Tag Archives: predictive maintenance

Dingo improves Trakka predictive maintenance capabilities with AI

Communications in mining, Equipment maintenance, IoT, Mining equipment, Mining maintenance, Mining services, Mining software, , , , , , , , ,

Dingo says its new Trakka Predictive Analytics solution uses artificial intelligence and machine learning to predict impending equipment failures with confidence, allowing customers to proactively perform corrective maintenance actions to minimise downtime and optimise asset life.

The release comes around five months since the company laid the groundwork for the new solution with an announcement that it would introduce practical machine learning models built using real customer data and targeted at specific industry problems from January.

The new Trakka solution includes a series of sophisticated predictive analytics models to provide anomaly detection and failure prediction for asset intensive industries, the company said. These models are built by uniting failure data from actual equipment, “Dingo’s industry expertise and data science to address common component-specific failure modes, such as final drive gear teeth wear”.

Powered by a proprietary machine-learning library, the Trakka Predictive Analytics solution can, Dingo says, predict the time until asset/component failure with a high degree of accuracy. The company said its customers will reap the benefits of these remaining useful life (RUL) models (pictured) as they:

  • Reduce unexpected failures and downtime;
  • Reduce repair cost as scheduling is optimised;
  • Reduce loss of wasted potential in capital;
  • Reduce unnecessary maintenance activities;
  • Reduce personnel and process risk by creating a safer and more controlled environment;
  • Improve component life by acting earlier;
  • Improve confidence in planning component replacements;
  • Improve equipment availability and reliability;
  • Improve budgeting and the bottom line, and;
  • Improve business related processes such as procurement, logistics and management.

Dingo said: “Before any predictions can be made, Dingo’s domain experts and data science team work with a customer’s historical failure and condition monitoring data to deploy or adapt existing models or create new machine learning models to correctly identify failures within the customer’s fleet.

“This process typically involves data collecting, cleansing and validation to ensure model outputs are as accurate as possible. The transition to online predictive analytics is complete once the data ingestion pipeline is ready and the models are fully trained and tested.”

The predictive models are designed with scalability in mind, Dingo said, meaning they can be easily re-trained to work with a broad range of asset and failure mode problems experienced by real mining operations, making them highly reusable.

“The models are continuously optimised through ongoing validation and the input of new data and equipment performance information,” Dingo said.

And, the platform connects a broad range of systems and software to provide data surrounding asset health, including enterprise resource planning & enterprise asset management systems, computerised maintenance management systems, fleet management systems and all forms of condition monitoring data, including oil analysis, visual inspections, sensor data, vibration and thermography.

Schenck Process filling screen performance data gaps with sensors

Comminution of minerals, Equipment maintenance, IoT, Mineral processing, Mining maintenance, Mining services, Mining software, , , , , ,

Schenck Process says performance data provided by extra sensors fitted to a prototype vibrating screen is substantially improving the understanding of operation of the equipment.

The data is also giving indicators about the overall performance of the processing cycle, according to the company.

Designed and developed in Australia by Schenck Process, the prototype screen is undergoing site trials, but the company already believes the new screen has the potential to change the way vibrating screens are developed and operated.

The standard condition monitoring system comprises two sensor nodes including six degrees of freedom MEMS accelerometers, a high-resolution accelerometer and a temperature probe. On the prototype screen, four additional sensors have been fitted, one on each corner.

Schenck Process Senior R&D Engineer, Doug Teyhan, said: “The measurement regime for the additional sensors includes spring amplitude and mean compression, allowing the estimation of tonnage and load bias (to determine if the feed is presented square to the screen or favouring a side) and the determination of spring operating characteristics and cumulative fatigue damage.

“We are also looking into the development of a predictive failure program to improve overall productivity and efficiency and significantly reduce the possibility of unplanned downtime.”

Historically, failure prediction has been determined by running components to the point of failure and assessing a mean time to this point based on a known operating history.

“The data generated by the prototype screen is utilised to estimate the operating stress of the screen at the most aggressive fatigue areas and assessing the cumulative damage of those areas based on the measurement of non-ideal operating characteristics,” Schenck Process said.

Using a Cumulative Damage System, which counts machine cycles and trend characteristics that have the potential to adversely affect vital component life expectation, the plan is to make the machine monitoring system a lead measure in predicting the potential for component failure, Schenck Process said.

