Problem Use Case
- An Israel based tier-2 fabric manufacturing unit wanted to address the fault management in their plant.
- They wanted to get an indication about the changes that should be made in the production line to get the higher fabric quality.
- They also wanted to know by doing some sort of comparison between the fabric produced online and a standard fabric sheet and provide output to the line operator whether the fabric is within the production standard.
- Canopus asked for the data that has been generated by the manufacturer during the non-woven fabric manufacturing in the continuous production lines and also the data from the controllers that controls almost every parameters in the production line.
- Canopus performed the analysis on the large amount of data stored on the controllers and developed a machine learning model in order to provide the prescriptive measures to the line operator to make necessary changes in the production line in order to produce the higher quality fabric.
- Canopus also performed deep learning on the images obtained from the production line cameras of images with defects and developed a comparative analysis model to provide an analysis output to the line operator between the comparative quality of the standard fabric and the fabric created online.
- Canopus achieved 89% accuracy in order to provide the corrective measures to the line operators based on their past data.