Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Abstract.

Driven by an increasing food demand and an urgency for intelligent land use, the size and complexity of agricultural machinery have increased significantly. Monitoring machine operation is an important task for the operators. Automatic monitoring systems could lighten their job and pave the way towards fully autonomous machines. Therefore, this paper proposes an automatic condition monitoring system for detecting operation anomalies on agricultural machine components with reciprocal motion, and applies it in a use-case on a combine harvester header cutter bar. Cyclostationary analysis techniques are exploited to develop filtering algorithms to extract informative features, which are monitored in control charts by implementation of statistical process control (SPC). Together with a comparison of several filtering and feature extraction techniques an analysis is provided on the influence of sensor type on anomaly detection performance. Filtering benefit was found to be highly dependent on the considered sensor type, with increases in Matthews correlation coefficient (MCC) ranging from 0 to 44%, resulting in maximal MCC values of 1. Suitable feature calculation resulted in average prediction performance improvements up to 40% in MCC values for both considered sensor types. These results highlight the importance of intelligent sensor selection for condition monitoring purposes on agricultural machinery and the added value of SPC involving cyclostationary analysis techniques for anomaly detection.