How CloudNC transformed its factory operations
When you need a part, you go to the hardware store. But when industries that build anything from smartphones to spaceships need highly technical, custom parts, they go to CloudNC to manufacture to their specifications.
The London-based company, named by the World Economic Forum as one of the 100 most promising technology pioneers of 2021, is at the forefront of a manufacturing revolution that uses high frequency time-series data to optimize the manufacturing of precision parts. Its mission is to revolutionize manufacturing by making it 10x more efficient, sustainable and faster.
This is not your father’s dusty old factory setup: CloudNC’s ambition to deliver autonomous manufacturing to the world relies on an optimized workflow that can take in customer specifications for a metal part, autonomously calculate how to machine it, and then optimally schedule its fabrication and ship it as quickly as possible.
This required that CloudNC transition from an old-factory model of batch-based utilization analytics to high frequency time-series data and use machine learning to unlock its value.
“We’re trying to remove as many hours as possible between customer design and delivery,” says Chris Angell, Lead Systems Engineer for CloudNC. Inside the factory, their goal is to maximize the number of jobs a CNC machine can produce, while minimizing the hands-on process and time wasted when a machine is idle or breaks down.
This goal requires real-time monitoring and optimization — all driven by time-series data.
- Continually update factory schedules based on current machine performance
- Predictive maintenance to prevent breakdowns
- Real-time reaction to early warning signs
- Optimizing how parts are created through machine learning
Improving efficiency by maximizing production capacity
One way to improve the manufacturing process is fabrication scheduling. This determines which jobs should be completed on which machines at what time. If a worker estimates that it takes an hour to create a part and it takes only 30 minutes, then a very expensive fabrication machine sits idle until it is given another task. On the other hand, if the worker doesn’t allocate enough fabrication time, then orders back up and deadlines could be missed.
That’s where Quix comes in. By constantly monitoring the tools, their fabrication capacity, and the count of parts that have been delivered so far, CloudNC can make better use of its machines to run at peak capacity, and therefore offer more reliable scheduling with lower overheads.
“Factory software can give you high-level stats, but the data is typically delayed and missing vital information for us” Angell said. CloudNC wanted to control its data, but its existing batch processing software prevented CloudNC from owning or easily accessing detailed data.
“We’re using Quix to get a lot more data — and faster — so we have a clear picture of what’s happening.”
This data-driven approach to real-time performance monitoring generates a kind of “digital twin” for the physical machine, tracking everything about the machine’s operation. It’s a bit like athletic performance monitoring when all sorts of vital statistics are taken in for a complete view of what’s happening in the body.
Angell says this deeper level of monitoring improves CloudNC’s operational performance through greater utilization of tools. And the data it collects is not only used for monitoring but also to dynamically adjust its scheduler via machine learning.
Predicting and fixing breakdowns before they happen
Everything needs maintenance. But when the parts made and materials used keep changing, the stress on the specialized machines varies greatly, making it nearly impossible to predict when they need servicing.
CloudNC uses Quix to understand wear and tear. “You can’t easily measure how sharp a tool-tip is over time, and a human visual inspection isn’t reliable,” Angell explained. “Historically, we wait for them to break. But by gathering data, we can track the use of each tool to predict the optimal time to change it,” Angell explained.
That includes monitoring things like the forces applied, material density and other conditions to generate a physics-based predictive model for wear and tear. As a result, CloudNC can plan for a reasonable lifespan for a drill bit and replace it just before it’s worn out, rather than waiting until it breaks — and suffering repair time delays.
Reacting to warning signs in real time: vibrations
A strong indicator of something going wrong in a CNC machine is vibration. It can suggest the machine is about to break down, or perhaps a defective piece of metal is being machined. In any case, it’s time to press pause and take corrective action.
“It’s important to get information from the machines on the factory floor to the agent with minimal latency, which is why we took the streaming data path,” Angell said.
“It doesn’t help us to batch process information about vibrations from yesterday or even a few minutes ago — we need to know and take action to stop the machine now. This immediate alerting helps us run more efficiently with far less downtime.”
