Drive Parameter Clustering for Mechanical Degradation Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating mechanical degradation in machines with complex systems and multiple components are limited, as they often require direct measurements and struggle with non-linear degradation processes, especially in applications like robotic grasping where sensor data is scarce.
Innovation Solution
A method using cluster analysis based on drive parameters measured during the motion of a movable component, employing a K-means algorithm to determine a degradation value independently of direct component measurements, allowing for reliable estimation of mechanical degradation in complex systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If data-driven methods are used for degradation estimation, then the approach can handle non-linear degradation processes, but it requires direct measurements of component degradation status which are often unavailable
Solution Approach 1:
The patent introduces drive parameters as an intermediary variable that indirectly reflects the degradation state of machine components. Instead of directly measuring component degradation, the system measures parameters from the drive unit (such as current, voltage, speed) that change in response to component degradation, thereby mediating between the unobservable degradation state and observable measurements
Solution Approach 2:
The patent replaces direct mechanical measurement of component degradation with electrical measurement of drive parameters. By substituting the measurement approach from direct mechanical sensing to electrical parameter monitoring, the system can infer degradation without requiring direct contact with or sensors on the degrading components
2Reliability
If model based approaches are used for degradation estimation, then physical degradation processes can be reconstructed, but the mathematical and system knowledge required is often unavailable for complex machines
Solution Approach 1:
The patent enables the drive unit to serve dual purposes: both driving the movable component and providing degradation information through its operational parameters. The drive unit essentially monitors itself, with its operational characteristics revealing the health status of driven components without requiring separate monitoring systems or complex mathematical models
Solution Approach 2:
The patent makes the drive parameters serve multiple functions: they control the motion of the movable component and simultaneously provide information about the degradation state of machine components. This multi-functionality eliminates the need for separate degradation sensing systems and reduces overall system complexity
3Measurement precision
If direct measurements of component degradation are taken, then accurate degradation status can be obtained, but the system becomes more complex and requires additional sensors
Solution Approach 1:
The patent introduces drive parameters as an intermediary variable that indirectly reflects the degradation state of machine components. Instead of directly measuring component degradation, the system measures parameters from the drive unit (such as current, voltage, speed) that change in response to component degradation, thereby mediating between the unobservable degradation state and observable measurements
Solution Approach 2:
The patent extracts degradation information from the drive parameters without requiring additional sensors on the degrading components. By taking out the relevant information from the existing drive unit measurements, the system avoids adding measurement complexity while still obtaining degradation status
Data Source
Figure 1~2
Figure 3~4
Figure 5~6
AI summary
A method for estimating a mechanical degradation of a machine (1) comprises using a drive unit (3a, 3a', 3b, 3b', 3c, 3c', 3d, 3e, 4) of the machine (1) to move a movable component (2a, 2b, 2c, 2d, 2e) of the machine (1) during an evaluation period. A drive parameter is measured during the evaluation period to set up a set of input data. A cluster analysis is performed by a computing unit (5) on the input data and a degradation value (d) for the machine (1) is determined by the computing unit (5) depending on a result of the cluster analysis.