Robot Drive Axis Torque Modeling for Failure Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing failure prediction systems for robots are not accurate in predicting failure across different operation patterns, leading to potential misuse of the robot's life expectancy.
Innovation Solution
A failure prediction system that collects torque values, derives an evaluation formula for time change, sets a failure threshold based on past torque values, and calculates an estimated torque value to determine if failure is predicted within a set time, allowing for accurate failure prediction irrespective of operation patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a method comparing current measurement value with reference value is used for failure prediction, then the prediction can be implemented simply, but the prediction accuracy deteriorates because it cannot account for different operation patterns and robot life expectancy
Solution Approach 1:
The system changes the parameter basis for failure prediction from static reference values to dynamic parameters that account for operation patterns and robot life expectancy. By deriving evaluation formulas that model torque value changes over time and incorporating robot usage history, the system adapts the prediction parameters to match actual operational conditions, thereby improving accuracy without excessive complexity
Solution Approach 2:
The system performs preliminary actions by collecting torque values and deriving evaluation formulas during normal operation before failure occurs. This preliminary data collection and model building enables the system to establish baseline behavior patterns and predict future failures more accurately, rather than relying on simple threshold comparisons that only work at the point of failure
2Ease of operation
If a simple reference value comparison method is used, then the system is easy to operate, but it cannot accurately predict failure across different operation patterns
Solution Approach 1:
The system implements self-service by automatically collecting torque data, deriving evaluation formulas, and updating predictions without requiring manual intervention. The robot's own operational data is used to build and refine the prediction model, allowing the system to maintain high reliability across different operation patterns while remaining easy to operate
Solution Approach 2:
The system incorporates feedback mechanisms where actual torque measurements during operation are continuously compared against predicted values. This feedback loop allows the system to refine its evaluation formulas and improve prediction accuracy over time, maintaining reliability without complicating operation
Data Source
AI summary
A failure prediction system includes: a processor, the processor being configured to: collect torque values of a drive axis of a robot that is operating in accordance with a given work program; derive an evaluation formula approximating a time change of the torque value which is most recent from among the collected torque values set a failure threshold that is the torque value at which it is determined that failure of the drive axis occurs, based on the evaluation formula and the time change of the torque value when the drive axis reached failure in the past; and calculate an estimated value for the torque value when a prediction time set in advance has elapsed in the evaluation formula, and determines whether failure of the drive axis is predicted within the prediction time according to comparison between the estimated value and the failure threshold.