Digital Flowchart Generation for Adaptive Assembly Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing self-learning manufacturing and assembly processes are rigid and inflexible, requiring machine-specific programming, which is costly and inefficient for flexible production and small series.
Innovation Solution
A computer-implemented method generates a machine-independent digital flowchart for manufacturing and assembly processes using video data and digital models, enabling autonomous learning and adaptation to changing conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If teach methods are used to detect and replicate motion sequences identically, then manufacturing precision is improved, but adaptability deteriorates
Solution Approach 1:
The patent transforms static, rigid motion sequences into dynamic, adaptive processes. The system continuously learns from video data and sensor feedback, allowing motion sequences to be automatically adjusted and optimized in real-time based on changing conditions, workpiece variations, and machine state, thereby maintaining precision while gaining adaptability.
Solution Approach 2:
The manufacturing system performs self-learning and self-optimization by automatically analyzing video data of the manufacturing process, detecting deviations, and adjusting parameters without external intervention. This self-service capability enables the system to adapt to changing conditions while maintaining manufacturing precision through autonomous continuous improvement.
2Manufacturing precision
If machine-specific programming is implemented, then manufacturing precision is improved, but device complexity increases
Solution Approach 1:
Instead of programming each machine with complex machine-specific instructions, the system creates a universal digital twin model that copies and represents the manufacturing process generically. This digital twin can be replicated across multiple machines without requiring machine-specific programming, reducing complexity while maintaining precision through the standardized digital model.
Solution Approach 2:
The patent develops a universal programming approach where a single digital flowchart and process model can control multiple different machines and manufacturing systems. This universal representation eliminates the need for machine-specific programming for each device, reducing overall system complexity while maintaining manufacturing precision through the standardized universal model.
3Productivity
If teach methods are used for autonomous learning, then productivity is improved, but loss of time increases
Solution Approach 1:
The system performs preliminary actions by pre-processing video data and sensor information to create the digital twin model before actual manufacturing begins. This preliminary model creation captures the essential process parameters and geometry, allowing rapid deployment and reducing setup time for subsequent production runs while maintaining high productivity.
Solution Approach 2:
The patent replaces traditional mechanical teach methods (manual programming, physical measurement, and trial-and-error setup) with automated optical and sensor-based systems. Video cameras and sensors automatically capture process data, which is then processed algorithmically to generate the digital twin, dramatically reducing the time required for process setup while increasing productivity through automation.
Data Source
AI summary
A computer-implemented method is for generating reference data for use in a manufacturing and/or assembly process. The method may include, as a method step, obtaining a digital model of a workpiece. Herein, the digital model may be, in particular, a 3D model. The digital model may also be, in particular, a CAD model. The workpiece may be, in particular, an assembled workpiece. In another step, the method may include obtaining video data of the manufacturing and/or assembly process of the workpiece. Furthermore, the method may include generating a digital flowchart of the manufacturing and/or assembly process based at least in part on the digital model and the video data.