Corner accuracy occurring in wire electrical discharge machining (WEDM) is influenced by machining parameters such as wire vibration, wire lag, and excessive discharge, etc. This study proposed an optimization method which can improve the corner accuracy of the WEDM process. The parameters of pulse-on time (ON), pulse-off time (OFF), open circuit voltage (OV), servo voltage (SV), wire tension (WT), and flushing pressure (WA) were selected to investigate the influences of the major parameters on the machining accuracy in this study. Three different corner angles of 30°, 60°, and 90° were chosen for the verification experiments. The response surface methodology (RSM) was used to analyze and investigate the effect of each parameter on the corner error. After integrating the response surface value and algorithm, an optimization system with a friendly human–machine interface, which has a procedure guiding function, was developed with use of C# language. The system can predict the corner error and also recommend optimal machining parameters for smaller corner error and faster machining speed based on the original machining parameters. Finally, cutting experiments were conducted to verify the proposed system, and the results showed that the proposed method can effectively improve the corner accuracy by 39%, 20%, and 33%.

Plastic materials can absorb moisture from the atmosphere even after drying. This absorbed moisture can cause many defects in the molding process. Conventionally, a dryer is used to reduce the moisture content. However, the use of a drying unit involves huge daily power consumption and is also time-consuming. Therefore, this study proposed a new method to reduce the impact of moisture on molded product part quality through the optimization of plasticization parameters while reducing drying time. Two plastic materials, polyurethane (TPU) and polycarbonate (PC), were used for the experimental verification. Key plasticization parameters, including back pressure, screw rotation speed, and barrel temperature were chosen; their influence was investigated by the design of experiments (DOE). Moisture-induced defects, such as air bubble area, part surface gloss, and appearance were measured and correlated with the plasticization parameters. It was found, after optimization via a three-level DOE and factorial design multivariate statistical analysis using TPU, that the gloss (GU) of the PC part without drying was very close to that (98.4 GU) of the fully dried PC. The proposed methodology may help molders to improve production efficiency and achieve cost savings.

This study proposes a hybrid optimization method which can help users to find optimal cutting parameters which will provide better efficiency and lower power consumption for a milling process. Empirical models including performance-power consumption characteristic curves of servo motors were built, and an optimization algorithm adopting the empirical models with procedure guiding function was developed. The empirical models were built based on the measurements from planned machining experiments with different combination of machining parameters including spindle speed, feedrate, and chip load, etc. After integrating the models and algorithm, an optimization system with human machine interface, which has procedure guiding function, was developed. The system can recommend optimal machining parameters for a milling process for shorter machining time and lower electricity costs based on the original machining parameters. Finally, cutting experiments were conducted to verify the proposed system, and the results showed that the proposed method can effectively enhance efficiency by 42.06% and save 34.74% in machining costs through reducing machining time and electrical power consumption.

Computer Numeric Control (CNC) five-axis milling plays a significant role in the machining of precision molds and dies, aerospace parts, consumer electronics, etc. This research aims to explore the potential of the machine learning (ML) technique in improving energy efficiency during the CNC five-axis milling process for sustainable manufacturing. The experiments with various machining parameters, forms of toolpath planning, and dry cutting conditions were carried out, and the data regarding energy consumption were collected simultaneously. The relationship between machine parameters and energy consumption was analyzed and built. Subsequently, a machine learning algorithm was developed to classify test methods and identify energy-efficient machining strategies. The developed algorithm was implemented and assessed using different classification methods based on the ML concept to effectively reduce energy consumption. The results show that the Decision Tree and Random Forest algorithms produced lower Root Mean Square Error (RMSE) values of 4.24 and 4.28, respectively, compared to Linear, Lasso, and Ridge Regression algorithms. Verification experiments were conducted to ascertain the real-world applicability and performance of the ML-based energy efficiency approach in an operational CNC five-axis milling machine. The findings not only underscore the potential of ML techniques in optimizing energy efficiency but also offer a compelling pathway towards enhanced sustainability in CNC machining operations. The developed algorithm was implemented within a simulation framework and the algorithm was rigorously assessed using machine learning analysis to effectively reduce energy consumption, all while ensuring the accuracy of the machining results and integrating both conventional and advanced regression algorithms into CNC machining processes. Manufacturers stand to realize substantial energy savings and bolster sustainability initiatives, thus exemplifying the transformative power of ML-driven optimization strategies.