Home

Welcome to the website for Dr. Q. Peter He’s research group at the Department of Chemical Engineering at Auburn University. Data analytics is the science and engineering of examining data to uncover hidden patterns, unknown correlations and other useful information that can be used to make better decisions or to develop effective solutions. Many statisticians and computer scientists treat data as numbers –without considering the meaning of the data or the system that generates the data. Not requiring any system/process knowledge was often claimed as one of the advantages of these methods. In our DE-PSE lab, we consider PSE principles (e.g., system dynamics, variable correlations) and fundamental chemical engineering laws (e.g., mass/energy balances, kinetics, thermodynamics) as useful and make use of these knowledge in method development.Our projects in various fields show that these PSE principles and fundamental ChE laws often hold the keys for breakthroughs and successful applications.

We have applied systems engineering enhanced machine learning and data analytics to many applications, including:

  • IoT-enabled cyber-manufacturing (NSF-CBET 1547163, completed)
  • Feature-based process monitoring for smart manufacturing (NSF-CBET 1805950, ongoing)
  • In-situ metrology and machine learning for additive manufacturing (NIST, ongoing)
  • Climate-smart agriculture irrigation management (USDA-NIFA, ongoing)
  • Data-Enabled Engineering Projects (DEEPs) for undergraduate data science and engineering education (NSF-DUE, ongoing)
  • Modeling of cellular dynamics and bioreactors (NSF-CBET 1264861, completed)
  • Investigation of interspecies interactions in a methanotroph-photoautotroph coculture for biogas conversion (DOE, DE-SC0019181, ongoing)

In all these completed and ongoing research activities, we have demonstrated that the true intelligence comes from the synergistic integration of human intelligence (e.g., domain knowledge and systems engineering principles) and machine/artificial intelligence (e.g., clustering, classification and regression).