Google Cloud has launched Visual Inspection AI, a new purpose-built solution to help manufacturers and consumer packaged goods companies to reduce defects and save on operational costs in the manufacturing and inspection process.
Traditionally supporting manufacturing quality control through its existing AI product, AutoML, Google Cloud’s Visual Inspection AI will automate the process allowing manufacturers to quickly and accurately find defects prior to shipping.
Identifying defects early in the process will allow customers to improve production throughput, increase yields, reduce rework and reduce return and repair costs. Visual Inspection AI can operate across a range of industries and use cases, which could save manufacturers millions annually.
Based on pilots run by Google Cloud customers, Visual Inspection AI can build accurate models with up to 300 times fewer human-labelled images than general purpose ML platforms. This allows the solution to be deployed quickly and easily in any manufacturing setting.
Additionally, Visual Inspection AI customers improved accuracy in production trials by up to 10 times compared with general purpose ML approaches. Rather than using simple anomaly detection, the product allows customers to train models to detect, classify and locate multiple defects in an image.
“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,” Google Cloud managing director for Manufacturing and Industrial Dominik Wee said.
“We’ve been delighted by the strong interest in Visual Inspection AI and we look forward to supporting more organisations as they continue to find innovative new ways to deploy AI at scale.”
“We’ve been listening to the specific needs of the industry and have brought the best of Google AI technologies to help address those needs,” Google Cloud head of Product for Industrial AI Mandeep Waraich said.
“The outcome is an AI solution that, built upon years of computer vision expertise, is purpose-built to solve quality control problems for nearly any type of discrete manufacturing process.”
With Google Cloud’s Visual Inspection AI:
- No computer vision or AI subject-matter expertise is required, with an intuitive user interface that guides employees through the necessary steps.
- Engineers can build more accurate models faster, with machine learning models able to be trained using only ten labelled images, automatically increasing in accuracy over time with more product exposure.
- Inspection models can be downloaded to machines on the factory floor and run autonomously at the edge, while combining insights from other integrated data sources, e.g. identifying cause of quality problems.
- Problems are resolved quicker by flagging defective components and locating and identifying the defect within each part.
Google Cloud’s new product can be applied by automotive manufacturers, or for electronics manufacturing services (EMS) and semiconductor production.
“Google Cloud’s approach to visual inspection is the roadmap most manufacturing companies are looking for,” IDC group vice president Kevin Prouty said.
“Manufacturers want flexibility, scale, inherent edge-to-cloud capabilities, access to both real-time and historical data and ease of use and maintainability.
“Google is one of those companies that has the potential to bring together IT, OT and an ecosystem of partners that manufacturers need to deploy AI on the shop floor at scale.”