Quix enables CloudNC to handle very high frequency time-series vibration data in order to perform this real-time monitoring and alerting, with the option to persist (save) data as needed.
Automated validation through machine learning
When a customer asks CloudNC to make a part, they provide the 3D model and then CloudNC’s team uses an ML model to calculate the optimal cutting paths to produce this part. Quix enables CloudNC to gather data on the manufacturing process and fine-tune the model’s instructions and parameters.
“At the moment, we don’t use this information at all,” Angell said.
“But now Quix has given us the environment to finally manage that information — to look at it, store it, or act on it immediately.”
Angell added that their ultimate goal is to use autonomous technology to optimize the machine learning model by automatically retraining it with more current data.
The Quix data environment enables time-series analysis in real time as well as in batch. For any company, one of the unfortunate effects of building up a vast database is that the more information you put in, the more difficult it is to extract insights. Because Quix efficiently stores time-series data, Angell said, CloudNC gains a high-performance environment for querying its dataset. This helps it get more value from the data it has already invested in gathering and storing.
How it works: CloudNC’s time-series streaming data architecture
It starts with a Linux box on the factory floor, which uses the Quix Streams client library to ingest high frequency time-series data from each machine to the cloud in very efficient format.
Real-time value is generated from the data using stream processing with results stored and consumed immediately by downstream systems. Data is kept in-memory throughout the entire pipeline, ensuring that the solution is efficient and low latency.
All raw and processed time-series data is persisted (stored) in Quix’s data catalogue where it creates long-term value from batch analytics, which is executed at regular intervals against historic data in the platform, as well as for developing, training and testing machine learning models.
The entire solution is built with code developed by CloudNC systems engineers and deployed within the Quix platform.
CloudNC started using Quix on simple parts analytics, such as recording machine cycle times by detecting patterns in the time-series data. This has grown to include Quix at the heart of both streaming and batch data analytics, enabling it to generate value from Quix using the Query API while moving toward higher-value real-time applications.
Lessons learned: Why streaming time-series data is essential
Plenty of research is available about tool-wear and other machine characteristics of interest to CloudNC — the challenge is applying it to the real world. By leveraging the Quix platform, the team at CloudNC has been able to research and assess candidate models on their own time-series data quickly and effectively. No lengthy infrastructure projects were required to build analysis environments and the team was quickly able to build production data pipelines at scale.
“One of the things I’ve observed in manufacturing is that traceability isn’t done well,” Angell said. “Simple things like, ‘When does my tool break?’ and ‘How often do I scrap tools?’ tend to go undocumented.”
It started with solving a simple problem — that people tended to be unreliable about recording when parts were produced — and has expanded to using high frequency time-series data across the organization. The breadth of data available and ease of access are opening up new opportunities for the team. “Now, even our finance team is curious about our data,” Angell said.
CloudNC uses Quix to optimize production efficiency, make better predictions for maintenance, and detect small problems before they cause big trouble. By owning their information and generating insights with very low latency, CloudNC is delivering on its promise to transform manufacturing.
What’s a Rich Text element?
The rich text element allows you to create and format headings, paragraphs, blockquotes, images, and video all in one place instead of having to add and format them individually. Just double-click and easily create content.
Static and dynamic content editing
A rich text element can be used with static or dynamic content. For static content, just drop it into any page and begin editing. For dynamic content, add a rich text field to any collection and then connect a rich text element to that field in the settings panel. Voila!
How to customize formatting for each rich text
Headings, paragraphs, blockquotes, figures, images, and figure captions can all be styled after a class is added to the rich text element using the "When inside of" nested selector system.
Mike Rosam is Co-Founder and CEO at Quix, where he works at the intersection of business and technology to pioneer the world's first streaming data development platform. He was previously Head of Innovation at McLaren Applied, where he led the data analytics product line. Mike has a degree in Mechanical Engineering and an MBA from Imperial College London.