In mostindustries, maintenance is a waiting game. Things are fixed when they break. But in the 21st century, an age defined by data and automation, that approach no longer makes sense. The solution could be predictive maintenance. This is an approach that uses sensors and software to analyze equipment performance in real time and predict when it might fail.
Edward Khomotso Nkadimeng, a lecturer and researcher in artificial intelligence and data systems in nuclear/particle physics at Stellenbosch University, hasresearchedhow a predictive maintenance model can help keep critical systems running—from research equipment to national infrastructure. He explains why this approach could be a practical tool for resilience across Africa.
What is a predictive maintenance model and why did you build one?
For decades after the global industrialboom, many industries relied on a simple rule: wait for a machine to break, then repair it. That made sense when machines were simpler and downtime was just part of the routine.
Periodic maintenance is common too, but still inefficient and often based on time, notactual machine condition. That approach costs time, money, and sometimes even safety. Modern systems are moreinterconnectedand expensive to halt.
A predictive maintenance model is a data-driven system that forecasts equipment failure beforeit happens. It predicts when systems are degrading, rather than just reacting. It monitors a variety of systems, from industrial pumps, compressors and turbines to scientific instruments, by collecting real‑time data like vibration (which measures how much a machine physically oscillates), temperature, pressure and voltage.
These measurements come from Internet of Things (IoT) or condition-monitoring sensors. Even machines that aren't ultra-cutting-edge can be instrumented to provide this data. Once collected, the data feeds into machine learning models that learn to recognize patterns associated with slow drift towards failure.
The model monitors a broad range of systems: industrial pumps, compressors, turbines, and high-precision scientific instruments (cyclotrons, vacuum pumps, beamline diagnostics). It is designed for systems where sensor datacan be collected—any instrument that generates measurable signals. It uses live data vibration, the physical oscillation of a machine component, where subtle changes in vibration amplitude or frequency often precede mechanical failures, such asbearing wear or rotor imbalance, as well as temperature, pressure and voltages.
While advanced machines may produce richer data, even legacy machinery can benefit with added sensors. The method is therefore broadlyapplicableto recognize when they're slowly drifting towards failure.
AtNRF-iThemba LABS, a South African national nuclear and accelerator research facility, and Stellenbosch University, I built a system like this out of necessity. Our teams include physicists, engineers and computer scientists who collaborate on high-precision experiments in nuclear and particle physics.
The research instruments are complex, expensive and often one of a kind. When they fail unexpectedly, experiments stop, data is lost, and public funds go to waste. For example, we work with 70 MeVcyclotronsfor isotope production, superconducting magnets,radiofrequency acceleration cavitiesand vacuum systems. These are one-of-a-kind instruments, sensitive to downtime.
So, the goal was to make an affordable, self-learning system that can scale from our research equipment to the industrial infrastructure that keeps African economies running pumps, turbines and power grids. Similar predictive maintenance systems are applied in industrial power plants, water utilities and aviation, reducingunplanned downtime by 20%–40%. Our adaptation for African labs and industrial systems uses low-cost Internet of Things sensors with cloud-based AI.
What did you learn from the model? Why is this useful?
The first thing I learned is that machines whisper before they scream. Long before a breakdown, they show tiny signs like slight vibrations, small voltage drops, or subtle changes in speed.
With enough data on vibration, temperature, pressure, voltage and motor load, for example, these data streams form the input for AI models. These patterns form a kind of language, and artificial intelligence becomes the translator.
By training the model on real operational data like pump vibration over time and other readings, we discovered that failures aren't random: they follow recognizable signatures. Once the system learns these patterns, it can predict what's coming and even suggest what to do next. The real benefit is timing, scheduling maintenance exactly when it is needed and not too early, which wastes parts and labor, and not too late (which risks catastrophic failure).
Instead of over-servicing equipment or waiting for something to fail, maintenance can happen exactly when it's needed. That saves resources, reduces downtime and keeps operations running smoothly. And because the principle is universal, it applies just as well in factories, hospitals and water systems as it does in research labs. For example, detecting a failing motor before a line shutdown in a manufacturing plant, or ventilator sensors predicting pump failure in a hospital, or monitoring municipal pumpsto prevent water shortages.
What are the practical implications of applying the model?
The practical impact is huge. Predictive systems help avoidblackouts, water shortages and unplanned shutdowns—issues that affect daily life and essential services. An example can be seen in South Africa's blackouts: the power utility Eskom's transformers are monitored for predictivefaults. In Cape Town, predictive maintenance of water systemsreduces pump downtime. They also make workplaces safer and budgets more efficient.
