The costs of poor quality are high
Quality assurance matters to manufacturers. The reputation and bottom line of a company can be adversely affected if defective products are released. If a defect is not detected, and the flawed product is not removed early in the production process, the damage can be costly – and the higher the unit value, the higher those costs will be. Indeed, poor quality potentially contributes to cost in a variety of ways:
- Re-work costs
- Production inefficiencies
- Wasted materials
- Expensive and embarrassing recalls
And worst of all, dissatisfied customers can demand returns.
The problem with traditional machine vision systems
To mitigate these costs, many manufacturers install cameras to monitor their products as they move along their production lines.
However, the data obtained may not always be useful – or more appropriately said, the data is useful, but existing machine vision systems may not be able to accurately assess it at full production speeds. That’s because too many variables make product defect analysis and prediction difficult. Furthermore, manufacturers need to perform their root cause analyses across a manufacturing process that has complex variables in order to determine which combinations of variables create high-quality products versus those that create inferior products. But to achieve this precision, the manufacturer needs to aggregate data across multiple systems to return a comprehensive view.
Legacy vision systems typically lack the accuracy, speed, and analytic capabilities required to fulfill manufacturers’ QA wish lists – and again, that’s because manufacturing processes can be incredibly complex, and older vision systems are often unable to consistently and accurately identify small flaws that may have a large impact on customer satisfaction. To further aggravate the situation, false positives (i.e., falsely detecting defects that aren’t actually present) can bog down production schedules.
On a larger level, the inability to aggregate data from multiple production lines or factories to determine the cause of variations in quality across multiple sites also prevents a holistic view of operational efficiency.
From the top down, then, many manufacturers find the current state of machine vision driven QA to fall far short of its potential for reducing the costs of quality.
Integrating legacy systems and AI on Azure
To mitigate these and other problems, our Spyglass Visual Inspection solution uses Deep Learning AI to achieve visibility over the entire line, which catches defects more quickly and more accurately than existing machine vision systems. Furthermore, because of its alerting and root-cause analysis capabilities, Spyglass Visual Inspection also helps to prevent defects before they ever arise.
Spyglass Visual Inspection is an easily implemented, rapid time-to-value QA solution that can reduce costs associated with product defects and increase customer satisfaction.
It works with images from any vision system, so companies who already have systems in place can leverage them for additional return-on-investment (ROI). By using cameras and other devices already in use on the production floor, the solution takes a lean approach to implementing new and emerging technologies like IoT, Deep Learning AI, and computer vision. This ensures that manufacturers control costs and achieve value at every stage of production and are truly able to reduce their cost of quality.
This figure outlines the architecture of the solution. Data from existing systems is placed at the front. Edge computing provides on-premises processing and real-time, AI-driven decision-making. The data then moves to Azure, where it is further processed. AI is again applied in a variety of ways that iteratively improve the system, and the results can be viewed using Power BI for even further insights into the system.
Benefits of Spyglass Visual Inspection
Spyglass Visual Inspection harnesses the power of Deep Learning AI, IoT, machine vision, and Azure. The result is that manufacturers minimize defects and reduce costs through advanced analytics. For the manufacturer, the benefits that matter are:
- Rapid ROI: Easy implementation and ramp-up enables immediate process improvements and a rapid return on your investment.
- Greater visibility: Predictive analytics and root cause analysis drive quality improvements across multiple lines or sites.
- Leverages existing vision systems: Extracts more value from existing industrial cameras and devices by augmenting them with AI-driven real-time insights.
- Fully transactable on the Azure Commercial Marketplace: No lengthy delays with procurement departments – the transaction can take place entirely on Microsoft paper, fast-tracking the above benefits for manufacturers.
All of these benefits combine, of course, into one overarching, easily-understood benefit: Spyglass Visual Inspection reduces a manufacturer’s cost of quality.
Azure services
Spyglass Visual Inspection is powered by Microsoft Azure. It leverages the following Azure services:
- Azure IoT Edge ingests images from industrial cameras on the production line and runs cloud AI algorithms locally.
- Azure IoT Hub receives images, meta data from images, and results from the defect detection analysis on the Edge.
- Azure Stream Analytics enables users to create dashboards that offer deep insights into the types and causes of defects that are occurring across a massive number of variables.
- Azure Data Lake Storage/Blob Storage stores the data. Because heterogeneous data from multiple streams can be stored, additional data types can be added to image-based analysis.
- Azure SQL Database is used to store the business rules that define what a good or bad product is and what alerts should be generated in the analytics.
- Azure Functions/Service Bus generates rules that trigger alerts so you can capture the most meaningful data for business users.
- Power BI provides interactive dashboards that make data easy to access and understand, so users can make analytics-driven decisions.
- Power Apps creates additional applications for manufacturers to act on the data and insights they have received.
Recommended next steps
If you want to learn more about Spyglass Visual Inspection -- how it works, and the results that manufacturers are achieving – be sure and visit our Deep Learning / Machine Vision resources page for eBooks, infographics, video, and more. You can also find Spyglass Visual Inspection on Microsoft's Azure Marketplace and AppSource.
Ready to take the next step? Please feel free to contact us and ask for a risk-free fit assessment to see if Spyglass Visual Inspection is right for your facilities and products.
This article was originally published at https://azure.microsoft.com/en-in/blog/maximize-existing-vision-systems-in-quality-assurance-with-cognitive-ai/ by Diego Tamburini, Principal Manufacturing Industry Lead, Azure Industry Experiences Team, and is updated and republished here with his kind permission.