(QualiSense: Tel Aviv, Israel) -- The main benefit of deploying artificial intelligence (AI) for quality inspection is significant improvement in defect detection. However, the data generated and stored by inspection systems can potentially deliver additional benefits, including major improvements in yield. Here, Miron Shtiglitz, director of product management at quality inspection software specialist QualiSense, explores the value of this data in greater depth.
ADVERTISEMENT |
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%. For manual inspectors in comparison, a host of factors, such as fatigue and cognitive bias, mean the error rate is usually closer to 10%. However, a significantly reduced error rate isn’t the only area where automation can be effective.
The limits of manual inspection
On high-volume production lines where 100% inspection is required, manual inspectors don’t have the time or capacity to record information about defects. In most cases, a human inspector can only 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, manual 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 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, introducing inspection systems that can replace manual inspectors has enormous implications. These systems automatically store in a database the data generated about defects. The effect of this will be greatest in applications where there is currently less than 100% inspection. Once a system is installed, it makes no difference from the machine’s point of view 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 is a sudden increase in the volume of defects during a shift. This doesn’t detract from the value of being able to retrospectively review the data. But 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 if OK or not, quality inspection systems can record more detailed data pertaining to things like type of defect. Systems that use deep learning algorithms will be far superior in the variety of data, and the accuracy of those data, when compared to simpler systems that rely on rule-based algorithms. That’s one of the benefits of augmented AI.
Unlocking the potential
The greater the variety of data, and the more these data 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 analytical tools will 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’s primary mission is developing software that will automate the process of model building when using AI for visual inspection. Working with leading manufacturers like Johnson Electric has given QualiSense 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 QualiSense’s AI system in defect detection are automatically stored on a database and can be accessed using standard analytical tools.
The company’s longer-term goal, however, is to supplement this with the development of its own analytical tools that will help not only to spot defects when they arise but also prevent them in the first place during the design phase.
QualiSense is on a mission to deliver a fast, scalable, and universally accessible augmented AI platform for production quality assurance. Discover more at qualisense.ai. For further information, email Zohar Kantor, chief revenue and customer success officer, at zohar.kantor@qualisense.ai.
Add new comment