For African countries especially, where technical resources are often stretched, predictive maintenance is a form of resilience. It replaces firefighting with foresight. By using affordable IoT sensors (small devices collecting data like temperature), cloud-based AI (online software that analyzes this data in real-time), andself-learning algorithms, maintenance becomes continuous, automated and smart.
It's the quiet side of AI, keeping the lights on, the pumps running and the economy stable. Physics, data and engineering can quietly work together to keep important systems alive and reliable.
As NASA's Mars Perseverance Rover continues to explore the surface of Mars, scientists on Earth have developed a new nanoscale metal carbide that could act as a "superlubricant" to reduce wear and tear on future rovers.
Credit: Pixabay/CC0 Public Domain
Researchers in Missouri University of Science and Technology's chemistry department and Argonne National Laboratory's Center for Nanoscale Materials, working with a class of two-dimensional nanomaterials known as MXenes, have discovered that the materials work well to reducefriction. The materials also should perform better than conventional oil-based lubricants in extreme environments, says Dr. Vadym Mochalin, associate professor of chemistry at Missouri S&T, who is leading the research.
"These superlubric materials are of special interest for advanced anti-wear and lubrication applications in extreme conditions, like those now experienced by the Perseverance rover on Mars," Mochalin says. He and his colleagues describe their discovery in a paper published in the March 2021 edition of the journalMaterials Today Advances("Achieving superlubricity with 2D transition metal carbides (MXenes) and MXene/graphene coatings").
Mochalin says he made the connection between this research and Perseverance's journey to Mars after watching the rover landing.
"When I watched the landing of the rover on Mars, I thought: "What if the lubricant in one of its wheels fails? Then I made the connection with our work on MXenes, because it came to mind that we have just found that MXenes demonstrate superlubricity in an atmosphere devoid of oxygen and humidity, close to what is there on Mars," Mochalin says.
MXenes (pronounced Maxines) are metal carbide materials that possess unusual properties. For example, their ability to conduct electricity makes them candidates for use in energy storage, sensing and optoelectronics. In this latest study of the materials, Mochalin and his team conducted a series of tests to determine how well they act as solid-state lubricants with certain materials.
The researchers conducted ball-on-disk friction tests at the nanometer scale by depositing a titanium carbide MXene onto a silicon substrate (the disk) that was coated with a thin layer of silica, which is the major ingredient of sand. They then tested the MXene's ability to withstand wear by sliding it against a diamond-like carbon-coated steel ball. They conducted these tests in a dry nitrogen environment, which greatly reduces humidity.
Mochalin says the tests found that the MXene interface between the steel ball and silica-coated disk resulted in a friction coefficient in the "superlubric regime" of 0.0067 to 0.0017. Friction coefficient refers to the amount of friction between two objects and determined by a value that is usually between 0 and 1. The lower the value, the less friction.
When the team added graphene to the titanium carbine MXene, the results were even better. Adding graphene "further reduced the friction by 37.3% and wear by the factor of 2" without affecting the MXene's superlubricant properties, the researchers write in their paper.
"These results open up new possibilities for exploring the family of MXenes in various tribological applications," write Mochalin and his colleagues. Tribology is the study of friction, wear and lubrication of interacting surfaces.
Down-to-earth benefits
While such superlubricants may prove useful for machines in extraterrestrial environments—from Mars rovers to asteroid mining equipment—they also may have more down-to-earth benefits. Unlike oil-based lubricants, MXenes would not rely on non-renewable energy sources such as coal or petroleum, Mochalin says.
More information
S. Huang et al. Achieving superlubricity with 2D transition metal carbides (MXenes) and MXene/graphene coatings,Materials Today Advances(2021).DOI: 10.1016/j.mtadv.2021.100133
Black Thursday, was a World War II air battle for ball bearings that took place on 14 October 1943, over Nazi Germany between forces of the United States8th Air Force and German Luftwaffe.
Philip Vaughan was granted a patent in 1794 for a ball bearing that sits between the axle and the wheel on a carriage. His design has the balls running inside deep grooves, and sealed in place with a stopper.
The temporary repairs saved the U.S. government an estimated $52 million, shaved nine months off the schedule, and allowed the ferry flight to proceed on September 22, 2022.
Futuristic, 'alien-like' nuclear fusion rockets developed in total secret could revolutionize space travel — if they actually work
By Harry Baker published
U.K. start-up Pulsar Fusion has unveiled plans to build a fleet of reusable nuclear fusion-powered rockets, known as Sunbirds, that could cut journey times across the solar system in half. But not everyone is convinced.
