Aus der Branche

Zurücksetzen
4 Ergebnisse
(c) BTMA
22.03.2023

BTMA welcomes digital dyeing and finishing company Alchemie

Alchemie Technology is the latest company to join the British Textile Machinery Association (BTMA), as all of the organisation’s members gear up to showcase an array of new innovations at ITMA 2023 in Milan from June 8-14 this year.

Cambridge-headquartered Alchemie is the inventor of two technologies – EndeavourTM and NovaraTM.

The Endeavour digital dyeing system produces no wastewater and reduces water consumption by up to 95% compared to traditional dyeing. The virtually waterless process delivers dyed fabric with high colour consistency and colour fastness and does not require post dyeing washing steps which leads to an energy reduction up to 85%. It can deliver any colour shade required and enables on-demand digital colour changeovers in any run length, from a few metres to several kilometres.

Alchemie Technology is the latest company to join the British Textile Machinery Association (BTMA), as all of the organisation’s members gear up to showcase an array of new innovations at ITMA 2023 in Milan from June 8-14 this year.

Cambridge-headquartered Alchemie is the inventor of two technologies – EndeavourTM and NovaraTM.

The Endeavour digital dyeing system produces no wastewater and reduces water consumption by up to 95% compared to traditional dyeing. The virtually waterless process delivers dyed fabric with high colour consistency and colour fastness and does not require post dyeing washing steps which leads to an energy reduction up to 85%. It can deliver any colour shade required and enables on-demand digital colour changeovers in any run length, from a few metres to several kilometres.

Similar energy savings can be achieved with the Novara precision finishing system which utilises a nozzle array to deliver finishing chemistry with millimetre resolution. Finishing chemistries penetrate deeply into the fabric due to the combination of high velocity liquid jetting and precisely-controlled vacuum and textile finishes are applied only where needed, reducing chemistry usage and enabling multi-functionality.

In the past year, Alchemie, backed by Swedish fashion giant H&M, has established a first demonstration hub at customer JSRTEX in Taiwan. It is now progressing plans to set up further centres at customer sites around the world.

Quelle:

BTMA / AWOL Media

09.01.2023

Shelton Vision AI: Maßgeschneiderte maschinelle Lernlösungen für die Textilindustrie

In den vergangenen drei Jahren hat ein spezielles KI-Entwicklungsteam des BTMA-Mitglieds Shelton Vision maßgeschneiderte maschinelle Lernlösungen für die Textilindustrie entwickelt.

Ziel war es, den Erkennungsprozess und die Genauigkeit bei der Benennung und Einstufung subtiler Mängel in Textilien in Echtzeit in Produktionsumgebungen zu verbessern.

Big-Data-Systeme von der Stange", wie sie hinter Technologien wie Gesichtserkennung und Google Maps stecken, lesen viele Tausende von Einzelbildern pro Sekunde und brauchen einfach zu lange, um genügend Daten für die Anforderungen in diesem speziellen Fall zu sammeln", sagt Mark Shelton, CEO und Geschäftsführer von Shelton Vision. "Die Textilindustrie zeichnet sich dadurch aus, dass sich die Produktpalette in vielen Bereichen innerhalb eines Jahres mehrmals ändert, und es ist nicht ungewöhnlich, dass innerhalb eines Jahres Hunderte, wenn nicht Tausende von verschiedenen Modellen auf der Grundlage präziser Einstellungen geprüft werden müssen".

Er fügt hinzu, dass es in der Regel mehr als 100 Fehlertypen gibt, die genau erkannt, klassifiziert (benannt) und in Echtzeit eingestuft werden müssen.

In den vergangenen drei Jahren hat ein spezielles KI-Entwicklungsteam des BTMA-Mitglieds Shelton Vision maßgeschneiderte maschinelle Lernlösungen für die Textilindustrie entwickelt.

Ziel war es, den Erkennungsprozess und die Genauigkeit bei der Benennung und Einstufung subtiler Mängel in Textilien in Echtzeit in Produktionsumgebungen zu verbessern.

