Mälardalen University

This course explores the integration of artificial intelligence (AI) in decision support systems specifically tailored for the energy and production sectors. Students will learn how AI technologies, such as machine learning, optimization, and data analytics, are transforming traditional operational strategies, enhancing decision-making processes, and driving efficiency in energy and production operations. The curriculum will cover foundational concepts of AI and decision support systems, along with practical applications such as predictive maintenance, demand forecasting, process optimization, and real-time decision support. Through hands-on projects, case studies, and industry-relevant examples, participants will gain insights into designing and implementing AI-driven solutions that improve operational performance, reduce costs, and support sustainability goals. By the end of this course, students will be equipped with the skills to develop and apply AI-driven decision support systems to solve complex challenges in energy and production environments. This course is ideal for professionals and students interested in leveraging AI for operational excellence in the energy and production industries.

This course is designed for engineers, scientists, operators, and managers interested in utilizing AI-based methods for condition monitoring and prognostics in industrial systems and high-value assets. Participants will learn to identify common failure causes and predict Remaining Useful Life (RUL) using historical data, involving tasks such as data processing, feature selection, model development, and uncertainty quantification. Led by experienced professionals from industry and academia, the course covers the basics of prognostics and introduces various AI methods, including deep learning. It represents state-of-the-art AI-driven prognostic techniques, advanced signal processing, and feature engineering methods.

Do you want to deepen your knowledge in Industrial Internet of Things? In this course, you will gain deeper knowledge and understanding of the Industrial Internet of Things (IIoT), platforms and cloud services used in manufacturing industries. You will learn to understand the use of IoT platforms and how to design and implement simple systems and how to create value by using IoT solutions within industrial systems. The course will provide you with practical and theoretical knowledge in IIoT, platforms and cloud services as well as in-depth knowledge in production, logistics and product development.

A smart factory is an industrial manufacturing facility that uses technology such as the Internet of Things (IoT), automation, and artificial intelligence (AI) to increase productivity and profitability. Smart factories use sensors and other technology to collect, share, and analyze data that helps improve production, increase safety, reduce energy consumption, and improve product quality. You will learn The various major technological areas of smart factories Fundamental principles of operation and control of smart factories Understand and describe how smart machines and products interact in smart factories

Virtual commissioning (VC) is a technique used in the field of automation and control engineering to simulate and test a system's control software and hardware in a virtual environment before it is physically implemented. The aim is to identify and correct any issues or errors in the system before deployment, reducing the risk of downtime, safety hazards, and costly rework. The virtual commissioning process typically involves creating a digital twin of the system being developed, which is a virtual representation of the system that mirrors its physical behaviour. The digital twin includes all the necessary models of the system's components, such as sensors, actuators, controllers, and interfaces, as well as the control software that will be running on the real system. Once the digital twin is created, it can be tested and optimized in a virtual environment to ensure that it behaves correctly under various conditions. The benefits of using VC include reduced project costs, shortened development time, improved system quality and reliability, and increased safety for both operators and equipment. By detecting and resolving potential issues in the virtual environment, engineers can avoid costly and time-consuming physical testing and debugging, which can significantly reduce project costs and time to market. The course includes different modules, each with its own specific role in the process. Together, the modules create a comprehensive virtual commissioning process that makes it possible to test and validate control systems and production processes in a simulated environment before implementing them in the real world. Modeling and simulation: This module involves creating a virtual model of the system using simulation software. The model includes all the equipment, control systems, and processes involved in the production process. Control system integration: This module involves integrating the digital twin with the control system, allowing engineers to test and validate the system's performance. Virtual sensors and actuators: This module involves creating virtual sensors and actuators that mimic the behavior of the physical equipment. This allows engineers to test the control system's response to different scenarios and optimize its performance. Scenario testing: This module involves simulating different scenarios, such as equipment failures, power outages, or changes in production requirements, to test the system's response. Data analysis and optimization: This module involves analyzing data from the virtual commissioning process to identify any issues or inefficiencies in the system. Engineers can then optimize the system's performance and ensure that it is safe and reliable. Expected outcomes Describe the use of digital twins for virtual commissioning process. Develop a simulation model of a production system using a systems perspective and make a plan for data collection and analysis. Plan different scenarios for the improvement of a production process. Analyze data from the virtual commissioning process to identify any issues or inefficiencies in the system and then optimize the system's performance. Needs in the industry Example battery production: Battery behaviors are changing over time. To innovate at speed and scale, testing and improving real-world battery phenomena throughout its lifecycle is necessary. Virtual commissioning / modeling-based approaches like digital twin can provide us with accurate real-life battery behaviors and properties, improving energy density, charging speed, lifetime performance and battery safety. Faster innovation (NPI) Lower physical prototypes Shorter manufacturing cycle time Rapid testing of new battery chemistry and materials to reduce physical experiments Thermal performance and safety It’s not just about modelling and simulating the product, but also validating processes from start to finish in a single environment for digital continuity. Suggested target groups Industry personnel Early career engineers involved in commissioning and simulation projects Design engineers (to simulate their designs at an early stage in a virtual environment to reduce errors) New product introduction engineers Data engineers Production engineers Process engineers (mediators between design and commissioning) Simulation engineers Controls engineer System Integration