By clicking Sign In, Join Free or Continue with Facebook, Linkedin, Twitter, Google, I agree to the Terms & Conditions and the Privacy Policy

Digital Transformation in Metals and Mining Industry

Contributed by: Anonymous
April 14, 2021

The In recent years, Metals and mining organizations across the world has started to follow in the footsteps of other industry players like Retail and Consumer to embark on their digital transformation journeys spanning across the entire value chain – from raw material sourcing to manufacturing, distribution and overall ecosystem development. In this two-part series on "Digital Transformation in Metals and Mining industry" we cover some of the interesting use cases of digital transformation across the entire value chain.

In the first part of the series we cover some interesting use cases in the upstream value chain


  • Autonomous vehicles are being used to carry out seamless transfer of raw material within the factories from designated point to point without any supervision. Technologies for free navigation utilize floor markings (metal, magnets, transponders) or laser technology in which position-determination functions something like in maritime transport (cross bearing) can be found. Newer technologies combine laser scanners and camera systems with digital-environment maps and enable navigation by characteristics of the environment.
  • Data driven procurement decision making: Advance data analytics are being used to make strategic calls/ hedging on procurement decisions of feedstock/ raw materials basis spot prices, future forecasts etc. in the ever-changing global scenarios.
  • Vendor/Supplier Risk Analytics: Develop highly robust sourcing strategies through supplier/vendor risk categorization using advanced analytics
  • Cooking: Aluminium foil is also used for barbecuing delicate foods,such as mushrooms and vegetables.
  • Art & Decoration: Heavier foils made of aluminium are used for art, decoration, and crafts, especially in bright metallic colours. Metallic aluminium, normally silvery in colour, can be made to take on other colours through anodisation. Anodising creates an oxide layer on the aluminium surface that can accept coloured dyes or metallic salts, depending on the process used. In this way, aluminium is used to create an inexpensive gold foil that actually contains no gold, and many other bright metallic colours. These foils are sometimes used in distinctive packaging.
  • Geochemical Sampling: Foil is used by organic/petroleum geochemists for protecting rock samples taken from the fields and in the labs where the sample is subject to biomarker analysis.


  • Use of Sensors for monitoring: Metso is using visual sensors to enable clients to monitor the bubbles in their steel production. The amount of air and the size of the bubbles in a steel furnace affects the quality of the final product. However, the intense heat makes it hard to take readings from the molten metal. Visual sensors, coupled with heat sensors, can scan the surface of the molten metal and quickly assess the quality of the steel and automatically identify any adjustments to the process that are needed. The result: a higher-quality, more consistent product.
  • 3D printing: Arconic has an agreement with Airbus to supply 3D-printed titanium fuselage and engine pylon components for commercial aircraft. The company, which expects to deliver the first additive-manufactured parts to Airbus in mid-2016, acquired RTI International Metals to expand its additive manufacturing capabilities to include 3D-printed titanium and specialty metals parts. It will employ advanced CT scan and Hot Isostatic Pressing (HIP) capabilities at its advanced aerospace facility in Whitehall, Michigan. HIP strengthens the metallic structures of traditional and additive-manufactured parts made of titanium and nickel-based superalloys. Arconic is further bolstering its additive manufacturing capabilities through a $60-million expansion in advanced 3D-printing materials and processes at its technical centre near Pittsburgh, Pennsylvania
  • Smart helmets for monitoring workers health and safety: Mining companies in Australia, including Rio Tinto, Anglo American and Newcrest Mining, are providing field workers with smart baseball caps (known as Smart Caps) that monitor their brainwaves to measure fatigue. The technology has been rolled out primarily with truck drivers and machinery operators, who are at risk from fatigue-related injuries. The Smart Cap uses an electroencephalogram (EEG) and proprietary algorithms to calculate a risk assessment number, which corresponds to a worker’s ability to resist falling asleep. The Smart Cap provides an early warning when a driver is approaching microsleep. At Rio Tinto, truck drivers are required to discuss a fatigue management plan with supervisors if their Smart Caps show they have high levels of fatigue. Mining companies are using Smart Cap data to better understand the dynamics of fatigue and improve workplace designs. Insights from the data have also shown that road characteristics can affect driver fatigue, encouraging designers to reconsider the design of roads and signage. Smart Caps have had a mixed reception. Some workers have objected to their introduction because of concerns over the information gathered being used for disciplinary reasons
  • Quality improvement through Machine learning: A European steelmaker was facing a high (above 20 percent) and variable (0-40 percent) rejection rate on the mechanical properties of a major new product family, leading to extensive value leakage in direct and indirect costs. A year of traditional hypothesis-driven analysis failed to identify the root cause of the problem. However, by using classification advanced analytics techniques on more than 300 variables of through-chain data – covering chemical composition, shift and maintenance logs, and process parameters – the company quickly succeeded in identifying the process parameters responsible for the rejections. A neural-network model allowed it to optimize the production formula, bringing the rejection rate to less than 1 percent in just 10 weeks.
  • Using Machine learning for predicting equipment failure: A global base metals smelting group was grappling with downtime and associated production losses due to unexpected failure of a blower occurring on average more than once a month. It also frequently had to divert maintenance resources from planned maintenance tasks to breakdown repair activities, reducing the efficiency of the maintenance team. A predictive model, leveraging existing sensors to collate operating and equipment data, was able to predict imminent failure on average 7 days in advance with an accuracy of 81 percent. This allowed the group to plan and synchronize maintenance interventions and prevent additional time lost due to re-planning, expediting, and procuring parts and avoiding failure and damage cascading across assets.
  • Scrap mix optimization using advanced analytics: A European steelmaker introduced a value-in-use model to optimize the scrap mix in the converter. Taking into account the scrap price, availability and characteristics (chemical and physical), the plant constraints (e.g., Zn content of dust, size of scrap loaders, logistics constraints in the scrap hall), the specific factor costs (e.g., refractories, lime), and finished product constraints, the company dynamically optimized its scrap menu and was able to reduce scrap cost by 10 percent.