U.K. company Pulsar Fusion has released plans to create a fleet of futuristic nuclear fusion rockets capable of reducing journey times across the solar system.(Image credit: Pulsar Fusion)
A U.K. start-up has shocked the space exploration community after unveiling plans to use a novelnuclear fusionpropulsion system to power an orbital fleet of reusable "alien-like" rockets, known as Sunbirds, which the company says could revolutionize how we explore thesolar system— and beyond.
The technology behind this ambitious project will begin testing this year and could make it into space by 2027,Richard Dinan, the founder and CEO of Pulsar Fusion, which is making the rockets, told Live Science. However, the company has set no timeline for when the futuristic spacecraft could become a reality. One expert told Live Science it could be at least a decade away, if not more.
Pulsar Fusion, which also makes traditional plasma thrusters and is developing nuclear fission engines, first announced theSunbird projecton March 6 after developing the concept in "complete secrecy" over the last decade, according to a statement emailed to Live Science. The project was then fully revealed to the public on March 11 at the Space-Comm Expo in London's ExCel center.
Scientists at the Department of Energy's Oak Ridge National Laboratory have invented a coating that could dramatically reduce friction in common load-bearing systems with moving parts, from vehicle drive trains to wind and hydroelectric turbines. It reduces the friction of steel rubbing on steel at least a hundredfold. The novel ORNL coating could help grease a U.S. economy that each year loses more than $1 trillion to friction and wear—equivalent to 5% of the gross national product.
"When components are sliding past each other, there's friction and wear," said Jun Qu, leader of ORNL's Surface Engineering and Tribology group. Tribology, from the Greek word for rubbing, is the science and technology of interacting surfaces in relative motion, such as gears and bearings. "If we reduce friction, we can reduce energy consumption. If we reduce wear, we can elongate the lifespan of the system for better durability and reliability."
With ORNL colleagues Chanaka Kumara and Michael Lance, Qu led a study published inMaterials Today Nanoabout a coating composed ofcarbonnanotubes that imparts superlubricity to sliding parts. Superlubricity is the property of showing virtually no resistance to sliding; its hallmark is a coefficient of friction less than 0.01. In comparison, when dry metals slide past each other, the coefficient of friction is around 0.5. With an oil lubricant, the coefficient of friction falls to about 0.1. However, the ORNL coating reduced the coefficient of friction far below the cutoff for superlubricity, to as low as 0.001.
"Our main achievement is we make superlubricity feasible for the most common applications," Qu said. "Before, you'd only see it in either nanoscale or specialty environments."
For the study, Kumara grew carbon nanotubes on steel plates. With a machine called a tribometer, he and Qu made the plates rub against each other to generate carbon-nanotube shavings.
Themultiwalled carbon nanotubescoat the steel, repel corrosive moisture, and function as a lubricant reservoir. When they are first deposited, the vertically aligned carbon nanotubes stand on the surface like blades of grass. When steel parts slide past each other, they essentially "cut the grass." Each blade is hollow but made of multiple layers of rolledgraphene, an atomically thin sheet of carbon arranged in adjacent hexagons like chicken wire. The fracturedcarbon nanotubedebris from the shaving is redeposited onto the contact surface, forming a graphene-rich tribofilm that reduces friction to nearly zero.
Making the carbon nanotubes is a multistep process. "First, we need to activate the steel surface to produce tiny structures, on the size scale of nanometers. Second, we need to provide acarbon sourceto grow the carbon nanotubes," Kumara said. He heated a stainless-steel disk to form metal-oxide particles on the surface. Then he usedchemical vapor depositionto introduce carbon in the form of ethanol so that metal-oxide particles can stitch carbon there, atom by atom in the form of nanotubes.
The new nanotubes do not provide superlubricity until they are damaged. "The carbon nanotubes are destroyed in the rubbing but become a new thing," Qu said. "The key part is those fractured carbon nanotubes are pieces of graphene. Those graphene pieces are smeared and connected to the contact area, becoming what we call tribofilm, a coating formed during the process. Then both contact surfaces are covered by some graphene-rich coating. Now, when they rub each other, it's graphene on graphene."
The presence of even one drop of oil is crucial to achieving superlubricity. "We tried it without oil; it didn't work," Qu said. "The reason is, without oil, friction removes the carbon nanotubes too aggressively. Then the tribofilm cannot form nicely or survive long. It's like an engine without oil. It smokes in a few minutes, whereas one with oil can easily run for years."
The ORNL coating's superior slipperiness has staying power. Superlubricity persisted in tests of more than 500,000 rubbing cycles. Kumara tested the performances for continuous sliding over three hours, then one day and later 12 days. "We still got superlubricity," he said. "It's stable."
