Industry Insights

From Visual Inspection to the Cognitive Future in Electronics Industry – IBM EGLF 2017

By looking back at 2015, no one could possibly deny that the Fourth Industrial Revolution (Industry 4.0) was the most talked-about topic for transformation in the Electronics industry. Tiny Smart sensors and actuators coupling with newly available IT technologies, such as Cloud, Analytics, Mobile, Social Media, and Security gave birth of Internet of Things (IoT). As IoT populated, data became unprecedentedly tremendous in both volume and diversity. The analytic approaches taken to analyze data became increasingly important which most corporations realized good data analytic results can unfold many unseen possibilities that would lead to cost/waste reduction, transformation, and even new opportunity creation. Therefore, two mainstream initiatives were taken:
a) Shifting the traditionally preventive operations of manufacturing, delivery, and maintenance of goods and services to the actively predictive nature to reduce errors, and increase quality and uptime through IoT implementation and data automation done by advanced analytics.
b) Adapting robotics, factory automation, and optimization logic to push the speed, efficiency, and throughput to the extreme which resulted in peak product volume and variety of products with far less manufacturing cost and resource consumption (or waste).
In 2016, when most people started to talk about Artificial Intelligence (AI), Cognitive computing gained its quick public attention and popularity which many have even considered it as the core technology for the next generation computing paradigm in Electronics industry’s operation, manufacturing, service, and many other areas. Through a fusion of man and machine, Cognitive computing technology has been used to power a wide range of applications, and adapted by different industries to replace most human-related tasks in a humanity way both inside and outside the production FABs.
The most crucial part of Cognitive computing is its unique cognitive nature – the capability of problem solving done not by programming but through machine learning including understanding, questioning, learning, and action in the form of natural language interaction, visualization, or even acoustic sensing over structured, unstructured, and semi-structured data processing.
IBM has long been offering Industry 4.0, IoT, Cognitive computing, and a wide variety of Analytics solutions and services to clients in the Electronics industry for operation, manufacturing and maintenance problem solving, optimization, and efficiency improvement ( ). On top of IBM’s well-known Watson IoT Cognitive applications that have already been applied in many fields and industries, Visual Inspection for Quality (VIQ) is a recent IBM Cognitive solution that can be installed in the production FABs for product surface inspection to improve production quality. It delivers highly accurate image recognition and classification results by judging product surface defects in a blink through machine learning and cognition. VIQ has been used in many manufacturing FABs for product defect trapping/classification and It’s also been proven that, with feeding sufficient product defect samples to VIQ’s own (machine) learning mechanism, VIQ is able to deliver up to stunning 95%+ of the (product) image classification accuracy rate. With this result, manual inspection resource reduction and quality uplift in the production lines can easily be expected.
VIQ is merely one Cognitive computing example for production line quality improvement – it eliminates ambiguity, error, and fatigue (either human physical or mental fatigue might cause errors and inaccuracy) to achieve high accuracy result which cannot possibly be accomplished by using the traditional programming techniques or human operations (Figure-1 Using Cognitive Computing to Combat the Challenges).

Figure-1 Using Cognitive Computing to Combat the Challenges

With its capabilities, differentiation, and cognitive nature (as shown in Figure-2 Cognitive Computing vs. Analytics), more and more clients in the industry are journeying to Cognitive business transformation according to a recent IBM Institute for Business Value (IBV) Report ( ).

Figure-2 Cognitive Computing vs. Analytics

As Cognitive transformation starts picking up its speed, how do you prepare yourself and get your innovative ideas realized by applying the right Cognitive computing technology in your manufacturing, operations and even in the future? IBM will launch the annual Electronics Global Leadership Forum (EGLF) in ShenZheng, China on September 13, 2017 ( ), and the answers will be revealed there. Come and join us!

Subject Matter Expert, IBM Global Electronics Center of Competence

More Industry Insights stories

Consortium-supported Blockchain Applications: Anti-Counterfeiting

In an earlier post[1], I described how some excellent use cases for blockchain technology may be held back by either lack of sufficient information on the full cost of process problems outside a company, or by a general preference at companies to not “go it alone” in building a new blockchain solution. The consortium approach […]

Continue reading

Blockchain Solutions: Sometimes it takes a village (i.e. a consortium)

I’m often the person who presents the basics of blockchain technology to people at electronics companies, which brings a small but enjoyable reward with it: I get to see the light come on in executives’ eyes when they realize that blockchain can solve a real-life problem for them. Our discussions almost always get more animated […]

Continue reading

Can Blockchain and Cognitive Analytics yield higher demand forecasting accuracy?

Written by: Jaime Marijuán Castro In the electronics industry nowadays, the average gross value of inventory (all types) as a percentage of revenue is 9,58 % (*), a pretty high ratio and proves that the cost of inventory is a matter of concern within the industry. High levels of inventory can be tackled in multiple ways, […]

Continue reading