Machine learning based quality prediction of manufactured fiber optic cables
A machine learning and fiber technology, applied in machine learning, fiber mechanical structure, optics, etc., can solve problems such as time-consuming and quality degradation of loose-tube fiber optic cables
Pending Publication Date: 2022-05-06
美乐福挤塑公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Clearly, making such offline measurements on fabricated fiber optic cables requires additional resources and can be very time consuming
Furthermore, any degradation in the quality of manufactured loose-tube fiber optic cables may only be detected after a considerable delay
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0009] Loose tube fiber optic cable is a fiber optic cable especially suitable for harsh outdoor environments. In loose tube fiber optic cables, the glass fibers used to carry the optical signal are loosely encapsulated by a semi-rigid protective sleeve or tube (so-called loose tube or loose buffer tube). The unfilled space inside the loose tube is usually filled with a tube filling compound, such as waterproof gel or jelly, or waterproof yarn (yarn) or the like.
[0010] In many respects, the most critical stage in the manufacture of loose tube fiber optic cables is the secondary overmolding stage that takes place in the secondary overmolding line. During the secondary overmolding stage, fiberglass (and possibly tube filling compound) is inserted into a loose tube (usually made of plastic). Initially, the loose tube has a very high temperature when it is extruded in the secondary overmolding stage. As the loose tube cools, the loose tube shrinks or shrinks, causing the glas...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
According to one aspect, there is provided a method for monitoring the quality of a loose tube fiber optic cable during manufacture in a secondary sheath wire. Initially, a trained machine learning algorithm is maintained in a machine learning database that is used to calculate expected values for one or more quality metrics for the manufactured loose tube fiber optic cable based on values for one or more production process parameters of the secondary sheath wire. The computing system monitors one or more values of one or more production process parameters during operation of the secondary overcoating line and calculates one or more expected values of one or more quality metrics in real time during monitoring using a trained machine learning algorithm, the trained machine learning algorithm utilizes monitored values of one or more production process parameters as inputs. The computing system outputs at least one or more expected values of the one or more quality metrics to the user equipment.
Description
technical field [0001] The present invention relates to the manufacture of fiber optic cables, and in particular to providing means for evaluating the quality of fiber optic cables during manufacture. Background technique [0002] A loose tube fiber optic cable is a fiber optic cable in which the glass fibers used to carry the optical signal are loosely encapsulated by a semi-rigid protective sleeve or tube (so-called loose tube). The quality of loose tube fiber optic cables manufactured in so-called secondary coating lines is usually monitored by periodically performing off-line measurements of different key characteristics of the recently manufactured fiber optic cables. For example, the key properties to be measured may include fiber excess length, tube shrinkage, and fiber light attenuation. Clearly, performing such offline measurements on fabricated fiber optic cables requires additional resources and can be very time consuming. Furthermore, any degradation in the qua...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/08G06N20/00G02B6/44
CPCG06N3/084G06N20/00G02B6/4486G02B6/4479G02B6/4483G05B19/41875G05B13/0265Y02P90/02B29C48/05B29C48/156B29C48/34B29D11/00673G02B6/04G02B6/4484G06N3/08G05B19/058G06N3/044G06N3/045
Inventor 桑帕·奥尔哈宁米科·拉赫蒂尤西·汉希罗瓦詹尼·哈朱哈托
Owner 美乐福挤塑公司