PSO-LSSVM的电力负荷预测研究

对影响电力负荷因素之间的非线性,有效提高电力负荷的预测精度,本文提出了一种最小二乘支持向量机(LSSVM)和粒子群优化技术(PSO)相结合的电力负荷预测方法。以历史负荷数据气象因素等作为输入,建立预测模型,对未来时刻电力负荷进行预测。该模型利用结构风险最小化原则代替传统的经验风险最小化,以充分挖掘原始数据的信息,并采用粒子群优化算法来优化最小二乘支持向量机的参数,旨在提高预测模型的训练预测精度。实际算例表明,使用PSO-LSSVM方法进行电力负荷预测,具有良好的可行性和有效性,与BP神经网络和LSSVM方法的预测结果相比,所提出的PSO-LSSVM模型预测平均误差仅为0.85%,具有更高的精度,适用于电力负荷预测。     

基于混沌理论和LSSVM的网络攻击预测算法

针对网络攻击具有多样性、时变性,传统预测方法预测精度较差的问题,提出一种混沌理论和LSSVM相融合的网络攻击预测算法.利用网络攻击频率时间序列预测模型参数之间的联系,采用粒子群优化算法对模型参数进行组合优化.采用最优参数的预测模型对具体网络攻击频率数据进行仿真测试,并与其它预测算法进行对比.实验结果表明,该方法对网络攻击频率预测精度要高于对比算法,是一种泛化能力好、预测结果可靠的网络攻击预测算法.     

基于退化特征空间重构的多轴承健康寿命协同预测方法研究

为顺应现代制造业发展要求,做到视情科学维修,延长设备健康寿命。针对传统方法预测准确率较低的问题,采用多个轴承全生命周期数据为实验数据集,并选取均方根、峰值因子、峭度、频谱分区求和四个特征作为预测模型的输入值。另外,采用卷积神经网络构建预测模型,训练模型时采用学习率衰减机制,提高训练效率。实验表明,该方法相较于其他传统方法具有较高的预测准确率,可以对轴承健康寿命进行有效预测。     

改进BP算法的辽宁省人均GDP预测研究

由于人均GDP时间序列具有复杂和非线性的特征,传统预测方法在预测分析时往往会产生很大的误差.运用Matlab软件采用不同的改进BP算法来建立和训练网络预测模型,以观测不同算法的精度和有效性;最后运用预测模型对辽宁省人均GDP进行了预测.     

轴承破裂原因分析

正用断口分析以及FEA仿真分析等方法,对轴承破裂进行了分析。结果表明,该轴承的破裂主要原因是槽口底角设计不合理,致应力集中。有一款关节轴承,内圈直径44mm,材料440C,内圈带槽口;外圈直径84mm,材料17-4PH。在极限静载荷试验中,内圈端面发生破裂,试验失败。     

基于小波变换和优化的LSSVM月径流预测研究

可靠的径流预测能使人们最大限度的协调水资源利用中出现的各种用水矛盾,为及时采取措施进行统筹安排做指导,以便获取最大的效益。对于月径流时间序列的非平稳特性,将小波变换与LSSVM相结合,利用Mallat算法中的db4小波进行3尺度分解及重构,提取出细节信号序列和逼近信号序列,LSSVM分别对每个系数序列预测,针对LSSVM模型参数选择费时费力这一问题,将全局寻优的粒子群算法引入到LSSVM的参数优化中来,构成小波PSO-LSSVM组合预测模型,实例仿真表明,该组合方法的预测精度比PSO-LSSVM模型的高,且参数寻优效果好。     

电子商务客户流失三阶段预测模型

采用某网上商场的2525名客户样本,构建了基于SMC和最小二乘支持向量机(LSSVM)的电子商务客户流失三阶段预测模型.首先应用SMC模型计算出客户活跃度,以0.5为阚值判断出客户流失状态,识别出正判客户和错判客户;其次将训练样本送入LSSVM进行训练和学习,进而对测试样本的客户流失状态进行判别,然后将误判客户样本输入最近邻分类器进行再判断.结果表明,与SMC模型、BP神经网络模型、LSSVM模型相比,三阶段模型对测试样本预测精度更高,是一种更有效和实用的分类方法,可为电子商务企业客户关系管理提供一个新的方法.     

