US 12,189,356 B2
Machine-learning-based quality prediction of manufactured fiber optic cable
Samppa Orhanen, Vantaa (FI); Mikko Lahti, Vantaa (FI); Jussi Hanhirova, Vantaa (FI); and Janne Harjuhahto, Vantaa (FI)
Assigned to Maillefer Extrusion Oy, Vantaa (FI)
Appl. No. 17/642,424
Filed by MAILLEFER EXTRUSION OY, Vantaa (FI)
PCT Filed Sep. 8, 2020, PCT No. PCT/FI2020/050574
§ 371(c)(1), (2) Date Mar. 11, 2022,
PCT Pub. No. WO2021/053265, PCT Pub. Date Mar. 25, 2021.
Claims priority of application No. 20195790 (FI), filed on Sep. 20, 2019.
Prior Publication US 2022/0342379 A1, Oct. 27, 2022
Int. Cl. G05B 19/05 (2006.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06N 20/00 (2019.01)
CPC G05B 19/058 (2013.01) [G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06N 20/00 (2019.01)] 19 Claims
OG exemplary drawing
 
1. A method for monitoring and controlling quality of loose tube fiber optic cable during manufacture in a secondary coating line, the method comprising:
maintaining, in a machine-learning database, a trained machine-learning algorithm for calculating expected values of one or more quality metrics of the loose tube fiber optic cable manufactured in the secondary coating line based on values of one or more production process parameters of the secondary coating line;
monitoring, by a computing system, one or more values of the one or more production process parameters of the secondary coating line during running of the secondary coating line;
calculating, by the computing system, in real-time during the monitoring, one or more expected values of the one or more quality metrics using the trained machine-learning algorithm, wherein monitored values of the one or more production process parameters are used as an input of the trained machine-learning algorithm;
outputting, by the computing system, at least the one or more expected values of the one or more quality metrics to a user device; and,
causing, by the computing system, adjusting, in real-time during the monitoring, the one or more process parameters to match the one or more expected values of the one or more process parameters.