20240013096. DUAL-MODEL MACHINE LEARNING FOR PROCESS CONTROL AND RULES CONTROLLER FOR MANUFACTURING EQUIPMENT simplified abstract (Liveline Technologies Inc.)

DUAL-MODEL MACHINE LEARNING FOR PROCESS CONTROL AND RULES CONTROLLER FOR MANUFACTURING EQUIPMENT

Organization Name

Liveline Technologies Inc.

Inventor(s)

Christopher Edward Couch of Ann Arbor MI (US)

John J. Burtenshaw of Tavistock (CA)

Joseph Eugene Hernandez of Farmington Hills MI (US)

Andrew J. Cabush of Boiling Springs SC (US)

Sean G. Scott of Walled Lake MI (US)

DUAL-MODEL MACHINE LEARNING FOR PROCESS CONTROL AND RULES CONTROLLER FOR MANUFACTURING EQUIPMENT - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240013096 titled 'DUAL-MODEL MACHINE LEARNING FOR PROCESS CONTROL AND RULES CONTROLLER FOR MANUFACTURING EQUIPMENT

Simplified Explanation

The patent application describes a method for training a machine learning model on data from manufacturing equipment to obtain a physics model that describes the evolution of the equipment's state space. A machine-learning-based controller agent is then configured to generate commands for the physics model to modify settings of a simulation of the equipment. The controller agent is trained on the settings and corresponding predicted output parameters using another learning algorithm. The method also includes receiving rules defining control actions for the equipment based on the output parameters being outside a predefined range.

• The method involves training a machine learning model on data from manufacturing equipment.
• The model obtains a physics model that describes the evolution of the equipment's state space.
• A machine-learning-based controller agent is configured to generate commands for the physics model.
• The commands modify settings of a simulation of the equipment.
• The physics model generates predicted output parameters based on input data.
• The controller agent is trained on the settings and predicted output parameters using another learning algorithm.
• The controller agent receives rules defining control actions for the equipment based on the output parameters being outside a predefined range.

Potential applications of this technology:

• Optimizing manufacturing processes by using machine learning to control equipment settings.
• Improving efficiency and productivity in manufacturing by accurately predicting output parameters.
• Enhancing equipment performance and reducing downtime through intelligent control actions.

Problems solved by this technology:

• Inefficient and manual control of manufacturing equipment settings.
• Lack of accurate prediction of output parameters.
• Difficulty in identifying and responding to equipment deviations from predefined ranges.

Benefits of this technology:

• Increased automation and efficiency in manufacturing processes.
• Improved accuracy and reliability in predicting equipment output parameters.
• Enhanced control and responsiveness to equipment deviations, leading to improved quality and reduced downtime.

Original Abstract Submitted

a method includes training a machine learning model on a training data set, that describes input parameters to and corresponding output parameters from manufacturing equipment, using at least one learning algorithm to obtain a physics model that describes evolution of a state space of the manufacturing equipment, configuring a machine-learning-based controller agent to generate commands for the physics model that modify settings of a simulation of the manufacturing equipment by the physics model such that, responsive to input data, the physics model generates corresponding predicted output parameters, and training the machine-learning-based controller agent on the settings and corresponding predicted output parameters using at least one other learning algorithm. the configuring may include receiving at the machine-learning-based controller agent rules defining control actions for the manufacturing equipment to be taken responsive to a value of at least one output parameter from the manufacturing equipment being outside a predefined range.