“The expanded monitoring system will also provide input into machine development of the next generation of vibrating screens by filling in the unknowns in the design process with real-time field data,” the company said.

According to Teyhan, the benefits for the customer – including increased availability and improved screen performance – are substantial and have the potential to initiate improvements in the processing cycle.

“And, from a screen operation point of view, the additional data is bringing to light characteristics not previously known. It is highlighting transient feed characteristics – not visible using traditional condition monitoring techniques – that impact the loading of the screen and affect machine life expectation,” he said.

“We also believe there are potential industry-wide benefits, through new design parameters and possible changes to machine construction techniques and materials,” he added.

To optimise the greater range and scope of data the screen is generating, the company is collaboratively investigating and assessing other performance variables, it said. The potential is for control of the variability in the feed rate, more consistent performance and improved overall efficiency of the cycle.

Newtrax AI helps out Agnico Eagles’s Goldex mine maintenance team

Communications in mining, Equipment maintenance, IoT, Mine operation news, Mining equipment, Mining maintenance, Mining safety, Mining services, Mining software, Precious metals, , , , , , ,

Newtrax Technologies says it has applied machine-learning algorithms to help Agnico Eagle Mines’ Goldex mine predict mobile equipment maintenance issues up to two weeks in advance.

With the two companies already having an existing relationship at the mine, in Quebec, Canada, Newtrax was approached in the fall to discuss the data Agnico had collected from sensors over the past six years. This amounted to 10 billion data points, according to Newtrax.

“This data was exactly what was needed to apply machine-learning algorithms in order to predict mobile equipment maintenance issues at least two weeks before they were supposed to happen,” Newtrax said.

Daniel Pinard, Team Lead, Special Projects with Agnico Eagle, said this predictive Newtrax AI solution allowed the company to intervene before incurring serious problems that could potentially break vehicle engines.

“Through the use of machine-learning algorithms with Newtrax, we were recently able to analyse an engine that had a potential problem and we saved it from failing. This helped Goldex mine avoid serious damage on that engine which saved them C$85,000 ($63,610).”

The Newtrax AI solution is unique in three ways, according to Michel Dubois, VP QA & Artificial Intelligence at Newtrax, “first, Newtrax has years of unique data that is extremely well suited for machine learning (ML)”.

This creates a source of training data for ML that is unique in the world, with the data growing every time a mining company decides to join in, he said.

“Second, we have a unique AI team who knows how to generate actionable results using existing AI algorithms. And, third, we have a unique approach where our AI specialists go underground and focus on quick wins, and they leverage those existing algorithms to solve high-value problems.”

This is the first ever applied case study for ML in the underground hard-rock mining industry with a defined return on investment, according to Newtrax.

Newtrax said it worked with artificial intelligence and ML researchers such as IVADO to apply existing algorithms to the data collected in mine sites.

Anglo readying predictive maintenance solutions following Barro Alto implementation

Automation, Base metals, Equipment maintenance, IoT, Mine operation news, Mineral processing, Mining equipment, Mining maintenance, Mining services, Mining software, , , , , , ,

Anglo American has highlighted its predictive maintenance efforts on equipment at its Barro Alto nickel mine in Brazil in its recently-published annual report.

The company said it is developing predictive models so it can make better informed operational decisions. These models, built by data scientists and often powered by artificial intelligence and machine learning, contain advanced algorithms that leverage the power of data to generate predictions, according to the company.

“At the operational level, we are using customised learning algorithms across a range of different applications,” Anglo said. “In one such instance, we monitor equipment health at a number of our operating sites, with the aim of improving operational performance through predictive maintenance.”

The company said at Barro Alto, which has two rotary kilns and two electric furnaces that smelt nickel ore, it is focusing its predictive maintenance efforts on key pieces of high-power equipment.

Anglo said: “By building a comprehensive data platform that monitors 38 major elements of the Barro Alto operation, we are increasing our knowledge of the performance of the equipment and we are using data to accurately forecast failures before they happen.”

Soon, the company will be able to “dynamically manage” maintenance intervals – only replacing parts when required – Anglo said. This ensures greater operational uptime and product throughput, according to the company. “The implementation is expected to improve furnace reliability, as well as realise cost savings for the nickel business,” Anglo said.

The learnings from Barro Alto are also being applied to fixed-plant assets in other operations, Anglo said. “This nascent project is on track to deliver considerable value from just one data analytics application.”