基于改进指数平滑算法的气温预测研究

本文主要研究了基于改进指数平滑算法的气温预测问题。首先引入时间序列模型概念,对常用气温预测模型进行简要分析,另外对一阶指数平滑算法进行相关推导,同时提出了自适应指数平滑算法;其次,结合广西容县近30年月均气温实测数据,分别建立BP神经网络预测模型、传统指数平滑算法预测模型以及改进后的基于自适应指数平滑算法的预测模型,对2016年气温数据进行预测并分析模型优势;最后,将改进模型用于预测2017年和2018年中未知月份的月平均气温值,并针对实验结果进行数据分析修正。通过对不同预测模型的比较和仿真实验,结果表明基于自适应指数平滑算法的气温预测模型预测精度较高,实用性强,具有一定的推广性。     

基于大涡模拟的多孔节流静压气体止推轴承性能分析

以多孔节流静压气体止推轴承为研究对象,采用大涡模拟获得气膜内流场结构,对比分析了简单孔式节流(有气腔)与环形孔式节流(无气腔)轴承内流场特性。结果显示简单孔式节流在气腔内部产生大量涡旋,并且涡旋随时间快速变化,轴承内气体流动不稳定,而环形孔式节流只在节流孔出口附近,产生微弱涡旋,轴承内气体流动平稳。分析了简单孔式节流气膜厚度、节流孔直径、供气压力等参数对轴承性能的影响。结果表明,低供气压力、小节流孔直径、薄气膜厚度、大气腔直径,有利于减小轴承承载面气压波动,轴承微幅自激振动越小,稳定性越好。     

BP神经网络在股价预测中的应用

对BP神经网络方法在股价预测中的应用进行了研究,对BP神经网络的结构进行了介绍。针对BP网络学习速度慢,采用弹性BP学习算法和tansig传递函数提高了收敛速度。在仿真过程中通过MATLAB编程实现了BP神经网络对中国石油近一年交易日的数据的训练和测试,获得了一定的预测精度,对BP算法和改进后的BP算法在预测股票中的收敛性能和拟合程度进行比较,并用训练好的BP网络股市预测模型来预测其股票数据,达到了预测效果。     

抽油机减速箱缺油保护系统的研制

抽油机减速箱损坏的主要原因是减速箱润滑油不足造成的,而目前抽油机减速箱内的油量情况难于实时发现并采取措施,减速箱缺油后,抽油机不能立即停机,而减速箱继续在缺油状态下长期运转,在大多数情况下将造成齿轮、轴承的损坏,甚至报废。为解决这一问题,我们研制了一种实时报警装置,当油量少于设定最小值时,它可以在现场发出报警信号,并对抽油机按要求采取强制停机等措施。     

基于LSSVM-CA模型的复杂土地利用变化模拟——以鄂州市为例

本文探索了最小二乘支持向量机（Least Squares Support Vector Machine ,LSSVM）获取元胞转换规则的可行性,并应用于复杂土地利用变化模拟预测。以湖北省鄂州市为研究区,以1991-2004年土地利用变化数据作为模型训练数据,运用改进的ROC分析方法对比分析了LSSVM和逻辑回归方法获取的元胞转换规则,在此基础上运用LSSVM-CA模型模拟了研究区2013年的土地利用情景,并对2020年和2030年土地利用情景进行预测。研究结果表明：①LSSVM对数量较大、变化过程较复杂土地利用类型的空间分布模拟效果更好,如耕地、建设用地、养殖水体和其他用地;②与2013年实际土地利用情景相比,LSSVM-CA模拟结果总体精度为0.80,Kappa系数为0.73,处于较高一致性水平,优于逻辑回归-CA模型结果;③未来,鄂州市主城区、城西新区、“葛华新城”、“红莲湖新城”以及南部的花湖开发区、沼山镇、太和镇建设用地需求较大,将占用大量耕地,东部和南部低丘岗地区的耕地将大量转变为林地。研究结论为LSSVM方法可用于获取元胞转换规则进行复杂土地利用变化模拟,并能取得较好的效果,模拟结果可为研究区土地规划、耕地和生态环境保护等提供决策参考。     

