From the Sector

Reset
4 results
09.01.2023

Shelton Vision AI: Tailored machine learning solutions for the textiles industry

Over the past three years, a dedicated AI development team at BTMA member Shelton Vision has been developing tailored machine learning solutions for the textiles industry.

The aim has been to elevate the detection process and the accuracy of naming and grading subtle defects in textiles, in real time within production environments.

“Big Data ‘off-the-shelf’ systems such as those behind technolgies like facial recognition and Google Maps involve reading many thousands of single images each second and simply take too long to accumulate sufficient data for what’s required in this specific case,” says Shelton Vision CEO and Managing Director Mark Shelton. “A feature of the textile industry is that in many sectors, the product range changes several times within a year and it is not uncommon to have to inspect hundreds, if not thousands of different styles in a year based on precise settings.”

In terms of defect types, he adds, there may typically be over 100 that need to be accurately detected, classified (named) and graded in real time.

Over the past three years, a dedicated AI development team at BTMA member Shelton Vision has been developing tailored machine learning solutions for the textiles industry.

The aim has been to elevate the detection process and the accuracy of naming and grading subtle defects in textiles, in real time within production environments.

“Big Data ‘off-the-shelf’ systems such as those behind technolgies like facial recognition and Google Maps involve reading many thousands of single images each second and simply take too long to accumulate sufficient data for what’s required in this specific case,” says Shelton Vision CEO and Managing Director Mark Shelton. “A feature of the textile industry is that in many sectors, the product range changes several times within a year and it is not uncommon to have to inspect hundreds, if not thousands of different styles in a year based on precise settings.”

In terms of defect types, he adds, there may typically be over 100 that need to be accurately detected, classified (named) and graded in real time.

“Added to this is the need to ‘filter out’ the random occurrence of ‘non defects’, such as loose threads, lint and dust on the surface – the number of which can be higher than actual defects – and it is clear that a bespoke system is required.”
The development team has consequently established metadata for identifying defect properties, enabling the successful identification of faults from a much smaller number of images.

“The system employs a unique combination of machine learning for automated style training and novel algorithms for defect detection, to provide high quality images for the AI real time defect classification and grading software,” Shelton explains. “Due to the inherent variation in fabric features – raw materials, construction, texture, colour and finishes, as well as the differing product quality standards in value chains and the regional variations in what defects are called – our AI engine uses models built for each individual company or group of companies, or product value chain.”

The AI models are constructed so that the user operatives can populate them with their own data produced by the vision system or by obtaining defect images from another imaging source (eg a mobile phone camera).  

The occurrence of defects is sporadic and many defect types occur infrequently, although when they do, they can have severe consequences. These scenarios re-enforce the need for the AI engine to be quickly set up and able to operate accurately with limited data sets of typically between 30 and 50 good quality images per defect type.

A further feature is a tool enabling the user to periodically ‘clean up’ the AI data during the set up phase. This is used to resolve conflicting data and to correct mis-named images.

Generally, the highest cost component of fabric production is the raw material and in addition to finished product inspection, a cost effective use for vision systems is in process operation.

Generally, the highest cost component of fabric production is the raw material and in addition to finished product inspection, a cost effective use for vision systems is in process operation.

“There is a need for the real time detection of defects that are being created in separate processes, such as printing or coating and for real time automated systems that can accurately determine the defects and their severity and provide a reliable signal for an operative to rectify the issue, This can result in considerable savings.

Prior to Shelton introducing powerful customised machine vision and real time defect classification, the only systems available were those that required manual sifting through vast numbers of images, which included both real defects and ‘non defect’ images. The task was very often overwhelming and did not provide much benefit beyond manual fabric inspection.

More information:
Shelton Vision fabric inspection
Source:

AWOL for British Textile Machinery Association (BTMA)

(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.

Source:

BTMA by AWOL Media

Folding / Plating (© 2021, Maag Brothers)
16.12.2021

Swiss Textile Machinery: Changes and opportunities through automation

For most textiles, finishing processes are not actually the last stage. Products often need an extra touch of expertise to make them perfectly ready for the customer. At this point in the value chain, that usually means manual tasks – but now there are technical solutions and intelligent systems which can handle complex operations better, while adding extra value and assured quality.
Automation brings reliability and efficiency, ultimately saving costs to produce the right quality every time. Swiss companies are specialized in many of these disciplines, with machinery for fabric inspection and presentation, labelling and tracking, folding and packaging. They have the technology to inspire a new vision at the post-production segment of the textile manufacturing processes. Optimization of workflows, with bottleneck management, is an obvious potential benefit. And it delivers measurable returns on investment. The wider picture with automation will prepare companies for the IoT and Industry 4.0.

