AI-Guided Solar Panel Installation Under Glare and Poor Lighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The installation of solar panels on rotatable structures poses challenges in ensuring all panels are coplanar and leveled, and conventional computer vision techniques are affected by environmental inconsistencies like glare and illumination issues, leading to inefficiencies and increased costs.
Innovation Solution
A solar panel handling system that combines an end-of-arm assembly tool with suction cups, a linear guide assembly, and machine learning techniques to overcome environmental inconsistencies, enabling precise positioning and leveling of solar panels on installation structures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional computer vision techniques are used for solar panel installation, then object detection can be performed, but detection accuracy deteriorates due to glare and illumination issues
Solution Approach 1:
The system dynamically adjusts camera exposure settings and selects between multiple cameras based on real-time lighting conditions. The controller monitors environmental factors and adapts the vision system's parameters to maintain detection accuracy across varying illumination levels and glare conditions.
Solution Approach 2:
The system introduces intermediate processing layers including multiple camera angles, infrared imaging capabilities, and AI-based image processing algorithms that serve as mediators between the harsh environmental conditions and the object detection task, filtering out glare effects and extracting reliable feature data.
2Use of energy by moving object
If solar panels are installed on rotatable structures to track the sun, then energy generation is improved, but installation complexity and leveling precision deteriorate
Solution Approach 1:
The system employs sensors and vision systems that provide real-time feedback on panel position, angle, and coplanarity during installation. The controller uses this feedback to automatically adjust robotic arm movements and clamping forces, ensuring precise leveling even on rotatable structures that will later track the sun.
Solution Approach 2:
The system replaces manual mechanical alignment processes with automated robotic positioning systems equipped with vision guidance and force feedback. This substitution enables precise control of panel orientation and coplanarity without relying on traditional mechanical leveling methods.
3Ease of operation
If manual installation methods are used for solar panels, then flexibility is maintained, but installation time and labor costs increase
Solution Approach 1:
The robotic system is designed with universal end effectors and programmable control capabilities that allow it to perform multiple installation tasks including panel handling, positioning, clamping, and electrical connections. This multi-functionality maintains operational flexibility while dramatically increasing installation speed compared to manual methods.
Solution Approach 2:
The system uses programmable parameters and configurable settings that allow rapid adaptation to different panel types, installation configurations, and site-specific requirements. By changing software parameters rather than physical hardware, the system maintains flexibility while achieving high-speed automated installation.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system enhances the efficiency and reliability of solar panel installation by using machine learning to adapt to environmental challenges, ensuring accurate alignment and leveling, thereby reducing installation costs and improving overall efficiency.
Implementation Method 1
an end of arm assembly tool with suction cups
Implementation Method 2
a force torque transducer configured to move the clamping tool along the installation structure
Data Source
AI summary
A system and method for installing solar panels are provided. The method includes obtaining an image of an in-progress solar installation. The image includes an image of one or more solar panels and one or more torque tubes. The method also includes detecting solar panel segments by inputting the image to a trained neural network that is trained to detect solar panels in poor lighting conditions. The method also includes estimating panel poses for the one or more solar panels, based on the solar panel segments, using a computer vision pipeline. The method also includes generating control signals, based on the estimated panel poses, for operating a robotic controller for installing the one or more solar panels.