Usingelectron microscopy, Kumara examined the mowed fragments to prove that tribological wear had severed the carbon nanotubes. To independently confirm that rubbing had shortened the nanotubes, ORNL co-author Lance used Raman spectroscopy, a technique that measures vibrational energy, which is related to the atomic bonding and crystal structure of a material.
"Tribology is a very old field, but modern science and engineering provided a new scientific approach to advance technology in this area," Qu said. "The fundamental understanding has been shallow until the last maybe 20 years, when tribology got a new life. More recently, scientists and engineers really came together to use the more advanced material characterization technologies—that's an ORNL strength. Tribology is very multidisciplinary. No one is an expert in everything. Therefore, in tribology, the key to success is collaboration."
He added, "Somewhere, you can find a scientist with expertise in carbon nanotubes, a scientist with expertise in tribology, a scientist with expertise in materials characterization. But they are isolated. Here at ORNL, we are together."
ORNL's tribology teams have done award-winning work that has attracted industrial partnerships and licensing. In 2014, an ionic anti-wear additive for fuel-efficient engine lubricants, developed by ORNL, General Motors, Shell Global Solutions and Lubrizol, won an R&D 100 award. ORNL's collaborators were Qu, Huimin Luo, Sheng Dai, Peter Blau, Todd Toops, Brian West and Bruce Bunting.
Similarly, the work described in the current paper was a finalist for an R&D 100 award in 2020. The researchers have applied for a patent of their novel superlubricity coating.
"Next, we hope to partner with industry to write a joint proposal to DOE to test, mature and license the technology," Qu said. "In a decade we'd like to see improved high-performance vehicles and power plants with less energy lost to friction and wear."
PhD candidate Jordan Noronha holding a sample of the new titanium lattice structure 3D printed in cube form. [Credit: RMIT]
By Michael Quin, RMIT University
A 3D-printed "metamaterial" boasting levels of strength for weight not normally seen in nature or manufacturing could change how we make everything from medical implants to aircraft or rocket parts.
RMIT University researchers in Melbourne, Australia, created the new metamaterial -- a term used to describe an artificial material with unique properties not observed in nature -- from common titanium alloy.
However, it's the material's unique lattice structure design, recently revealed in theAdvanced Materialsjournal, that makes it anything but common: Tests show it is 50% stronger than the next strongest alloy of similar density used in aerospace applications. Interestingly, the initial lattice shape was inspired by corals.
In their paper, the researchers list potential applications as: "in demanding thermal protection systems such as those for hypersonic vehicles," "titanium drones used to monitor or fight bushfires or severe industrial fires at close range and with extended flight times," or "as implant materials, as well as lightweight structures to replace magnesium alloy components in defense and aerospace (being lighter, stronger, and more heat and corrosion resistant)."
Improving nature's own design Lattice structures made from hollow struts were originally inspired by nature: strong hollow-stemmed plants like the Victoria water lily or the hardy organ pipe coral (Tubipora musica) showed the way in combining lightness and strength.
However, as RMIT's Distinguished Professor Ma Qian explained, decades of trying to replicate these hollow "cellular structures" in metals has been frustrated by the common issues of manufacturability and load stress concentrating on the inside areas of the hollow struts, leading to premature failures.
"Ideally, the stress in all complex cellular materials should be evenly spread," Qian said. "However, for most topologies, it is common for less than half of the material to mainly bear the compressive load, while the larger volume of material is structurally insignificant."
Metal 3D printing provides unprecedented innovative solutions to these issues.
By pushing 3D printing design to its limits, the RMIT team optimized a new type of lattice structure to distribute the stress more evenly, enhancing its strength or structural efficiency.
"We designed a hollow tubular lattice structure that has a thin band running inside it. These two elements together show strength and lightness never before seen together in nature," said Qian. "By effectively merging two complementary lattice structures to evenly distribute stress, we avoid the weak points where stress normally concentrates."
Compression testing shows (left) stress concentrations in red and yellow on the hollow strut lattice, while (right) the double lattice structure spreads stress more evenly to avoid hot spots. [Credit: RMIT]
Laser-powered strength They 3D printed this design at RMIT's Advanced Manufacturing Precinct using a process called laser powder bed fusion, where layers of metal powder are melted into place using a high-powered laser beam.
Testing showed the printed design -- a titanium (Ti-6Al-4V TP-HSL) lattice cube -- was 50% stronger than cast magnesium alloy WE54, the strongest alloy of similar density used in aerospace applications. The new structure had effectively halved the amount of stress concentrated on the lattice's infamous weak points.
The double lattice design also means any cracks are deflected along the structure, further enhancing the toughness.
