Deep reinforcement learning for process design: Review and perspective

The transformation toward renewable energy and feedstock supply in the chemical industry requires new conceptual process design approaches. Recently, deep reinforcement learning (RL), a subclass of machine learning, has shown the potential to solve complex decision-making problems and aid sustainable process design. However, its suitability...

Transfer learning for process design with reinforcement learning

Process design is a creative task that is currently performed manually by engineers. Artificial intelligence provides new potential to facilitate process design. Specifically, reinforcement learning (RL) has shown some success in automating process design by integrating data-driven models that learn to build process flowsheets with process...

Flowsheet generation through hierarchical reinforcement learning and graph neural networks

Process synthesis experiences a disruptive transformation accelerated by artificial intelligence. We propose a reinforcement learning algorithm for chemical process design based on a state-of-the-art actor-critic logic. Our proposed algorithm represents chemical processes as graphs and uses graph convolutional neural networks to learn from...

Flowsheet Recognition using Deep Convolutional Neural Networks

Flowsheets are the most important building blocks to define and communicate the structure of chemical processes. Gaining access to large data sets of machine-readable chemical flowsheets could significantly enhance process synthesis through artificial intelligence. A large number of these flowsheets are publicly available in the scientific...

Investigation of Lagrangian coherent structures in a wake-induced boundary layer transition

The evolution of coherent structures in a flat plate boundary layer transition induced by the cylinder wake is investigated using the particle image velocimetry (PIV) technique. The finite-time Lyapunov exponent (FTLE), which characterizes the amount of stretching about the flow trajectory, is used to extract the Lagrangian coherent structures....

User Modeling and Personalization in the Microblogging Sphere

Microblogging has become a popular mechanism for people to publish, share, and propagate information on the Web. The massive amount of digital traces that people have left in the microblogging sphere, creates new possibilities and poses challenges for user modeling and personalization. How can microblogging activities be exploited to infer...

Analyzing viewpoint diversity in twitter

Information diversity has a long tradition in human history. Recently there have been claims that diversity is diminishing in information available in social networks. On the other hand, some studies suggest that diversity is actually quite high in social networks such as Twitter. However these studies only focus on the concept of source...

Study of Froude and Hughes Methods by Numerical Towing Tank

A Numerical Wave Model for the Refraction and Diffraction of Irregular Waves. Part II: Numerical Experiments of the Wave Model CREON

The numerical wave model CREON is developed to predict the propagation and transformation of wave properties in shallow water. In Gao et al. (1993), which is referred to as Part I in the following, a description is given of the theoretical and numerical treatment of the model. In the present report, we present various computational results. The...