What is Edge Learning?
Manufacturing and logistics companies across the board are grappling with a growing number of challenges including supply chain disruptions, retaining qualified labor, and rising transportation and raw material costs. In the wake of these market trends, artificial intelligence (AI) has been touted as a “game changer” that can alleviate these burdens through more efficient workflows, reduced costs, improved quality, and increased uptime (Rapp) .
However, AI has struggled to find a stable foothold, particularly among small- to medium-sized operations. The allure of greater efficiency and throughput is intriguing, but some logistics and manufacturing facilities are still skeptical if AI can make a meaningful impact on the production floor. And factors such as the perceived learning curve, personnel requirements, and investment in technology infrastructure (Fujimaki) may give companies the false notion that AI is expensive, time-consuming, and difficult to deploy.
Edge learning breaks this stigma, providing a practical, scalable AI-based solution for automating manufacturing and logistics applications.
What is edge learning?
Edge learning is an AI technology in which processing takes place on-device, or “at the edge” of where the data originates. Leveraging a set of pre-trained algorithms, the technology is simple to setup, requiring less time and fewer images for training compared to other AI-based solutions, like deep learning.
Edge learning is a viable solution for beginners and experts alike. It can be deployed by engineers looking for an easy way to integrate automation into their lines or by experienced engineers who regularly use machine vision but lack specific AI expertise. Being both extremely capable and easy to use, edge learning can automate a range of applications across the factory and across industries.
What are the benefits of edge learning?
Edge learning makes automation easy. Since it requires neither specialized knowledge of machine vision nor AI, line engineers can train the technology using their existing knowledge of required tasks. The solution only needs a handful of sample images to learn the difference between unacceptable and acceptable parts and requires no prior AI or machine vision experience. Read on to learn more about the benefits of using this powerful technology.
How does edge learning work?
Using a single, smart camera-based solution, edge learning can be deployed on any factory line within minutes. This type of solution typically integrates several components including machine vision hardware, rule-based tools, and AI capabilities.
Edge learning runs entirely in a smart camera equipped with integrated lighting, an autofocus lens, and a powerful sensor, all of which work together to deliver precise inspection capabilities.
Lighting is key for a high-quality imaging as it maximizes contrast, minimizes dark areas, and brings out the necessary detail.
A high-speed autofocus lens ensures that the object of interest is always in focus, even as distance changes. It does so by instantly adjusting focus as the region of interest (ROI) changes. Liquid autofocus lenses are smaller and lighter than equivalent mechanical lenses, reducing the size and weight of the camera while making it resistant to the shock and vibration of a production line.
A large and capable sensor offers high resolution and a wide field of view (FOV) for any given application.
Machine Vision Tools
Rule-based vision tools are well-suited for specialized tasks, such as location, measurement, and orientation. For the purposes of edge learning, they are combined in ways specific to the demands of factory automation, eliminating the need to chain vision tools or build complex logic sequences when training the system.
These tools provide fast preprocessing of images, extracting density, edge, and other feature information for the purposes of detecting and analyzing manufacturing defects. By identifying and clarifying the relevant parts of the image, these tools reduce computational load, compared to traditional deep learning approaches.
Instead of using rules created by human programmers, AI learns by example, building a neural network and devising effective pass/fail thresholds from labeled examples of acceptable and unacceptable parts. In essence, it mimics the way humans learn.
AI capabilities can have large training requirements. Edge learning, on the other hand, takes advantage of the fact that factory automation images have specific structural contents, and so pre-trains its algorithms with that domain knowledge. Not starting from scratch results in a less learning-intensive application.
What is edge learning used for?
Manufacturers and logistics companies can deploy edge learning to address a wide range of challenges across all industries from automotive and electronics to consumer packages goods and logistics.
Automotive: Inspect Textured Metal Sheet
Safeguard quality using edge learning to detect and classify imperfections and differentiate flaws from acceptable anomalies.
Electronics: Resistor Quality Check
Inspect resistors and classify them as “NG” (damaged or scratched) or OK with edge learning tools
Packaging: Classify and Sort by Size & Color
Classify and separate products based on size, color, and visual characteristics using edge learning tools.
Logistics: Detect Process Issues
Prevent equipment damage or processing delays by determining the hygiene of trays or items stuck within cross-belt sorters or conveyors.
A common barrier to deploying AI in factory automation is the perceived level of complexity. Today, advances in AI technology, like edge learning, are changing that narrative.
Edge learning is a game-changing technology that’s both extremely capable and simple to deploy. It can automate a variety of tasks, without prior AI experience or technical expertise. From part inspection to sortation and character reading applications, edge learning is the easy answer for bringing automation to the factory floor.
Research and information regarding AI manfacturing and procedures described above were sourced from the following:
- Rapp. (2022, January 7). Artificial Intelligence in Manufacturing: Real World Success Stories and Lessons Learned. Retrieved from: https://www.nist.gov/blogs/manufacturing-innovation-blog/artificial-intelligence-manufacturing-real-world-success-stories
- Dr. Fujimaka. (2020, December 7). Removing Barriers to AI Adoption in Manufacturing. Retrieved from: https://www.automation.com/en-us/articles/december-2020/removing-barriers-to-ai-adoption-in-manufacturing