Make Intelligent Decisions
We Optimise Every Step of the Mining Value Chain
brains.app is a real-time decision-making platform for asset intensive industries powered by Artificial Intelligence (AI) and Industrial Internet of Things (IIOT) technology.
Collecting, cleaning, interpolating and assimilating a federated data lake ready for AI. The brains.app platform enables a portfolio of process optimization applications targeting the mining value chain; resulting in accelerated value delivery in terms of increased throughput, recovery and reduced energy, water and waste footprint.
Material Handling Model
BASF Intelligent Mine Material Handling Model tracks material flows and geometallurgical and physical properties (Material Transport) with associated uncertainty from the pit throughout the processing plant, providing real time information and predictions of when material will arrive at a particular point. It also tracks and predicts the effect of the incoming material on processes in real time (Material Influence).
The flow of material can be simulated to indicate the material properties that will arrive at processes of interest in the future, allowing pre-emptive action to be taken to improve processing efficiency.
Dual Modelling Approach
The Dual Modelling approach combining Machine Learning and First Principle Models to create the BASF Technology that includes the platform and the out-of-the-box Optimization applications have been proven at mining majors and make BASF Intelligent Mine uniquely positioned in the market. This has allowed us to sign up a scale up our distribution strategy with leading Mining industry suppliers, enabling us to scale by focussing on our product and partnering with Industry giants for sales and marketing.
A Virtual Sensor is the output of a digital asset; a real time model output (including uncertainty) based on both dynamic and static inputs which can be used in operational and financial decision making, automated control and both machine learning and empirical simulation-based prediction models.
They differentiate from the “soft sensor” as they are processed in the cloud, with the benefit of constant retraining and re-calibration. The accuracy and robustness of the outputs are cross verified using equivalent outputs of parallel models. Their deployment is non-intrusive.
The data generated by hard and soft sensors can be used to reconcile production metrics, creating a single source of truth for the mining operation. This Reconciliation decreases the total uncertainty of data along the value chain to produce a coherent data set that can confidently be used in reporting and in enhanced re-optimisation of mine planning.
The BASF Intelligent Mine Value Model accurately calculates (and when paired with the digital process model predicts) asset based operating unit costs in real time using dynamic financial variables.
Data Assimilation and Data Quality
The data is organized into a connected virtual asset/metric structure. In this structure, data of varying resolution is filtered both practically and statistically through the BASF Intelligent Mine Data Quality Model, which ensures only quality data is used in process simulation.
A Digital Asset is a set of configurable models associated with a specific piece of equipment. They differ from a digital twin as they are required to be “real time plug and play” based on the asset type.