Robust discrimination between long‐range dependence and a change in mean

In this article we introduce a robust to outliers Wilcoxon change‐point testing procedure, for distinguishing between short‐range dependent time series with a change in mean at unknown time and stationary long‐range dependent time series. We establish the asymptotic distribution of the test statistic under the null hypothesis for L₁ near epoch dependent processes and show its consistency under the alternative. The Wilcoxon‐type testing procedure similarly as the CUSUM‐type testing procedure (of Berkes I., Horváth L., Kokoszka P. and Shao Q. 2006. Ann.Statist. 34:1140–1165), requires estimation of the location of a possible change‐point, and then using pre‐ and post‐break subsamples to discriminate between short and long‐range dependence. A simulation study examines the empirical size and power of the Wilcoxon‐type testing procedure in standard cases and with disturbances by outliers. It shows that in standard cases the Wilcoxon‐type testing procedure behaves equally well as the CUSUM‐type testing procedure but outperforms it in presence of outliers. We also apply both testing procedure to hydrologic data.     

A simple test of changes in mean in the possible presence of long‐range dependence

We propose a simple testing procedure to test for a change point in the mean of a possibly long‐range dependent time series. Under the null hypothesis, the series is stationary with long‐range dependence and our test statistic converges to a non‐degenerate distribution, whereas under the alternative, the series has a change point in the mean and the test statistic diverges to infinity. We demonstrate the good size and power properties of our test via simulations and illustrate its usefulness by analysing two real data sets.     

Empirical likelihood confidence intervals for the mean of a long‐range dependent process

Abstract. This paper considers blockwise empirical likelihood for real‐valued linear time processes which may exhibit either short‐ or long‐range dependence. Empirical likelihood approaches intended for weakly dependent time series can fail in the presence of strong dependence. However, a modified blockwise method is proposed for confidence interval estimation of the process mean, which is valid for various dependence structures including long‐range dependence. The finite‐sample performance of the method is evaluated through a simulation study and compared with other confidence interval procedures involving subsampling or normal approximations.     

DEM‐CFD modeling of particle systems with long‐range electrostatic interactions

To investigate dynamic behaviors of monocharged particle systems, a direct truncation (DT) method and a hybrid particle‐cell (HPC) method are implemented into the discrete element method coupled with computational fluid dynamics (DEM‐CFD) with defined cutoff distances. The DT method only considers electrostatic interactions between particles within the cutoff distance while the HPC method computes electrostatic interactions in the entire computational domain. The deposition process of monocharged particles in a container in air was simulated using the developed DEM‐CFD. It was found that using the DT method, the macrostructure, evolution of granular temperature, and radial distribution function of the particle system were sensitive to the specified cutoff distance. In contrast, using the HPC method, these results were independent of the specified cutoff distance, as expected. This implies that, although electrostatic interactions between particles with large separation distances are weak, they should be considered in DEM‐CFD for accurate modeling of charged particle systems. © 2015 The Authors AIChE Journal published by Wiley Periodicals, Inc. on behalf of American Institute of Chemical Engineers AIChE J, 61: 1792–1803, 2015     

Asymptotic self‐similarity and wavelet estimation for long‐range dependent fractional autoregressive integrated moving average time series with stable innovations

Abstract. Methods for parameter estimation in the presence of long‐range dependence and heavy tails are scarce. Fractional autoregressive integrated moving average (FARIMA) time series for positive values of the fractional differencing exponent d can be used to model long‐range dependence in the case of heavy‐tailed distributions. In this paper, we focus on the estimation of the Hurst parameter H = d + 1/α for long‐range dependent FARIMA time series with symmetric α‐stable (1 < α < 2) innovations. We establish the consistency and the asymptotic normality of two types of wavelet estimators of the parameter H. We do so by exploiting the fact that the integrated series is asymptotically self‐similar with parameter H. When the parameter α is known, we also obtain consistent and asymptotically normal estimators for the fractional differencing exponent d = H ? 1/α. Our results hold for a larger class of causal linear processes with stable symmetric innovations. As the wavelet‐based estimation method used here is semi‐parametric, it allows for a more robust treatment of long‐range dependent data than parametric methods.     

Local Whittle estimation of multi‐variate fractionally integrated processes

This article derives a semi‐parametric estimator of multi‐variate fractionally integrated processes covering both stationary and non‐stationary values of d. We utilize the notion of the extended discrete Fourier transform and periodogram to extend the multi‐variate local Whittle estimator of Shimotsu (2007) to cover non‐stationary values of d. Consistency and asymptotic normality is shown for d ∈ (?1/2,∞). A simulation study illustrates the performance of the proposed estimator for relevant sample sizes. Empirical justification of the proposed estimator is shown through an empirical analysis of log spot exchange rates. We find that the log spot exchange rates of Germany, United Kingdom, Japan, Canada, France, Italy and Switzerland against the US Dollar for the period January 1974 until December 2001 are well decribed as I(1) processes.     

