Filter Coefficient Optimization for Motor Control Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing motor control devices face complexity in calculating optimal parameters for notch filters, leading to increased costs and reduced reliability due to the need for external measuring instruments and complex circuit configurations.
Innovation Solution
A machine learning device that optimizes filter coefficients based on measurement information from external instruments, allowing for the detachment of these instruments after adjustment, thereby simplifying the setting of filter parameters and improving reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traditional methods are used to determine notch filter parameters, then filter optimization can be achieved, but the circuit configuration becomes complex and costs increase
Solution Approach 1:
The patent extracts the filter parameter optimization function from the motor control device itself and places it in an external machine learning device. This allows the motor control device to maintain a simple circuit configuration while still achieving optimal filter parameters through external computation and training.
Solution Approach 2:
The patent replaces complex mechanical/circuit-based parameter tuning methods with machine learning algorithms. The machine learning device uses computational models to determine optimal filter parameters, substituting physical trial-and-error adjustment with intelligent computational optimization.
2Measurement precision
If external measuring instruments are permanently installed, then measurement accuracy is maintained, but costs increase and reliability decreases
Solution Approach 1:
The patent performs filter parameter optimization in advance using the external measuring instrument during the machine learning training phase. Once the optimal parameters are determined, they are stored and used without requiring the measuring instrument to remain installed, thus maintaining measurement accuracy during calibration while improving reliability during operation.
Solution Approach 2:
The external measuring instrument is used temporarily during the learning phase to capture vibration data and determine optimal filter parameters. After the parameters are established, the measuring instrument can be detached or discarded, as the optimized filter parameters are retained for ongoing operation without needing continuous measurement.
3Adaptability or versatility
If multiple parameters for notch filter are determined manually, then filter characteristics can be adjusted, but the calculation process becomes difficult and time-consuming
Solution Approach 1:
The machine learning device performs self-learning by automatically analyzing vibration data and determining optimal filter parameters without requiring manual intervention. The system trains its own model using collected data, enabling it to autonomously adapt filter characteristics while simplifying the operation for users.
Solution Approach 2:
The system uses feedback from vibration measurements to continuously improve filter parameter determination. The machine learning device analyzes the actual vibration data, compares it with expected patterns, and adjusts the filter parameters accordingly, creating a closed-loop optimization process that is both accurate and easy to operate.
Data Source
AI summary
Setting of parameters that determine filter characteristics is facilitated. Machine learning of optimizing the coefficients of a filter provided in a motor control device that controls rotation of a motor for a machine tool, a robot, or an industrial machine is performed on the basis of measurement information of an external measuring instrument provided outside the motor control device and a control command input to the motor control device.