A privacy preserving framework for federated learning in smart healthcare systems

Federated Learning (FL) is a platform for smart healthcare systems that use wearables and other Internet of Things enabled devices. However, source inference attacks (SIAs) can infer the connection between physiological data in training datasets with FL clients and reveal the identities of participants to the attackers. We propose a comprehensive smart healthcare framework for sharing physiological data, named FRESH, that is based on FL and ring signature defense from the attacks. In FRESH, physiological data are collected from individuals by wearable devices. These data are processed by edge computing devices (e.g., mobile phones, tablet PCs) that train ML models using local data. The model parameters are uploaded by edge computing devices to the central server for joint training of FL models of disease prediction. In this procedure, certificateless ring signature is used to hide the source of parameter updates during joint training for FL to effectively resist SIAs. In the proposed ring signature schema, an improved batch verification algorithm is designed to leverage additivity of linear operations on elliptic curves and to help reduce the computing workload of the server. Experimental results demonstrate that FRESH effectively reduces the success rate of SIAs and the batch verification method significantly improves the efficiency of signature verification. FRESH can be applied to large scale smart healthcare systems with FL involving large numbers of users.     

Droplet formation and shrinking in aqueous two-phase systems using a membrane emulsification method

Using a membrane emulsification method based on porous hollow-fiber membranes in combination with an aqueous two-phase system (ATPS), we are able to produce “water-in-water” droplets with narrow-dispersed size distributions. The equilibrium phases of the aqueous two-phase system polyethylene glycol-dipotassium hydrogen phosphate are used for this purpose. The droplet diameter of a given fluid system is determined by the flow rates of the continuous and disperse phase as well as the hollow fiber dimensions. When diluting the disperse phase and thus moving the ATPS system out of equilibrium, the droplet size can be further reduced in comparison to the equilibrium case. Generally, droplets formed with this method have diameters 20%–60% larger than the inner hollow fiber diameter. The new strategy of diluting the disperse phase allows the production of droplet diameter below the inner diameter of the membrane.     

测定土塑限的试验方法研究

塑限是细粒土的一个重要特征，它反映了土粒和水相互作用时的性态。土的塑限指标的测定长期采用滚搓法。该法最大的缺点是要求试验者作出很大的判断。本文为圆锥设计了一个环型样杯来测土的塑限。环型样杯直径20毫米，高20毫米，用于3～10毫米的圆锥入土深度的试验中。     

不同瓦斯压力测定法在贵州某矿的对比应用研究

本论文通过采用胶圈-黏液封孔瓦斯压力测定法和传统的注浆封孔法进行煤层瓦斯压力测定,得出了胶圈-黏液封孔瓦斯压力测定法测压时间短,压力值更准确,其明显优于传统的注浆封孔测压法,且测压设备能重复使用,故值得在煤矿企业推广使用,能够有效的指导矿井生产,提高工作效率。     

Unsupervised cross-domain rolling bearing fault diagnosis based on time-frequency information fusion

In recent years, data-driven methods have been widely used in rolling bearing fault diagnosis with great success, which mainly relies on the same data distribution and massive labeled data. However, bearing equipment is in normal working state for most of the time and operates under variable operating conditions. This makes it difficult to obtain bearing data labels, and the distribution of the collected samples varies widely. To address these problems, an unsupervised cross-domain fault diagnosis method based on time-frequency information fusion is proposed in this paper. Firstly, wavelet packet decomposition and reconstruction are carried out on the bearing vibration signal, and the energy eigenvectors of each sub-band are extracted to obtain a 2-D time-frequency map of fault features. Secondly, an unsupervised cross-domain fault diagnosis model is constructed, the improved maximum mean discrepancy algorithm is used as the measurement standard, and the joint distribution distance is calculated with the help of pseudo-labels to reduce data distribution differences. Finally, the model is applied to the motor bearing for comparison and verification. The results demonstrate its high diagnosis accuracy and strong robustness.     

