All Factories Who YOLO See Instant Quality Improvements
Popular machine learning algorithms, like You Only Look Once (YOLO), make their way to the factory floor for visual inspection, collision detection, and workstation monitoring.
Assembly Line
An implementation of YOLO-family algorithms in classifying the product quality for the acrylonitrile butadiene styrene metallization
Date: March 31, 2022
Authors: Yuh Wen Chen, Jing Mau Shiu
Topics: Convolutional Neural Network
Tweet | Pocket | Instapaper
In the traditional electroplating industry of Acrylonitrile Butadiene Styrene (ABS), quality control inspection of the product surface is usually performed with the naked eye. However, these defects on the surface of electroplated products are minor and easily ignored under reflective conditions. If the number of defectiveness and samples is too large, manual inspection will be challenging and time-consuming. We innovatively applied additive manufacturing (AM) to design and assemble an automatic optical inspection (AOI) system with the latest progress of artificial intelligence. The system can identify defects on the reflective surface of the plated product. Based on the deep learning framework from You Only Look Once (YOLO), we successfully started the neural network model on graphics processing unit (GPU) using the family of YOLO algorithms: from v2 to v5. Finally, our efforts showed an accuracy rate over an average of 70 percentage for detecting real-time video data in production lines. We also compare the classification performance among various YOLO algorithms. Our visual inspection efforts significantly reduce the labor cost of visual inspection in the electroplating industry and show its vision in smart manufacturing.
Read more at The International Journal of Advanced Manufacturing Technology
Realtime Robotics enhances responsive workcell monitoring by reading CAD files with CAD Exchanger
Date: February 25, 2022
Tweet | Pocket | Instapaper
It was Realtime Robotics who managed to fuse all the latest technological achievements and academic research and to elaborate a specialized toolkit for on-the-fly motion planning. “Realtime Robotics has created technology that solves a 30-year-old challenge in the robotics industry. Our motion planning solution allows industrial automation to move collision-free and respond to obstacles in real time,” says Will Floyd-Jones, Co-Founder & Robotics Engineer in Realtime Robotics.
The initial plan to cobble together various libraries was no longer relevant when Realtime Robotic stumbled upon CAD Exchanger. “We would have to hack a bunch of things together and try to figure out how to get them to import data in one common way. And then we discovered that CAD Exchanger has already solved the problem and would just do that for us,” explains Will Floyd-Jones, Co-Founder & Robotics Engineer in Realtime Robotics.
Read more at CAD Exchanger Blog
Cloud-edge-device collaboration mechanisms of deep learning models for smart robots in mass personalization
Date: March 28, 2022
Authors: Chen Yang, Yingchao Wang, Shulin Lan, Lihui Wang, Weiming Shen, George Q Huang
Tweet | Pocket | Instapaper
Personalized products have gradually become the main business model and core competencies of many enterprises. Large differences in components and short delivery cycles of such products, however, require industrial robots in cloud manufacturing (CMfg) to be smarter, more responsive and more flexible. This means that the deep learning models (DLMs) for smart robots should have the performance of real-time response, optimization, adaptability, dynamism, and multimodal data fusion. To satisfy these typical demands, a cloud-edge-device collaboration framework of CMfg is first proposed to support smart collaborative decision-making for smart robots. Meanwhile, in this context, different deployment and update mechanisms of DLMs for smart robots are analyzed in detail, aiming to support rapid response and high-performance decision-making by considering the factors of data sources, data processing location, offline/online learning, data sharing and the life cycle of DLMs. In addition, related key technologies are presented to provide references for technical research directions in this field.
Read more at ScienceDirect
Inventory Optimization for AI Hardware Manufacturing - with Gopalan Oppiliappan of Intel
Inside or Outside?
Date: March 30, 2022
Author: Jim Camillo
Tweet | Pocket | Instapaper
According to ASSEMBLY magazine’s 26th annual capital equipment spending survey (December 2021), manufacturers, on average, meet 40 percent of their assembly system needs with equipment built in-house. Manufacturers that are able to build quality automation equipment in-house gain many benefits. Some of the main ones, according to Treter, include being able to fully protect intellectual property; maintaining the confidentiality of a new product or a proprietary assembly process; and using the team’s extensive product knowledge to modify or redesign equipment whenever necessary.
Read more at Assembly Magazine
Flying Through Giga Berlin
The Old Switcheroo: Hiding Code on Rockwell Automation PLCs
Date: March 31, 2022
Author: Sharon Brizinov
Tweet | Pocket | Instapaper
Team82 and Rockwell Automation today disclosed some details about two vulnerabilities in Rockwell programmable logic controllers and engineering workstation software. CVE-2022-1161 affects numerous versions of Rockwell’s Logix Controllers and has a CVSS score of 10, the highest criticality. CVE-2022-1159 affects several versions of its Studio 5000 Logix Designer application, and has a CVSS score of 7.7, high severity. Modified code could be downloaded to a PLC, while an engineer at their workstation would see the process running as expected, reminiscent of Stuxnet and the Rogue7 attacks.
Read more at Claroty Blog
Surge Demand
Thirteen new smart factories across Asia and Europe are added to the World Economic Forum’s global lighthouse network. Manufacturers in the US face issues with perception and high labor force turnover. Near-shoring drive gains to Mexico. UPS strengthens partnership with Google to analyze data from RFIDs on packages.