18484682. FEEDBACK CONTROL DEVICE THAT SUPPRESSES DISTURBANCE VIBRATION USING MACHINE LEARNING, ARTICLE MANUFACTURING METHOD, AND FEEDBACK CONTROL METHOD simplified abstract (CANON KABUSHIKI KAISHA)

From WikiPatents
Jump to navigation Jump to search

FEEDBACK CONTROL DEVICE THAT SUPPRESSES DISTURBANCE VIBRATION USING MACHINE LEARNING, ARTICLE MANUFACTURING METHOD, AND FEEDBACK CONTROL METHOD

Organization Name

CANON KABUSHIKI KAISHA

Inventor(s)

Ryo Nawata of Tokyo (JP)

Yuichiro Miki of Tokyo (JP)

FEEDBACK CONTROL DEVICE THAT SUPPRESSES DISTURBANCE VIBRATION USING MACHINE LEARNING, ARTICLE MANUFACTURING METHOD, AND FEEDBACK CONTROL METHOD - A simplified explanation of the abstract

This abstract first appeared for US patent application 18484682 titled 'FEEDBACK CONTROL DEVICE THAT SUPPRESSES DISTURBANCE VIBRATION USING MACHINE LEARNING, ARTICLE MANUFACTURING METHOD, AND FEEDBACK CONTROL METHOD

Simplified Explanation

The feedback control device described in the patent application takes information about the difference between a measured value and a target value of a controlled object as input and outputs a control amount for the object. It consists of a first control unit that calculates a control amount based on the control deviation, a second control unit that also calculates a control amount based on the control deviation, with the parameter for the calculation determined by machine learning, an operation unit that uses the control amounts to operate the controlled object, and a sampling unit that periodically thins out the control deviation information input to the second control unit.

  • The patent describes a feedback control device that uses machine learning to determine a parameter for calculating the control amount.
  • The device has two control units that calculate control amounts based on the control deviation.
  • The operation unit uses the control amounts to operate the controlled object.
  • The sampling unit periodically thins out the control deviation information input to the second control unit.

Potential applications of this technology:

  • Industrial automation: The feedback control device can be used in various industrial processes where precise control of a controlled object is required, such as manufacturing, chemical processing, and power generation.
  • Robotics: The device can be applied in robotic systems to control the movements and actions of robots, enabling more accurate and efficient operations.
  • Autonomous vehicles: The technology can be utilized in self-driving cars and other autonomous vehicles to control their speed, direction, and other parameters, improving safety and performance.

Problems solved by this technology:

  • Improved control accuracy: By using machine learning to determine the parameter for calculating the control amount, the device can adapt and optimize the control process, leading to more precise control of the controlled object.
  • Reduced human intervention: The feedback control device automates the control process, reducing the need for manual adjustments and interventions, saving time and resources.
  • Enhanced system stability: The device continuously monitors and adjusts the control amount based on the control deviation, ensuring the controlled object operates within the desired range and minimizing deviations from the target value.

Benefits of this technology:

  • Increased efficiency: The feedback control device optimizes the control process, leading to improved efficiency in various applications, such as manufacturing, energy management, and transportation.
  • Enhanced productivity: By automating the control process and reducing human intervention, the device allows for continuous and reliable operation, increasing productivity in industrial and robotic systems.
  • Improved safety: The precise control provided by the device helps maintain safe operating conditions for controlled objects, reducing the risk of accidents and errors.


Original Abstract Submitted

The feedback control device takes information regarding a control deviation between a measured value and a target value of a controlled object as input, and outputs a control amount for the controlled object; comprising: a first control unit that takes information regarding the control deviation as input, and outputs a first control amount for the controlled object; a second control unit that takes information regarding the control deviation as input and outputs a second control amount for the controlled object, and in which a parameter for calculating the second control amount is determined by machine learning; an operation unit that operates the controlled object using the first control amount output from the first control unit and the second control amount output from the second control unit; and a sampling unit for thinning out at a predetermined period information regarding the control deviation input to the second control unit.