Machine Learning Component Supply Device Vibration Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing component supply devices require skilled operators to set vibration operation parameters through trial and error, imposing a significant burden, as these parameters depend on the weights, sizes, and shapes of components, making it inefficient to change component postures for easy gripping.
Innovation Solution
A component supply device equipped with a machine learning device that learns and automatically adjusts vibration operation parameters based on component arrangement and kind data, using a state observation unit, determination data acquisition unit, and learning unit to associate operation parameters with component arrangement data, thereby efficiently changing component postures for easy gripping.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If skilled operators set vibration operation parameters through trial and error, then the components can be arranged in grippable postures, but the operator burden and time consumption increase substantially
Solution Approach 1:
The system performs self-learning by automatically acquiring component data, executing vibration operations, observing results, and updating its own control parameters without human intervention. The machine learning unit stores learned parameters for future use, enabling the system to serve itself in optimizing component arrangement
Solution Approach 2:
The patent replaces the mechanical trial-and-error process performed by skilled operators with an automated machine learning system that uses computational algorithms to determine optimal vibration parameters based on component characteristics and observed arrangement results
2Adaptability or versatility
If vibration operation parameters are manually adjusted for different component types, then the components can be efficiently arranged, but the adaptability to various component weights, sizes, and shapes is limited
Solution Approach 1:
The system automatically adjusts vibration operation parameters (magnitude, frequency, phase difference, duration) based on learned relationships between component characteristics and effective arrangement outcomes. The machine learning unit modifies these parameters dynamically according to the specific component type being processed
Solution Approach 2:
The vibration control unit is designed to handle multiple component types with varying weights, sizes, and shapes by using a unified machine learning approach that learns optimal parameters across different component categories, making the system universally applicable to diverse components
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This solution enables rapid and efficient setting of operation parameters, allowing the component supply device to automatically determine optimal vibration settings for gripping components, reducing operator burden and improving supply efficiency.
Implementation Method 1
vibration units 50 composed of an actuator such as a voice coil and a cylinder are provided on four corners, for example, of the tray 4. When the rate of the components 5b, whose back sides face upward, is increased among the components 5 on the tray 4, the component supply device 1 makes each of the vibration units 50 vibrate at a predetermined magnitude and a predetermined frequency
Data Source
AI summary
A machine learning device in a component supply device includes: a state observation unit, a determination data acquisition unit, and a learning unit. The state observation unit observes state variables representing a current state of an environment. The state variables include (i) vibration operation parameter data representing an operation parameters for a vibration operation of a tray, (ii) component arrangement data representing an arrangement and a posture of components on the tray, and (iii) component kind data representing a kind of the components. The determination data acquisition unit acquires determination data representing a suitability determination result of the vibration operation, which represents efficiency in supply of the components. The learning unit learns the operation parameters, the component arrangement data, and the component kind data while associating the operation parameters with the component arrangement data and the component kind data, by using the state variable and the determination data.