Featured Product
This Week in Quality Digest Live
Innovation Features
Jennifer Chu
High-speed experiments help identify lightweight, protective ‘metamaterials’
Michael King
Augmenting and empowering life-science professionals
Rich Nobliski
Helping narrow the manufacturing skills gap with 3D tech
NIST
NIST scientists perfect miniaturized technique
Kristi McDermott
Technology and what the future requires for patients and providers to thrive

More Features

Innovation News
New tool presents precise, holistic picture of devices, materials
Enables better imaging in small spaces
Helping mines transform measurement of blast movement
Handles materials as thick as 0.5 in., including steel
For companies using TLS 1.3 while performing required audits on incoming internet traffic
Accelerates service and drives manufacturing profitability
Process contains leaks, improves thermal performance in buildings
Delivered by SpaceX launch to demonstrate in-space capabilities
Recognized among early adopters as a leading innovation for the life sciences industry

More News

Miron Shtiglitz

Innovation

Boosting Quality Inspection With Big Data

How production managers can increase yield by automating defect detection

Published: Monday, February 5, 2024 - 12:03

The main benefit of deploying artificial intelligence (AI) for quality inspection is a significant improvement in defect detection. However, the data generated and stored by inspection systems have the potential to deliver additional benefits, including major improvements in yield.

Anyone working in the world of quality inspection will be aware of the limits of manual inspection and the potential benefits of greater automation, including systems that use AI and deep learning algorithms. With recent advances in AI, the most sophisticated inspection systems available today can reduce the error rate to below 1%. In comparison, for manual inspectors a host of factors, such as fatigue and cognitive bias, means the error rate is usually closer to 10%.


Quality inspection sensors on the job

However, a significantly reduced error rate isn’t the only area where automation can have a significant effect.

Limits of manual inspection

On high-volume production lines where 100% inspection is required, manual inspectors have neither the time nor capacity to record information about defects. In most cases, a human inspector can do little more than alert a supervisor if there was a higher number of defects on their shift.

If inspectors are required to inspect one or two parts per minute, the most that can be expected is a quick checkbox system. The variety of these data is limited, which undermines their value. Many factories operate along these lines, and in some cases hard copies, rather than digital records, are still the norm.
 
In some factories, inspectors are required to inspect parts at a rate of 20 per minute. In such cases, there is no time to log anything or store any data pertaining to the type of defect or its frequency. When a defect is detected, the part is simply discarded onto a pile. While this could be reviewed later offline, the information it would yield is limited because all the parts are mixed up.
 
At the opposite end of the spectrum, where 100% inspection isn’t required and sampling is used instead, any data generated are limited by the lower volume. With a much smaller sample size, the data can’t pinpoint where the problems really lie.

The three Vs of big data

The concept of big data has been around since the 1990s, and it has gained increasing traction in recent years with the arrival of smart factories. The latter go hand in hand with the arrival of Industry 4.0, which aims to provide greater traceability and derive additional data from manufacturing systems. When thinking about big data, it’s useful to refer to the three Vs: volume, velocity, and variety.

In terms of volume, the introduction of inspection systems that can replace manual inspectors has enormous implications. These systems automatically store data about defects on a database. The impact of this will be greatest in applications with less than 100% inspection. Once a system is installed, it makes no difference to the machine whether it inspects one part every hour or one part every second. So, the result will be a massive increase in data for applications where sampling was previously the norm.
 
From a velocity perspective, the data generated by these systems are vastly superior to that provided by manual inspection because processing and categorization are generally done in real time. Managers can be automatically updated by email or SMS if, for example, there’s a sudden increase in the volume of defects during a shift. This doesn’t detract from the value of retrospectively reviewing the data. However, the opportunity for real-time alerts, and therefore, instantaneous action, is a significant step forward for production managers.

Perhaps most important is the variety of these data. Where manual inspectors can rarely log much more than whether a part is OK or not, quality inspection systems can record more detailed data pertaining to things such as the type of defect. Systems that use deep learning algorithms will be far superior in the variety and accuracy of data compared to more simple systems that rely on rule-based algorithms. That is one of the benefits of augmented AI.

Unlocking the potential

The greater the variety of data, and the more they can be correlated with data from other machines and their sensors, the greater the possibilities for optimizing production processes. For example, maintenance schedules could be optimized using data that showed the correlations between defect frequency and length of intervals between maintenance activity. Correlations between a category of defect and a specific machine or production line could help guide root cause analysis to find where defects were being introduced.
 
Once gathered, data are automatically stored in a database where they await analysis. At this stage, the correct query is key to unlocking the value contained in the data. Standard available analytical tools allow users to create their own dashboard for this purpose. These data can be integrated with other systems, like a manufacturing execution system, to further increase potential value.
 
QualiSense develops software that will automate the process of model building when using AI for visual inspection. Working with leading manufacturers like Johnson Electric has provided access to vast quantities of proprietary data for model training. The immediate aim is to build a system that identifies defects. The data generated by the AI system in defect detection are automatically stored on a database and can be accessed using standard analytical tools. The longer-term goal, however, is to supplement this with developing proprietary analytical tools that will not only will spot defects when they arise but also help to prevent them in the first place during the design phase.

QualiSense strives to deliver a fast, scalable, and universally accessible augmented AI platform for production quality assurance. Discover more at qualisense.ai.

Discuss

About The Author

Miron Shtiglitz’s picture

Miron Shtiglitz

QualiSense vice president of product and delivery Miron Shtiglitz brings more than a decade of experience in image inspection and a wide array of expertise in Industry 4.0 applications. In 2012, he founded ScanDirect, a company specializing in visual inspection and 3D measurement, primarily operating in China. Later in 2017, he joined Kitov, a smart AI-based visual inspection company with an integrated robot, where he led the application team. Throughout his career, he has led product integration in leading companies, including Flex, JABIL, Mitutoyo, SolarEdge, and more. He holds a bachelor’s degree in computer science from Tel Aviv University. In addition to professional pursuits, he has a passion for rugby and was a member of the Asa Tel Aviv rugby club, representing the Israeli national team.