From the Sector

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.

• Formula 1 cars will be cheaper in future

Carbon is the stuff Formula 1 cars are made of, at least the bodywork. But until now, carbon has been expensive. It can be produced more cheaply and efficiently if artificial intelligence monitors the production processes. A camera system combined with artificial intelligence automatically detects defects in the production of carbon fibres. This makes expensive manual inspection of the carbon fibres obsolete and the production price of the carbon fibre can be reduced in the long term.

For this idea, the young engineer Deniz Sinan Yesilyurt received the second prize of the "Digitalisation in Mechanical Engineering" Young Talent Award on 6 December.

Carbon fibres are sought after because of their good properties. They are very light - they weigh up to 50 percent less than aluminium. The combination of low weight and good mechanical properties offers many advantages. Especially in times of the energy transition, lightweight materials like carbon are more relevant than ever before. At the same time, carbon fibres are as resistant to external stresses as metals. However, achieving these good properties of carbon fibres is very complex.

Up to 300 individual fibre strands - bundles of individual fibres - have to be monitored simultaneously during production. If carbon fibres tear, it costs time and money to sort out the damaged fibres. This is just one example of various defects that can occur in the fibres during production.

Therefore, Deniz Sinan Yesilyurt attached a camera to the carbon fibre line that takes pictures of various fibre defects during production and collects them in a database. The artificial intelligence in the camera's information technology system evaluates the fibre defects by assigning the images to predefined reference defects. In doing so, it recognises various fibre defects with a classification accuracy of 99 per cent. The process can also be used in other areas that produce chemical fibres.

Deniz Sinan Yesilyurt received the prize from the German Engineering Federation (VDMA) in Frankfurt am Main, Germany. He is a Bachelor's graduate at the Institut für Textiltechnik (ITA) of RWTH Aachen University. The full title of his bachelor's thesis is: "Development of a Kl-supported process monitoring using machine learning to detect fibre damage in the stabilisation process". The VDMA awarded the prize to a total of four theses from different universities. The prize is awarded for outstanding theses and was offered in Germany, Austria and Switzerland.

Perstorp has been acquired by PETRONAS Chemicals Group Berhad (PCG), Malaysia´s leading integrated chemicals provider and part of PETRONAS Group, on 11 October 2022.

In May this year, PCG signed a Securities Purchase Agreement with Financière Forêt S.à.r.l, a company under PAI Partners, a European private equity firm, to acquire the entire equity interest in Perstorp, a leading sustainability-driven global specialty chemicals company based in Sweden. With the completion of the acquisition, Perstorp is now PCG’s wholly-owned subsidiary.

PCG will strive to ensure the timely completion of Perstorp’s growth projects in a safe and cost-effective manner. Perstorp has several projects lined up in the near future, including the launch of Project Air which aims to reduce carbon emissions through the production of sustainable methanol. Recently, The European Union Innovation Fund selected Project Air, as one of the 17 large-scale green tech projects, which together will be granted more than EUR 1.8 billion. Project Air is a gamechanger for the chemical industry, moving from fossil raw materials to recycled and bio-based feedstock, thereby enabling sustainable chemical products to a large variety of industries and end products. At full capacity, it will reduce global CO2 emissions with close to 500,000 metric tons per year from today’s levels, corresponding to one percent of current emissions in Sweden.

Due to rising Covid-19 cases in Shenzhen, CHIC GBA (Greater Bay Area), scheduled from November 2-4, 2022, will be postponed to 2023 for pandemic control and integrated into CHIC Shanghai in spring.

CHIC Shanghai will be held at the National Exhibition and Convention Center from March 8-10, 2023.

