Robot Diagnostics Using Simulation and cGAN Fault Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to predict abnormalities in industrial robots at an early stage, leading to equipment downtime and reduced production output.
Innovation Solution
A robot diagnostic system using a first robot, a second robot for simulation, a model builder to learn normal and abnormal driving states, and a diagnostic device to diagnose abnormalities through a built model, leveraging dynamic time warping and conditional generative adversarial networks (cGAN) to analyze vibration, current, and location data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a diagnostic system is implemented to detect robot abnormalities, then reliability is improved, but device complexity increases
Solution Approach 1:
The patent uses a second robot to simulate and replicate the driving patterns of the first robot, creating a virtual copy that can be used for diagnostic purposes without interfering with the actual robot's operation. This copying approach allows the system to analyze abnormal conditions through simulation data while maintaining the original robot's functionality.
Solution Approach 2:
The patent introduces a model builder as an intermediary component that processes data from both robots and generates diagnostic models. This intermediary layer simplifies the overall system by providing a dedicated module that handles the complex task of pattern recognition and abnormality detection, separating the diagnostic function from the robot control functions.
2Productivity
If real-time monitoring is implemented to prevent downtime, then productivity is improved, but use of energy increases
Solution Approach 1:
The system performs preliminary actions by collecting and analyzing operational data during normal operation to build diagnostic models in advance. The model builder continuously learns from robot operations, preparing diagnostic capabilities before actual failures occur, allowing for early detection without requiring continuous high-energy monitoring during critical moments.
Solution Approach 2:
The patent maintains continuity of useful action by implementing ongoing data collection and model refinement processes that operate continuously during robot operation. The system consistently monitors and learns from operational patterns, ensuring that diagnostic accuracy improves over time while maintaining steady-state energy consumption rather than requiring intermittent high-energy bursts.
Data Source
AI summary
A robot diagnostic system includes a first robot, a second robot configured to simulate driving of the first robot, a model builder configured to learn data on a normal driving state or an abnormal driving state of the first robot or the second robot and build a model that is configured to determine whether the first robot is abnormal, and a diagnostic device configured to receive data on the driving of the first robot and diagnose a state of the first robot through the built mode.