Crusher Bridge Prediction

Application

Rock bridging is a recurring problem in mining, especially in the operation of medium-capacity jaw crushers. Bridging refers to the blockage or jamming of the crusher due to input material forming an arch or “bridge” across the jaw. The blockage prevents further material from entering and may halt the plant until it is corrected, often with a rock breaker. The contribution of bridging and rock breaking to downtime should be measured from the site’s own event history.

Early detection of such bridging events can significantly reduce the downtime and increase the efficiency of the operation. It enables timely intervention to dislodge the bridged material before it becomes a full-blown problem that halts production.

Minealytics utilises anomaly detection models for this purpose. Anomaly detection involves identifying unusual patterns or outliers in the data which do not conform to expected behaviour. In this context, the anomalies represent potential bridging events. The key to these models is the utilisation of historical and real-time operational data to identify signs that indicate the potential for a bridge to occur.

In the case of the Minealytics Overload Detection model, the process-data model was evaluated at multiple lead times. Shorter horizons and richer process inputs can provide useful warning before an event, but the useful horizon and performance need to be re-established for each site against labelled bridge events, false alarms and missed events.

The challenge lies in the fact that bridged events are not directly captured in the control system. The model uses indirect evidence, such as the rock breaker running signal, to identify these events. False positives and missed events are therefore important parts of the data-engineering and integration work. An installation can use a graduated corrective response as model confidence increases, with the response limits, fallback and alarm behaviour defined during site integration.

This is where continuous monitoring, model refinement, and further integration with specialised sensor technologies like specialised cameras provide significant improvements. With more accurate and diverse data, the model’s precision increases, reducing the number of false positives and further enhancing the efficiency of mining operations.

Overload Detection Model for Jaw Bridge Prediction

The Minealytics Overload Detection model uses a supervised classification model to detect bridging. 23 input features have been used for the training, and it has been shown that using only the crusher and grizzly currents results in a significant reduction (>15%) in accuracy.

Training Metrics and Model Evaluation

Historical evaluation compared multiple input sets and prediction horizons. Results are dataset-specific and should be reported with the event definition, class balance, false-positive rate, missed-event rate and validation method. A new installation requires a fresh evaluation before outputs are used for control.

Neural Preventive Anomaly Detection for Bridging and Blocked Chutes

A primary jaw crusher bridge prediction system employing a time-series prediction neural network offers significant advantages in enhancing the efficiency and safety of crushing operations in mining. The system is trained on historical data to recognise patterns leading to material bridging — a common issue where materials form an arch over the crusher intake, hindering material flow and potentially causing operational disruptions and equipment damage.

The key advantage of this system lies in its ability to predict the likelihood of bridging events up to 20 seconds in advance using upstream process signals (ROM level, feeder pressure or current, etc.), providing a crucial window for preemptive action. As the system forecasts an impending bridge, it progressively increases the response strength, such as by adjusting the apron feeder speed, to mitigate the risk. This dynamic throttling of the feeder speed based on real-time predictions helps maintain a consistent material flow, reducing the chances of operational halts and enhancing overall productivity.

Moreover, the adaptability of such a neural network model allows for its application in predicting bridging in other critical areas, such as chutes. This scalability means that the same predictive technology can be applied across different points in the material-handling process, offering a comprehensive solution to a widespread challenge in mining operations.

The supervised model is trained against the characteristics and event definitions of the mining operation. Its usefulness depends on label quality, operating coverage, false alarms and missed events. When validated, the prediction can support feed-rate decisions and other bounded operational responses.

Technology

By training a machine-learning model on labelled images of typical and atypical ore conditions, Minealytics can achieve a high level of granularity in real-time monitoring. For example, the algorithm can be trained to recognise and differentiate between ore, empty space, and potential bridges. When the system detects a bridge forming, it can alert operators to take corrective action immediately, thus preventing potential jams, equipment damage, or inefficiencies.

Semantic segmentation can support real-time bridge detection and, when combined with time-series process data, may support predictive analysis. The prediction horizon, event definition and response are validated against the site data before they are used operationally.

Neural Modeling of Ore Characteristics

The impact of ore hardness on the crushing process is a critical factor in mining operations, yet it poses a significant challenge in terms of measurement and modelling. Ore hardness directly influences the amount of energy required for effective crushing, the wear rate on crushing equipment, and the overall efficiency of the process. Traditional methods of estimating ore hardness through crusher parameters, such as electrical current draw, offer some insights but are often inadequate. These parameters can indicate changes in the crushing load, but the relationship between current draw and ore hardness is not straightforward and can be influenced by various other factors, making empirical modelling difficult and often unreliable.

This complexity has led to the exploration of advanced techniques like neural models for a more accurate assessment of ore hardness. Neural networks, with their ability to learn from large datasets and identify intricate patterns, can be trained on a range of data inputs, including crusher operation parameters, to develop a more precise understanding of the relationship between these variables and ore hardness. By continuously analysing operational data, these models can adapt to the subtle changes in ore characteristics, providing a dynamic and more accurate representation of ore hardness in real time. This capability is especially valuable in optimising the crushing process, as it allows for more informed and responsive adjustments to the crusher settings, improving energy efficiency, reducing equipment wear, and enhancing overall process control. In the realm of data-driven, AI-enhanced mining operations, the use of neural models for measuring ore hardness exemplifies the shift towards more sophisticated, adaptive, and efficient management of natural resources.