Industrial process control using unstructured data

An industrial system management system, comprising:

• at least one processing system;
• and
• a non-transitory computer readable medium coupled to the at least one processing system, the non-transitory computer readable medium storing instructions that cause the at least one processing system to perform operations comprising:
• determining a set of components collectively representing the industrial system, wherein each component is pre-associated with a set of machine learning features for a machine learning-based industrial system control model;
• associating each machine learning feature with a data stream from the industrial system;
• generating a set of machine learning feature values for each machine learning feature based on the associated data stream;
• and
• generating a set of control instructions for the industrial system, using the machine learning feature values in the machine learning-based industrial system control model.