For most textiles, finishing processes are not actually the last stage. Products often need an extra touch of expertise to make them perfectly ready for the customer. At this point in the value chain, that usually means manual tasks – but now there are technical solutions and intelligent systems which can handle complex operations better, while adding extra value and assured quality.
Automation brings reliability and efficiency, ultimately saving costs to produce the right quality every time. Swiss companies are specialized in many of these disciplines, with machinery for fabric inspection and presentation, labelling and tracking, folding and packaging. They have the technology to inspire a new vision at the post-production segment of the textile manufacturing processes. Optimization of workflows, with bottleneck management, is an obvious potential benefit. And it delivers measurable returns on investment. The wider picture with automation will prepare companies for the IoT and Industry 4.0.

New business models
The advantages of automation in mills with high-volume production are obvious: consistent quality, increased efficiency, waste reduction in some cases, as well as significant medium-term cost reductions in every case.
That description focuses on the aims of modern mills in low-cost markets. But producers in Europe and USA could reach out for more. For them, automation could be a game-changer, offering unique new opportunities.
Reshoring is a growing trend now. It shows great potential and is definitely driven by sustainability and changes in consumer mindsets. “We believe that the time is right – the machines and solutions certainly are – to push automation also to the very end of the production line, replacing intensive manual work and take the chance for reshoring. The current situation is kind of a transition time which is expected to last for a couple more years in the textile industry,” says Rueedi. He adds that any investments in these prime markets pay off much faster because of higher labour costs.
Innovation transformed through automation can do much more than simply replacing the nimble fingers of humans. It also enables new business models, guaranteeing prosperous future business, alongside greater job security.

Digital workflow and process control
The Swiss company Maag Brothers is a leading supplier of high-end machines for quality assurance in the final make-up processes, specifically fabric inspection, plating/folding, selvedge printing and packaging. Maag reports on a practical example from a mill in India which recognized the potential of automation.
An analysis at the customer’s mill identified the main goals as modernization of the workflow at quality control and packing processes. Maag’s new system covers tasks from fabric inspection to dispatch, and offers transparent and easily adjustable processes with real-time process control. It’s a digital solution, resulting in a slim organization, paperless, and the basis for further optimization towards Industry 4.0 to exploit its full potential. The customer’s own calculation showed a ROI for the installation at less than three years – along with a reduction in manpower and savings in fabric costs for shade samples.

Perfectly labelled, efficient data...
Smooth processes start with a label. Swiss company Norsel is an expert in grey fabric labelling systems, for piece tracking through all textile processes. High-quality label printing and proper sealing on all kind of fabrics ensure readability and sustainability after dyehouse processes such as mercerizing, high temperature dyeing and even hot calendering. No roll mix-up during dyeing, easy sorting of fabric rolls and rapid delivery make processes in the mill much more efficient. Using RFID codes lifts fabric inventory control to the highest level, with all information readily transferred to a database and integrated through any ERP software.
It’s a foolproof way to avoid the risk of human errors from hand-written notes on grey fabrics and article sheets, by opting for reliable, secure and forward-looking solutions.

Sample collections – the silent salesmen
First impressions count, so fabric producers like to present their collection perfectly – and that’s only possible with automated solutions. Swiss producer Polytex continuously refines its solutions, underlining its leading position in sample making equipment. Fully-automatic high-performance sample production lines are designed to satisfy the highest expectations. Fully-automatic lines or robotic machines set the standards for quality and performance. Even the most demanding clients can achieve their goals with impeccable samples, quickly and efficiently made, for flawless collections that are sure to impress.

Automation drives buying
First impressions are also the trigger for quick purchase decisions. The proof is there on every store shelf. Customers of Espritech are also well aware of it. They trust this Swiss producer of automated folding machinery to provide the final touch of class to home textiles and apparel products before they go on display. The folding systems are generally large mechatronic devices, loaded with latest technologies in mechanics, electronics, sensors and pneumatics. “Textile producers are amazed how folding machines solve the tricky task of reliably handling chaotically behaving materials. They see process optimization potential and the impact. We observe a slow but continuous change of mindset installing sophisticated technology even in the last steps of textile finishing,” says Philipp Rueedi, CFO at Espritech.

Swiss weaving machinery manufacturers are in the forefront of novel application development ©Stäubli
Multilayer Aramid
17.03.2021

Swiss weaving: Fabrics of the future

  • Swiss weaving machinery manufacturers are in the forefront of novel application development

Shoes and electronic calculators are probably not the first products people would associate with the textile weaving process. But they certainly signpost the future for woven fabrics, as two examples of the ever-wider possibilities of latest technology in the field. Fashion and function already combine in the increasing popularity of woven fabrics for shoes, and this is a present and future trend. Calculators in fabrics? That’s another story of ingenious development, using so-called ‘meander fields’ on the back and keys printed on the front of the material.

