Industrial Panel Discussion
Harnessing AI and Machine Learning for Monitoring, Optimization and Control in Process Industries
Panel Oragnizers: Leo Chiang, Martin Klaučo
Panelists and topics
Birgit Braun – The Dow Chemical Company
Subtitle: Machine Learning in the Chemical Industry – Success Stories and What We Need to Move to Scale
Abstract: The chemical industry, along with various other sectors, are investing in digital transformation to accelerate innovation and drive efficient production. Success stories from Dow are shared together with encountered challenges to successfully scale ML and AI in the industry.
Subtitle: Production optimization with Machine Learning
Abstract: Leveraging and developing a robust optimization model via machine learning tailored for a large-scale plant, resulting in significant cost savings and improved operational transparency. Real-time efficiency insights, supporting high productivity and informed decision-making during reduced work capacity.
Subtitle: AI Enabled Industrial Autonomous Operation in the Chemical Industry
Abstract: Autonomous operations are the future of smart manufacturing and represent the last stage in the shift towards autonomy. It is when industry makes the final move away from factory automation to fully autonomous plants and systems.
In the case of automation, equipment, production lines, etc. operate mainly on their own but are controlled by human beings when required. With autonomy, however, technologies like machine learning and AI enable machines to self-sufficiently manage day-to-day manufacturing systems and operations with little to no human interaction. The main objective of autonomous operations is to minimize manual interactions and maximize self-directed plant operations.
Automation typically runs from start to finish with little variation. It is usually a one-dimensional, static sequence of tasks. AI-driven autonomous systems, however, take many layers of legacy and modern applications and infrastructure into consideration. They then use predictive maintenance, smart sensors, digital twins, etc. to monitor, respond, and adapt to large, complex organizational systems. They are therefore associated with many different benefits and can add value to the manufacturing business. For example, they can reduce operational costs, ensure production flexibility, reduce risks, and improve safety.