Robotic Coating Program Generation for Thickness and Collision Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Programming robots for coating operations in industrial settings is a time-consuming, error-prone, and complex task due to the need for precise control of coating thickness and collision avoidance.
Innovation Solution
A method involving machine learning to generate robotic programs by processing training data, using a coating prediction module to simulate and adjust coating thickness, and ensuring collision-free paths within an industrial sub-cell, utilizing a coating dispersion object to emulate the coating behavior of the robot.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional manual programming methods are used for robot coating operations, then the robot can be programmed to apply coating material, but the programming process becomes time-consuming and error-prone
Solution Approach 1:
The system creates a digital twin (virtual representation) of the physical robot, coating gun, and industrial cell environment. This virtual model allows for simulation and programming without affecting the actual physical system, enabling error-free programming in a risk-free virtual environment before deployment to the real robot.
Solution Approach 2:
The system performs preliminary simulation and collision detection in the virtual environment before actual coating operations. By pre-testing the robotic program in the digital twin, potential errors and collisions are identified and resolved beforehand, preventing time-consuming corrections during actual production.
2Manufacturing precision
If precise control of coating thickness is implemented, then coating quality improves, but the complexity of the programming task increases
Solution Approach 1:
The system incorporates a coating prediction module that uses machine learning models to predict the coating thickness outcome based on programmed parameters. This feedback mechanism allows the system to automatically adjust programming parameters to achieve desired coating thickness, reducing the complexity of manual precise control while improving coating quality.
Solution Approach 2:
The system replaces complex manual programming and physical trial-and-error with automated machine learning-based prediction and optimization. The coating prediction module automatically calculates optimal programming parameters, substituting the need for complex manual programming while achieving precise coating thickness control.
3Reliability
If collision detection and avoidance are implemented in real-time, then safety improves, but the programming and simulation process becomes more complex
Solution Approach 1:
The system implements collision detection in the virtual digital twin environment, which accurately replicates the physical industrial cell geometry and obstacles. By performing collision detection in the virtual model, the system identifies potential collisions without risking the actual physical system, and the same detection logic can be applied in real-time during operation.
4Manufacturing precision
If iterative tuning of programming parameters is performed to achieve desired coating thickness, then coating quality improves, but the time required for programming increases
Solution Approach 1:
The system replaces manual iterative tuning with automated machine learning-based parameter optimization. The coating prediction module uses trained models to directly compute optimal programming parameters that achieve desired coating thickness, eliminating the need for time-consuming iterative adjustments while maintaining high coating quality.
Solution Approach 2:
The system performs preliminary optimization of programming parameters using the coating prediction module before actual coating operations. By pre-calculating optimal parameters in the virtual environment, the system avoids time-consuming iterative tuning during production while ensuring desired coating thickness uniformity.
Data Source
AI summary
Systems and a method predict a generation of a robotic program for industrial coating. Inputs are received including a virtual representation of a robot, a coating gun, elements of the object surface to be coated and a set of desired coating thickness ranges. Inputs on a coating dispersion object are also received. Training data of a plurality of robotic programs for industrial coating and of their corresponding coating thickness coverage on a plurality of surfaces are received. The training data are processed in x, y tuples so as to learn a mapping function to generate a coating prediction module. Starting with a given selected valid thickness coverage as input parameters, it is proceeded in an iterative manner to predict a robotic program via the coating prediction module. A coating robotic program is generated for each surface element based on the resulting predicted coating programs.