Robot Speed Reducer Diagnosis Using Maintenance Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing abnormality diagnosis devices cannot recognize cause-and-effect relationships between target apparatuses when an abnormality occurs, limiting their ability to predict and notify abnormalities in associated movable parts.
Innovation Solution
An abnormality diagnosis device with a maintenance history storage unit and control unit that predicts abnormalities in associated movable parts by analyzing maintenance data and sensor data, using correlation analysis to identify linked components and outputting predictive information to operators.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional abnormality diagnosis devices are used, then abnormality detection is possible, but cause-and-effect relationships between apparatuses cannot be recognized
Solution Approach 1:
The system segments the diagnosis process into distinct functional modules: data acquisition unit that collects maintenance data and operation data separately, correlation analysis unit that processes relationships between different apparatuses, and abnormality prediction unit that generates predictions. This segmentation enables the system to handle complex multi-apparatus relationships while maintaining clear cause-and-effect tracking.
Solution Approach 2:
The correlation analysis unit serves as an intermediary between raw data and abnormality predictions. It analyzes maintenance data and operation data to identify causal relationships between apparatuses, then transmits this relationship information to the abnormality prediction unit. This intermediary layer preserves cause-and-effect information that would otherwise be lost in traditional direct detection systems.
2Reliability
If maintenance data is collected and analyzed across multiple apparatuses, then predictive capability improves, but system complexity increases
Solution Approach 1:
The abnormality prediction unit is designed to handle multiple types of apparatuses and multiple categories of maintenance data through a unified analysis framework. The correlation analysis unit can process various data formats and identify relationships across different apparatus types, reducing the need for apparatus-specific complex processing while maintaining high predictive accuracy.
Solution Approach 2:
The system performs preliminary correlation analysis on maintenance data and operation data before abnormality detection is needed. By pre-processing data to establish baseline relationships and patterns, the system reduces the computational complexity required during actual abnormality prediction events, while improving reliability through thorough preliminary analysis.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An abnormality diagnosis device diagnoses an abnormality of a plurality of speed reducers (14) included in a robot (101) in accordance with disturbance torque regarding a state of the respective speed reducers (14) acquired from a sensor (13) installed in the robot (101), and outputs a result of the diagnosis to a display unit (62), the abnormality diagnosis device including a maintenance history DB (32) configured to store maintenance data on maintenance made for the respective speed reducers (14), and a control unit (51) configured to detect an abnormality in the respective speed reducers (14) in accordance with the disturbance torque. The control unit (51), when detecting an abnormality in one speed reducer (14a) in accordance with the disturbance torque, predicts an abnormality in another speed reducer (14b) caused in association with the abnormality in the one speed reducer (14a) in accordance with the maintenance data, and outputs information on the predicted abnormality to the display unit.