How to start a deep learning factory automation project in five steps

how to implement a deep learning project

Deep learning image analysis is opening factory automation opportunities across a wide range of industries. From inspecting surface defects to sorting variable parts, checking final assemblies, grading product quality, or reading challenging text, deep learning-enabled vision systems can handle numerous new applications.

Traditional, or “rules-based” machine vision performs reliably with consistent and well-manufactured parts and excels in high-precision applications. Those include guidance, identification, gauging, and inspection, all of which can be executed at extremely fast speeds and with great accuracy. This kind of machine vision is great with known variables: is a part present or absent? Exactly how far apart is this object from that one? Where does this robot need to fixture this part? These tasks are easy to deploy on the assembly line in a controlled environment. But what happens when things aren’t so clear cut?

Enter deep learning for machine vision. Deep learning uses examples-based algorithms and neural networks to analyze defects, locate and classify objects, and read printed markings. By teaching a computer what a good image is with a bunch of examples, it will be able to tell the difference between a good part and a defective one, considering those expected variations.

Getting Started with Deep Learning - Example-based mobile device 

However, plant managers rightly hesitate to risk their existing qualified processes in favor of a new technology’s potential rewards. If a plant manager brings in new technology and it improves efficiency, they get a bonus. If they bring in new tech and it brings the line down, the negative impacts are numerous.

Implementing deep learning in five steps

But successfully implementing deep learning into an automation strategy can yield cost savings, improvements to inefficient internal processes, automate complex inspection applications that are impossible with rules-based vision tools, and help increase throughput. 

Here are five areas to consider before deploying your first deep learning pilot project: 

  1. Set the proper expectations
  2. Understand deep learning's return on investment
  3. Master your resource planning and needs
  4. Start small with an initial pilot project
  5. Undergo a phased project approach

The following in-depth guide can help factories and manufacturers who are new to deep learning avoid costly missteps and lost time, while generating organizational buy-in for the technology’s considerable upside. If done properly, the first successful project can lead to a more ambitious and strategic roll out.

To learn more on these five steps, download the free guide “Getting started with a deep learning factory automation project.

More Posts on

GET ACCESS TO SUPPORT & TRAINING FOR PRODUCTS & MORE

Join MyCognex