Ensemble local kernel learning for online prediction of distributed product outputs in chemical processes

Ensemble Just-In-Time Learning-Based Soft Sensor for Mooney Viscosity Prediction in an Industrial Rubber Mixing Process

The lack of online sensors for Mooney viscosity measurement has posed significant challenges for enabling efficient monitoring, control, and optimization of industrial rubber mixing process. To obtain real-time and accurate estimations of Mooney viscosity, a novel soft sensor method, referred to as multimodal perturbation- (MP-) based ensemble just-in-time learning Gaussian process regression (MP-EJITGPR), is proposed by exploiting ensemble JIT learning. This method employs perturbations on similarity measure and input variables for generating the diversity of JIT learners. Furthermore, a set of accurate and diverse JIT learners are built through an evolutionary multiobjective optimization by balancing the accuracy and diversity objectives explicitly. Moreover, all base JIT learners are combined adaptively using a finite mixture mechanism. The proposed method is applied to an industrial rubber mixing process for Mooney viscosity prediction, and the experimental results demonstrate its effectiveness and superiority over traditional soft sensor methods.

Spatial variation of heavy metal contamination in the riparian sediments after two-year flow regulation in the Three Gorges Reservoir, China

Regular impoundment of the Three Gorges Reservoir (TGR) with intensified human activities in the watershed imparts a significant effect on the environmental changes in the riparian zone. In this study, six heavy metals (Cd, Cr, Cu, Ni, Pb and Zn) in the riparian sediments of the entire TGR mainstream were investigated in 2014 and 2016 to identify their contamination and risk characteristics and decipher the main factors for the variation of the metal contamination. The results showed that the concentrations of the heavy metals in the sediments did not vary significantly between 2014 and 2016, and their contamination degrees decreased in the order of Cd> > Cu ≈ Zn > Pb > Cr ≈ Ni in 2014 and Cd> > Zn > Cu ≈ Pb > Cr ≈ Ni in 2016. The potential eco-risk of Cd was extremely high in the two years, while the eco-risk of other metals was very low. The sediments showed a moderate to high contamination level, a high potential eco-risk but a low toxic risk to aquatic biota in the two years. Spatially, the contamination and risk levels of heavy metals were relatively higher in the downstream TGR region in 2014 except for the sites close to the urban areas but in the upper-middle TGR region in 2016. Increasing anthropogenic influence contributed to the high contamination and risk levels of Cd, Cu, Pb and Zn in the upper-middle region in 2016. The results indicated that the Cd contamination in the riparian sediments of the TGR was still a vital environmental issue, and the decreased sediment inputs from the upstream major tributaries, the periodic and anti-seasonal flow regulation, local geomorphological characteristics and anthropogenic activities determined the contamination distribution of heavy metals in the riparian sediments.

Big Data Analytics in Chemical Engineering

Big data analytics is the journey to turn data into insights for more informed business and operational decisions. As the chemical engineering community is collecting more data (volume) from different sources (variety), this journey becomes more challenging in terms of using the right data and the right tools (analytics) to make the right decisions in real time (velocity). This article highlights recent big data advancements in five industries, including chemicals, energy, semiconductors, pharmaceuticals, and food, and then discusses technical, platform, and culture challenges. To reach the next milestone in multiplying successes to the enterprise level, government, academia, and industry need to collaboratively focus on workforce development and innovation.