Big-Data-Systeme von der Stange", wie sie hinter Technologien wie Gesichtserkennung und Google Maps stecken, lesen viele Tausende von Einzelbildern pro Sekunde und brauchen einfach zu lange, um genügend Daten für die Anforderungen in diesem speziellen Fall zu sammeln", sagt Mark Shelton, CEO und Geschäftsführer von Shelton Vision. "Die Textilindustrie zeichnet sich dadurch aus, dass sich die Produktpalette in vielen Bereichen innerhalb eines Jahres mehrmals ändert, und es ist nicht ungewöhnlich, dass innerhalb eines Jahres Hunderte, wenn nicht Tausende von verschiedenen Modellen auf der Grundlage präziser Einstellungen geprüft werden müssen".

Er fügt hinzu, dass es in der Regel mehr als 100 Fehlertypen gibt, die genau erkannt, klassifiziert (benannt) und in Echtzeit eingestuft werden müssen.

Hinzu kommt die Notwendigkeit, das zufällige Auftreten von "Nicht-Fehlern" wie losen Fäden, Fusseln und Staub auf der Oberfläche herauszufiltern - deren Anzahl höher sein kann als die der tatsächlichen Fehler - und es ist klar, dass ein maßgeschneidertes System erforderlich ist.
Das Entwicklungsteam hat daraufhin Metadaten zur Identifizierung von Defekteigenschaften erstellt, die eine erfolgreiche Identifizierung von Fehlern aus einer viel geringeren Anzahl von Bildern ermöglichen.

"Das System nutzt eine einzigartige Kombination aus maschinellem Lernen für das automatische Stiltraining und neuartigen Algorithmen für die Fehlererkennung, um qualitativ hochwertige Bilder für die KI-Software zur Klassifizierung und Klassifizierung von Fehlern in Echtzeit zu liefern", erklärt Shelton. "Aufgrund der inhärenten Unterschiede bei den Stoffmerkmalen - Rohstoffe, Konstruktion, Textur, Farbe und Veredelung - sowie der unterschiedlichen Produktqualitätsstandards in den Wertschöpfungsketten und der regionalen Unterschiede bei der Bezeichnung von Mängeln verwendet unsere KI-Engine Modelle, die für jedes einzelne Unternehmen oder jede Gruppe von Unternehmen oder Produktwertschöpfungskette erstellt werden."

Die KI-Modelle sind so aufgebaut, dass die Anwender sie mit ihren eigenen Daten füllen können, die vom Bildverarbeitungssystem erzeugt werden oder indem sie Fehlerbilder von einer anderen Bildgebungsquelle (z. B. einer Handykamera) erhalten.  

Das Auftreten von Defekten ist sporadisch, und viele Defekttypen treten nur selten auf, können aber schwerwiegende Folgen haben, wenn sie auftreten. Diese Szenarien machen deutlich, dass die KI-Engine schnell eingerichtet und in der Lage sein muss, mit begrenzten Datensätzen von typischerweise 30 bis 50 qualitativ hochwertigen Bildern pro Fehlerart genau zu arbeiten.

Quelle:

AWOL for British Textile Machinery Association (BTMA)

(c) BTMA
The James Heal AirPro air permeability tester
11.10.2022

BTMA: Testing equipment manufacturer James Heal celebrates 150th anniversary

Long-standing BTMA member James Heal is celebrating its 150th anniversary this year, the company’s formation dating back to 1872, when it was listed as an oil and tallow merchant and mill furnisher in Yorkshire, UK.

Today, as a testing equipment manufacturer for textiles and nonwovens, James Heal continues to expand its range, with a focus on making testing simple – most notably with the introduction of its Performance Testing collection of instruments, most recently the AirPro and HydroView systems.

AirPro
The new James Heal AirPro air permeability tester is used to test the resistance of the flow of air through woven, knitted and nonwoven textiles. Its software offers flexibility with standards and  comprehensive reporting options and different test head sizes are available, making it suitable for a range of applications and standards

Long-standing BTMA member James Heal is celebrating its 150th anniversary this year, the company’s formation dating back to 1872, when it was listed as an oil and tallow merchant and mill furnisher in Yorkshire, UK.

