Visual Quality Control: “Yes – There’s Now Even an App for That!”
Perform a visual inspection using commercial, off-the-shelf devices such as iPads and iPhones.
Operations teams are looking for easy to deploy computer vision solutions that can scale with their needs. AI technologies have been proven to evolve their ability to accurately identify issues and take action. By easily adding intelligent ‘eyes’ to manufacturing operations, IBM Maximo Visual Inspection enables reliability and quality teams to use commodity devices to quickly identify defects in production outputs as well as remotely monitor assets for potential disruptions. Having a solution that learns about operations and equipment creates a big advantage for teams pressured to produce increasingly higher-quality outputs.
IBM Maximo Visual Inspection makes computer vision with deep learning more accessible to manufacturing operations. IBM Maximo Visual Inspection includes an intuitive toolset that empowers subject matter experts to label, train and deploy deep learning vision models, without coding or deep learning expertise. It includes the most popular deep learning frameworks and their dependencies, and it is built for easy and rapid deployment and increased team productivity. By combining IBM Maximo Visual Inspection software with off the shelf mobile and edge devices, enterprises can rapidly deploy a fully optimized and supported platform with blazing performance.
IBM Maximo Visual Inspection simplifies the process of gathering and labeling data, training new AI models, and deploying those models at the edge. IBM Maximo Visual Inspection Mobile is an iOS app that works seamlessly with IBM Maximo Visual Inspection, empowering operations to leverage the high-resolution integrated imaging capabilities inherent in iOS products. Configurable business rules can be applied to the results to determine whether subsequent action or alerting is required. Supervisors use an integrated reporting dashboard in the app to gain further insight.
iPhone 12 mounted on industrial robot performing visual inspection
Improve uptime and reduce defects: Use deep learning to analyze processes and outputs to continually improve error and defect detection and execute root-cause analysis.
Get flexibility to train and deploy anywhere: Inspect and monitor anywhere — from the factory to the field. Train models and deploy them on premises, in the cloud or on edge devices.
IBM Maximo Visual Inspection makes computer vision with deep learning more accessible to manufacturing operations
Enable quick action and issue resolution: AI can spot issues within milliseconds and will quickly alert the right resource to inspect, diagnose and rectify any issue, anywhere.
Empower any subject matter expert: The streamlined user interface allows domain experts to easily bring data and train models. Users with limited deep learning skills can now build models for AI solutions.
Adopt innovation easily: Put AI innovation into the hands of reliability and quality professionals.
Increase adaptability with custom model support: Import custom models so that data scientists no longer need to train, tune or deploy them.
In a recent interview with John Ward, IBM Solution Leader for Global Automotive and Aerospace & Defense Industries, he explains how companies can improve product quality and reduce costs with IBM Maximo Visual Inspection.
What is IBM Maximo Visual Inspection?
IBM Maximo Visual Inspection detects and identifies objects in images and videos to stop defects at the point of installation.
For context, what challenges do manufacturers face without IBM Maximo Visual Inspection?
Manufacturers rely on people for inspecting, watching product 24 hours a day seven days a week. Often, they don’t notice a mistake until the end of the line. Then they have to rebuild the product, increasing rework costs and warranty failure costs. They end up carrying a lot of work in process inventory and sometimes they run out of space. A major automotive company told us if they don’t detect an error in station, and they have to take the car apart to fix it, the car just isn’t as good as another one coming off the same line.
What pain points does IBM Maximo Visual Inspection address right now?
With IBM Maximo Visual Inspection, you can detect and correct a problem in station. Fixing products in the factory is a huge advantage. By building the product right the first time, manufacturers can reduce costs, deliver on schedule, and improve customer satisfaction. For example, automotive companies can have millions or even billions set aside for warranties. If they can reduce these costs by catching problems before they go out, this can free up cash for areas like new product design or new equipment.
The solution can also be used as a training aid. Operators can get instant feedback when they forget a part versus finding that out ten stations down the line. This allows them to build more products faster and with higher quality. With machine learning, knowledge can be shared across multiple shifts and multiple teams so that every person can work smarter than the day before and help operators be successful.
How can IBM Maximo Visual Inspection help an organization address the new realities of operating in a pandemic?
To adapt to the new reality, companies are having to mix and match people. They lose skills when they have to move people around because of contact tracing or as people become ill. Visual inspection can help prevent inexperienced people from making a mistake. The pandemic has also caused a lot of issues with start-ups and shut-downs, which makes it difficult for employees to get into their rhythm. With IBM Maximo Visual Inspection, they can ensure a process is executed correctly by anyone.
What are some common use cases?
One of our most popular use cases is around connectors and electronic components. IBM uses the solution for IBM Power® Systems and IBM z®. Sometimes the plugs don’t get pushed in all the way, and it’s hard to spot because they’re underneath other components. IBM Maximo Visual Inspection can alert you to these problems. It can also make sure the right part is installed and installed correctly.
For example, in the automotive industry there is a lot of customization — think door handles or interiors. It gets confusing when you’re building 300 cars in a shift. IBM Maximo Visual Inspection can ensure the right part is installed for the build. Another important use case is around damage — especially for just-in-time parts. When bad parts go out to the line, it can stop production. We can make sure that the arriving parts are up to specification before they go out.
How can management leverage this technology?
We talked a lot about inspection at a station, but the technology can also help line coordinators and quality people, giving them a dashboard in their pocket, identifying who needs additional training, for instance.
For an even broader picture, we have a dashboard that can give a global view across multiple plants. Our enterprise dashboard, Inspector Supervisor, can show you how a given plant is performing. As a general manager, you can see the number of inspections, number of defects, and the percentage of defects per product. As a department manager, you can also drill down into the performance of your stations. You can even click on an image and retrain that image right through the dashboard. It’s all about rapid response — fixing problems on the floor — how quickly can the platform become smarter so your business is smarter.
In the longer term, how does IBM Maximo Visual Inspection help an organization become more resilient?
IBM Maximo Visual Inspection helps you capture and retain knowledge so regardless of whether it is Sally, Joe or John, you can have a consistent process.
What’s next for IBM Maximo Visual Inspection?
The next phase will be augmented reality. We’re working on a guided workflow that can step you through a whole inspection process.This is especially important for large products where you need to get in, and under, and around for an inspection. With a more mobile process, you can inspect equipment and assets in the field.
For more information: www.ibm.com
