中文摘要：

The existing optimized performance prediction of carbon fiber protofilament process model is still unable to meet the production needs. A way of performance prediction on carbon fiber protofilament was presented based on support vector regression( SVR) which was optimized by an optimization algorithm combining simulated annealing algorithm and genetic algorithm( SAGA-SVR). To verify the accuracy of the model,the carbon fiber protofilament production test data were analyzed and compared with BP neural network( BPNN). The results show that SAGA-SVR can predict the performance parameters of the carbon fiber protofilament accurately.

英文摘要：

The existing optimized performance prediction of carbon fiber protofilament process model is still unable to meet the production needs. A way of performance prediction on carbon fiber protofilament was presented based on support vector regression （SVR） which was optimized by an optimization algorithm combining simulated annealing algorithm and genetic algorithm （SAGA-SVR）. To verify the accuracy of the model, the carbon fiber protofilament production test data were analyzed and compared with BP neural network （BPNN）. The results show that SAGA-SVR can predict the performance parameters of the carbon fiber protofilament accurately.