Data-Driven Process Monitoring and Fault Diagnosis: A Comprehensive Survey
This paper presents a comprehensive review of the historical development, the current state
of the art, and prospects of data-driven approaches for industrial process monitoring. The …
of the art, and prospects of data-driven approaches for industrial process monitoring. The …
Neural recommender system for the activity coefficient prediction and UNIFAC model extension of ionic liquid‐solute systems
For the ionic liquid (IL)‐solute systems of broad interest, a deep neural network based
recommender system (RS) for predicting the infinite dilution activity coefficient (γ∞) is …
recommender system (RS) for predicting the infinite dilution activity coefficient (γ∞) is …
Generalizing property prediction of ionic liquids from limited labeled data: a one-stop framework empowered by transfer learning
Ionic liquids (ILs) could find use in almost every chemical process due to their wide spectrum
of unique properties. The crux of the matter lies in whether a task-specific IL selection from …
of unique properties. The crux of the matter lies in whether a task-specific IL selection from …
A framework of hybrid model development with identification of plant‐model mismatch
Y Chen, M Ierapetritou - AIChE Journal, 2020 - Wiley Online Library
Hybrid modeling has attracted increasing attention in order to take advantage of the
additional data to improve process understanding. Current practice often adopts mechanistic …
additional data to improve process understanding. Current practice often adopts mechanistic …
Fault diagnosis using data fusion with ensemble deep learning technique in IIoT
S Venkatasubramanian, S Raja… - Mathematical …, 2022 - Wiley Online Library
Detecting the breakdown of industrial IoT devices is a major challenge. Despite these
challenges, real‐time sensor data from the industrial internet of things (IIoT) present several …
challenges, real‐time sensor data from the industrial internet of things (IIoT) present several …
Artificial intelligence modeling-based optimization of an industrial-scale steam turbine for moving toward net-zero in the energy sector
Augmentation of energy efficiency in the power generation systems can aid in decarbonizing
the energy sector, which is also recognized by the International Energy Agency (IEA) as a …
the energy sector, which is also recognized by the International Energy Agency (IEA) as a …
Hidden representations in deep neural networks: Part 2. Regression problems
Deep neural networks are an important class of machine learning models useful for
representing complex input-output relationships. While their recent success is unparalleled …
representing complex input-output relationships. While their recent success is unparalleled …
Prediction of infinite‐dilution activity coefficients with neural collaborative filtering
Accurate prediction of infinite dilution activity coefficient (γ∞) for phase equilibria and
process design is crucial. In this work, an experimental γ∞ dataset containing 295 solutes …
process design is crucial. In this work, an experimental γ∞ dataset containing 295 solutes …
AI-DARWIN: A first principles-based model discovery engine using machine learning
A Chakraborty, A Sivaram… - Computers & Chemical …, 2021 - Elsevier
The limitations of AI-based black-box models regarding reliability and interpretability have
long been a major concern for researchers who have been arguing the case for hybrid …
long been a major concern for researchers who have been arguing the case for hybrid …
XAI‐MEG: Combining symbolic AI and machine learning to generate first‐principles models and causal explanations
A Sivaram, V Venkatasubramanian - AIChE Journal, 2022 - Wiley Online Library
Current machine learning methods generally do not reveal any mechanistic insights or
provide causal explanations for their decisions. While this may not be a big concern in …
provide causal explanations for their decisions. While this may not be a big concern in …