On-device Anomaly Detection in Conveyor Belt Operations

Mining 4.0 leverages advancements in automation, digitalization, and interconnected technologies from Industry 4.0 to address the unique challenges of the mining sector, enhancing efficiency, safety, and sustainability. Conveyor belts are crucial in mining operations by enabling the continuous and efficient movement of bulk materials over long distances, which directly impacts productivity. While detecting anomalies in specific conveyor belt components, such as idlers, pulleys, and belt surfaces, has been widely studied, identifying the root causes of these failures remains critical due to factors like changing production conditions and operator errors. Continuous monitoring of mining conveyor belt work cycles for anomaly detection is still at an early stage and requires robust solutions. This study proposes two distinctive pattern recognition approaches for real-time anomaly detection in the operational cycles of mining conveyor belts, combining feature extraction, threshold-based cycle detection, and tiny machine-learning classification. Both approaches outperformed a state-of-the-art technique on two datasets for duty cycle classification in terms of F1-scores. The first approach, with 97.3% and 80.2% for normal and abnormal cycles, respectively, reaches the highest performance in the first dataset while the second approach excels on the second dataset, scoring 91.3% and 67.9%. Implemented on two low-power microcontrollers, the methods demonstrated efficient, real-time operation with energy consumption of 13.3 and 20.6 ${\mu}$J during inference. These results offer valuable insights for detecting mechanical failure sources, supporting targeted preventive maintenance, and optimizing production cycles.

A noise-robust acoustic method for recognition of foraging activities of grazing cattle

To stay competitive in the growing dairy market, farmers must continuously improve their livestock production systems. Precision livestock farming technologies provide individualised monitoring of animals on commercial farms, optimising livestock production. Continuous acoustic monitoring is a widely accepted sensing technique used to estimate the daily rumination and grazing time budget of free-ranging cattle. However, typical environmental and natural noises on pasture noticeably affect the performance and generalisation of current acoustic methods. In this study, we present an acoustic method called Noise-Robust Foraging Activity Recognizer (NRFAR). The proposed method determines foraging activity bouts by analysing fixed-length segments of identified jaw movement events associated with grazing and rumination. The additive noise robustness of NRFAR was evaluated for several signal-to-noise ratios, using stationary Gaussian white noise and four different non-stationary natural noise sources. In noiseless conditions, NRFAR reaches an average balanced accuracy of 89%, outperforming two previous acoustic methods by more than 7%. Additionally, NRFAR presents better performance than previous acoustic methods in 66 out of 80 evaluated noisy scenarios (p<0.01). NRFAR operates online with a similar computational cost to previous acoustic methods. The combination of these properties and the high performance in harsh free-ranging environments render NRFAR an excellent choice for real-time implementation in a low-power embedded device. The instrumentation and computational algorithms presented within this publication are protected by a pending patent application: AR P20220100910. Web demo available at: https://sinc.unl.edu.ar/web-demo/nrfar

Using segment-based features of jaw movements to recognize foraging activities in grazing cattle

Precision livestock farming optimizes livestock production through the use of sensor information and communication technologies to support decision making, proactively and near real-time. Among available technologies to monitor foraging behavior, the acoustic method has been highly reliable and repeatable, but can be subject to further computational improvements to increase precision and specificity of recognition of foraging activities. In this study, an algorithm called Jaw Movement segment-based Foraging Activity Recognizer (JMFAR) is proposed. The method is based on the computation and analysis of temporal, statistical and spectral features of jaw movement sounds for detection of rumination and grazing bouts. They are called JM-segment features because they are extracted from a sound segment and expect to capture JM information of the whole segment rather than individual JMs. Two variants of the method are proposed and tested: (i) the temporal and statistical features only JMFAR-ns; and (ii) a feature selection process (JMFAR-sel). The JMFAR was tested on signals registered in a free grazing environment, achieving an average weighted F1-score greater than 95%. Then, it was compared with a state-of-the-art algorithm, showing improved performance for estimation of grazing bouts (+19%). The JMFAR-ns variant reduced the computational cost by 25.4%, but achieved a slightly lower performance than the JMFAR. The good performance and low computational cost of JMFAR-ns supports the feasibility of using this algorithm variant for real-time implementation in low-cost embedded systems.