Optimal zero-crossing group selection method of the absolute gravimeter based on improved auto-regressive moving average model

An absolute gravimeter is a precision instrument for measuring gravitational acceleration, which plays an important role in earthquake monitoring, crustal deformation, national defense construction, etc. The frequency of laser interference fringes of an absolute gravimeter gradually increases with the fall time. Data are sparse in the early stage and dense in the late stage. The fitting accuracy of gravitational acceleration will be affected by least-squares fitting according to the fixed number of zero-crossing groups. In response to this problem, a method based on Fourier series fitting is proposed in this paper to calculate the zero-crossing point. The whole falling process is divided into five frequency bands using the Hilbert transformation. The multiplicative auto-regressive moving average model is then trained according to the number of optimal zero-crossing groups obtained by the honey badger algorithm. Through this model, the number of optimal zero-crossing groups determined in each segment is predicted by the least-squares fitting. The mean value of gravitational acceleration in each segment is then obtained. The method can improve the accuracy of gravitational measurement by more than 25% compared to the fixed zero-crossing groups method. It provides a new way to improve the measuring accuracy of an absolute gravimeter.

Application of Seasonal Auto-regressive Integrated Moving Average Model in Forecasting the Incidence of Hand-foot-mouth Disease in Wuhan,China

Outbreaks of hand-foot-mouth disease（HFMD） have occurred many times and caused serious health burden in China since 2008. Application of modern information technology to prediction and early response can be helpful for efficient HFMD prevention and control. A seasonal auto-regressive integrated moving average（ARIMA） model for time series analysis was designed in this study. Eighty-four-month（from January 2009 to December 2015） retrospective data obtained from the Chinese Information System for Disease Prevention and Control were subjected to ARIMA modeling. The coefficient of determination（R^2）, normalized Bayesian Information Criterion（BIC） and Q-test P value were used to evaluate the goodness-of-fit of constructed models. Subsequently, the best-fitted ARIMA model was applied to predict the expected incidence of HFMD from January 2016 to December 2016. The best-fitted seasonal ARIMA model was identified as（1,0,1）（0,1,1）12, with the largest coefficient of determination（R^2=0.743） and lowest normalized BIC（BIC=3.645） value. The residuals of the model also showed non-significant autocorrelations（P_（Box-Ljung（Q））=0.299）. The predictions by the optimum ARIMA model adequately captured the pattern in the data and exhibited two peaks of activity over the forecast interval, including a major peak during April to June, and again a light peak for September to November. The ARIMA model proposed in this study can forecast HFMD incidence trend effectively, which could provide useful support for future HFMD prevention and control in the study area. Besides, further observations should be added continually into the modeling data set, and parameters of the models should be adjusted accordingly.

CONSTRUCTION OF POLYNOMIAL MATRIX USING BLOCK COEFFICIENT MATRIX REPRESENTATION AUTO-REGRESSIVE MOVING AVERAGE MODEL FOR ACTIVELY CONTROLLED STRUCTURES

The polynomial matrix using the block coefficient matrix representation auto-regressive moving average(referred to as the PM-ARMA)model is constructed in this paper for actively controlled multi-degree-of-freedom(MDOF)structures with time-delay through equivalently transforming the preliminary state space realization into the new state space realization.The PM-ARMA model is a more general formulation with respect to the polynomial using the coefficient representation auto-regressive moving average(ARMA)model due to its capability to cope with actively controlled structures with any given structural degrees of freedom and any chosen number of sensors and actuators.(The sensors and actuators are required to maintain the identical number.)under any dimensional stationary stochastic excitation.

A Study of Wind Statistics Through Auto-Regressive and Moving-Average (ARMA) Modeling

Statistical properties of winds near the Taichung Harbour are investigated. The 26 years'incomplete data of wind speeds, measured on an hourly basis, are used as reference. The possibility of imputation using simulated results of the Auto-Regressive (AR), Moving-Average (MA), and/ or Auto-Regressive and Moving-Average (ARMA) models is studied. Predictions of the 25-year extreme wind speeds based upon the augmented data are compared with the original series. Based upon the results, predictions of the 50- and 100-year extreme wind speeds are then made.