Today, as a testing equipment manufacturer for textiles and nonwovens, James Heal continues to expand its range, with a focus on making testing simple – most notably with the introduction of its Performance Testing collection of instruments, most recently the AirPro and HydroView systems.

AirPro
The new James Heal AirPro air permeability tester is used to test the resistance of the flow of air through woven, knitted and nonwoven textiles. Its software offers flexibility with standards and  comprehensive reporting options and different test head sizes are available, making it suitable for a range of applications and standards

HydroView
The HydroView hydrostatic head tester is meanwhile designed to measure the penetration of water in materials which have an end use that requires water resistance, such as those in the medical, geotextiles and nonwovens sectors. It is also proving essential in the testing of end-use applications for technical textiles, such as in protective gloves, diving dry suits and winter sports apparel, to fishing waders, roofing, tenting, ground sheets and more.

Quelle:

BTMA / AWOL Media

(c) BTMA by AWOL Media
08.09.2022

Shelton Vision presents new fabric inspection technique

A new fabric inspection technique for accurately detecting the most subtle of defects on patterned fabrics during high speed production has been developed by BTMA member Shelton Vision, of Leicester, UK.

The patent-pending system has been integrated into the company’s WebSpector platform and validated through factory trials on a purpose-built full scale in-house demonstration system with sophisticated fabric transport capabilities. As a result, a first system has already been ordered by a manufacturer of both plain and patterned fabrics, including camouflage, in Colombia. This follows the successful conclusion of a 21-month Innovate UK project in which techniques for the resolution of complex pattern deformations were developed by machine vision and computer scientists in the company, backed up by the machine vision and robotics department at Loughborough University.

A new fabric inspection technique for accurately detecting the most subtle of defects on patterned fabrics during high speed production has been developed by BTMA member Shelton Vision, of Leicester, UK.

The patent-pending system has been integrated into the company’s WebSpector platform and validated through factory trials on a purpose-built full scale in-house demonstration system with sophisticated fabric transport capabilities. As a result, a first system has already been ordered by a manufacturer of both plain and patterned fabrics, including camouflage, in Colombia. This follows the successful conclusion of a 21-month Innovate UK project in which techniques for the resolution of complex pattern deformations were developed by machine vision and computer scientists in the company, backed up by the machine vision and robotics department at Loughborough University.

Restrictions
Traditional methods for defect detection rely on human inspection which is ineffective, with detection rates under 65%, while the Shelton WebSpector machine vision system offers a sophisticated platform for automated defect detection of over 97%, but until now has been restricted to plain textiles.

While pattern matching and neural network approaches have previously been tried for patterned textiles, they have failed to provide a practical solution due to the extreme complexity associated with pattern matching on deformable substrates like textiles, as well as the time required to train a neural network for each pattern type.

Challenges
The challenge is that fabrics are not rigid and can be creased or stretched and are also subject to local distortion,” says Shelton Vision Managing Director and CEO Mark Shelton. “As a result, inspection without the technique we have developed, would lead to thousands of false positives. Our sophisticated pattern inspection software techniques ensure a clean image, allowing the detection of faults on fabrics running at speeds of up to a hundred metres a minute.”

The full system consists of:

  • A camera and lighting system for optimum image capture at high speed and associated image processing hardware.
  • Self-training software utilising statistical analysis to automate the system configuration for new textile products.
  • An advanced suite of defect detection algorithms for the detection of all textile defect types.
  • An AI-driven defect classification system which learns and automates defect naming in real time, as well as a real time defect grading capability based on client decision rules.
  • A system for recording and retrieving complete roll map images for subsequent review and quality control.

The generation of textile roll maps with complete defect data allows for an optimised textile cut plan, improved downstream processing and quality assurance.

Quelle:

BTMA by AWOL Media