On the technology in general, Anglo said: “Data analytics augments the intelligence in our people by helping them make better, confident data-driven decisions. Remote monitoring of assets takes people away from physical equipment and helps avoid high-energy failures, which leads to a safer working environment. Reducing unplanned equipment failures can also bring significant environmental benefits owing to the reduced likelihood of spillages.”

Anglo plans to extend the reach of its data analytics platforms to all aspects of its value chain and extend operational decision support to the mining and processing phases of its assets, it said.

Mining3 and Ava Group gear up for launch of Aura IQ conveyor monitoring system

Bulk handling, Equipment maintenance, Mining equipment, Mining maintenance, Mining safety, Mining services, Mining software, , , , , , ,

Mining3 and Ava Group have revealed a little more about the plans to launch an innovative predictive asset monitoring solution for conveyors.

Under the development and commercialisation agreement signed last month, Ava’s Future Fibre Technologies (FFT) subsidiary will use its Aura advanced fibre optic sensing platform, combined with Mining3’s signal processing algorithms, to bring to market a brand new FFT solution – Aura IQ.

“This automated system will provide the global mining industry with the world’s most advanced solution in wear detection of conveyor rollers with the ability to pre-empt failure, generating significant time and cost savings,” Mining3 said.

Prof Paul Lever, CEO of Mining3, said: “Our focus remains on accelerating the research and development process to deliver breakthrough technology for our members and the global mining industry. The new development and commercialisation partnership with the Ava Group facilitates this outcome and ensures the industry benefit from much-needed advancements in technology.”

Ava Group’s Head of Extractives and Energy, Andrew Hames, said: “Mining companies are striving to realise the full benefits of evolving digital capabilities to enhance improvements in productivity; including looking at ways of using data more effectively to improve asset management, reliability and introduce predictive capability.

“This partnership is a result of our focus towards providing innovative solutions to clients in key strategic sectors. The opportunity for Ava Group and FFT is transformational for the industry and adjacent markets as we further leverage the technologies’ applications.”

Aura IQ is expected to launch in Q2 FY2019 and provide a first mover advantage for Ava Group, in a potential total addressable market of up to A$300 million ($213 million), Mining3 said.

Dingo’s new Denver Asset Health Centre to improve predictive maintenance coverage

Base metals, Coal technology, Energy minerals, Equipment maintenance, Gem stone mining, Industrial minerals, IoT, Mining equipment, Mining maintenance, Mining services, Mining software, Precious metals, Steel and iron ore, , , , , ,

Dingo Software, a leader in providing predictive maintenance solutions to asset-intensive industries, has opened up its new Asset Health Centre in Denver, Colorado.

The modern, purpose-designed facility will provide operations with asset health coverage 24 hours a day, seven days a week, Dingo says.

“From a sophisticated control room, Dingo analysts will monitor equipment condition, using a proprietary predictive analytics platform enriched with decades of maintenance expertise, to identify impending issues and then prescribe the corrective maintenance actions for immediate resolution,” the company said.

“This actionable intelligence will dramatically improve decision-making and could be the difference between an inexpensive repair and a catastrophic breakdown costing millions in parts and productivity losses.”

Currently managing over $12 billion worth of heavy equipment across six continents, the new centre, combined with its facility in Brisbane, Australia (pictured), will provide operations with a convenient, cost-effective way to monitor and maintain equipment, according to the company.

Dingo CEO Paul Higgins said the Denver team will be able to serve customers remotely using its award-winning, cloud-based predictive maintenance software, Trakka®, and team of Condition Intelligence™ experts. “Right now, around 250 different operations globally are capitalising on Dingo’s remote Asset Health services,” he said.

Safety is another major benefit Dingo will deliver to these operations, according to Higgins.

“When people work on a site they’re exposed to inherent dangers, so being offsite and working from a remote centre is advantageous,” he said. “And well-maintained equipment is always safer. It’s an issue that Dingo and its customers take very seriously.”

Other benefits include access to subject-matter expertise: “Dingo’s team of analysts has deep domain expertise in a range of fields.” Higgins said. “We have people with fixed plant, mobile, and underground experience; experts who understand trucks, shovels, drills—as well as a range of condition monitoring technologies.”

It would be an extremely expensive endeavour for one customer to find, and hire, an equivalent team of experts, according to Dingo.