Noise reduction of acoustic Doppler velocimeter data based on Kalman filtering and autoregressive moving average models

Oceanic turbulence measurements made by an acoustic Doppler velocimeter(ADV)suffer from noise that potentially affects the estimates of turbulence statistics.This study examines the abilities of Kalman filtering and autoregressive moving average models to eliminate noise in ADV velocity datasets of laboratory experiments and offshore observations.Results show that the two methods have similar performance in ADV de-noising,and both effectively reduce noise in ADV velocities,even in cases of high noise.They eliminate the noise floor at high frequencies of the velocity spectra,leading to a longer range that effectively fits the Kolmogorov-5/3 slope at midrange frequencies.After de-noising adopting the two methods,the values of the mean velocity are almost unchanged,while the root-mean-square horizontal velocities and thus turbulent kinetic energy decrease appreciably in these experiments.The Reynolds stress is also affected by high noise levels,and de-noising thus reduces uncertainties in estimating the Reynolds stress.

Cyclic moving average control approach to cylinder pressure and its experimental validation

Cyclic variability is a factor adversely affecting engine performance. In this paper a cyclic moving average regulation approach to cylinder pressure at top dead center （TDC） is proposed, where the ignition time is adopted as the control input. The dynamics from ignition time to the moving average index is described by ARMA model. With this model, a one-step ahead prediction-based minimum variance controller （MVC） is developed for regulation. The performance of the proposed controller is illustrated by experiments with a commercial car engine and experimental results show that the controller has a reliable effect on index regulation when the engine works under different fuel injection strategies, load changing and throttle opening disturbance.

Application of the Moving Averaging Technique in Surplus Production Models

Surplus production models are the simplest analytical methods effective for fish stock assessment and fisheries management. In this paper, eight surplus production estimators(three estimation procedures) were tested on Schaefer and Fox type simulated data in three simulated fisheries(declining, well-managed, and restoring fisheries) at two white noise levels. Monte Carlo simulation was conducted to verify the utility of moving averaging(MA), which was an important technique for reducing the effect of noise in data in these models. The relative estimation error(REE) of maximum sustainable yield(MSY) was used as an indicator for the analysis, and one-way ANOVA was applied to test the significance of the REE calculated at four levels of MA. Simulation results suggested that increasing the value of MA could significantly improve the performance of the surplus production model(low REE) in all cases when the white noise level was low(coefficient of variation(CV) = 0.02). However, when the white noise level increased(CV= 0.25), adding the value of MA could still significantly enhance the performance of most models. Our results indicated that the best model performance occurred frequently when MA was equal to 3; however, some exceptions were observed when MA was higher.

Deep Learning-Based Stock Price Prediction Using LSTM Model

The stock market is a vital component of the broader financial system,with its dynamics closely linked to economic growth.The challenges associated with analyzing and forecasting stock prices have persisted since the inception of financial markets.By examining historical transaction data,latent opportunities for profit can be uncovered,providing valuable insights for both institutional and individual investors to make more informed decisions.This study focuses on analyzing historical transaction data from four banks to predict closing price trends.Various models,including decision trees,random forests,and Long Short-Term Memory(LSTM)networks,are employed to forecast stock price movements.Historical stock transaction data serves as the input for training these models,which are then used to predict upward or downward stock price trends.The study’s empirical results indicate that these methods are effective to a degree in predicting stock price movements.The LSTM-based deep neural network model,in particular,demonstrates a commendable level of predictive accuracy.This conclusion is reached following a thorough evaluation of model performance,highlighting the potential of LSTM models in stock market forecasting.The findings offer significant implications for advancing financial forecasting approaches,thereby improving the decision-making capabilities of investors and financial institutions.

Autoregressive moving average model for matrix time series

In the paper,the autoregressive moving average model for matrix time series(MARMA)is inves-tigated.The properties of the MARMA model are investigated by using the conditional least square estimation,the conditional maximum likelihood estimation,the projection theorem in Hilbert space and the decomposition technique of time series,which include necessary and suf-ficient conditions for stationarity and invertibility,model parameter estimation,model testing and model forecasting.

