基于SVM的柔性生产模式下生产过程质量智能预测

Intelligent prediction for process quality of flexible manufacturing system based on SVM

提出了一种基于支持向量机(SVM)的柔性生产模式下生产过程质量智能预测方法.该方法基于结构风险最小化,能较好地解决小样本学习问题,避免了人工神经网络等智能方法在训练时所表现出来的过学习、泛化能力弱等缺点.实验表明:该方法具有预测精度高、速度快、容易实现等优点,为柔性生产模式下的生产过程质量预测提供了一种切实有效的方法.

Traditional method for quality prediction of producing process can＇t fit flexible manufacturing system （FMS） well, which can only make products in small batch. It is difficult for this method to predict the future product quality of FMS quickly and accurately. The paper puts forward a new intelligent prediction method based on support vector machine （SVM） for process quality of FMS. it can solve the small-batch learning better and avoid such disadvantages as over-training, weak normalization capability, ect., which artificial neural networks prediction has, because it is based on structure risk minimization. The application example shows that the model is higher in accuracy and learning speed, easier to realize and so on. So, it is more suitable for quality prediction of producing process of FMS.