  • Swiss weaving machinery manufacturers are in the forefront of novel application development

Shoes and electronic calculators are probably not the first products people would associate with the textile weaving process. But they certainly signpost the future for woven fabrics, as two examples of the ever-wider possibilities of latest technology in the field. Fashion and function already combine in the increasing popularity of woven fabrics for shoes, and this is a present and future trend. Calculators in fabrics? That’s another story of ingenious development, using so-called ‘meander fields’ on the back and keys printed on the front of the material.

These glimpses of the outlook for modern weavers are among the highlights of developments now being pioneered by Swiss textile machinery companies. All weaving markets require innovation, as well as speed, efficiency, quality and sustainability. Member firms of the Swiss Textile Machinery Association respond to these needs at every point in the process – from tightening the first thread in the warp to winding the last inch for fabric delivery. They also share a common advantage, with a leading position in the traditional weaving industry as well as the expertise to foster new and exciting applications.

Technology and research cooperation
The concept of a ‘textile calculator’ was developed by Jakob Müller Group, in cooperation with the textile research institute Thuringen-Vogtland. Müller’s patented MDW® multi-directional weaving technology is able to create the meander fields which allow calculator functions to be accessed at a touch. A novel and useful facility, which suggests limitless expansion.

Today, the latest woven shoes are appreciated for their precise and comfortable fit. They score through their durability, strength and stability, meeting the requirements of individual athletes across many sports, as well as leisurewear. Stäubli is well known as a leading global specialist in weaving preparation, shedding systems and high-speed textile machinery. Its jacquard machines offer great flexibility across a wide range of formats, weaving all types of technical textiles, lightweight reinforcement fabrics – and shoes.

It’s possible to weave new materials such as ceramics, mix fibers such as aramid, carbon and other, and produce innovative multi-layers with variable thicknesses. Such applications put special demands on weaving machines which are fulfilled by Stäubli high-performance TF weaving systems.

Great weaving results are impossible without perfect warp tension, now available thanks to the world-leading electronic warp feeding systems of Crealet. Some market segments in weaving industry today demand warp let-off systems which meet individual customer requirements. For example, the company has recognized expertise to understand that geotextile products often need special treatment, as provided by its intelligent warp tension control system. Individual and connective solutions are designed to allow external support via remote link. Crealet’s warp let-off systems are widely used in both ribbon and broadloom weaving, for technical textiles applied on single or multiple warp beams and creels.

Functional, sustainable, automated
Trends in the field of woven narrow fabrics are clearly focused on functionality and sustainability. The Jakob Müller Group has already embraced these principles – for example using natural fibers for 100% recyclable labels with a soft-feel selvedge. It also focuses as much as possible on the processing of recycled, synthetic materials. Both PET bottles and polyester waste from production are recycled and processed into elastic and rigid tapes for the apparel industry.

For efficient fabric production environments, it is now recognized that automated quality solutions are essential. Quality standards are increasing everywhere and zero-defect levels are mandatory for sensitive applications such as airbags and protective apparel.

Uster’s latest generation of on-loom monitoring and inspection systems offers real operational improvements for weavers. The fabric quality monitoring prevents waste, while the quality assurance system significantly improves first-quality yield for all applications. Protecting fabric makers from costly claims and damaged reputations, automated fabric inspection also removes the need for slow, costly and unreliable manual inspection, freeing operators to focus on higher-skilled jobs.

Smart and collaborative robotics (cobots) offer many automation possibilities in weaving rooms. Stäubli’s future oriented robotics division is a driver in this segment with first effective installations in warp and creel preparation.

Control and productivity
Willy Grob’s specialized solutions for woven fabric winding focus on reliable control of tension, keeping it constant from the start of the process right through to the full cloth roll. Continuous digital control is especially important for sensitive fabrics, while performance and productivity are also critical advantages. In this regard, the company’s large-scale batching units can provide ten times the winding capacity of a regular winder integrated in the weaving machine.

The customized concept by Grob as well as design and implementation result in great flexibility and functionality of the fabric winding equipment – yet another example of Swiss ingenuity in textile machinery.  
There is even more innovation to come in weaving – and in other segments – from members of the Swiss Textile Machinery Association in future! This confident assertion is founded on an impressive statistic: the 4077 years of experience behind the creative power of the association’s member firms. It’s proof positive that their developments grow out of profound knowledge and continuous research.