Tool wear monitoring is necessary for cost reduction and productivity improvement in the machining industry. Machine learning has been proven to be an effective means of tool wear monitoring. Feature engineering is the core of the machining learning model. In complex parts milling, cutting conditions are time-varying due to the variable engagement between cutting tool and the complex geometric features of the workpiece. In such cases, the features for accurate tool wear monitoring are tricky to select. Besides, usually few sensors are available in an actual machining situation. This causes a high correlation between the hand-designed features, leading to the low accuracy and weak generalization ability of the machine learning model. This paper presents a tool wear monitoring method for complex part milling based on deep learning. The features are pre-selected based on cutting force model and wavelet packet decomposition. The pre-selected cutting forces, cutting vibration and cutting condition features are input to a deep autoencoder for dimension reduction. Then, a deep multi-layer perceptron is developed to estimate the tool wear. The dataset is obtained with a carefully designed varying cutting depth milling experiment. The proposed method works well, with an error of 8.2% on testing samples, which shows an obvious advantage over the classic machine learning method.

Due to the enclosed chip evacuation space in deep hole drilling process, chips are accumulated in drill flutes as drilling depth increases, resulting in the increase of drilling torque and lead to drill breakage. Peck drilling is a widely used method to periodically alleviate the drilling torque caused by chip evacuation; the drilling depth in each step directly determines both drill life and machining efficiency. The existing drilling depth optimization methods face problems including low accuracy of the prediction model, the hysteresis of signal diagnosis, and onerous experiments. To overcome these problems, a novel drilling depth optimization method for peck drilling based on the iterative learning optimization is proposed. First, the chip evacuation torque coefficients (CETCs) are introduced into the chip evacuation torque model to simplify the model for learning. Then, the effect of chip removal process in peck drilling on drilling depth is analyzed. The extended depth coefficient by chip removal (EDCbCR) is introduced to develop the relationship between the extended depth in each drilling step and drilling depth. On the foundation of the modeling above, an iterative learning method for drilling depth optimization in peck drilling is developed, in which a modified Newton's method is proposed to maximize machining efficiency and avoid drill breakage. In experiments with different cutting parameters, the effectiveness of the proposed method is validated by comparing the optimized and measured results. The results show that the presented learning method is able to obtain the maximum drilling depth accurately with the error less than 10%.