Two-Stage Hybrid Model for Efficiency Prediction of Centrifugal Pump.

Accurately predict the efficiency of centrifugal pumps at different rotational speeds is important but still intractable in practice. To enhance the prediction performance, this work proposes a hybrid modeling method by combining both the process data and knowledge of centrifugal pumps. First, according to the process knowledge of centrifugal pumps, the efficiency curve is divided into two stages. Then, the affinity law of pumps and a Gaussian process regression (GPR) model are explored and utilized to predict the efficiency at their suitable flow stages, respectively. Furthermore, a probability index is established through the prediction variance of a GPR model and Bayesian inference to select a suitable training set to improve the prediction accuracy. Experimental results show the superiority of the hybrid modeling method, compared with only using mechanism or data-driven models.

Robust Soft Sensor with Deep Kernel Learning for Quality Prediction in Rubber Mixing Processes.

Although several data-driven soft sensors are available, online reliable prediction of the Mooney viscosity in industrial rubber mixing processes is still a challenging task. A robust semi-supervised soft sensor, called ensemble deep correntropy kernel regression (EDCKR), is proposed. It integrates the ensemble strategy, deep brief network (DBN), and correntropy kernel regression (CKR) into a unified soft sensing framework. The multilevel DBN-based unsupervised learning stage extracts useful information from all secondary variables. Sequentially, a supervised CKR model is built to explore the relationship between the extracted features and the Mooney viscosity values. Without cumbersome preprocessing steps, the negative effects of outliers are reduced using the CKR-based robust nonlinear estimator. With the help of ensemble strategy, more reliable prediction results are further obtained. An industrial case validates the practicality and reliability of EDCKR.

The influence of relative humidity and ground material on indoor walking-induced particle resuspension.

The resuspension of indoor particulate matters caused by people indoor walking could affect indoor air quality and human health. Therefore, it is particularly important to study the resuspension rules of the particulate matters in different indoor environments. The influence of the ground material and the relative humidity on resuspension of the particulate matters were investigated under three kinds of ground materials and three different relative humidity. Results showed that different relative humidity and different ground materials had different effects on the mass concentration of the particulate matters. In addition, different particle sizes had diverse influence on the mass concentration. Compared with low-level loop pile carpet and shaggy carpet, hardwood floor was more conductive to human health which was less likely to cause the resuspension of the particulate matters. At the same time, relative humidity had a great influence on the resuspension of the particulate matters. With the increase of relative humidity, the resuspension rate of fine particulate matters decreased.

Research Progress on the Collaborative Drag Reduction Effect of Polymers and Surfactants.

Polymer additives and surfactants as drag reduction agents have been widely used in the field of fluid drag reduction. Polymer additives can reduce drag effectively with only a small amount, but they degrade easily. Surfactants have an anti-degradation ability. This paper categorizes the mechanism of drag reducing agents and the influencing factors of drag reduction characteristics. The factors affecting the degradation of polymer additives and the anti-degradation properties of surfactants are discussed. A mixture of polymer additive and surfactant has the characteristics of high shear resistance, a lower critical micelle concentration (CMC), and a good drag reduction effect at higher Reynolds numbers. Therefore, this paper focuses more on a drag reducing agent mixed with a polymer and a surfactant, including the mechanism model, drag reduction characteristics, and anti-degradation ability.