• Rising global demand for particularly high-performance silicon carbide (SiC)-based semiconductors

• Increase in production capacities at the Shanghai (China), St. Marys (USA) and Meitingen (Germany) sites

SGL Carbon will significantly increase capacities for the production of graphite products for the semiconductor industry by 2024. As part of the investment budget for the Business Unit Graphite Solutions set out in the medium-term planning, a mid-range double-digit million euro amount will be made available for the expansion of production over the next two years. The company is thus responding to the strong growth in demand in this sector and strengthening its commitment to the global megatrend of digitalization.

The expansion program will take place in several steps over the next two years. In St. Marys, North America, and at the Chinese site in Shanghai, capacities for purification and for high-precision, computer-controlled processing of graphite components and felts will be expanded. In Meitingen (Germany), a new plant for the production of carbonized and graphitized soft felt is under construction. Further capacity expansions at various locations are being planned.

• Sales increase of 10.7% to €549.8 million in the first half of 2022
• EBITDApre improves by 22.6%, higher than the increase in sales, to €87.9 million
• Positive business development, price increases and strict cost management led to forecast increase on June 7, 2022

Despite uncertain general conditions in the first six months 2022, SGL Carbon's business model is proving its resilience. After €270.9 million in Q1 2022, SGL Carbon was able to increase sales to €278.9 million in Q2. Accordingly, sales for the first half of 2022 amount to €549.8 million, which corresponds to a sales plus of €53.1 million or 10.7% compared to the same period of the previous year.

The increase in sales was driven in particular by customers in the semiconductor industry and growth in the industrial applications market segment. Demand from the automotive and chemical industries was also encouraging.

EBITDApre, as one of the Group's key performance indicators, improved by €16.2 million (+22.6%) to €87.9 million (H1 2021: €71.7 million). Consequently, the EBITDApre margin increased from 14.4% to 16.0%. In addition to the higher utilization of production capacities due to higher sales, the improvement in earnings was also driven by the largely successful passing-on of higher raw material and energy costs to customers as well as savings from the transformation program.

EBITDApre does not include positive one-off effects and non-recurring items totaling €10.6 million (H1 2021: minus €5.2 million). As a result, EBIT in H1 2022 increased significantly from €38.3 million to €69.6 million. Taking into account the financial result of minus €16.6 million (H1 2021: minus €14.0 million), consolidated net income for the first six months of the current fiscal year amounted to €48.8 million, compared to €17.9 million in the prior-year period.

Business Units
With an increase in sales of €22.2 million (+10.0%) to €243.4 million, the Graphite Solutions (GS) business unit made a major contribution to SGL Carbon’s sales growth. In particular, continued high demand from customers in the semiconductor sector, which represents approximately one third of the segment's sales, led to the positive business development in GS. As a result of the predominantly high-margin business, EBITDApre at GS improved by 22.7% to €54.0 million.

The Process Technology (PT) business unit benefited from the good order situation in the chemical industry in H1 2022 and consequently increased sales to €49.2 million (H1 2021: € 40.8 million). EBITDApre also improved from €0.1 million in the prior year’s first half to €4.1 million in H1 2022.

The Carbon Fibers (CF) business unit benefited in the 1st half 2022 from final deliveries to a major automotive manufacturer whose contract expired as scheduled on June 30, 2022. Segment sales increased by 5.8% year-on-year to €176.0 million. In contrast, EBITDApre at CF decreased by €4.2 million to €28.2 million despite the good order situation and successful price increases. It should be noted that CF was impacted by a special effect from energy derivatives for price hedging in the amount of €9.2 million in the first quarter of 2022.

With an increase in sales of 15.6% to €69.6 million, the Composite Solutions (CS) business unit continued its upward trend. The specialist for customized component solutions for the automotive industry improved its EBITDApre from €5.7 million in the first half of 2021 to the current €9.7 million, based in particular on price and volume effects.

Balance sheet figures
Working capital rose by 11.7% to €381.1 million as of June 30, 2022. This was mainly due to higher inventories (€ +73.9 million) and an offsetting increase in trade payables (€ +29.0 million). A targeted build-up of inventories in critical raw materials due to disruptions in transport routes and the recent Covid lockdown in Shanghai were some of the reasons for the higher inventory levels.

