A Low-Cost Multi-Sensor Data Acquisition System for Fault Detection in Fused Deposition Modelling

Area of Science:

• Manufacturing Technology
• Additive Manufacturing
• Industry 4.0

Background:

• Fused Deposition Modelling (FDM) is a key Industry 4.0 technology offering benefits like rapid prototyping and cost-effectiveness.
• However, FDM 3D printing is susceptible to defects, posing challenges for quality control and fault diagnosis.
• Effective monitoring systems are crucial for identifying and mitigating these defects during the printing process.

Purpose of the Study:

• To develop and evaluate a low-cost multi-sensor data acquisition system (DAQ) for real-time fault detection in FDM 3D printing.
• To analyze the impact of various fault conditions on sensor data (vibration, current, sound).
• To implement a Convolutional Neural Network (CNN) model for accurate classification of normal and faulty printing conditions.

Main Methods:

• A multi-sensor DAQ system was designed using an Arduino microcontroller, integrating vibration, current, and sound sensors.
• Time and frequency domain analyses were employed to extract features from sensor data, with chi-square method for feature selection.
• K-means clustering and normal distribution curves were used for data clustering and threshold setting, followed by CNN model training and evaluation.

Main Results:

• The developed DAQ system successfully captured real-time multi-sensor data under various fault conditions.
• Feature extraction and selection methods identified significant patterns indicative of defects.
• The CNN model achieved approximately 94% accuracy in classifying normal versus fault conditions, with strong recall, precision, and F1 scores.

Conclusions:

• The proposed low-cost multi-sensor DAQ system is effective for detecting faults in FDM 3D printing.
• The integrated approach of sensor data analysis and CNN classification offers a reliable solution for quality assurance in additive manufacturing.
• This system contributes to improved monitoring and control in Industry 4.0 manufacturing environments.