Electrolysis of aluminium is a complex process taking place in a harsh environment with few reliable measurements of what is actually taking place inside the electrolysis cell. For several decades Hydro has been working with models to better understand what is going on inside the cells. A lot of knowledge is embedded in these models, knowledge that we would like to transfer to our operators in the plants. In the ALTT project Hydro has been working with SINTEF, Cybernetica and Attensi to develop tools for accelerated learning and decision support that combines the knowledge in dynamic models with simulation, gaming and gamification. Currently we are integrating the gamified, heat balance learning tool we have developed to the learning needs for the operators. The objective is to accelerate learning, increase competence and enable the operators to make better decisions.
Prosjektet har introdusert nye tanker rundt hvordan vi kan drive opplæring og gjort læring tilgjengelig der operatørene er. Vi opplever at operatørene etterspør varmebalansespillet som er utviklet i prosjektet. Sammen med den dokumenterte læringseffekten fra spillet er dette en tydelig indikasjon på akselerert læring. Selv om vi ikke kan måle effekten dette har på driftsresultatet i dag, forventer vi at akselerert læring på sikt vil bidra til potensialet som skissert i søknaden. Vi ser også at prosjektet har bidratt til en positiv holdning til spill-basert læring i Hydro, og dette har vært positivt for introduksjon av denne type læring i andre sammenhenger i Hydro.
Hydro is a global company with aluminium production, sales and trading activities throughout the entire value chain. Hydro has 13000 employees in more than 50 countries on all continents. Over a long time, Hydro has developed a dynamic model, describing some of the key process variables in an electrolysis cell. This model is tailored for process monitoring and on-line control. However, a major challenge is to make the model-embedded knowledge available to operational personnel. Some of the electrolysis processes have long response times between the action of an operator and the results of the action (in some cases up to 3-5 weeks). This is particularly challenging with respect to fast learning and adaptation. ALTT will focus on bringing together learning, workplace and decision-support using novel technologies to accelerate learning. The main innovation will be a learning environment that combines gaming, gamification and simulation for decision support and effective workplace learning.