SGL Carbon's net financial debt slightly increased by €6.6 million to €212.9 million as of June 30, 2022 (Dec. 31, 2021: €206.3 million), which was due to a lower free cash flow of €7.5 million for H1 2022 (H1 2021: €56.6 million).

Guidance increase
On June 7, 2022, SGL Carbon raised its sales and earnings guidance for fiscal year 2022. The company now expects sales of €1.1 billion (previously: around €1.0 billion) and EBITDApre of €130 - 150 million (previously: €110 - 130 million). Based on the pleasing business development, realized price increases, a stringent cost management, and taking into account the currently known risks, SGL’s management expects to achieve the earnings forecast for 2022 at the upper end of the stated range.

Akzo Nobel N.V.  publishes results for second quarter 2022

Highlights Grow & Deliver (compared with Q2 2021)

• Revenue up 14% and 10% higher in constant currencies1, pricing up 16%
• ROS2 at 8.7% (2021: 13.3%), resulting from lower volumes and continued raw material and freight costs inflation
• Adjusted EBITDA at €337 million (2021: €419 million)
• Acquisition of Grupo Orbis completed in April 2022. Intended acquisition of Kansai Paint’s business in Africa announced in June 2022. Intended acquisition of the liquid wheel coatings business of Germany-based Lankwitzer Lackfabrik GmbH announced in July 2022

Highlights Q2 2022 (compared with Q2 2021)

• Pricing up 16%; offsetting the increase of raw material and other variable costs. Volumes 9% lower
• Operating income at €205 million (2021: €384 million), includes €44 million negative impact from Identified items (2021: €49 million net positive impact). OPI margin 7.2% (2021: 15.3%)
• Adjusted operating income3 at €249 million (2021: €335 million)
• Net cash from operating activities decreased to negative €52 million (2021: positive €168 million)
• Net income attributable to shareholders at €106 million (2021: €261 million)
• EPS from total operations at €0.60 (2021: €1.40); adjusted EPS from continuing operations at €0.84 (2021: €1.20)

International technology group ANDRITZ has received an order from Yanpai Filtration Technology Co., Ltd. (YANPAI®), China, to supply batt forming equipment with an aXcess card and crosslapper for a needlepunch line producing PTFE filtration products at its site in Tiantai. The PTFE felts will be used as smoke filters in waste incineration plants. Start-up of the line is planned for the second half of 2022.

Yanpai is one of the leading Chinese producers of nonwoven filters for dust and air treatment and of woven filter fabrics used in solid/liquid separation. Established in 1990, Yanpai was at the forefront of development work on new industrial filtration fabrics. Today, Yanpai is a company with facilities in China and the USA.

The European Pultrusion Technology Association (EPTA) has published a report from its latest conference, which focuses on advances in sustainability and recycling.

More than 130 professionals from the global pultrusion community gathered at the 16th World Pultrusion Conference in Paris on 5-6 May 2022. Organised by EPTA in collaboration with the American Composites Manufacturers Association (ACMA), the event featured 25 international speakers sharing insight on market trends, developments in materials, processing and simulation technologies, and innovative pultruded applications in key markets such as building and infrastructure, transportation and wind energy.

‘Bio-pultrusion’:  
Composites based on natural fibres offer a number of benefits, including low density and high specific strength, vibration damping, and heat insulation. The German Institutes for Textile and Fiber Research Denkendorf (DITF) are developing pultrusion processes using bio-based resins and natural fibres. Projects include the BioMat Pavilion at the University of Stuttgart, a lightweight structure which combines ‘bamboo-like’ natural fibre-based pultruded profiles with a tensile membrane.