“We can deliver the right expertise at the right time to help with the right issue,” Higgins said.

Dingo also provides clients with access to its proprietary equipment health database.

“We have one of the largest databases of asset health information in the world,” Higgins said. “Even when a customer has its own in-house team, they may only have access to the data they have generated. With over 25 years’ worth of asset performance data, we know what good looks like and, when equipment is underperforming, we know how to fix it.”

He added: “We’ve developed the unified platform specifically to enable access across multiple mining operations. An example is the senior management asset performance dashboard, which provides a comprehensive view of fleet health to ensure mines are operating at peak performance.”

Ultimately the Asset Health Centre doesn’t function as a complete outsourcing option, according to Dingo.

“Some customers take more of the workload on themselves, others don’t have the resources and want to move quickly so they bring us in,” Higgins said. “We don’t replace the customer’s team, we help them. We filter the noise and streamline decision-making, so they can focus on other, more pressing issues.”

Dingo is expanding the use of practical machine learning models in its Trakka predictive maintenance software with two new releases next year.

Weir Minerals offers productivity, safety and throughput improvements with Synertrex

Automation, Base metals, Bulk handling, Comminution of minerals, Communications in mining, Energy minerals, Equipment maintenance, Metallurgy, Mineral processing, Mining equipment, Mining services, Mining software, Precious metals, Steel and iron ore, Water management, , , , ,

Weir Minerals has announced the launch of its Synertrex® platform, an advanced Industrial Internet of Things (IIoT) technology, which, it says, is set to transform the mining industry.

Delivering an advanced level of understanding, it allows operators to monitor every aspect of their equipment’s operation, prevent problems and increase throughput, according to Weir.

It uses network connectivity to capture equipment data and relay it to service centres, service technicians, their customers and Weir’s design centres for trend monitoring, proactive components supply and product improvement.

Ricardo Garib, Minerals Division President, said: “We believe our Synertrex platform will have a significant impact on the mining industry, transforming customer operations through improved productivity and safety.”

The company worked with technology market leaders Microsoft and Dell to develop “sophisticated predictive software and hardware” robust enough to operate in extreme conditions across the globe, he added.

IIoT is a network of equipment that connects to the internet and shares data that can be converted into unique insights. Demand for IIoT-enabled products is growing rapidly, particularly in the mining industry where it is being used in a number of areas including analytics, machine learning, and robotics.

“Synertrex is a cutting edge IIoT platform which harnesses the latest digital technology to transform productivity, foresee risk and enhance performance,” Weir said.

Using cloud computing, it involves placing smart sensors on an array of Weir Minerals’ products to gather critical operating data for advanced analysis. The data is transformed into powerful insights relayed to the customer through a digital interface.

“It can identify problems before they occur, reducing downtime, and optimise equipment performance across an entire circuit,” Weir said.

“Remote management allows for simplified maintenance. Wear and tear can be easily monitored, and trouble spots detected before they escalate into major issues. Whether it’s a drive system, structural or lubrication issues, Synertrex provides the tools to keep mining equipment at its most profitable.”

Through the platform, customers have detailed real-time insight into how equipment is performing, and machines will be able to learn over time, according to Weir.

Information is displayed on an easy to understand dashboard, which can be accessed via any device or integrated into existing operational systems. It will convey real-time, fact-based insights into machine performance and health, remaining useful life and other crucial indicators.

Fred Bradner, Vice President of Global Strategy, Sales and Marketing, said: “This platform will redefine field service standards and lead to greater performance, reliability and ultimately return on investment.”

At this stage, the platform can be paired with Warman® pumps, Cavex® hydrocyclones, GEHO® PD pumps, Enduron® HPGR, Enduron® screens and Enduron® crushers; however Weir has plans to expand the range of compatible products.

Customers with existing Weir products who wish to enable Synertrex will be able to retrofit sensors to equipment.

John McNulty, Vice President of Global Engineering and Technology, said: “This technology is backed by our 147 years of experience and unrivalled service support. Our team travel to the customers’ site to install the sensors, connect to the cloud and provide training to ensure they fully understand how the Synertrex platform works and what it can do.

“The data gathered from Synertrex combined with our in-depth product knowledge, provides unique insights on performance that only the OEM can deliver. Our extensive service network can quickly act on the outputs from Synertrex to provide unrivalled on-site support to our customers.”