基于贝叶斯网络的数控机床热误差建模

Thermal Error Modeling of NC Machine Tools Based on Bayesian Networks

为消除数控机床热误差对加工精度的影响,提出基于贝叶斯网络的数控机床热误差建模方法。贝叶斯网络热误差模型用图论的语言系统地描述产生热误差的各种因素间的因果依赖关系,在此基础上进行概率推理,按照概率论的原则对各因素间的内在关联进行分析、利用,降低推理的计算复杂度,最终根据热误差值的区域概率分布得到建模结果。模型兼顾先验知识和样本数据,随着数据的更新,模型能够反映机床加工过程中的工况变化,不断修正建模结果。对数控加工中心进行建模实验,结果表明,基于贝叶斯网络的建模方法具有表达直观、建模精度高和自适应的特点,能有效描述机床热误差。

In order to eliminate the influence ot the thermal error on machining precision ot me workpieee, a novel method based on Bayesian networks （BN） was utilized to implement error compensation. The method described causal relationships of factors inducing thermal deformation by graph theory and estimated the thermal error by Bayesian statistical techniques. Due to well combination of domain knowledge and sampled data, the BN method could adapt to the change of running state of machine, and obtain satisfactory prediction accuracy. Experiments on spindle thermal deformation were conducted to evaluate the model performance. Experimental results indicate that the BN method performs far better than that by least squares analysis in terms of model estimation accuracy.