Scribd
Upload
13 views2 pages

Problem Assignment

The document discusses an AI-based fault detection system for yarn manufacturing that addresses defects like slubs and uneven thickness, which traditionally rely on manual inspection. It utilizes high-speed cameras, microcontrollers, and AI algorithms to analyze yarn quality in real-time, improving efficiency and reducing material wastage. While the system enhances production quality, it faces limitations such as high initial setup costs and the need for AI model training and calibration.

Uploaded by

tushar.nitharwal2004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
13 views2 pages

Problem Assignment

The document discusses an AI-based fault detection system for yarn manufacturing that addresses defects like slubs and uneven thickness, which traditionally rely on manual inspection. It utilizes high-speed cameras, microcontrollers, and AI algorithms to analyze yarn quality in real-time, improving efficiency and reducing material wastage. While the system enhances production quality, it faces limitations such as high initial setup costs and the need for AI model training and calibration.

Uploaded by

tushar.nitharwal2004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

AI-Based Fault Detection in Yarn Manufacturing

Problem
In the textile industry, defects in yarn significantly impact the quality of the final
fabric. Issues like slubs, neps, and uneven thickness often go unnoticed until later
stages, leading to material wastage and reduced efficiency. Traditional methods of
fault detection rely heavily on manual inspection, which is time-consuming and
error-prone. To enhance accuracy and speed, an AI-driven approach can be
integrated into the winding, warping, or sizing processes to detect and rectify
defects in real-time.
Solution
5
The proposed system uses a combination of high-speed cameras,
microcontrollers, and AI algorithms to analyze yarn quality at various stages. The
camera captures real-time images of the yarn, while an AI model processes the
4
data to identify defects. If a fault is detected, the system triggers an alert or an
automatic correction mechanism, improving production efficiency.
3
Components Used
● High-resolution camera: Captures detailed images of yarn for analysis.
2
● Microcontroller (ESP32/Raspberry Pi): Processes image data and
communicates with AI algorithms.
1
● AI Model (CNN-based): Detects patterns and identifies defects in yarn
structure.
● Display/Alert System: Notifies the operator of defects in real time.
● Actuator Mechanism (Optional): Can automatically correct minor yarn
defects.
Working Principle
. Image Capture: The high-speed camera continuously takes images of
the yarn during processing.
. Preprocessing: The images are converted into grayscale and enhanced
to highlight potential defects.
. AI Analysis: A trained convolutional neural network (CNN) scans the
images to detect inconsistencies.
. Decision Making: If a defect is found, the system classifies its severity
and either alerts the operator or corrects it.
. Real-Time Monitoring: The data is displayed on a screen, allowing
operators to take immediate action.
Advantages
● Reduces manual inspection errors
● Improves yarn quality consistency
● Speeds up defect identification
● Minimizes material wastage
● Enhances overall productivity
Limitations
● Initial setup cost is high
● Requires proper training of AI model
● Needs periodic calibration for accuracy
This AI-based system offers a significant improvement over traditional yarn fault
detection methods, ensuring better efficiency and product quality in textile
manufacturing.

You might also like