A deep learning approach for drilling tool condition monitoring in Raiseboring

Abstract: Drilling tool wear can significantly affect the performance of the drilling operation and add extra cost to it. Accurate detection of drilling tool condition is very important for enabling proactive maintenance, minimizing downtime, and optimizing drilling processes.  This study investigates the possibility of detecting drilling tool condition of a Raisboring machine using drilling signals with deep learning methods. Given the current situation where the operators of the machine are responsible for detecting drilling abnormalities, which introduces bias and inconsistency to the process, it is crucial to develop an automated machine health monitoring system.  The objectives of this study were to explore the effectiveness of deep learning approaches in detecting drilling tool faults based on sensor data collected during drilling operations; as well as to find out which drilling signal is most effective for this problem.  The working dataset consists of labeled samples representing two drilling tool conditions (new and worn) and includes four channels: RPM, torque, feed force, and ground acceleration signals. To implement this, both time-domain features and frequency-domain features were extracted from the drilling signals and used as input to fully connected neural networks (FCNNs) and convolutional neural networks (CNNs). Performance metrics such as accuracy, precision, recall, and F1-score were used to assess the models’ performance. The results indicate that deep learning has great potential in detecting drilling tool condition. More specifically, the vibration signal, which yielded the highest results with the different algorithms.  The study highlights the potential of deep learning techniques for real-time, automated monitoring of drilling tool condition, enabling timely maintenance interventions and enhanced operationalefficiency.