Real-Time 3D Printing Quality Control via Neural Network Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current 3D printing technologies lack real-time quality evaluation and feedback control mechanisms, making it difficult to ensure the quality of the printed objects and optimize the printing process.
Innovation Solution
A 3D printing system and method that utilizes an artificial neural network model based on machine-learning to evaluate the quality of the 3D printing process in real-time by analyzing thermal images and ultrasonic signals, allowing for feedback control of process variables such as laser intensity, speed, and material discharge.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If real-time quality evaluation and feedback control are implemented using neural networks and sensors, then 3D printing quality and process reliability are improved, but system complexity and device complexity increase
Solution Approach 1:
The patent implements real-time feedback control by continuously monitoring 3D printing process parameters (temperature, velocity, acceleration) using sensors and comparing them against target values. The system adjusts process parameters dynamically based on deviations detected during printing, enabling closed-loop quality control that improves reliability without requiring overly complex manual intervention systems.
Solution Approach 2:
The patent replaces complex manual quality inspection and adjustment mechanisms with automated sensor-based monitoring and neural network analysis. Instead of mechanical inspection systems, the invention uses optical sensors, thermal sensors, and machine learning algorithms to evaluate printing quality in real-time, reducing mechanical complexity while improving detection accuracy.
2Measurement precision
If multiple sensors and neural network models are deployed for real-time quality evaluation, then measurement precision and detection accuracy improve, but device complexity and cost increase
Solution Approach 1:
The patent employs a multi-functional sensor system where a single sensor array captures multiple types of data (temperature, velocity, acceleration, positional information) simultaneously. The neural network model processes these diverse data types through unified input layers, allowing one sensor system to perform multiple quality evaluation functions rather than requiring separate specialized sensors for each measurement type.
Solution Approach 2:
The patent combines multiple measurement functions into an integrated monitoring system. Instead of using separate independent sensor systems for temperature, motion, and quality detection, the invention merges these functions into a coordinated sensor array that collects all process parameters through a unified acquisition and processing architecture, reducing overall system complexity while maintaining comprehensive measurement capabilities.
3Manufacturing precision
If real-time monitoring and feedback control are implemented, then manufacturing precision and process control improve, but loss of time for data collection and processing increases
Solution Approach 1:
The patent performs preliminary actions by pre-establishing target values for process parameters and pre-configuring neural network models with optimized architecture and training data. The system continuously compares real-time sensor readings against these pre-set targets rather than performing complex analysis during processing, enabling rapid quality evaluation. The neural network models are pre-trained to make real-time predictions about printing quality based on process parameter deviations.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables real-time estimation and improvement of 3D printing quality by detecting abnormalities and adjusting process parameters, thereby enhancing the quality and efficiency of the 3D printing process.
Implementation Method 1
a base material supplied to a 3D printing object is melted by a laser source for 3D printing
Implementation Method 2
a base material supplied to a 3D printing object is melted by a laser source
Implementation Method 3
measuring a thermal image and an ultrasonic signal for the 3D printing object
Implementation Method 4
measuring a thermal image and an ultrasonic signal for the 3D printing object
Data Source
AI summary
A method of feedback controlling a 3D printing process in real time, and a system therefor are disclosed. The method includes collecting big data, generated through 3D printing experiments, related to process variables of 3D printing, measurement signals, and 3D printing quality of the 3D printing object; building an artificial neural network model by performing machine-learning based on the collected big data; evaluating whether or not a 3D printing quality of the 3D printing object is abnormal in real time based on an actual measurement signal of the 3D printing object and the artificial neural network model; and feedback controlling printing quality of the 3D printing object in real time based on the evaluation result of whether or not the 3D printing quality of the 3D printing object is abnormal.