Energy management strategy for parallel hybrid electric vehicles based on approximate dynamic programming and velocity forecast

In parallel hybrid electric vehicles (HEVs), the power split between the engine and the electric motor as well as the gear shift in the gearbox determines the overall energy efficiency. In this paper an adaptive energy management strategy with velocity forecast is proposed to optimize the fuel consumption in parallel HEVs, which is formulated into a mixed-integer optimization problem. Approximate dynamic programming with a novel actor-gear-critic design is presented for simultaneously controlling the power split and gear shift online. The power split as a continuous variable is determined from an actor network to realize the energy distribution between two power sources. The gear shift as a discrete variable is obtained from a gear network to adjust the gear ratio in the gearbox. The concept enables an online learning of the energy management strategy for different driving behaviors without the requirement of a system model and the driving cycle. Simulation results indicate that the proposed strategy achieves close fuel economy compared with the optimal solutions resulting from dynamic programming. Furthermore, a multi-stage neural network is introduced for velocity forecast, providing a computationally efficient training framework with good prediction performance. The velocity prediction is finally combined with the energy management strategy for an effective application and fuel economy.     

基于泊松分布和伽马分布的网络舆情热点发现

本文提出了一种基于泊松分布和伽马分布的网络舆情热点实时识别方法。该方法使用话题的人气和时间间隔特征两方面来识别舆情热点,发现单位时间内（如1小时）参与话题讨论的人数成泊松分布,回帖的时间间隔服从伽马分布。本研究用历史数据证明了该方法具有良好的识别效果。     

A stock rank prediction method combining industry attributes and price data of stocks

Stock forecasting has always been challenging as the stock market is affected by a combination of factors. Temporal Convolutional Network (TCN) based on convolutional structure has been widely used in time series prediction in recent years, but the dilated causal convolution structure leaves it unable to effectively learn the dependencies between data at different time points. This paper proposes a method for stock ranking prediction. To enhance the ability of TCN to handle dependencies within series, we first develop a channel-time dual attention module (CTAM). In conjunction with TCN to process complex historical stock price data, CTAM can adaptively learn the importance of multiple price nature series of stocks and model the dependencies between the data at different times. On the other hand, due to the market industry rotation, some stocks with specific industry attributes may become market preference for a period time. To apply the industry attributes to the stock prediction, we construct an industry-stock Pearson correlation matrix and extract a vector that fully characterizes the industry attributes of stocks from it through a matrix factorization algorithm. Furthermore, the historical market preference is modeled according to the industry attribute of the stocks to generate the dynamic correlation between stocks and market preference, and this correlation is combined with the historical price features extracted by TCN for stock ranking prediction. We conduct experiments on three datasets of 950 constituent stocks of the Shanghai Stock Exchange Index, 750 constituent stocks of the Shenzhen Stock Exchange 1000 Index and 486 stocks of the S&P500 to demonstrate the effectiveness of the proposed method. On the Shanghai Stock Exchange Index dataset, the Investment Return Ratio (IRR) obtained by using the predict results of our method to guide the exchange reached 1.416, and the Sharpe Ratio (SR) reached 2.346. On the Shenzhen Stock Exchange Index dataset, the IRR reached 1.434 and the Sharpe ratio reached 2.317. On the S&P500, the IRR reached 1.491 and the Sharpe ratio reached 2.031.