Process Safety and Environmental Considerations of Hydrogen Production

The current excitement about artificial intelligence (AI), particularly machine learning (ML), industrial internet of things (IIoT), Industry 4.0 is palpable and contagious. The expectation that AI is poised to “revolutionize,” perhaps even take over, humanity has elicited prophetic visions and concerns from some luminaries. Sure, the advances AI has made in the last 10 years, for example, AlphaGo, autonomous cars, Alexa, Watson, and other such systems, in game playing, robotics, computer vision, speech recognition, and natural language processing are indeed stunning advances. But, as with earlier AI breakthroughs, such as expert systems in the 1980s and neural networks in the 1990s, there is also considerable hype and a tendency to overestimate the promise of these advances. So, what are different this time? What are the true potential and values for industry?

We would like to share some views and perspective through a review of recent innovative advances of system identification, model predictive control, and real-time data analytics in process industry applications. More importantly, we explore how those innovations and applications successfully added tremendous value for process industries. As industrial practitioners of AI/ML, we witnessed the progressive development in applications of AI/ML technology for advanced process control (APC), process optimization, and asset performance management (APM), also learnt lessons of what is working and what not. AI/ML is a powerful enabler, but success requires a solid foundation of domain knowledge and understanding of both AI/ML and the use cases to address. On this road, challenges and opportunities exist simultaneously, we propose a list of strategies for industrial applicants references.