AI Inspection Service Automates Composite Part Deviation Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current inspection processes for composite structures are semiautomated, leading to inefficiencies and increased costs due to the need for manual comparison of inspection data with design parameters, resulting in time-consuming and costly revisions to nesting programs when parts fail inspection.
Innovation Solution
An electronic device equipped with a processor, memory storing a model-based definition (MBD), and an AI client service that receives inspection data, compares it to the MBD, determines deviations, and updates a digital thread to automate the inspection process, reducing material waste and improving efficiency by revising cutting scripts and nesting programs automatically.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual inspection processes are used, then human operators can compare inspection data with design parameters, but the process becomes time-consuming and costly
Solution Approach 1:
The patent replaces manual inspection operations with an automated AI-based inspection system. The AI client service automatically receives inspection data, compares it with model-based definitions, determines deviations, and identifies defective parts without human intervention. This substitution of mechanical manual operations with automated AI processing directly reduces inspection time while maintaining measurement precision through systematic algorithmic comparison.
Solution Approach 2:
The inspection system performs self-service by automatically executing the entire inspection workflow including data reception, comparison with design parameters, deviation determination, and defect identification. The AI client service autonomously operates without requiring human operators to manually compare measurements against specifications, enabling the system to inspect itself and eliminate time-consuming manual processes.
2Reliability
If failed parts are remade using the same amount of material, then all parts can be replaced, but material waste increases and efficiency decreases
Solution Approach 1:
The patent implements feedback by having the AI client service receive inspection data, compare it with model-based definitions, determine deviations, and identify defective parts. This feedback loop enables the system to detect which specific parts failed inspection and provides information that can be used to revise nesting programs, allowing material to be reallocated efficiently to parts that need replacement rather than replacing all parts with the same material用量.
Solution Approach 2:
The system changes parameters by using model-based definitions (MBD) that contain detailed geometric and dimensional information about parts. The AI client service compares inspection measurements against these precise MBD parameters to determine deviations and identify defects. This parameter-based approach enables precise determination of defective parts and facilitates optimized material utilization in subsequent nesting program revisions.
3Loss of substance
If nesting programs are revised manually, then material usage can be optimized, but the revision process takes an entire day and reduces efficiency
Solution Approach 1:
The patent replaces manual nesting program revision with automated AI-driven optimization. The AI client service analyzes inspection results, determines defective parts, and provides recommendations for nesting program revisions. This automated approach eliminates the need for human operators to manually revise nesting programs, reducing the revision time from an entire day to a fraction of that time while maintaining or improving material usage efficiency.
4Extent of automation
If semiautomated inspection processes are used, then automated machine operations can be combined with manual operations, but the process remains costly and less efficient
Solution Approach 1:
The patent transitions from semiautomated to fully automated inspection by implementing a self-service AI client service that autonomously performs all inspection functions. The system automatically receives inspection data from automated inspection devices, compares data with model-based definitions, determines deviations, and identifies defective parts without requiring human operators. This complete automation eliminates the costs and efficiency limitations associated with semiautomated processes that require manual comparison and decision-making.
Data Source
AI summary
An electronic device includes at least one processor, at least one memory storing a model based definition (MBD) representing a model of a part, and an artificial intelligence (AI) client service. The AI client service, in response to execution by the at least one processor, is configured to receive inspection data corresponding to a cut part being fabricated based on the model of the part, compare the received inspection data to the MBD to determine any deviations of the cut part from the MBD, determine whether the cut part is defective based on the comparison, and update a digital thread corresponding to the part when the cut part is determined to be defective.