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.

Peri-implantitis is a common implant-supported prosthesis complication, and marginal bone loss affects the stress distribution in implant systems. This three-dimensional finite element analysis study investigated how bone loss affects the implant assembly; in particular, models including two implant systems with different connection systems (external or internal hexagon), abutment materials (titanium or zirconia), and bone loss levels (0, 1.5, 3, or 5 mm) were created. We observed that the maximum von Mises stress distinctly increased in the groups with bone loss over 1.5 mm compared to the group without bone loss, regardless of the connection system or abutment material used. Moreover, the screw stress patterns with bone loss progression were determined more by the connection systems than by the abutment materials, and the magnitude of the stress on the fixture was affected by the connection systems with a similar pattern. The highest stress on the screw with the external hexagon connection system increased over 25% when bone loss increased from 3 to 5 mm, exceeding the yield strength of the titanium alloy (Ti–6Al–4V) when 5 mm bone loss exists; clinically, this situation may result in screw loosening or fracture. The highest stress on the fixture, exceeding the yield strength of pure titanium, was noted with the internal hexagon connection system and 1.5 mm bone loss. Titanium and zirconia abutments—both of which are clinically durable—presented similar screw and fixture stress patterns. Therefore, clinicians should pay more attention to maintaining the peri-implant bone to achieve the long-term stability of the implant-supported prosthesis.

The type of implant-abutment connection is one of the factors influencing the distribution of occlusal forces. This study aims to investigate the biomechanical performance of the mandibular all-on-4 treatment with different implant–abutment connections. Two connection types with 30° abutments and 18-mm implant fixtures were chosen for the posterior implants of the all-on-4 assembly. For the external hexagon connection (EHC) group, the implants with 4 mm in diameter were used. For the internal hexagon connection (IHC) group, we selected implants with 4.3 mm in diameter. A vertical force of 190 N was applied to the cantilever region. The FEA results indicated that the most stressed region in the two groups was prosthetic screws, followed by multi-unit abutments (MUAs). The lowest values of von Mises stress were both observed on the bone. The peak stress value of the implant screw and implant fixture in the EHC group were 37.75% and 33.03% lower than the IHC group, respectively. For stress distribution patterns, the load force tended to be concentrated at locations where components were interconnected. The EHC and IHC are clinically durable under the tested loading conditions, but the prosthetic screws and MUAs can be the weak point on the posterior implant within the mandibular all-on-four assembly. The peak stress values of implant screw and implant fixture in the EHC groups were lower than the IHC group.

Three groups of zirconia abutments (n = 5) consisting of different connection designs or manufacturers were investigated (All-Zr, ASC-Zr, and AM-Zr groups). All-electric dynamic test instruments were used to place static loading on a specimen with a crosshead speed set at 1 mm/min. A Kruskal–Wallis test and a post hoc Mann–Whitney U test were used for statistical evaluation. The mean fracture resistance was 252.37 ± 82.79 N for the All-Zr group, 384.62 ± 45.24 N for ASC-Zr group, and 361.83 ± 90.31 N for the AM-Zr group. The difference of fracture resistance between the three groups was marginally significant (Kruskal–Wallis test, p = 0.054), with the ASC zirconia abutment tending to have higher fracture resistance than the full zirconia abutment. The modes of failure among the three types of abutments are different. The All-Zr group showed an oblique fracture line starting from the buccal aspect at the region of the implant platform. While the ASC-Zr and AM-Zr groups showed a relatively horizontal fracture line with a greater distance from the implant platform. The titanium inserts cannot significantly improve the fracture resistance of the zirconia abutment. However, they may alter the modes of failure, allowing buccal fracture surfaces of the zirconia abutments to be placed away from the implant platform, thereby protecting the implant–abutment connection.

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.

The geometry of implants plays a crucial role in the success of All-on-Four treatments for the lower jaw. This study builds upon prior research by evaluating the biomechanical performance of implant-supported prostheses in full-arch fixed dental restorations, specifically focusing on different implant lengths and connection types in cases of mild atrophic resorption of the mandible. Four groups were analyzed using finite element analysis (FEA): We utilized 13 or 18 mm posterior 17-degree tilting implants, each paired with two kinds of abutment connections. The external hexagon connection (EHC) group utilized 4 mm diameter implants, while the internal hexagon connection (IHC) group employed 4.3 mm diameter implants. A vertical force was applied to the cantilever region located at the distal side of the posterior implant. The maximum stress regions were observed in prosthetic screws and multi-unit abutments (MUAs) across all groups, with the lowest von Mises stress values noted in the bone. Stress peaks for implant screws and fixtures in the 13 mm group were 19.98% and 11.42% lower, respectively, compared to the IHC group. Similarly, in the 18 mm group, stress peaks were reduced by 33.16% and 39.70% for the EHC group compared to the IHC group. The stress levels on all components remained below the ultimate strength of the titanium alloy. For the same implant lengths, the stress in the prosthetic screw, MUAs, implant screw, and implant fixture positions was lower in the EHC group. When implant length was increased, a decrease in stress levels was observed in the implant screw and fixture of the EHC group and only in the implant screw of the IHC group. However, an increase in stress was noted in the prosthetic screw and MUAs for both groups.