Recirculating Load Prediction

Application

Controlling comminution circuits, such as those involving SAG (Semi-Autogenous Grinding) mills, ball mills, and other grinding operations, is a complex task due to the large number of measured and hidden variables that affect the underlying processes. Different advanced control approaches, including theoretical and empirical model-based methods, have become widespread to address these challenges with only limited success.

Using the Minealytics AI model for recirculation load prediction in a circuit with a primary SAG (Semi-Autogenous Grinding) mill followed by a recirculating ball mill offers several advantages, particularly in optimising the efficiency and throughput of the grinding process.

Solution: Neural Mill Control

Minealytics specialises in AI-based control for mining applications. AI models, particularly those using machine learning, can adapt to changing process conditions more dynamically. They can learn from new data as it becomes available, making them suitable for environments where ore characteristics and operational conditions vary frequently. AI models excel in forecasting future process behaviour based on historical and real-time data. This predictive ability can be particularly advantageous in anticipating issues like equipment overload, maintenance needs, or changes in ore quality. AI models can identify and learn complex, non-linear relationships in data that might be difficult to model explicitly in traditional APC systems. They can effectively utilise vast amounts of historical and real-time data, extracting valuable insights that might be missed by traditional methods. As more data is collected, AI models can be retrained and improved, potentially increasing their accuracy and reliability over time. They can also easily integrate diverse data sources, including sensor data, operational parameters, and external factors like weather, which might impact the comminution process.

By using the Minealytics Recirculation Load prediction model, a balance of utilisation between the SAG mill and the ball mill can be achieved. This ensures that neither the SAG mill is overloaded nor the ball mill is underutilised, maintaining an efficient grinding process. With the predictive model, adjustments can be made to the feed rate, water addition, or grinding media in the SAG mill to control the size and amount of material that will be recirculated to the ball mill, helping to maintain optimal throughput in the circuit.

Overloading the SAG mill can lead to issues like increased wear, reduced grinding efficiency, and higher energy consumption. Predicting the recirculation load allows for pre-emptive adjustments to the SAG mill’s operation (such as reducing feed rate or adjusting the grind size setting) before an overload condition occurs. Efficient management of the recirculation load can also lead to energy savings: by avoiding over-grinding in the SAG mill and reducing unnecessary work in the ball mill, the overall energy consumption of the grinding process can be reduced.

Consistent and optimal grinding results in better liberation of valuable minerals, potentially improving recovery rates in the subsequent concentration processes. Predicting and managing the recirculation load can reduce the wear and tear on both the SAG and ball mills, leading to lower maintenance costs and longer equipment life. Ore characteristics can vary significantly; predictive modelling of the recirculation load allows for adaptive responses to these changes, ensuring consistent grinding performance. In practice, the predicted recirculation load information can be used to adjust parameters like the SAG mill’s feed rate, speed, and water addition to control the mill’s output. This proactive approach helps maintain the desired efficiency and throughput of the grinding circuit, while also minimising the risk of overloading the SAG mill.

Technology

The Minealytics Mill Control models compare candidate AI architectures against the plant’s own data and the control objective. The selected model is monitored against measured process behaviour after deployment.

In time series modelling, the goal is to predict future values based on past observations. This can include forecasting future sales, predicting equipment failures, or anticipating market trends. The model is trained on a dataset where the desired output (like future sales) is known for past time points. The model learns to associate patterns in the input data with these outcomes.

Attention mechanisms allow a model to focus on specific parts of the input sequence that are most relevant for making a prediction. This is particularly useful in long sequences where certain segments are more informative. Originally developed for natural language processing, transformers use self-attention to weigh the importance of different parts of the input data. They are highly effective in capturing long-range dependencies in data. In time series, attention models can identify crucial time steps that most significantly influence future values, improving the accuracy of long-term forecasts.

1D convolutions can be used to process temporal information, capturing patterns across different time scales. CNNs can efficiently handle large datasets and can capture complex patterns in the data, making them suitable for a variety of forecasting tasks.

Originally developed for generating high-quality audio, WaveNet is a deep neural network that uses dilated convolutions to process time series data. These allow the network to have a very large receptive field, meaning it can consider information from many previous time steps without a significant increase in computational complexity. WaveNet can be particularly effective for long-term predictions in time series data due to its ability to capture long-range dependencies.