Aus der Branche

Zurücksetzen
4 Ergebnisse
Photo: Calderdale College
02.08.2023

BTMA: Apprenticeship Training Course for Textile Engineering Technicians in UK

West Yorkshire is to have a first-of-its-kind apprenticeship training course for textile engineering technicians, reflecting a resurgence in the industry locally, and more generally in the UK.

Calderdale College has partnered with the Textile Centre of Excellence (TCoE) and the British Textile Machinery Association (BTMA) to develop the bespoke Level 3 apprenticeship course which will start in September 2023.

Engineering Technician apprentices at Calderdale College will receive training from the TCoE, helping them to develop the engineering maintenance skills required to close the skills gap in West Yorkshire’s textile industry.

While the region has been a flourishing hub for textile excellence since the 19th century and is being revitalised through digitalization and the localisation of supply chains, its success is currently being hindered by an ageing workforce and high staff turnover.

West Yorkshire is to have a first-of-its-kind apprenticeship training course for textile engineering technicians, reflecting a resurgence in the industry locally, and more generally in the UK.

Calderdale College has partnered with the Textile Centre of Excellence (TCoE) and the British Textile Machinery Association (BTMA) to develop the bespoke Level 3 apprenticeship course which will start in September 2023.

Engineering Technician apprentices at Calderdale College will receive training from the TCoE, helping them to develop the engineering maintenance skills required to close the skills gap in West Yorkshire’s textile industry.

While the region has been a flourishing hub for textile excellence since the 19th century and is being revitalised through digitalization and the localisation of supply chains, its success is currently being hindered by an ageing workforce and high staff turnover.

Through adapting the engineering training at Calderdale College to address the current requirements of the textile industry, the unique new course will ensure the passing on of vital know-how and good practice aligned with the new skills demanded by Industry 4.0 and automation.

Collaborative Apprenticeships
Calderdale College has developed the programme over a two-year period through close collaboration with the TCoE and the BTMA, as well as through consultation with British heritage weaver AW Hainsworth and a number of other local textile companies.

The course launch follows on closely from the success of the Collaborative Apprenticeships project launched in 2022 at Calderdale College. To date, this has seen the college engage with over 100 local employers on the benefits of increasing the quantity and improving the quality of the apprenticeships that they offer, as well as encouraging others to introduce apprenticeships for the first time.

“Over the years, we’ve seen how beneficial apprenticeships can be for several sectors, particularly in terms of helping businesses to retain staff and ensuring that they have a steady flow of skilled workers coming in,” said Claire Williams, head of employer engagement at Calderdale College. “Having identified that employers in the textile manufacturing industry were struggling to find apprenticeship training that was designed around their needs, we knew that alongside employers and our partners, we needed to satisfy this critical gap in the market. We hope that this programme will act as a leading example for the rest of the industry to follow.”

Quelle:

British Textile Machinery Association

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