人工智能方法用于熔喷过程在线检测的研究

熔喷生产最终产品质量的控制，对于过程优化具有重要的意义。产品质量的在线检测是过程监测与质量控制必不可少的。本文首次在熔喷系统中引入人工智能的研究方法，对熔喷非织造布的厚度与纤维直径进行在线预测。实测数据与人工神经网络的预测结果吻合较好，从而证实了人工神经网络用于模拟熔喷过程的可行性。网络的输入包括：挤出机温度、喷头温度、熔融体挤出速率、空气流率及接收距离。神经元计算的输出是纤维直径与熔喷非织布的厚度。文中进一步提出了将神经网络与专家系统相结合的研究路线，以实现熔喷过程的优化控制。

APPLICATION OF ARTIFICIAL INTELLIGENCE TO QUALITY CONTROL FOR MELT BLOWN PROCESS

Contrul of final product quality in the melt blown system is of great significance for the process optimization.On line measurement is essential for process monitoring and quality control.In this paper ,the artificial intellingence (AI) is fist applied to model the melt blown process and on -line predict the fibre diameter and the thickness of nonwovens The feasibifity for the application fo neural networks to melt blown process ins successfully demonstrated through comparison of the experimental data and the predicting results.The network inputs include extruder temperature,die temperature ,melt flow rate,air flow rate, die to-collector distance.The outputs of fibre diameter and product thickness are obtained by neural computing.Further work is discussed to combine the expert system with the neural network for the optimum control of a melt blown process.