Additive Manufacturing Failure Mode Detection Using Subsystem Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Diagnosing failed builds and performance issues in additive manufacturing devices is time-consuming and requires human labor, making it difficult to identify the root cause of failures efficiently.
Innovation Solution
A system and method that determine parameters associated with additive manufacturing device subsystems, compare them with threshold values using machine learning or statistical models, and identify failure modes, providing a visually interactive interface for quick diagnosis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual diagnosis by expert is used, then diagnostic accuracy can be achieved, but diagnostic time and human labor requirements increase significantly
Solution Approach 1:
The patent replaces the manual mechanical diagnostic process with an automated computer-based system that uses machine learning models and algorithms to analyze sensor data, compare parameters against thresholds, and identify failure modes automatically, eliminating the need for expert manual intervention while maintaining diagnostic accuracy
Solution Approach 2:
The patent introduces an intermediary automated diagnostic system that acts as a mediator between the additive manufacturing device sensors and the final diagnosis, using trained machine learning models to process sensor data and generate diagnostic conclusions, thereby reducing both time and human labor requirements
2Reliability
If manual diagnosis process is used, then root cause identification can be achieved, but the process becomes difficult and time-consuming
Solution Approach 1:
The patent segments the complex diagnostic process into distinct automated components: data collection from sensors, parameter extraction, threshold comparison, failure mode identification, and root cause analysis. Each segment is handled by specific software modules, simplifying the overall process while maintaining reliability
Solution Approach 2:
The patent implements feedback mechanisms where the automated system continuously monitors device parameters, compares them against learned thresholds, and provides real-time diagnostic feedback, enabling reliable root cause identification through systematic analysis rather than complex manual procedures
3Productivity
If automated diagnostic system is implemented, then diagnostic time is reduced and productivity improves, but system complexity increases
Solution Approach 1:
The patent creates a universal automated diagnostic platform that can handle multiple failure modes, subsystems, and parameter types through a single integrated system using machine learning models, achieving high diagnostic throughput without proportionally increasing system complexity
Solution Approach 2:
The patent uses copying by creating virtual representations of device parameters and failure patterns through machine learning models, allowing the system to analyze and diagnose issues through simulated data patterns rather than requiring complex physical diagnostic equipment
Data Source
AI summary
A system for diagnosing an additive manufacturing device is provided. The system includes one or more processors, one or more non-transitory memory modules communicatively coupled to the one or more processors and storing machine-readable instructions. The machine-readable instructions, when executed, cause the one or more processors to: determine parameters associated with at least one subsystem of the additive manufacturing device, the parameters being related to a build generated by the additive manufacturing device; compare the parameters with threshold values; and determine a failure mode, among a plurality of failure modes, associated with a subsystem of the at least one subsystem of the additive manufacturing device based on the comparison of the parameters with the threshold values.