Study lead author and RMIT PhD candidate Jordan Noronha said they could make this structure at the scale of several millimeters or several meters in size using different types of printers.
This printability, along with the strength, biocompatibility, corrosion, and heat resistance, make it a promising candidate for many applications from medical devices such as bone implants to aircraft or rocket parts.
"Compared with the strongest available cast magnesium alloy currently used in commercial applications requiring high strength and light weight, our titanium metamaterial with a comparable density was shown to be much stronger or less susceptible to permanent shape change under compressive loading, not to mention more feasible to manufacture," Noronha said.
The team plans to further refine the material for maximum efficiency and explore applications in higher-temperature environments.
While currently resistant to temperatures as high as 350 °C, they believe it could be made to withstand temperatures up to 600 °C using more heat-resistant titanium alloys for applications in aerospace or firefighting drones.
As the technology to make this new material is not yet widely available, its adoption by industry might take some time.
"Traditional manufacturing processes are not practical for the fabrication of these intricate metal metamaterials, and not everyone has a laser powder bed fusion machine in their warehouse," he said. "However, as the technology develops, it will become more accessible and the printing process will become much faster, enabling a larger audience to implement our high-strength multi-topology metamaterials in their components. Importantly, metal 3D printing allows easy net shape fabrication for real applications."
Technical Director of RMIT's Advanced Manufacturing Precinct, Distinguished Professor Milan Brandt, said the team welcomed companies wanting to collaborate on the many potential applications. "Our approach is to identify challenges and create opportunities through collaborative design, knowledge exchange, work-based learning, critical problem solving, and translation of research," he said.
The U.S. Department of Defense has finally, after much speculation and anticipation, given the green light to production of the Northrop Grumman B-21 Raider, the Air Force’s newest stealth bomber. The aircraft is named after the daring air raid of Japan's islands, including Tokyo, during World War II. These were led by Lt. Col. James “Jimmy” Doolittle, a mission that the Air Force said “changed the course of World War II.”
Defense undersecretary William LaPlante told Defense One that Northrop Grumman will begin production in low numbers following the B-21's testing and then providing a solid path forward for its manufacture.
The U.S. Air Force wants at least 100 B-21 aircraft, but Northrop Grumman pointed out that a few defense analysts have said they believe the order number should be closer to 200.
The first B-21s could be delivered as soon as 2025-2026. The B-21 Raider has been in the development and planning stage for more than a decade now. Once it becomes operational, the B-21 will serve as a nuclear deterrent and help carry out national security objectives.
The Air Force described the B-21 Raider as a component of a larger family of long-range strike systems including intelligence, reconnaissance, attack, and communications. The aircraft is designed to carry nuclear weapons and will be able to support both manned and unmanned operations.
No issues with product or shipping. Works as designed.
Hi Mr. Cole,
Thank you for your positive feedback! We are glad to hear that our 6204-2RS C3 ball bearing is working well for you. Our team strives to provide high-quality products and smooth shipping experiences for our customers. Thank you for choosing SKF Brand. Have a great day!
My ankles would have been much happier if I had found these sooner! The DC-12 work exactly as advertised. Buy them ASAP.
Hi Bobby,Thank you for your kind words! We are thrilled to hear that our DC-12™ has been a game changer for you and your ankles. We are always happy to help and appreciate your support. Happy Jeeping!Steve
Great product. When the JL’s came out with the doors that would stay open I nearly traded in my JK. This is a much cheaper option.
Hi Mikeal! We are thrilled to hear that you are enjoying our DC-12™ Flex Arm Assembly! We are happy to provide a more affordable option for keeping your doors open on your JK. Thank you for choosing our product and happy Jeeping! Steve
I wanted a better quality bearing and wasn't able to find SKF on other websites. My customers will be able to use his machine for another 15 years.
Hi Pete,
Thank you for your positive feedback on our 6005-2RS SKF Sealed Radial Ball Bearing. We are glad to hear that it met your expectations for quality. At Intech, we strive to provide our customers with top-notch products that will last for years to come. We appreciate your support and hope to assist you with any future bearing needs.
Best,
Steve
I've been looking for a floppy door solution for years and I finally found it! These hold the door in the exact position you want and it holds great and the doors are still very easy to close. I love them and I'm very happy with my purchase.
Hi Jerad!
Thank you for taking the time to leave us a review. We're so glad to hear that our DC-12™ was able to solve your floppy door problem after years of searching. Your complaint about Jeep doors was my inspiration for inventing this product. We also like making produts here in the USA and take pride in providing top-quality products that make our customers' lives easier. We appreciate your business and hope to serve you again in the future.
