Data-driven Soft Sensors in the process industry

By Petr Kadlec, Bogdan Gabrys, Sibylle Strandt. Computers and Chemical Engineering, 2009

1,730 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Modelling Multi-Component Predictive Systems as Petri Nets (2017, background): “A review of data-driven soft sensors in the process industry is presented in (Kadlec et al. 2009).”
Data Mining and Analytics in the Process Industry: The Role of Machine Learning (2017, background): “as temperature and flow can be routinely recorded from the process, some key performance indices are very difficult to measure online [2].”
A Survey on Deep Learning for Data-Driven Soft Sensors (2021, background): “As a result, data-driven modeling has become the mainstream soft sensing modeling methods [6], [7].”
Review of soft sensor methods for regression applications (2016, background): “plied for prediction [2; 93], but their parameters are usually learned offline.”
Data-Based Techniques Focused on Modern Industry: An Overview (2015, background): “deal with high dimension correlated data sets [2], [3].”
Deep Learning-Based Feature Representation and Its Application for Soft Sensor Modeling With Variable-Wise Weighted SAE (2018, background): “Usually, soft sensors can be classified into two main categories, which are first-principle models (FPM) [9] (white-box models) and data-driven models [2] (black-box models).”
A Review on Soft Sensors for Monitoring, Control, and Optimization of Industrial Processes (2021, methodology): “The model-driven family of soft sensors is most commonly based on first principle models [4].”