Research on 3D Path Optimization for an Inspection Micro-Robot in Oil-Immersed Transformers Based on a Hybrid...

Area of Science:

• Robotics and Automation
• Electrical Engineering
• Artificial Intelligence

Background:

• Manual inspection of oil-immersed transformers for insulation faults is inefficient and potentially hazardous.
• Micro-robots offer a promising alternative for automated inspection but face challenges with path planning due to limited battery life.

Purpose of the Study:

• To develop and validate a hybrid algorithmic framework for optimizing the 3D inspection path of micro-robots in oil-immersed transformers.
• To enhance the efficiency and accuracy of detecting insulation faults like discharge carbon traces.

Main Methods:

• Formulated inspection point visiting as a Constrained Traveling Salesman Problem (CTSP) solved by Ant Colony Optimization (ACO).
• Employed a hybrid path planning strategy combining A* algorithm, Rapidly-exploring Random Tree (RRT), and Particle Swarm Optimization (PSO) for obstacle avoidance.
• Utilized B-spline interpolation for trajectory smoothing.

Main Results:

• Achieved a 52.6% reduction in path length compared to the unoptimized A* algorithm.
• Demonstrated exceptional stability with the A*-ACO combination.
• Generated smooth trajectories with limited path curvature (<0.033) and torsion (<0.026).

Conclusions:

• The proposed hybrid algorithm significantly enhances micro-robot inspection path planning efficiency for oil-immersed transformers.
• This approach offers practical value and theoretical support for advancing micro-robot inspection technologies in transformer maintenance.
• Improved path optimization leads to more efficient and accurate fault detection.