Energy based fault detection improves robot joint diagnosis
Energy-Based Fault Detection and Isolation Framework for Flat Port-Hamiltonian Mechanical Systems
Robotics
Summary
Mechanical systems like robots can develop faults that affect their movement, but it's hard to detect problems when the control system hides those errors. The authors created a method that looks at energy flows in the system during planned motions to spot different kinds of faults without needing complex observers. They tested their approach on a simulated robot arm and showed it can distinguish normal operation from various faults with reasonable accuracy. This helps keep machines running smoothly by finding problems early from simple measurements.
What this means in practice
- •For robotics engineers: Detect and distinguish different joint faults in robotic arms from planned motion data without complex observers.
- •For industrial maintenance teams: Monitor automated machinery to identify actuator degradation and mechanical anomalies early using energy residual methods.
Authors
Johnny Garcia, Nicolas Salguero, Naveed Iqbal, Brahim Brahmi, Ramy Rashad
Abstract
Fault diagnosis during regulated motion requires informative signals even when feedback attenuates tracking deviations. This paper develops an energy-based diagnostic framework that constructs mechanical port-power residuals without a dedicated dynamic observer. Spectral Hamiltonian Algebraic Power Evaluation (SHAPE) combines port-Hamiltonian variables and differential flatness to generate nominal power references from planned motion for fully actuated mechanical systems with collocated actuation. Subtracting these references from commanded effort multiplied by measured flow yields residuals whose final evaluation requires neither recursive observer updates nor measured-state dynamics calculations. Continuous wavelet transform (CWT) scalograms and a shared-encoder convolutional neural network are used to distinguish nominal operation, actuator loss of effectiveness, anomalous friction, and vibration from complete trajectories. Evaluation uses a simulated six degree of freedom Kinova manipulator under model predictive control and fixed plant-model mismatch, with single faults at a specified joint. Across five training seeds and 3000 held-out test runs, SHAPE-CWT achieves a mean accuracy of 84.69 percent, versus 81.67 percent for torque residuals and 97.17 percent for the generalized momentum observer under common CWT processing. The respective sample standard deviations are 0.70, 0.70, and 0.37 percentage points. These results demonstrate useful fault-type discrimination from algebraic power residuals, while severity-excitation profiles and offline velocity perturbations reveal limits to their diagnostic capability.