3D Printer Layer Anomaly Detection Using LSTM Sensor Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing 3D printing technologies lack real-time anomaly detection, leading to inefficiencies and material wastage due to quality deviations in printed layers, which are difficult to identify through conventional post-print tests.
Innovation Solution
Implementing a machine learned recurrent neural network (RNN) model with long short-term memory (LSTM) units to analyze sensor data and reconstruct layer data sets, detecting deviations in real-time and notifying users of anomalies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual quality assessment methods are used for 3D printed layers, then quality checks can be performed, but the process becomes time-consuming and inefficient
Solution Approach 1:
The patent replaces manual mechanical quality assessment with an automated machine learning system that uses sensor data and image processing to detect anomalies in 3D printed layers. The system substitutes human operators with computational algorithms including autoencoders and convolutional neural networks that can rapidly analyze print quality without time-consuming manual intervention.
2Loss of substance
If real-time anomaly detection is implemented using machine learning models, then material wastage is reduced, but the system complexity increases
Solution Approach 1:
The patent introduces machine learning models as intermediary systems between the 3D printing process and quality assessment. These models including autoencoders and convolutional neural networks act as mediators that process sensor data and images to detect anomalies, enabling real-time detection without requiring complex direct measurement systems while reducing material wastage through early anomaly identification.
3Measurement precision
If post-printing quality tests are performed on completed objects, then quality can be assessed, but the process lacks causal explanation and requires extensive manual inspection
Solution Approach 1:
The patent implements preliminary quality detection during the printing process itself rather than after completion. The machine learning system continuously monitors sensor data and images during printing, enabling early detection of anomalies before they propagate through subsequent layers. This preliminary action eliminates the need for extensive post-printing manual inspection while providing causal explanations through identified anomaly patterns.
Data Source
AI summary
Examples of systems for detecting anomaly in a print job performed by a three-dimensional printer are described herein. In an example, a data set pertaining to a set of layers printed based on a print job of the 3D printer may be processed by an anomaly detection engine. Thereafter, a data set of a layer being printed by the 3D printer may be obtained. Based on the data set of the set of layers and the data set of the layer being printed, an anomaly may be detected in real-time.