好。本文构建的模型不仅在连续预测过程中表现出更高的预测精度,且能捕捉到动态时间序列中的趋势特点,这对维护反应堆安全,有效防止核电厂事故有极大的用处。基于软注意力的GRU模型能在瞬态反应堆工况下提供一段时间的连续预测,在工程应用中和提高反应堆安全性上具有一定的参考价值。

基于优化极限学习机模型的反应堆中子通量与k_(eff)预测方法研究

通过模拟和扩展人类智能,人工智能能够解决预测反应堆k_(eff)和中子通量等问题。本研究选用国际原子能机构(International Atomic Energy Agency,IAEA)反应堆作为研究对象,以稳态时的堆芯中子通量和k_(eff)为预测量,通过堆芯物理分析程序ADPRES生成数据样本后,利用极限学习机(Extreme Learning Machine,ELM)构建中子通量和k_(eff)的基础神经网络模型,随后通过随机森林(Random Forest,RF)评估特征值重要程度以建立各模型最佳输入特征子集,采用遍历方法确定隐藏层最佳神经元数目,最后使用鲸鱼优化算法(Whale Optimization Algorithm,WOA)对其初始权值与阈值进行优化,进一步提高了模型的精度。研究结果显示:经降维优化处理后,神经网络的预测能力有较大提升,其中k_(eff)的预测精度提高了两个量级,中子通量的预测误差降低了87.24%,并且减少了模型训练时间。本文构建方法对快速评估堆芯物理特性有一定参考意义。

开采沉陷动态预测时间函数参数变化规律研究——以Weibull为例

针对开采沉陷动态预测模型中时间函数参数主要以最大下沉点的下沉时间序列为基础反演获取,在工作面上方空间位置变化规律研究不足的问题;依据工作面推进过程中覆岩受力、垮落情况,在平面方向上将采空区分为竖向整体受压区、中间区、动态完全区3个区间;以Weibull时间函数为例,分析了动态预测m、k 2个参数的含义、空间分布规律及特点,并构建2个参数的分区数学模型及选取准则;分别以实测最终值、概率积分法预测值为基准,通过实例验证了其正确性,丰富了开采沉陷动态预测参数研究。

基于参数辨识的磁聚焦式扭矩传感器模型研究

为解决磁聚焦式扭矩传感器模型未知参数问题,实现其更精确地测量,文中通过对此传感器机理分析建立了数学模型与非零初始条件下的系统模型,确定了辨识参数矩阵。提出了一种预测误差法与自适应粒子群算法相结合的参数辨识方法。搭建正弦激励校准实验系统对其进行验证,结果表明,该方法有效地实现了传感器参数的辨识,得到的传感器模型具有较高的精度,为其动态特性分析与误差补偿提供了可靠依据。

A progressive approach to predict shot peening process parameters for forming integral panel of Al7050-T7451

In this paper,a progressive approach to predict the multiple shot peening process parameters for complex integral panel is proposed.Firstly,the invariable parameters in the forming process including shot size,mass flow,peening distance and peening angle are determined according to the empirical and machine type.Then,the optimal value of air pressure for the whole shot peening is selected by the experimental data.Finally,the feeding speed for every shot peening path is predicted by regression equation.The integral panel part with thickness from 2 mm to 5 mm and curvature radius from 3200 mm to 16000 mm is taken as a research object,and four experiments are conducted.In order to design specimens for acquiring the forming data,one experiment is conducted to compare the curvature radius of the plate and stringer-structural specimens,which were peened along the middle of the two stringers.The most striking finding of this experiment is that the outer shape error range is below 3.9%,so the plate specimens can be used in predicting feeding speed of the integral panel.The second experiment is performed and results show that when the coverage reaches the limit of 80%,the minimum feeding speed is 50 mm/s.By this feeding speed,the forming curvature radius of the specimens with different thickness from the third experiment is measured and compared with the research object,and the optimal air pressure is 0.15 MPa.Then,the plate specimens with thickness from 2 mm to 5 mm are peened in the fourth experiment,and the measured curvature radius data are used to calculate the feeding speed of different shot peening path by regressive analysis method.The algorithm is validated by forming a test part and the average deviation is 0.496 mm.It is shown that the approach can realize the forming of the integral panel precisely.

多参数评价准噶尔盆地车莫古隆起北部断层封闭性

车莫古隆起北部地区在侏罗系中相继发现了一系列断块油气藏,断层封闭性的好坏控制了研究区油气的生成和聚集。为了研究多类型断层封闭能力,利用地震、测井等资料,采用断面正应力、断面紧闭指数、泥质含量和泥岩削刮比等参数,针对不同性质的断裂优选多种参数组合方式,开展断层封闭性评价,结合3Dmove软件虚拟井法进行封闭性分析,最后运用模糊数学评价方法得到综合评价指标,总结影响断层封闭能力的各种因素,预测有利断层。研究结果表明,车莫古隆起北部地区断层封闭性中等偏差,其中,现今封闭性好于成藏期。断层封闭能力主要受走向、规模以及泥岩与砂岩的厚度影响,与断面正压力无明显关系。沙窝地地区断层封闭性好于莫西庄地区,庄北地区断层封闭性最差。通过多种方法综合研究车莫古隆起北部断层封闭性,对预测有利断层、寻找油气富集的断块油气藏具有重要意义。