Techniques for unveiling faults during knitting production

• Autor(es): Catarino, André P. ; Rocha, A. M. ; Monteiro, João L. ; Oliveira, Filomena
• Data: 2004
• Identificador Persistente: http://hdl.handle.net/1822/5768
• Origem: RepositóriUM - Universidade do Minho
• Assunto(s): Monitoring; Fault detection; Knitting machines; Signal processing; Pattern detection
• Tipo de Documento: Documento de conferência
• Idioma: Inglês

Descrição

Detection of faults during production of knitted fabric is crucial for improved quality and productivity. The yarn input tension is an important parameter that can be used for this purpose. This paper will present and discuss a computer-based monitoring system which was developed for the detection of faults and malfunctions during the production of weft knitted fabric, using the yarn input tension. In particular, it will present the method used to unveil the appearance of faults, based on two different approaches: comparison with a previously acquired waveform and a particular pattern matching technique - Average Magnitude Cross-Difference.