TY - JOUR

T1 - Predicting condition states, based on displacement data, generated by acceleration sensors on industrial linear vibrating screens through neural networks

AU - Krukenfellner, Philip

AU - Rückert, Elmar

AU - Flachberger, Helmut

N1 - Publisher Copyright: © 2001-2012 IEEE.

PY - 2024/10/4

Y1 - 2024/10/4

N2 - Vibrating screens are crucial in the waste and mineral processing industries. However, they often lack comprehensive digital monitoring, which necessitates subjective condition assessments. This study introduces a system developed in cooperation with IFE Aufbereitungstechnik GmbH that provides an objective machine state evaluation using permanently installed acceleration sensors, developed by eSensial Data Science GmbH. Unlike previous research, data for this project was collected from a linear vibrating screen, which is operating in a waste processing plant, introducing uncertainties and occasionally missing data due to sensor damage to the analysis. The study focuses on applying supervised machine learning algorithms to predict the machine’s operating condition. In particular, decision trees, multi-layer perceptron networks, and long-short-term memory networks were evaluated using classical performance metrics like the MSE and the R2-Score. The models were also tested with respect to missing input data. The multilayer perceptron network achieved a prediction accuracy of over 90%. Further, it displayed the ability to determine previously unlabeled intermediate states. Additionally, the main cause of prediction errors was identified, and a method of handling missing input data was developed.

AB - Vibrating screens are crucial in the waste and mineral processing industries. However, they often lack comprehensive digital monitoring, which necessitates subjective condition assessments. This study introduces a system developed in cooperation with IFE Aufbereitungstechnik GmbH that provides an objective machine state evaluation using permanently installed acceleration sensors, developed by eSensial Data Science GmbH. Unlike previous research, data for this project was collected from a linear vibrating screen, which is operating in a waste processing plant, introducing uncertainties and occasionally missing data due to sensor damage to the analysis. The study focuses on applying supervised machine learning algorithms to predict the machine’s operating condition. In particular, decision trees, multi-layer perceptron networks, and long-short-term memory networks were evaluated using classical performance metrics like the MSE and the R2-Score. The models were also tested with respect to missing input data. The multilayer perceptron network achieved a prediction accuracy of over 90%. Further, it displayed the ability to determine previously unlabeled intermediate states. Additionally, the main cause of prediction errors was identified, and a method of handling missing input data was developed.

KW - Machine Learning

KW - Aufbereitung

KW - Sensoren

KW - Schwingsiebe

KW - Schwingungsüberwachung

KW - Abfallaufbereitung

KW - Machine learning

KW - Mineral Processing

KW - Sensors

KW - Vibrating Screens

KW - Vibratoin Monitoring

KW - Waste processing

KW - Vibration monitoring

KW - Vibrating screens

KW - Mineral processing

UR - http://www.scopus.com/inward/record.url?scp=85205982745&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2024.3464635

DO - 10.1109/JSEN.2024.3464635

M3 - Article

VL - ??? Stand: 11. November 2024

JO - IEEE sensors journal

JF - IEEE sensors journal

SN - 1530-437X

IS - ??? Stand: 11. November 2024

ER -