Laboratory‐ and pilot plant‐scale study on the dehydration of cyclohexane by pervaporation

In this work, pervaporation is applied for the dehydration of industrial cyclohexane, used as a solvent and reaction medium in the manufacture of synthetic rubbers. Working with initial concentrations of water in cyclohexane within the range of 0.090–0.110 kg m^?3, an experimental study was performed (i) in the laboratory, using a radial cell with a membrane area of 0.0178 m²; and (ii) in a pilot plant located at the industrial site, with a plate‐and‐frame membrane module and a total membrane area of 3 m 2 . In both cases, the same pervaporation membrane, with a preferential flux of water, was used. The mass transfer coefficient was determined, together with its dependence on the hydrodynamic regime. The higher hydraulic resistance of the plate‐and‐frame module generated a pressure decrease that limited the feed velocity, thus increasing the mass transfer resistance of the pervaporation process in comparison with the bench‐scale system. Copyright © 2005 Society of Chemical Industry     

Estimation of the long‐memory stochastic volatility model parameters that is robust to level shifts and deterministic trends

I provide conditions under which the trimmed FDQML estimator, advanced by McCloskey (2010) in the context of fully parametric short‐memory models, can be used to estimate the long‐memory stochastic volatility model parameters in the presence of additive low‐frequency contamination in log‐squared returns. The types of low‐frequency contamination covered include level shifts as well as deterministic trends. I establish consistency and asymptotic normality in the presence or absence of such low‐frequency contamination under certain conditions on the growth rate of the trimming parameter. I also provide theoretical guidance on the choice of trimming parameter by heuristically obtaining its asymptotic MSE‐optimal rate under certain types of low‐frequency contamination. A simulation study examines the finite sample properties of the robust estimator, showing substantial gains from its use in the presence of level shifts. The finite sample analysis also explores how different levels of trimming affect the parameter estimates in the presence and absence of low‐frequency contamination and long‐memory.     

Correlations between the Shape of Viscosity Functions and the Molecular Structure of Long‐Chain Branched Polyethylenes

The viscosity functions of long‐chain branched metallocene‐catalyzed ethene homopolymers and copolymers (LCB‐mPE) were described by an extended Carreau‐Yasuda model. The two characteristic relaxation times, λ₁ and λ₂, and the slope of the viscosity function between these two characteristic relaxation times can be correlated to the zero shear‐rate viscosity, η₀, and the molar mass . The characteristic relaxation times, λ₁ and λ₂ (describing the main curvatures of the viscosity function) exhibit a power law dependency on the molar mass, . The parameterization of the viscosity function can be used for a molecular characterization and flow simulations of various kinds.

     

Particle‐scale investigation of the solid dispersion and residence properties in a 3‐D spout‐fluid bed

Three‐dimensional modeling of the gas–solid flow in a spout‐fluid bed is conducted at the particle‐scale level. Both the local and systematic dispersion behaviors of solid phase are initially investigated. Then, the solid circulating and resident behaviors are discussed. The results demonstrate that vigorously lateral solid dispersion appears in the spout region and the periphery of the fountain, whereas intensely vertical dispersion exists in the central region of the bed. Moreover, the inlet configuration of bed strongly affects the distribution of lateral dispersion, while its influence on the vertical one disappears in the fountain. Strong anisotropy of solid dispersion along the three directions is obtained. Systematic dispersion intensity along the vertical direction is an order of magnitude larger than the lateral one. In addition, two circulating patterns of solid phase can be identified. Solid residence time is the smallest in the spout region and the largest in the bottom corner. © 2014 American Institute of Chemical Engineers AIChE J, 60: 2788–2804, 2014     

Quantum‐chemical treatment of the linoleic acid molecule and two of its conjugated isomers

The structural, vibrational and electronic properties of the linoleic acid molecule and two of its conjugated isomers were investigated theoretically by performing the molecular mechanics (MM+ force field), the semi‐empirical self‐consistent‐field molecular‐orbital (PM3), and the density functional theory (B3LYP) calculations. The geometries of the considered molecules were optimized; the vibrational dynamics and the electronic properties were calculated in their ground states in the gas phase. It was found that the excess charge accumulated on hydrogen atoms bonded to double‐bonded carbon atoms is relatively small, which may cause these hydrogen atoms to be easily abstracted.     

A full‐scale trickling filter for the simultaneous removal of ammonium,iron and manganese from potable water

Ammonium, iron, manganese and hydrogen sulfide are a serious problem for water reservoirs all over the world. The aim of this work was the design, construction and operation of a full‐scale trickling filter for the simultaneous removal of the above pollutants. The long‐term removal efficiency and the effect of environmental and operating conditions on filter performance were studied. Start‐up time of the filter was minimized using as inoculum backwash water from an existing pilot‐scale plant, while natural advection was adequate to provide sufficient aeration. Redox potential variation throughout the filter depth enhanced simultaneous removal of the pollutants. Under steady operating conditions the filter presented perfect performance, while under pollutant concentration and/or hydraulic loading shocks the filter retained high removal efficiency. Seasonal or daily temperature variations did not affect filter performance since raw water temperature was constant at 20 °C. The proposed system exhibited high pollutant removal rates for all hydraulic and pollutant loadings tested, under various environmental conditions. The simplicity of the installation and the minimal operating cost provide an effective solution to a serious environmental and social problem. Copyright © 2010 Society of Chemical Industry     

A coupled population balance model and CFD approach for the simulation of mixing issues in lab‐scale and industrial bioreactors

Lab‐scale (70 L) and industrial scale (70 m³) aerated fermenters are simulated using a commercial computational fluid dynamics code. The model combines an Euler‐Euler approach for the two‐phase flow, a population balance model for biological adaptation to concentration gradients, and a kinetic model for biological reactions. Scale‐up at constant volumetric mass transfer coefficient is performed, leading to concentration gradients at the large scale. The results show that for a given concentration field and a given circulation time t_c, the population (physiological) state depends on the characteristic time of biological adaptation T_a. The population specific growth rate (T_a?t_c) is found independent of the spatial location and closely related to the volume average concentration. Oppositely, the population specific uptake rate (T_a～t_c) is spatially heterogeneous. The resulting local disequilibria between the uptake rate and the growth rate provide an explanation for the decreased performances of poorly macromixed industrial bioreactors. © 2013 American Institute of Chemical Engineers AIChE J, 60: 27–40, 2014