About the project
Background
Membrane separation technology has become an important tool in water and wastewater treatment, offering an effective means of removing contaminants and recovering valuable resources. Both gravity-driven and pressure-driven membrane processes are extensively used across various industries, ranging from municipal and industrial wastewater treatment plants to desalination applications.
Optimizing membrane separation processes is a multifaceted challenge and requires a comprehensive understanding of various influencing factors; membrane material, feed composition, and fouling tendencies. Traditional approaches often involve extensive trial-and-error experimentation to achieve efficiency and cost reduction. The upcoming paradigm shift in the operation and management of membrane systems will revolve around the integration of cognitive analytics, which utilizes artificial intelligence (AI) and machine learning (ML) to make the most of available data.
Despite the abundance of data in the water industry, a significant proportion, estimated to be more than 90%, remains unutilized, particularly within membrane technology. Achieving real-time, closed-loop stability in membrane systems remains a universal challenge, highlighting the need for continuous innovation and advancements in this field. By applying advanced data analytics techniques, the efficiency of membrane separation processes can be improved, ensuring that permeate flux and contaminant rejection are maintained at desired levels while maximizing permeate recovery and minimizing costs. Additionally, it can enable real-time monitoring and predictive maintenance, promising a paradigm shift to revolutionize water treatment efficiency and process sustainability. This project aims to optimize membrane processes using advanced data analytics techniques, leading to better water quality and resource management.
Project partners: Sunnfjord kommune, NMBU, ScanWater, DOSCON
Objectives
- 1. Further develop the intelligent membrane technology established during IntelMEM Phase I (2021-2022) that can effectively remove natural organic matter from surface water, while simultaneously ensuring microbiological safety and compliance with other chemical parameters used to assess the quality of water intended for consumers;
- 2. Develop and validate the industrial prototype based on the rough prototype from IntelMEM Phase I. The industrial prototype will be tested in the relevant environment (TRL 5-6) of a water treatment plant that currently faces challenges in securing a backup water supply due to high concentrations of natural organic matter in the available water sources;
- 3. Maintain the IntelMEM Living Lab, which includes a community of practice for end-users, researchers, technology providers, and public organizations.
Cognitive Analytics of Gravity- and Pressure-Driven Membrane Separation: Industrial PhD
The overall objective of the project is to explore and enhance the understanding, optimization, and operational efficiency of gravity—and pressure-driven membrane separation processes by cognitive analytical methods. This PhD project aims to use cognitive analytics to optimize gravity- and pressure-driven membrane processes for improved efficiency and cost-effectiveness in water and wastewater treatment applications. This project will be conducted as an industrial PhD, financially supported by the Research Council of Norway and DOSCON AS.
DOSCON AS will be the industrial partner, and NMBU will be the research institute. The project reflects and supports the REALTEK’s strategy by contributing to safeguarding the basis for life in the future through outstanding research and dissemination of knowledge and innovation. The project supports the SDG targets 6.1, 6.3, 11.6, 12.4, and 13. The project is also related to the REALTELK’s strategic priority to establishing a state-of-the-art membrane laboratory, with the ambtion for large scale funding from the RCN INFRA program.
Project number: 354232
Project period: 2024-2028
Industial PhD: Anura Kumara Arembage
Main supervisor: Zakhar Maletskyi
Co-supervisor: Kristian Hovde Liland
Participants
Participants at NMBU