Google Cloud has launched Visual Inspection AI, a computer vision platform to help manufacturers reduce defects and deliver savings through the inspection process, according to the company last month.
Defects in products, such as computer chips, cars, and machinery, cost manufacturers “billions of dollars” annually, Google reports.
Specifically, quality-related costs can consume 15% to 20% of sales revenue.
The challenges are due partly to high production volumes that outpace the ability of workers to manually inspect each part.
See more: Google Data Portfolio Review
Visual Inspection AI is designed to automate the quality control process and enable manufacturers to quickly and accurately detect defects before products are shipped.
The platform is intended to help manufacturers identify defects early in the process to increase production throughput and yields, while reducing rework, return, and repair costs.
“AI has proven to be particularly beneficial in helping to automate the visual quality control process for manufacturers — a particular pain point felt by the industry,” said Dominik Wee, managing director of manufacturing and industrial, Google Cloud.
Kevin Prouty, group VP at IDC, said Google Cloud’s approach to visual inspection is a “road map” for most manufacturers.
See more: Top 15 Artificial Intelligence Software
Industry Use Cases
There are many uses cases for the Visual Inspection AI, including in automotive manufacturing, electronics manufacturing services (EMS), and semiconductor production.
A typical auto factory produces about 300,000 vehicles each year, and up to 10% of them may have parts that underwent rework or replacement during the production process to “address some type of production defect.”
Of the 15 million printed circuit boards produced each year in a typical EMS factory, up to 6% may be reworked or scrapped during the assembly process, due to internal or external “quality failures,” such as soldering errors or missing screws.
In the semiconductor industry, a chip fabrication plant that produces 600,000 wafers a year could see yield losses of up to 3% from cracks and “other defects.”