Applications for recycled carbon fibre (rCF):
The use of rCF in composite components has the potential to reduce their cost and carbon footprint. However, it is currently used to a limited extent since manufacturers are uncertain about the technical performance of available rCF products, how to process them, and the actual benefits achievable. Fraunhofer IGCV is partnering with the Institute for Textile Technology (ITA) in the MAI ÖkoCaP project to investigate the technical, ecological and economic benefits of using rCF in different industrial applications. The results will be made available in a web-based app.

Circularity and recycling:
The European Composites Industry Association (EuCIA) is drafting a circularity roadmap for the composites industry. It has collaborated with the European Cement Association (CEMBUREAU) on a position paper for the EU Commission’s Joint Research Centre (JRC) which outlines the benefits of co-processing end-of-life composites in cement manufacturing, a recycling solution that is compliant with the EU’s Waste Framework Directive and in commercial operation in Germany. Initial studies have indicated that co-processing with composites has the potential to reduce the global warming impact of cement manufacture by up to 16%. Technologies to allow recovery of fibre and/or resin from composites are in development but a better understanding of the life cycle assessment (LCA) impact of these processes is essential. EuCIA’s ‘circularity waterfall,’ a proposed priority system for composites circularity, highlights the continued need for co-processing.

Sustainability along the value chain:
Sustainability is essential for the long-term viability of businesses. Resin manufacturer AOC’s actions to improve sustainability include programmes to reduce energy, waste and greenhouse gas emissions from operations, the development of ‘greener’ and low VOC emission resins, ensuring compliance with chemicals legislation such as REACH, and involvement in EuCIA’s waste management initiatives. Its sustainable resins portfolio includes styrene-free and low-styrene formulations and products manufactured using bio-based raw materials and recycled PET.

With global consumers becoming more conscious about personal hygiene and environmental protection, exhibitors at Cinte Techtexil China will spotlight materials and technologies for products that respond to these trends. The fair will probe into the associated growth opportunities as the country is one of the leading markets for nonwovens and technical textiles. The event will be held from 6 – 8 September at the Shanghai New International Expo Centre.

The technical textiles and nonwovens industries, the latter notably, are significantly expanding amid the pandemic. A recent forecast[1] predicts that the global polypropylene nonwoven fabric market will continue to rise at a CAGR of 6.7%, reaching USD 39.23 billion by 2028. The anticipated growth is bolstered by demands in end-use industries such as sanitation, medical, automotive and more. In 2020, Asia Pacific was named the largest regional market in the world and is expected to grow significantly over the forecasted period.

The prediction reaffirms the growth prospects of nonwovens. In this regard, industry players expressed much optimism about associated future opportunities during Cinte Techtextil China last year. “The field of nonwovens is poised for a positive growth as the awareness of personal hygiene and pandemic prevention sustains in the domestic market,” commented Mr James Gao, Head of Marketing and Textile Technologies, Uster Technologies (China) Co Ltd. He added: “We decided to join the fair and showcase our new launches as we remain confident in the future development of the industry, especially since China is dominating the global scene.”

Going green is the way forward
Turning to yarns and fibres, the sector is shifting to greener and smarter production that echoes the trend towards sustainability that is gaining considerable traction across the globe. Meanwhile in China, this movement was observed by many exhibitors at the 2021 edition, including Mr Roberto Galante, Plant Manager of FMMG Technical Textiles (Suzhou) Co Ltd, the Chinese subsidiary of the Fil Man Made Group. He mentioned: “The market is paying more attention to environmental protection, and we receive enquiries about special yarns for this every day. We focus on technical yarns for filtration as well as anti-bacterial properties, which are very important for the environment. The potential here in China is incredible and this is a big opportunity for everybody.”

Cinte Techtextil China’s product categories cover 12 application areas, which comprehensively span across a full range of potential uses in modern technical textiles and nonwovens. These categories also cover the entire industry, from upstream technology and raw material providers to finished fabrics, chemicals and other solutions. This scope of product groups and application areas ensures that the fair is an effective business platform for the entire industry.