Surface roughness, which has a significant influence on fatigue strength and wear resistance, is an important technical parameter. In practical machining, it is unstable and may be larger than the acceptable surface roughness due to unstable machining process. This will seriously deteriorate the surface performance of the workpieces. Therefore, an effective surface roughness stabilization method is of great significance to improve machining efficiency and reduce machining cost. In this paper, a surface roughness stabilization method is proposed and illustrated by taking five-axis machining as an example. A self-learning surface roughness prediction model based on Pigeon-Inspired Optimization and Support Vector Machine is firstly constructed and its prediction error is only 8.69% in the initial stage. This model has the self-learning ability that the prediction accuracy can be improved with the increase of training data. Furthermore, a machining parameters self-adaption adjustment method based on digital twin is proposed to make the machined surface quality stable. In this method, considering the feasibility of practical machining operation, the cutter posture (i.e. lead angle and tilt angle in five-axis machining) and spindle speed are selected as the adjustable parameters. When the predicted surface roughness doesn’t meet the requirements, the Gradient Descent algorithm is applied to recalculate the new parameters for adjustment. According to the experimental results, the proposed method can stabilize surface roughness and improve the surface quality, which is vital for the precision manufacturing of complex workpiece. Meanwhile, it also greatly improves the intelligence level of manufacturing and production.

对疲劳强度和耐磨性有重要影响的表面粗糙度是重要的技术参数。在实际加工中，由于加工过程不稳定，它是不稳定的，并且可能大于可接受的表面粗糙度。这将严重降低工件的表面性能。因此，有效的表面粗糙度稳定化方法对提高加工效率和降低加工成本具有重要意义。本文提出了一种表面粗糙度稳定化方法，并以五轴加工为例进行了说明。首先建立了基于Pigeon启发式优化和支持向量机的自学习表面粗糙度预测模型，其初始预测误差仅为8.69％。该模型具有自学习能力，可以随着训练数据的增加而提高预测精度。提出了一种基于数字孪生的加工参数自适应调整方法，以使加工表面质量稳定。在这种方法中，考虑到实际加工操作的可行性，选择刀具姿态（即五轴加工中的导程角和倾斜角）和主轴速度作为可调参数。当预测的表面粗糙度不符合要求时，将使用“梯度下降”算法重新计算新参数以进行调整。实验结果表明，该方法可以稳定表面粗糙度，提高表面质量，对于复杂工件的精密制造至关重要。与此同时，