Predicting Filter Medium Performances in Chamber Filter Presses with Digital Twins Using Neural Network Technologies

TL;DR

This paper presents a neural network-based digital twin framework for chamber filter presses that predicts operational parameters and filter medium lifespan, enhancing efficiency and maintenance planning in solid-liquid separation processes.

Contribution

It introduces a novel neural network model integrated into a digital twin for real-time prediction of filter press performance and medium degradation, improving operational flexibility and predictive maintenance.

Findings

Recurrent neural network outperformed feedforward models in accuracy.

Achieved low relative errors of 5% for pressure and 9.3% for flow rate on known data.

Predicted data deviations within 8.2% for pressure and 4.8% for flow rate.

Abstract

Efficient solid-liquid separation is crucial in industries like mining, but traditional chamber filter presses depend heavily on manual monitoring, leading to inefficiencies, downtime, and resource wastage. This paper introduces a machine learning-powered digital twin framework to improve operational flexibility and predictive control. A key challenge addressed is the degradation of the filter medium due to repeated cycles and clogging, which reduces filtration efficiency. To solve this, a neural network-based predictive model was developed to forecast operational parameters, such as pressure and flow rates, under various conditions. This predictive capability allows for optimized filtration cycles, reduced downtime, and improved process efficiency. Additionally, the model predicts the filter mediums lifespan, aiding in maintenance planning and resource sustainability. The digital twin framework enables seamless data exchange between filter press sensors and the predictive model, ensuring continuous updates to the training data and enhancing accuracy over time. Two neural network architectures, feedforward and recurrent, were evaluated. The recurrent neural network outperformed the feedforward model, demonstrating superior generalization. It achieved a relative $L^2$-norm error of $5\%$ for pressure and $9.3\%$ for flow rate prediction on partially known data. For completely unknown data, the relative errors were $18.4\%$ and $15.4\%$, respectively. Qualitative analysis showed strong alignment between predicted and measured data, with deviations within a confidence band of $8.2\%$ for pressure and $4.8\%$ for flow rate predictions. This work contributes an accurate predictive model, a new approach to predicting filter medium cycle impacts, and a real-time interface for model updates, ensuring adaptability to changing operational conditions.