IBM Brings Cognitive Manufacturing To The Factory Floor

IBM has made sizable investments in the Internet of Things (IoT) space over the past several years.

Last October, the company announced it would be spending $3B U.S. to bring Watson cognitive computing to IoT, and allocated more than $200M U.S. to its global Watson IoT headquarters in Munich.

When that announcement was made, IBM had 6,000 clients globally tapping Watson IoT solutions and services, and the momentum continues with its announcement earlier today that the company was launching a new IBM Watson IoT solution, Cognitive Visual Inspection.

Announced at Hannover Messe 2017, Cognitive Visual Inspection will provide manufacturers with a ‘cognitive assistant’ on the factory floor to minimize costly defects and increase product quality.

In fact, based on early testing of a production cycle that typically takes 8 days with ½ day required for needed visual inspection, the new IBM solution reduced inspection time by 80 percent and cut manufacturing defects by 7-10 percent.

Using an ultra-high definition (UHD) camera and cognitive capabilities from IBM Watson, the solution captures images of products as they move through production and assembly, and together with human inspectors, can detect defects in products, including scratches or pinhole-size punctures.

The solution, which continuously learns based on human assessment of the defect classifications in the images, is designed to help manufacturers improve for product excellence, achieve never seen before specialization levels, and deliver on the promise of Industry 4.0.

According to Business Insider Intelligence, the installed base of manufacturing IoT devices is expected to swell 3 times — from 237 million in 2015 to 923 million in 2020. By that year, manufacturers will spend approximately $267 billion on the IoT. 

Manufacturing of these devices require the highest level of inspection for quality during every stage of production.  Over half of these quality checks involve visual confirmation, which helps ensure that all parts are in the correct location, have the right shape or color or texture, and are free from scratches, holes or foreign particles.

Automating these visual quality checks is difficult due to volume and variety of products, as well as the fact that defects can be any size –from a tiny puncture to a cracked windshield on a vehicle.

The new solution helps inspectors accelerate the sometimes tedious and expertise-based visual inspection process to quickly identify and classify defects in the manufacturing process – helping to increase production yield.