Work Apparatus State Diagnosis Using Multi-Pressure Feature Quantities
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for diagnosing the state of robotic work apparatuses, such as welding guns, face challenges in accurately determining device abnormalities due to variations in operational pressures and external disturbances, leading to inconsistent and unreliable state assessments.
Innovation Solution
A diagnosis system that acquires first and second data by actuating a work apparatus at different pressures, calculates a feature quantity indicating the relation between these data sets, and determines the device's state based on this feature quantity, using statistical methods like Mahalanobis distance to differentiate between normal and abnormal conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If operational data is collected at varying pressures, then the system can capture more comprehensive operational characteristics, but the reliability of state determination deteriorates due to pressure-induced variations
Solution Approach 1:
The patent transforms the operational data by calculating feature quantities that represent relationships between data points obtained at different pressures. This parameter transformation converts raw pressure-dependent data into pressure-independent feature quantities, thereby eliminating the harmful influence of pressure variations while preserving the essential operational characteristics for reliable state determination.
2Measurement precision
If single-pressure data is used for diagnosis, then the measurement process is simple, but the measurement precision deteriorates due to inability to distinguish pressure effects from abnormality effects
Solution Approach 1:
The patent applies partial action by selecting and calculating only the necessary feature quantities from the collected operational data. Instead of analyzing all raw data directly, the system computes specific relationship-based feature quantities that are sufficient for state determination, thereby achieving high measurement precision without requiring excessive computational complexity.
Solution Approach 2:
The system changes the parameter representation from raw operational data at single pressure to relationship-based feature quantities derived from multi-pressure data. This parameter transformation enables precise abnormality detection by separating pressure effects from actual device state, while maintaining manageable system complexity through focused feature calculation.
3Measurement precision
If multiple operational conditions are tested, then the accuracy of device state assessment improves, but the time required for diagnosis increases
Solution Approach 1:
The patent performs preliminary action by pre-calculating and storing feature quantities that represent relationships between operational data at different pressures. During actual diagnosis, the system directly utilizes these pre-computed feature quantities rather than performing complex multi-pressure analysis from scratch, thereby achieving high assessment accuracy while minimizing diagnosis time.
Data Source
AI summary
An example diagnosis system determines a state of a target device that includes a work apparatus. The diagnosis system includes circuitry that is configured to acquire first data generated in response to operating the work apparatus at a first pressure, configured to acquire second data generated in response to operating the work apparatus at a second pressure, configured to calculate a feature quantity indicating a relation between the first data and the second data, and configured to determine the state of the target device based on the feature quantity.