Surface roughness and machining accuracy are essential indicators of the quality of parts in milling. With recent advancements in sensor technology and data processing, the cutting force signals collected during the machining process can be used for the prediction and determination of the machining quality. Deep-learning-based artificial neural networks (ANNs) can process large sets of signal data and can make predictions according to the extracted data features. During the final stage of the milling process of SUS304 stainless steel, we selected the cutting speed, feed per tooth, axial depth of cut, and radial depth of cut as the experimental parameters to synchronously measure the cutting force signals with a sensory tool holder. The signals were preprocessed for feature extraction using a Fourier transform technique. Subsequently, three different ANNs (a deep neural network, a convolutional neural network, and a long short-term memory network) were applied for training in order to predict the machining quality under different cutting conditions. Two training methods, namely whole-data training and training by data classification, were adopted. We compared the predictive accuracy and efficiency of the training process of these three models based on the same training data. The training results and the measurements after machining indicated that in predicting the surface roughness based on the feed per tooth classification, all the models had a percentage error within 10%. However, the convolutional neural network (CNN) and long short-term memory (LSTM) models had a percentage error of 20% based on the whole-data training, while that of the deep neural network (DNN) model was over 50%. The percentage error for the machining accuracy prediction based on the whole-data training of the DNN and CNN models was below 10%, while that of the LSTM model was as large as 20%. However, there was no significant improvement in the results of the classification training. In all the training processes, the CNN model had the best analytical efficiency, followed by the LSTM model. The DNN model performed the worst.

About 30–50% of oral cancer patients require mandibulectomy and autologous fibula reconstruction. Autograft is the gold standard choice because of its histocompatibility; however, it requires additional surgery from the patient and with possible complications such as loss of fibula leading to calf weakening in the future. Allograft and xenograft are alternatives but are susceptible to immune response. Currently, no personalized bone xenografts are available in the market for large fascial bone defects. In addition, a large-sized complex shape bone graft cannot be produced directly from the raw material. We propose the use of porcine bones with 3D CAD/CAM carving to reconstruct a personalized, wide range and complex-shaped bone. We anticipate that patients can restore their native facial appearance after reconstruction surgery. Supercritical CO₂ (SCCO₂) technology was employed to remove the cells, fat and non-collagenous materials while maintaining a native collagen scaffold as a biomedical device for bone defects. We successfully developed 3D CAD/CAM carved bone matrices, followed by SCCO₂ decellularization of those large-sized bones. A lock-and-key puzzle design was employed to fulfil a wide range of large and complex-shaped maxillofacial defects. To conclude, the 3D CAD/CAM carved bone matrices with lock and key puzzle Lego design were completely decellularized by SCCO₂ extraction technology with intact natural collagen scaffold. In addition, the processed bone matrices were tested to show excellent cytocompatibility and mechanical stiffness. Thus, we can overcome the limitation of large size and complex shapes of xenograft availability. In addition, the 3D CAD/CAM carving process can provide personalized tailor-designed decellularized bone grafts for the native appearance for maxillofacial reconstruction surgery for oral cancer patients and trauma patients.

Blisks are not easily machined because of their complex curved surfaces and the high-precision requirements of surface machining. Lightweight alloy materials with superior mechanical properties, such as titanium alloy and stainless steel, are popular material choices for manufacturing turbine blisks. However, these materials are difficult to cut and require advanced machine tools and processing technologies. Because aerospace-grade parts are complex and require precise dimensions and high surface quality, machining these parts by using three-axis machine tools is difficult. Using multi-axis machine tools for the machining of complex parts can cause the achievement of precise dimensions, high quality, and the required surface roughness. In the multi-axis machining of aerospace blisks, tool path planning is considered the most difficult task. In this study, we examined the implementation of five-axis machining technology for the manufacturing of an aerospace blisk. Processing modules from computer-aided manufacturing software (NX10) are used for five-axis tool path generating, and 5-axis machining numerical control code is generated through post-processing calculations. Solid cutting simulation software (VERICUT) is used to verify whether tools exhibited overcut or interference. A sensory tool holder (SPIKE) is used to analyze cutting force during the rough machining of a blisk. The sensory tool holder is also adopted to evaluate the spindle runout and tool holding status. In order to obtain a consistent cutting allowance and surface accuracy, the online measurement system is used to generate a measurement path for semi-finish and finish machining. The real cut is performed with SUS304 and demonstrates the practical application. Through improvements in process planning, the machining time was shortened by 16.5%.

Blisks subjected to rough machining for channel creation must undergo finishing processes, and such processes must achieve the required tolerance limits. A high-quality surface finish and predictable long tool life are critical for the finish milling of blisks. Accordingly, the aim of this study was to optimize parameters for the finish machining of an Inconel 718 alloy monolithic blisk. Ball-cone mills were used to machine the blade surface at a constant depth. A sensory tool holder was used to collect cutting force signals during machining, and a digital microscope was used to examine tool wear. The surface texture measuring instrument was used to measure blisk blade surface roughness to evaluate processing quality. This study manipulated two cutting parameters, namely cutting speed and feed per tooth, and investigated their effects. The relationship between cutting conditions and machining efficiency was analyzed. According to the experimental results, we identified a set of optimal parameters at effective cutting speeds of 46.53 m/min, feed per tooth of 0.1 mm/tooth, and depth of cut of 0.05 mm for marginal tool wear and fast cutting speeds. Then the corresponding tool life was estimated by using the derived parameters.

Blisks subjected to rough machining for channel creation must undergo finishing processes, and such processes must achieve the required tolerance limits. A high-quality surface finish and predictable long tool life are critical for the finish milling of blisks. Accordingly, the aim of this study was to optimize parameters for the finish machining of an Inconel 718 alloy monolithic blisk. Ball-cone mills were used to machine the blade surface at a constant depth. A sensory tool holder was used to collect cutting force signals during machining, and a digital microscope was used to examine tool wear. The surface texture measuring instrument was used to measure blisk blade surface roughness to evaluate processing quality. This study manipulated two cutting parameters, namely cutting speed and feed per tooth, and investigated their effects. The relationship between cutting conditions and machining efficiency was analyzed. According to the experimental results, we identified a set of optimal parameters for marginal tool wear and fast cutting speeds and then estimated the corresponding tool life by using the derived parameters.

Turbomolecular pumps (TMPs), boasting advantageous high pumping rates, stability, and cleanliness, have been widely used in the semiconductor and photoelectric industries. In the aviation industry, the lightweight rotors of turbomolecular pumps can enhance the performance of generators. With technological advancements and increased industrial performance demands, various designs for turbomolecular pump rotors utilizing twisted and curved blade surfaces have been proposed. This increase in complexity runs parallel with machining difficulties. Contact and noncontact reverse engineering equipment was used to reconstruct a computer-aided design (CAD) model of turbomolecular pump rotors. The machining of thin and long blades, cutting tool arrangement, and toolpath was planned. Postprocessing was used to convert the toolpath into numerical control (NC) programming codes, which were combined with solid model cutting simulation software to verify the efficacy of the generated machining NC program for turbomolecular pump rotors. A five-axis horizontal machining center (CK type) with aluminum alloy AL6061-T6 was used to conduct actual machining tests measuring the efficiency of the machining methods. The rapid prototyping (RP) blocks can be creatively used as a jig and stuffed between the blades to suppress the chatter problem during processing, and the roughness of the surface of the blades can be reduced from 4.4 μm to 1.3 μm. The processed rotor can meet the flow test requirements, and the overall research can be used as a reference for the industry.