CP-Ti-G2 (Commercially pure titanium grade-2) has become the preferred biocompatible material for various devices mainly used in orthopedic and dental implants and it is also used in aviation and aircraft. While CP-Ti deals with good ductility, higher stiffness, and fatigue resistance. The novelty of present research work was to create a rough surface on CP-Ti-G2 through the WEDM process. Further, this rough surface was used in the development of bone marrow cells on it. Propagation and diversity of bone marrow cells were applied in dental implant osteointegration applications. Six WEDM factors were analyzed through the BBD design of the experiment. 54 trial experiments were conducted to observe the MRR and SR output responses. After machining, surface topography was examined through SEM and EDX. ANOVA was applied to analyze the significance of factors. It was observed that POT (pulse on time), POFT (pulse off time), PC (peak current), and SGV (spark gap voltage) are the most significant factors. The WEDM factors have also been significantly deteriorating the microstructure of machined samples remarkably deeper, wider craters, globules of debris, and micro cracks. A multi-objective optimization ‘desirability’ function was applied to obtain the optimal solutions by numerical and supervised machine learning algorithms. They lead to the reflection of parametric machine learning algorithms to surmise about the effectiveness of WEDM process. The results show a good agreement between actual and predicted values.

CP-Ti-G2（商业纯钛 2 级）已成为主要用于骨科和牙科植入物的各种设备的首选生物相容性材料，也用于航空和飞机。而 CP-Ti 则具有良好的延展性、更高的刚度和抗疲劳性。当前研究工作的新颖之处在于通过 WEDM 工艺在 CP-Ti-G2 上创建粗糙表面。此外，这个粗糙的表面被用于在其上发育骨髓细胞。骨髓细胞的增殖和多样性应用于牙种植体骨整合应用。通过实验的BBD设计分析了六个线切割因素。进行了 54 次试验以观察 MRR 和 SR 输出响应。加工后，通过SEM和EDX检查表面形貌。应用方差分析来分析因素的显着性。据观察，POT（脉冲开启时间）、POFT（脉冲关闭时间）、PC（峰值电流）和 SGV（火花隙电压）是最重要的因素。WEDM 因素也显着恶化了加工样品的微观结构，显着更深、更宽的陨石坑、碎片小球和微裂纹。应用多目标优化“合意性”函数，通过数值和监督机器学习算法获得最优解。它们导致参数化机器学习算法的反映，以推测 WEDM 过程的有效性。结果显示实际值和预测值之间具有良好的一致性。和 SGV（火花隙电压）是最重要的因素。WEDM 因素也显着恶化了加工样品的微观结构，显着更深、更宽的陨石坑、碎片小球和微裂纹。应用多目标优化“合意性”函数，通过数值和监督机器学习算法获得最优解。它们导致参数化机器学习算法的反映，以推测 WEDM 过程的有效性。结果显示实际值和预测值之间具有良好的一致性。和 SGV（火花隙电压）是最重要的因素。WEDM 因素也显着恶化了加工样品的微观结构，显着更深、更宽的陨石坑、碎片小球和微裂纹。应用多目标优化“合意性”函数，通过数值和监督机器学习算法获得最优解。它们导致参数化机器学习算法的反映，以推测 WEDM 过程的有效性。结果显示实际值和预测值之间具有良好的一致性。应用多目标优化“合意性”函数，通过数值和监督机器学习算法获得最优解。它们导致参数化机器学习算法的反映，以推测 WEDM 过程的有效性。结果显示实际值和预测值之间具有良好的一致性。应用多目标优化“合意性”函数，通过数值和监督机器学习算法获得最优解。它们导致参数化机器学习算法的反映，以推测 WEDM 过程的有效性。结果显示实际值和预测值之间具有良好的一致性。