Multi-output Gaussian Process Regression Model with Combined Kernel Function for Polyester Esterification Processes

In polyester fiber industrial processes,the prediction of key performance indicators is vital for product quality.The esterification process is an indispensable step in the polyester polymerization process.It has the characteristics of strong coupling,nonlinearity and complex mechanism.To solve these problems,we put forward a multi-output Gaussian process regression(MGPR)model based on the combined kernel function for the polyester esterification process.Since the seasonal and trend decomposition using loess(STL)can extract the periodic and trend characteristics of time series,a combined kernel function based on the STL and the kernel function analysis is constructed for the MGPR.The effectiveness of the proposed model is verified by the actual polyester esterification process data collected from fiber production.

Present State of Pasture Types of the Central Kyzylkum

The modern state of desert pastures of the Central Kyzylkum has been studied. The pasture territories of the Central Kyzylkum are distributed on sandy soils (14%), salt marshes (6%), gravellyloamy gray-brown soils (75%) and riparian nature-territorial complexes (5%). The main (75%) areas of pasture are occupied by the gravelly-loamy gray-brown soils which are dominated by species of sagebrushes. There are formed of 8 pasture types depending on the properties of natural complexes. The main type of pasture is sagebrushes (Mixto artemisieta), which occupy 60% of the pasture area, and then follow Peganeta harmala, Mixto calligoneta, Halocnemeta strobilacei, Tamariceta varia, Haloxyleta aphylli, Convolvuleta hamadae and Mixshrubs pasture types. The share of fodder plants is high (an average of 83%) in the flora of the study area. According to seasonal grazing, pastures of the Central Kyzylkum can be divided 5 groups: year-round, spring, spring-summer, autumn-winter and unsuitable pastures for grazing. Among them are prevail year-round grazing pastures. The numbers of annual plants and abundance venomous plants in the flora are indicators of pasture degradation in the study area. Annual plants may occupy 55% of composition of plant communities on degraded sites, besides the pasture types which formed under the influence of anthropogenic factors. In Central Kyzylkum newly formed and transformed pasture types occupy 25% of pastures.