计及SOC自恢复的混合储能平抑风电功率波动控制

混合储能系统能够较好地应对复杂的风电波动,有效地提高电网的稳定性和安全性。在混合储能平抑风电功率波动的典型应用场景下,该文首先提出一种计及荷电状态(SOC)自恢复的混合储能平抑风电功率波动控制方法,在满足风电平抑需求的情况下,通过模型预测控制快速调节储能在平抑功率过程中的荷电状态,提高储能持续稳定运行能力;然后,为提高混合储能系统协调运行能力,设计了加权滑动平均(WMA)-模糊控制策略对超级电容和蓄电池功率进行动态分配;最后,结合实际风电功率数据,通过仿真验证了所提策略能有效平衡储能寿命和平抑风电波动的矛盾,能充分考虑两种储能设备的特性差异并提高功率分配的合理性。

基于改进JRD及误差修正的轴承剩余寿命预测方法

目前,风电机组齿轮箱性能发生初始退化时难以识别,现有退化指标易出现剧烈波动、单调性较差,且无法准确预测齿轮箱关键部件如轴承的剩余使用寿命(RUL),针对该问题,提出了一种基于改进杰森-瑞丽散度(JRD)及误差修正的双指数模型轴承RUL预测方法。首先,提取了振动信号样本的多域特征指标,利用高斯混合模型(GMM)与指数型权重JRD,得到了样本的后验概率分布向量,再经归一化处理得到置信值(CV);然后,对轴承从初始健康状态退化至当前检查时刻的CV值进行了相空间重构,提取了CV序列的动力学特征,并将其作为相关向量机(RVM)的训练集,获得了支撑整个退化轨迹的相关向量;最后,利用双指数模型拟合了相关向量,外推趋势至失效门限以计算RUL,并引入了差分整合移动平均自回归模型(ARIMA),对拟合相关向量产生的拟合误差进行了预测,以修正预测的结果。实验结果表明:改进后的退化指标单调性指标提高14.3%;且在不同工况、不同时刻下,经误差修正后的轴承的RUL预测结果较未修正之前有明显提高。研究结果表明:该预测方法可为风电机组齿轮箱重要部件的预测性维护提供参考。

基于水电储能调节的风光水发电联合优化调度策略

为缓解新能源装机容量扩大引起的弃风弃光现象,在已有梯级水电上下电站之间加入储能泵站,提出风光水储短期优化调度策略。构建以风光水储系统负荷跟踪误差最小、梯级水电站发电量最大和梯级水电站发电耗水量最小的多目标优化调度模型;提出基于季节性自回归移动平均(seasonal auto-regressive lntegrated moving average, SARIMA)模型和Copula函数的风光出力预测模型作为优化调度模型的边界条件,通过SARIMA预测模型将风光出力历史数据分解为季节性分量、趋势分量以及随机噪声余项进行全天96个调度时段风光出力预测,并叠加上基于Copula函数生成风光出力预测误差,然后通过拉丁超立方采样以及K-means聚类进行场景生成和缩减得到5个风光出力场景。选取风光典型日出力数据为例进行算例分析,算例结果表明:所提预测模型较SARIMA模型可以显著提高预测准确度,模型预测风光出力均方根误差从33.34、229.49 MW分别下降至0.697、9.534 MW;所提优化调度策略可以在全年丰、平、枯水期有效减少弃风弃光现象,并可将过剩新能源中的50%转化为上级水库储存水能。

基于ARIMA-TCN混合模型的高速铁路时间同步方法

列控系统作为高速铁路的核心系统,保持其系统的时间同步对于行车安全至关重要。针对现有时间同步方法易受时变上下行传输时延、随机时钟跳变等影响,导致主从时钟偏移估计不准确的问题,提出一种基于差分自回归移动平均-时域卷积神经网络(ARIMA-TCN)混合模型的高速铁路时间同步方法。首先,根据上下行链路传输速率的不对称比,建立高速铁路时钟的数学理论和实际观测模型。然后,使用拉依达准则识别处理跳变异常值,完成实际时间序列的预处理。再次,使用ARIMA模型平滑时间序列中不确定时延带来的噪声抖动,获得平稳的时间序列。最后,通过提出的注意力增强TCN模型进行预测补偿,完成时钟偏移的补偿校正。通过实验仿真,得到基站区间内位置、基站间距以及车速对高速铁路时间同步的影响性分析。实验结果表明:与对比方法相比,所提方法补偿后的均方根误差较最小二乘法减少了75%、较最大似然估计方法误差减少了44.4%,较BP神经网络方法误差减少了16.7%,验证所提方法具有更低的同步误差和更高的同步精度。

