In the process of drilling holes in workpieces, breakage of the drill bit presents a significant problem. If the drill breaks during the drilling process, the desired depth of the hole is not achieved, resulting in an incomplete machining state. Continuing with tapping operations in such an incomplete state can lead to the tap tool colliding with the unprocessed surface of the workpiece, potentially causing damage to the machine tool. To prevent this issue, it is effective to introduce a system that detects drill breakages in real-time and automatically stops the machine tool before transitioning to tapping operations. This system can prevent damage to the tap tool and the machine tool.
In this study, we verified a method to detect drill breakages by monitoring the current flow in the motor of the machine tool. Through this approach, we aim to capture the unique current changes that occur during drill breakages, thereby improving the precision and safety of the machining process.
To detect drill breakages during drilling operations, an advanced anomaly detection algorithm was developed for analyzing the electrical current data. Clamp-style current sensors were installed on each motor of the machine tool, and multiple drilling cycles were conducted on the workpiece. The electrical current data from each cycle were collected for analysis.
Figure 3 displays the overlaid electrical current data from each drilling cycle. In the figure, the blue and red lines represent the electrical current data from cycles where drilling was completed normally and where the drill bit broke, respectively. Focusing on the electrical current data around 4 seconds after the start of processing, it is observed that the current during normal operations forms a trapezoidal shape, whereas the current during a drill breakage takes a triangular shape. This indicates that a sudden increase in load occurs at the moment of drill breakage.
Furthermore, it was observed that the electrical current data during drill breakage becomes flat after about 5 seconds. This suggests that the cutting load disappears due to the drill breakage, resulting in a decreased workload for the motor of the machine tool. Capturing this characteristic suggests the possibility of detecting drill breakages.
Additionally, upon applying the developed anomaly detection algorithm, a significant increase in the anomaly level was confirmed in the processing cycles where drill breakages occurred, demonstrating the effectiveness of the algorithm.
The method developed in this study, which analyzes the current data from servo motors, is limited to detecting molding defects related to the filling and metering processes, as it cannot utilize information from the holding pressure stage. Compared to internal pressure sensors, the information that can be extracted is limited; however, it has been demonstrated that the detection of short shots is possible by extracting unique feature sets. This study marks the first successful detection of short shots using a configuration that installs a clamp-type current sensor on the servo amplifier of the injection molding machine.
The greatest advantage of this method is that it allows for the easy initiation of short shot detection without the need for modifying the mold. This enables manufacturers to reduce costs while conducting efficient and rapid quality control.
Moving forward, we will endeavor to develop new technologies that cater to a broader range of defect detection in molding processes.
