Machine-Learning Additive Manufacturing for Fewer Failed Prints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Additive manufacturing is a heuristic and iterative process prone to failures and suboptimalities due to inadequate part orientation, material selection, and print settings, leading to resource wastage and inefficiencies, with accumulated knowledge often remaining inaccessible and not iteratively improved within enterprises.
Innovation Solution
A machine-learning-based system utilizing a blockchain to store and iteratively strengthen additive manufacturing knowledge, training models on user experience data to provide optimized part configurations and reduce failures by automating corrective actions and recommendations for improved production outcomes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If additive manufacturing is performed using traditional heuristic methods, then fabrication can be completed, but the process is prone to failures and suboptimalities leading to resource wastage
Solution Approach 1:
The system performs preliminary analysis of manufacturing data from previous fabrication attempts before actual production. The machine learning model predicts potential failures and optimizes parameters in advance, preventing defects before they occur and reducing material wastage from failed prints
Solution Approach 2:
The system implements a feedback loop where manufacturing data from each fabrication job is collected, analyzed, and used to retrain the machine learning model. This continuous feedback improves prediction accuracy over time, enabling better defect prevention and reduced material waste in subsequent operations
2Loss of information
If accumulated manufacturing knowledge is stored but remains inaccessible, then data is preserved, but efficiency improvements cannot be achieved
Solution Approach 1:
The system replaces manual knowledge retrieval and analysis with an automated machine learning model that processes manufacturing data. The ML model automatically extracts patterns and insights from historical data, transforming inaccessible information into actionable optimization recommendations without human intervention
Solution Approach 2:
The machine learning model autonomously analyzes manufacturing data, identifies optimization opportunities, and generates recommendations without requiring manual querying or analysis. The system serves itself by continuously learning from new data and automatically improving its predictions for defect prevention and parameter optimization
3Manufacturing precision
If multiple print jobs are attempted to achieve acceptable outputs, then quality can be improved, but time and resources are consumed
Solution Approach 1:
The machine learning model performs preliminary optimization of fabrication parameters based on historical data before production begins. By predicting the optimal combination of parameters for high-quality output, the system eliminates the need for multiple trial print jobs, achieving target quality in the first attempt and reducing fabrication time
Data Source
AI summary
Systems and methods for machine-learning-based additive manufacturing use a machine-learning model to process an input vector describing a new part transaction, thereby providing part optimization outputs and command initiation outputs to configure additive manufacturing of a new part. The machine-learning model is trained based on entries in a user experience database, each entry in the user experience database including data defining requirements for an additively manufactured part previously fabricated or attempted to be fabricated, specifications describing an additive manufacturing fabrication device, a selection of a raw material type fed to the fabrication device for fabrication of the additively manufactured part, a fabrication spatial orientation of the additively manufactured part within the fabrication device, a fabrication slicing resolution of the additively manufactured part, and a toolpath taken by the fabrication device in fabricating the additively manufactured part.