基于小波分解和ARIMA-GARCH-GRU组合模型的制造业PMI预测

制造业采购经理人指数(PMI)是反映国家经济运行情况的重要指标,而传统预测模型对该类时序数据预测精度不高。针对制造业PMI指数的非线性、波动性和数据量少的特点,提出一种基于一维离散小波变换进行数据预处理的组合模型。时序数据经过小波变换,由整合移动平均自回归–广义自回归条件异方差模型(ARIMA-GARCH)处理稳态低频数据,门控循环单元(GRU)处理波动性强的高频数据,将各频段预测结果进行融合得到最终预测结果。为验证模型有效性,选取一定数据量的PMI指数进行实验。结果表明,与其他常见模型对比,本文构建的组合模型具有较好的预测精度与性能,平均绝对误差(MAE)、均方根误差(RMSE)、平均绝对百分比误差(MAPE)分别达到0.00329、0.004162、0.65%。

基于SARIMA和SVR组合模型的转向架系统寿命评估

随着地铁运营时间和里程的增加,地铁车辆逐渐接近其理论寿命,为确保车辆运行安全性,需对其重要子系统进行健康状态及剩余寿命评估。文中选取车辆转向架系统作为研究对象,提出了一种基于协方差优选法的季节性回归移动平均(SARIMA)和支持向量回归(SVR)的组合模型对转向架寿命进行评估。首先,将车辆转向架系统历史故障率转化为健康指数,然后基于协方差优选法将SARIMA和SVR进行赋权组合,根据转向架系统历史健康指数进行预测,最后建立历史和预测的健康指数与运行时间的数学模型,分析得到转向架系统的剩余寿命。以某地铁车辆转向架系统为例进行算例分析及验证,结果表明组合模型可更准确地预测其健康状态,为有关维修部门开展维修维护策略提供理论依据,估计得出其剩余寿命,为车辆寿命后期退役及延寿决策提供理论数据分析支撑。

基于季节ARIMA模型对某三级综合性医院门诊量的预测研究

目的 通过建立季节ARIMA模型,对浙江省某三级综合性医院门诊量进行预测,为医院合理配备门诊人力资源提供依据。方法 以2013年1—6月浙江省某医院门诊量数据为基线,利用SPSS软件构建季节ARIMA模型,对2023年7—12月的门诊量进行预测,通过对比门诊量实测值,评价季节ARIMA模型预测门诊人次的精度。结果 该综合性医院门诊量呈现逐年上升趋势,并呈现周期性波动的特征。拟合的最优季节ARIMA模型为ARIMA(0,1,1)(1,0,1)12,BIC(贝叶斯信息准则)为5.273,MAPE(平均绝对百分误差)为14.265,R2(模块决定系数)为0.408,总体相对误差为1.83%,预测结果良好。结论 季节ARIMA模型较好地模拟了该三级综合性医院门诊量在时间序列上的变化趋势,为该院门诊量的短期预测提供理论依据。

基于IPSO-LSTM的井下动目标位置预测实验研究

提升井下人员定位精度能够加强矿山安全监测,最大程度保障井下人员的生命安全。针对现有测距类算法受现场环境影响致使定位精度不足的问题,提出一种基于IPSO-LSTM的定位模型,应用于井下动目标的位置预测。采用LSTM构建指纹定位模型,通过UWB无线模块采集距离信息以构建距离-位置指纹关系数据库,利用数据库对PSO-LSTM模型进行训练,最后将训练好的模型进行目标轨迹预测。为比较不同改进策略对PSO的提升效果,对比了混沌映射随机初始化种群位置、非线性惯性权重递减、非对称优化学习因子和适应度函数优化4种改进策略,实验证明改进的PSO优化算法收敛速度快、鲁棒性好。为验证IPSO-LSTM的定位效果,以平均定位误差作为评价指标,将IPSO-LSTM模型与Chan算法、PSO-LSTM模型、LSTM神经网络、SSA-LSTM模型和GWO-LSTM进行对比,结果显示,IPSO-LSTM定位模型的平均定位误差为30 mm,相对传统Chan算法、LSTM、PSO-LSTM模型分别提升了76%、49%、24%。为降低局部误差偏大的现象,采用中值滤波对输入信息处理,进一步提升了定位精度。研究对进一步提高现有井下动目标定位系统的精度和稳定性具有重要意义和参考价值。

