Share 3D printing market trends, knowledge and our stories with you

AEye Assistant Overview

Posted by on

3D printing features an automated process for instant prototyping and customization of the product. The rapid development of 3D printing technology in novel material technology has increased the application of 3D printing in a wide range of areas. Its fusion with cloud manufacturing has reduced the threshold for designing and promoted innovation due to improved integration.

For SMEs, a suitable and affordable solution is required to boost their digital transformation on the factory floor to counter the current challenges by using an appropriate monitoring solution. Our engineers have worked hard to add the finest feature to cloud manufacturing known as AEye Assistant. It is a well-developed Artificial Intelligence computer vision tool that aids without the presence of labor through image-based detection.

The cloud manufacturing platform is fed by manufacturing resources provided by the resource supplier in combined support with the cloud operator. This cloud operator is responsible for defect detection, operation, and maintenance. Our AEye Assistant is a cloud operator tool that assists resource users in producing parts with high quality and efficiency.

It evaluates the quality of the 3D printing part as quality monitoring is still considered a big challenge in Additive Manufacturing. Highly experienced users need to babysit their 3D printers so that their part manufacturing does not fail. If such failures are detected during the initial phases of printing, it may alert the user to either pause or stop the printing process so that corrective measures can be taken in a timely manner. This prevents reprinting the part from scratch.

Our AEye Assistant provides an innovative method for the quality assessment of Fused Filament Fabrication 3D printed products through integration of a camera, image processing, and supervised machine learning. The camera functions through a Raspberry Pi, which is set up next to the 3D printer. Images of the part are taken through several critical stages of the printing process, according to the geometry of the part. Any 3D printing defects during the printing of products are detected through developing Neural Networks.

AEye System

Failures usually occur during material extrusion in 3D printing due to incorrect part positioning, missing material flows, detachment of the printing layers, unbalanced material cooling, and shrinking in the absence of a hot chamber. However, for such challenges, most commercial printers do not have the option to detect such failures due to the unavailability of feedback and monitoring tasks. Due to such complications, it has increased the use of resources such as energy, material, and time.

As of right now, it is a difficult job for the user to tackle challenges of failure due to the lack of references present in layer-by-layer manufacturing by which they can evaluate their printed part. AEye Assistant can help you to improve the quality of the product by detecting material flow problems and optimizing process parameters.

The spaghetti-shape-error which is related to the tangling of the filament requires a restart of the entire 3D printing process. To eliminate such failures, the “brain” of AEye Assistant – Deep Learning-Based Object Detector, a cutting-edge, real-time deep Learning algorithm – functions. Every time the camera takes a picture of the part, it is transferred to the TSD backend system, where it is run through the Deep Learning algorithm. After the numerical synthesis, the algorithm displays the coordinates of several boxes along with one numeric relevant to each of the boxes which provides details about the spaghetti-shape-error.

Let Us Monitor The AI Failure Detection Job For You!

So, what are you waiting for? Sign up to join our Beta Testing Trial account to get to know more about AEye Assistant!








Post a comment

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>