After completing this course successfully, the students are capable of:
- explaining the principles and main concepts of Smart Industry (smartness, smart products, smart technologies for specific business/organizational/application domain).
- applying and evaluating Industry 4.0 (I4.0) technical architectures, with emphasis on the application of Artificial Intelligence (AI), Industrial Internet-of-Things (I-IoT) and Digital Twin.
- identifying the suitability, applicability and benefits of certain types of I4.0 technologies in a specific business context, e.g., supply chain management.
- explaining the role of the Findable, Accessible, Interoperable and Reusable (FAIR) data management principles for successful I4.0 use cases.
- designing and to developing a small I4.0 application and integrate it in the existing IT landscape of a case study.
Smart industry is about improving industrial processes by applying technologies for contextual sensing and data analytics (mining events, situations and trends) through the so called Industry 4.0 (I-4.0) architectures. The most common Smart Industry use cases include machine monitoring for predictive maintenance (e.g., in manufacturing processes), indoor air quality monitoring (e.g., toxic gases), monitoring environmental conditions (e.g., CO2 levels), asset tracking (e.g., monitoring location of supplies) and inventory management (e.g., monitoring medical equipment in a hospital).|
I-4.0 architectures guide the use of Artificial Intelligence (AI), ubiquity computing, Service-Oriented Architecture (SOA), Industrial Internet of Things (I-IoT), autonomous cyber-physical systems (CPS), digital twins and cloud computing through systems that can partly or completely take over the human’s thinking process. For example, a Smart Factory uses these I-4.0 technologies to support the whole production process to integrate all areas of the enterprise, e.g., marketing, research and development (R&D), manufacturing, warehousing, sales and supply chain. Within these smart factories, machines and devices are connected and generate data during the execution of the processes, so the identified insights from these data can be used to understand what is actually happening in the factory and processes can be optimized faster. This creates new opportunities in the whole business value chain, once lead times can be shortened and work can be performed more efficiently.
However, these integrated networks of automation devices (sensors and actuators), services, and enterprises bring interoperability challenges for the industry ecosystem. Interoperability defines the way of interconnection between sensors, devices, manufacturing systems, and people, including exchange of products and materials among facilities. Identifying interoperability issues begins by tracking legacy systems in the wide range of heterogeneous distributed industrial machineries. The integration of these systems with new technologies, composed of software and other equipment, rely on different communication protocols (technical interoperability) and data standards (syntactic and semantic interoperability).
Establishing automatic interoperability for seamless integration is an arduous and challenging task. This course gives emphasis to interoperability solutions that enable sustainable and robust distributed systems for Smart Industry. This course covers software engineering for I-4.0 architectures, including enterprise architecture for digital transformation, ontology engineering for data science, FAIR data management and stewardship, and I-IoT platforms.
The course is structured as follows:
Theory lectures will emphasize the following topics:
- Theory lectures covering background and basic concepts, interoperability as a key aspect of Smart Industry, the Findable, Accessible, Interoperable and Reusable (FAIR) data principles, and I-4.0 architectures and technologies.
- Practical lectures given by external lecturers that provide applications (cases) for project assignments. The students will form groups and each group of students will choose a case to work for some weeks, receiving weekly feedbacks from the external lecturers.
- The learning goals will be tested through an exam (covering theory part) and the project assignment (covering practical part).
Practical lectures will emphasize these application domains:
- Digital Transformation, Digitalization and Automation
- Interoperability for Artificial Intelligence (AI)
- Cyber-Physical Systems, technology-enhanced work, human-machine symbiosis
- I4.0 architectures and technologies with focus on I-IoT platforms
- FAIR data management and Industrial Data Spaces
- Digital twins, data-driven decision making, reasoning, simulation
- Distributed agent-based decision making
- Systems Lifecycle Management and Continuous Engineering
- Business models of smart connected product
- Smart healthcare: e-Health, wearables, mobile apps, data-driven personalized diagnostics.
- Smart logistics and transportation: connected sensors support supply chain management, fleet maintenance and fuel consumption optimization.
- Smart city: smart buildings to optimize energy use, disaster risk reduction
- Smart grid: detect and isolate shortages and outages, optimize potency systems and integration of customer-owned power generation systems
- Smart manufacturing: monitoring production processes using sensors and improving manufacturing performance, predictive and preventive maintenance and additive manufacturing
Assumed previous knowledge
|Knowledge on design science research methodology, architecture of information systems, software engineering and linked data.|
|Master Business Information Technology||Required materials|
Recommended materials-Instructional modes
|5-10 papers that will be selected and made available in the Canvas page before the course starts|
|Self study without assistance|