基于R语言时间序列的ARIMA模型预测某三甲综合医院人均月住院费用和住院日的研究

目的运用自回归积分滑动平均模型(Autoregressive Intergrated Moving Average,ARIMA)建立月平均住院费用和住院日的医学经济学模型,为医院精细化管理提供依据。方法利用R4.0.2软件对2017年1月—2021年12月四川大学华西医院宜宾医院(宜宾市第二人民医院)的平均住院费用和住院日数据建立时间序列ARIMA预测模型。结果住院费用最优模型为ARIMA(0,1,1),赤池信息准则(Akaike information criterion,AIC)=924.35,贝叶斯信息准则(Bayesian Information Criterion,BIC)=928.51,残差Ljung-Box Q=12.51(P=0.768),可认为残差序列为白噪声。平均住院日的最优模型为ARIMA(5,1,1),AIC=87.49,BIC=104.11,残差Ljung-Box Q=10.05(P=0.612),可认为残差序列为白噪声。2022年1—12月实际值与预测值基本吻合,月人均住院费用和人均住院日的平均相对误差为0.55%、0.29%。结论建立基于时间序列ARIMA模型能够为合理配置卫生资源提供强有力的数据支撑。

基于WPD-ARIMA-GARCH组合模型的酱卤肉制品安全风险区间预测

针对传统确定性预测不能提供不确定性信息的难题,本研究提出了一种点估计和区间估计组合预测模型,并将其创新性地应用在食品安全风险预警领域。在点估计部分,使用小波包分解(wavelet packet decomposition,WPD)对周风险等级序列分解后,应用差分自回归移动平均(autoregressive integrated moving average,ARIMA)模型进行预测;在区间估计部分,使用广义自回归条件异方差(generalized autoregressive conditional heteroskedast,GARCH)模型对残差进行预测。本实验将建立的WPD-ARIMA-GARCH组合模型运用于某地区酱卤肉制品的风险预测,结果表明2019年的3月底和7月底该地区的酱卤肉制品安全风险较高,与实际情况相符;同时,该模型在10个不同地区的酱卤肉制品风险预测中,均方误差、平均绝对误差和平均绝对百分比误差分别为1.626、0.806和20.824;其90%置信区间的预测区间平均宽度和覆盖宽度标准值均为0.024,可以覆盖所有真实值。该模型具有较高的预测精度和较低的误差,能对酱卤肉制品质量安全起到风险防控作用,可为日常食品安全监管提供相应的技术支持。

基于ARIMA模型的天津地区单中心HPV感染趋势及基因型特征

目的采用自回归移动平均(ARIMA)模型构建时间序列,分析天津地区单中心人乳头瘤病毒(HPV)感染趋势及基因型特征。方法选择2018年1月-2022年12月某院进行HPV检测的7236例女性患者,比较2018-2022年天津地区HPV感染情况及基因型分布。建立ARIMA模型时间序列,分析模型拟合。预测2023年HPV感染数,并与实际发生数进行比较,评价模型的预测效果。结果2018-2022年天津地区HPV感染率为14.41%;HPV感染率在31~40岁年龄段最高,感染率为15.47%。阳性标本中HPV单一型别感染比率最高,占比为73.54%(767/1043),以高危型HPV为主。低危型感染占比最高的是HPV-6型,为2.59%,高危型感染占比最高的是HPV-16型,为16.06%。建立ARIMA模型,确定最佳模型为ARIMA(0,1,2)(0,1,1)12,其AIC值和BIC值分别为3.877、4.005,经白噪声检验Ljung-Box Q=8.828差异无统计学意义(P>0.05)。利用模型预测2023年HPV感染数,实际值、预测值的总体趋势基本保持一致,模型RMSE、MAPE、MAE分别为6.289、34.149、4.706,提示模型的预测效果较好。结论天津地区女性人群中,HPV病毒感染类型以单一高危型感染为主,其中HPV-16型感染率最高。天津地区HPV感染存在季节性,ARIMA模型在HPV感染流行趋势的预测中效果较好,适用于短期预测。