Back to search

IKTPLUSS-IKT og digital innovasjon

Intelligent use of data to build optimization tools for cyber-physical systems in the process industry

Alternative title: Intelligent bruk av data for utvikling av optimaliseringsverktøyer for kompleke cyper-fysiske systemer

Awarded: NOK 11.4 mill.

The process industry is one of the biggest producers of data, where a typical process generates thousands of data points each second. Parts of the process industry has used real-time data for decision making for more than 50 years and has up to now been the leading industry in terms of intelligent use of data. However, in spite of many successes, there is still a large potential for further improvements in developing decision support tools to address future challenges with industry 4.0. By decision-support tools, we mean computer-based algorithms that determine how to operate a system in order to achieve a desired objective, e.g. minimize operational costs and energy consumption. Also, parts of the process industry is still using mainly manual control, and there is a need to develop simpler and cheaper approaches that can be used in these industries. The three main challenges of developing efficient optimization tools for complex cyber-physical systems are : 1. Lack of good models that can be used in optimization algorithms (offline model development) 2. Wrong value of model parameters used in the optimization problem (online model update) 3. Handling of active constraints. Since most of the economic benefit of optimal operation lies in controlling the right active constraints, the research has recently been focused in this directions. We have proposed a new framework where optimal operation is achieved directly using real-time process measurements as feedback, which we call the primal-dual feedback optimizing control. In addition, we study the alternative method of region-based control, where the simplest approach is to use simple PID controllers and selectors. This is is the preferred approach for simpler problems. An more general alternative is to incorporate the constraints model predictive control (MPC). In terms of machine learning, the focus is on how to combine reinforcement learning with model predictive control (MPC), that is, using the various parameters in MPC as hyperparameters for machine learning.

This project resulted in new methodologies and algorithms for optimal process operation using real-time process data. Traditionally, optimizing process operations require detailed process models, which are not only time consuming to develop and maintain, but are also often simplified leading to plant-model mismatch. In this project, we developed optimization strategies using feedback control, where real-time measurements/data is used to drive the process to its economic optimum operation, without the need for detailed process models. We also developed algorithms for large-scale processes where such feedback-based optimization strategies are used for multiple unit operations that are coupled to one another. This would enable scaling our algorithms to large-scale processes, and naturally lends itself to optimal allocation of shared resources such as in eco-industrial parks. This project also developed safe black-box optimization strategies and data-driven approaches that learns the optimum actions using only the measurements observed from the process. Furthermore, this project also developed algorithms for neural network-based real-time control strategies, as well as algorithms to efficiently generate training data samples to learn control policies that scale well to large-scale systems. These algorithms were demonstrated on several applications ranging from oil and gas, chemical processes, heat exchanger networks, biomedical systems, which is indicates the impact of the algorithms.

This project aims to address the main challenges related to developing optimization tools for the process industries, which are: 1. Lack of good models that can be used in optimization algorithms (offline model development) 2. Wrong value of model parameters used in the optimization problem (online model update) 3. Numerical robustness including computational issues By leveraging big data and machine-learning algorithms, we can develop decision-support tools for complex cyber-physical systems that can be a part of the industrial internet-of-things. In this project, we will utilize process data to develop machine-learning based models (also known as digital-twins), that can be used for developing optimization tools. This will enable us to address the challenges with respect to developing models for optimization. Reinforcement learning approaches will also be used to operate the processes in new operating conditions other than the conditions used to train the model. To address the computational robustness issues of solving optimization problems, we also aim to approximate computationally intensive optimization problems using machine-learning algorithms. Instead of developing surrogate models that will be used in the optimizer, we plan to build surrogate optimizers or AI optimizers that approximate the numerical optimization solvers. This project aims to restructure existing process industries by utilizing data more efficiently and it will also open new industrial applications that could benefit from data-driven decision-support tools. At the same time, this project will also develop novel algorithms for machine-learning-based optimization and thus move the research front and develop new subject areas in the field of online process optimization and autonomous decision-making. Therefore, this project will address challenges in the short to medium time horizon.

Funding scheme:

IKTPLUSS-IKT og digital innovasjon