Automation and AI Bringing Fleet Maintenance Into the 21st Century
How Alliora Achieved Smart Scaling With Robotic Palletizing
A common question people have when getting started with automation is which is the best task to automate first. For Alliora, palletizing seemed like an obvious choice. “There are 2 reasons we chose to automate palletizing. Firstly, it is a very physical job. The boxes are between 5 kg and 12 kg. It is very repetitive, it is very heavy, and it is very physical. People don’t like doing the palletizing task. Secondly, sometimes we have a high level of orders. In this case, we can’t have any people on the line.”
RoboDK releases intuitive palletizing plugin for any robot brand
Robot software company RoboDK has released a new palletizing plugin for intuitive programming of palletizing applications, compatible with almost any robot brand. It accelerates this normally tedious programming task and improves deployment efficiency.
The conventional options for robot programming make deploying palletizing applications almost dull as palletizing itself. For example, a pallet holding 800 boxes would require a robot program with at least 1600 points in it. Creating this program would be repetitive and time-consuming. Users would need to manually teach each box position to the robot or hard code a script to do it for them.
The New Space Race: How 3-D Printing Is Driving Current And Future Space Exploration
The ability to print parts is also helping reduce the complexity of rockets. Dubbed by some as “the most complex flying machine ever built,” the Space Shuttle used a staggering 2.5 million parts. Using 3-D printing, manufacturers can consolidate many of the complex components into multifunction assemblies, which can make them easier, faster and less expensive to produce, as well as more reliable to operate.
As the cost and complexity of manufacturing rockets and rocket engines have decreased in recent years, a number of private space exploration companies have emerged. Among the newest players in the field, our customer Privateer Space, co-founded by Steve Wozniak, is using 3-D printing to create small cube satellites that will monitor and remove debris from orbit.
Tiny machine learning design alleviates a bottleneck in memory usage on internet-of-things devices
Researchers are working to reduce the size and complexity of the devices that these algorithms can run on, all the way down to a microcontroller unit (MCU) that’s found in billions of internet-of-things (IoT) devices. An MCU is memory-limited minicomputer housed in compact integrated circuit that lacks an operating system and runs simple commands. These relatively cheap edge devices require low power, computing, and bandwidth, and offer many opportunities to inject AI technology to expand their utility, increase privacy, and democratize their use — a field called TinyML.
Koch Ag & Energy High Value Digitalization Deployments Leverages AWS
This application uses existing plant sensors, Monitron sensors, Amazon Lookout and SeeQ software to implement predictive maintenance on more complex equipment. The goal accomplished was successfully implementing predictive maintenance requires data from thousands of sensors to gain a clear understanding of unique operating conditions and applying machine learning models to achieve highly accurate predictions. In the past modeling equipment behavior and diagnosis issues requiring significant investment in time money inhabiting scaling this capability across all assets.
The Factory OS
Hardware manufacturing is the bedrock of our society. Everything from automotive and air transport, energy, consumer goods, medicine, and much more is manufacturing. Despite the focus being taken away for the past few decades, these things did not become less important. We interact with them every day. And now, the great challenges of the 2020s are in addressing climate change, energy, new forms of sustainable transportation, and promoting the use of robotics to create safer work and lifestyles by reducing stressful and rote labor. To take on these new challenges, companies new and old need new methods of building. These methods are rooted in more flexibility, more automation, and a freer flow of data.
In isolation, all of these things sound good; however, we have found that existing systems claim flexibility, traceability, and collaboration, but they do very little to actually deliver on those claims. We believe that is because these systems were built in a fundamentally different time — a time when factories were not connected and people were not interacting with software on a daily (or minutely) basis.
A Factory OS fixes this. Below, we discuss the history of how existing manufacturing software solutions came to be and what has changed to necessitate a more connected Factory OS workflow. Then, we look at how a flexible, modular, and connected approach of a Factory OS enables the next generation of manufacturing. Finally, we will discuss how a Factory Operating System enables the evolution of society in the 21st century and how making the companies and people building hardware faster, more flexible, and more connected enables entirely types of product categories and workflows.