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...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.展开更多
准确预测商品销量的走向对零售企业具有重要意义,构建自回归移动平均模型(ARMA模型,Auto-Regressive and Moving Average Model)对零售商品时序销量数据进行预测分析;传统ARMA模型无法准确描述商品销量中同时存在的非平稳非线性特征;论...准确预测商品销量的走向对零售企业具有重要意义,构建自回归移动平均模型(ARMA模型,Auto-Regressive and Moving Average Model)对零售商品时序销量数据进行预测分析;传统ARMA模型无法准确描述商品销量中同时存在的非平稳非线性特征;论文分别采用支持向量回归(SVR,Support Vector Regression)方法和极限学习机(ELM,Extreme Learning Machine)方法,对时序模型中非线性误差进行预测并进行误差补偿,提高了商品销量的预测精度;提出了遗传优化的选择性集成定阶方法,用以简化ARMA模型的复杂定阶过程,降低了对数据平稳性程度要求;论文收集了某电商平台商品销量数据,对ARMA、选择性集成ARMA、ARMASVR、ARMA-ELM四种预测模型的性能进行了对比分析,结果表明,选择性集成ARMA模型预测精度在平稳和非平稳时序数据下分别提高23.58%和41.28%;组合模型相比仅采用线性平稳时序模型的预测结果更符合实际,其中,ARMA-SVR模型在小样本、非平稳时序下预测精度比ARMA-ELM模型高出约三分之一。展开更多
Three forecasting models are set up: the auto\|regressive moving average model, the grey forecasting model for the rate of qualified products P t, and the grey forecasting model for time intervals of the quality cata...Three forecasting models are set up: the auto\|regressive moving average model, the grey forecasting model for the rate of qualified products P t, and the grey forecasting model for time intervals of the quality catastrophes. Then a combined forewarning system for the quality of products is established, which contains three models, judgment rules and forewarning state illustration. Finally with an example of the practical production, this modeling system is proved fairly effective.展开更多
This paper presents an Ethernet based hybrid method for predicting random time-delay in the networked control system.First,db3 wavelet is used to decompose and reconstruct time-delay sequence,and the approximation com...This paper presents an Ethernet based hybrid method for predicting random time-delay in the networked control system.First,db3 wavelet is used to decompose and reconstruct time-delay sequence,and the approximation component and detail components of time-delay sequences are fgured out.Next,one step prediction of time-delay is obtained through echo state network(ESN)model and auto-regressive integrated moving average model(ARIMA)according to the diferent characteristics of approximate component and detail components.Then,the fnal predictive value of time-delay is obtained by summation.Meanwhile,the parameters of echo state network is optimized by genetic algorithm.The simulation results indicate that higher accuracy can be achieved through this prediction method.展开更多
基金Project supported by the National Key R&D Program of China (Grant No. 2022YFF0607504)。
文摘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.
文摘准确预测商品销量的走向对零售企业具有重要意义,构建自回归移动平均模型(ARMA模型,Auto-Regressive and Moving Average Model)对零售商品时序销量数据进行预测分析;传统ARMA模型无法准确描述商品销量中同时存在的非平稳非线性特征;论文分别采用支持向量回归(SVR,Support Vector Regression)方法和极限学习机(ELM,Extreme Learning Machine)方法,对时序模型中非线性误差进行预测并进行误差补偿,提高了商品销量的预测精度;提出了遗传优化的选择性集成定阶方法,用以简化ARMA模型的复杂定阶过程,降低了对数据平稳性程度要求;论文收集了某电商平台商品销量数据,对ARMA、选择性集成ARMA、ARMASVR、ARMA-ELM四种预测模型的性能进行了对比分析,结果表明,选择性集成ARMA模型预测精度在平稳和非平稳时序数据下分别提高23.58%和41.28%;组合模型相比仅采用线性平稳时序模型的预测结果更符合实际,其中,ARMA-SVR模型在小样本、非平稳时序下预测精度比ARMA-ELM模型高出约三分之一。
文摘Three forecasting models are set up: the auto\|regressive moving average model, the grey forecasting model for the rate of qualified products P t, and the grey forecasting model for time intervals of the quality catastrophes. Then a combined forewarning system for the quality of products is established, which contains three models, judgment rules and forewarning state illustration. Finally with an example of the practical production, this modeling system is proved fairly effective.
基金supported by National Natural Science Foundation of China(No.61034005)
文摘This paper presents an Ethernet based hybrid method for predicting random time-delay in the networked control system.First,db3 wavelet is used to decompose and reconstruct time-delay sequence,and the approximation component and detail components of time-delay sequences are fgured out.Next,one step prediction of time-delay is obtained through echo state network(ESN)model and auto-regressive integrated moving average model(ARIMA)according to the diferent characteristics of approximate component and detail components.Then,the fnal predictive value of time-delay is obtained by summation.Meanwhile,the parameters of echo state network is optimized by genetic algorithm.The simulation results indicate that higher accuracy can be achieved through this prediction method.
