Study of Glass Fiber Textile Control Based on Image Processing and Neural Network

ABSTRACT

Research on weft fiber cut problems of glass fiber has improved the efficiency of textile production. Glass fiber textile machine is a major producer machine of glass fiber cloth. In production, detection of textile machines weft usually adopts the contact type, requiring the weft to maintain a certain pressure on the sensor. This way can make the glass fiber weft fluff, and produce glass fiber dust, and may also cause harm to the human health and damage to the textile machine. Using video monitoring method detection weft, speed and image identification rate will directly affect the stability of the system. This paper presents a detection method of glass fiber textile’s weft fiber cut based on neural network, selecting multiple features which are directly related to the image with the weft as neural network input vector, through repeated training samples to remove tiny ripple effects which are caused by weft textile jitter, overcome the traditional method detection accuracy is not high. Experiments show that this method can effectively avoid the weft jitter, making accurate detection of the weft fiber cut, and achieving satisfactory results.

Keywords: