Solution: Time Series Forecasting for Neural Control

Time series forecasting can play a significant role in solving the problem of apron feeder control by providing accurate predictions of material flow rates. By analysing historical data and using forecasting techniques, engineers can make informed decisions to optimise the operation of apron feeders, or the control can be automated based on the predictions. Since there are multiple sensors and other data sources, AI-based models can efficiently bring together this data and create accurate predictions.

Our technology uses Convolutional Neural Networks (CNNs) to accurately predict material flow rates from several variables including current apron feeder speed and current flow rate. Depending on the equipment and setup, any number of variables can be added to help model the future flow rate. CNNs are traditionally known for their prowess in image and video recognition tasks. However, their ability to recognise patterns in spatial data makes them a powerful tool for time series prediction as well. CNNs can automatically learn relevant features from the raw time series data, which makes feature engineering a less tedious task. CNNs are generally robust to noise and outliers, thanks to their hierarchical feature learning. This makes them well-suited for feedrate estimation, where data is generally noisy due to high flow rate, vibration, equipment malfunction, sensor errors, or other operational issues. Convolutional  layers can learn to recognise both local and global patterns in time series data, which is crucial when dealing with feedrate estimation where short-term fluctuations and long-term trends both play significant roles.

In summary, CNN-based time series prediction for feedrate estimation can offer a robust, scalable, and accurate solution, well-aligned with your goals to transform mining into a more data-driven and autonomous industry.

Utilising AI modeling for feedrate prediction provides a powerful tool for performance evaluation of alternative or competing control strategies. With the ability to accurately predict future feedrate changes under varying conditions, AI models serve as a reliable

benchmark against which different control methods can be assessed in a real or simulated environment. This enables continuous learning and data-driven decisions to optimise control algorithms, and choose the most efficient and robust strategy at staging, thus reducing risks, minimising operational costs, and enhancing overall performance.

Another use-case for AI models is the predictive alarming. By leveraging the capabilities of AI to accurately forecast feedrate changes, the alarm system can proactively notify operators of potential issues, such as equipment overloads or inefficiencies, well before they become critical. This enables timely interventions, minimises downtime, and allows for more optimal resource allocation. Moreover, the predictive nature of the system can adapt to the ever-changing conditions in the mine, such as varying ore properties, making it a highly dynamic and robust solution. Overall, an AI-based predictive alarm system for the primary crushing circuit aligns well with the goal of transitioning from conventional, stable and reactive alarm systems to more data-driven, proactive, and autonomous operations.