Controlling multi-stage manufacturing process based on internet of things (IOT) sensors and cognitive rule induction

A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions readable by a processor to cause the processor to at least:

• receive data indicative of a history of processing conditions at stages in the multi-stage manufacturing process in manufacturing a product, the processing conditions expressed in terms of process variables and corresponding values measured by sensors operatively coupled to processing units in a manufacturing facility implementing the multi-stage manufacturing process;
• select a subset of process variables that influence product quality, from the process variables;
• training a machine learning algorithm using at least the data and the subset of process variables, the machine learning algorithm learning causal relationships between the processing conditions and the product quality and trained to output a control rule based on at least one of the causal relationships, the control rule for controlling a process variable set point at a stage in the multi-stage manufacturing process,
• wherein the control rule includes at least a rule to set an operating condition at a future manufacturing process stage that follows a current manufacturing process stage.

A method comprising:

• receiving data indicative of a history of processing conditions at stages in the multi-stage manufacturing process in manufacturing a product, the processing conditions expressed in terms of process variables and corresponding values measured by sensors operatively coupled to processing units in a manufacturing facility implementing the multi-stage manufacturing process;
• selecting a subset of process variables that influence product quality, from the process variables;
• training a machine learning algorithm using at least the data and the subset of process variables, the machine learning algorithm learning causal relationships between the processing conditions and the product quality and trained to output a control rule based on at least one of the causal relationships, the control rule for controlling a process variable set point at a stage in the multi-stage manufacturing process,
• wherein the control rule includes at least a rule to set an operating condition at a future manufacturing process stage that follows a current manufacturing process stage.