Automated control of a manufacturing process

A computing device comprising:

• a processor;
• and
• a non-transitory computer-readable medium operably coupled to the processor, the computer-readable medium having computer-readable instructions stored thereon that, when executed by the processor, cause the computing device to
• train a generative adversarial network with an autoencoder using a first plurality of observation vectors, wherein each observation vector of the first plurality of observation vectors includes state variable values for state variables and an action variable value for an action variable, wherein the state variables define a machine state, wherein the action variable defines a next action taken in response to the machine state, wherein the first plurality of observation vectors successively define sequential machine states to manufacture a product;
• generate a second plurality of observation vectors using the trained generative adversarial network with the autoencoder, wherein a plurality of observation vectors includes the first plurality of observation vectors and the generated second plurality of observation vectors;
• train a machine state machine learning model to predict a subsequent machine state using the plurality of observation vectors;
• and
• output a description of the trained machine state machine learning model.

A method of training a machine state predictive model, the method comprising:

• training, by a computing device, a generative adversarial network with an autoencoder using a first plurality of observation vectors, wherein each observation vector of the first plurality of observation vectors includes state variable values for state variables and an action variable value for an action variable, wherein the state variables define a machine state, wherein the action variable defines a next action taken in response to the machine state, wherein the first plurality of observation vectors successively define sequential machine states to manufacture a product;
• generating, by the computing device, a second plurality of observation vectors using the trained generative adversarial network with the autoencoder, wherein a plurality of observation vectors includes the first plurality of observation vectors and the generated second plurality of observation vectors;
• training, by the computing device, a machine state machine learning model to predict a subsequent machine state using the plurality of observation vectors;
• and
• outputting, by the computing device, a description of the trained machine state machine learning model.