Ai, Industry-4-0 6 October 2022

Detection of defects in fish loins using machine vision and deep learning

detection of defects in fish
Share post

Machine vision technology assisted by deep learning is an important ally for fish processing and distribution factories that makes it possible to inspect 100% of the production to ensure high standards of quality and food safety of the product that finally reaches the consumer’s table.

The new Visum DeepSight Loins™ system from IRIS Technology is a machine vision system designed for the detection of physical surface defects in fresh and frozen fish loins that makes it possible to automate the inspection of loins, quantify, classify and reject non-conformities to ensure superior quality of the final product.

Machine Vision and Deep Learning

While traditional computer vision systems learn to classify and recognize features from a set of historical images in order to correctly predict and classify new ones, deep learning neural networks are able to learn features from pixels (individual and group) and have an input layer (the raw image), a series of intermediate layers that are interconnected to simulate how a biological brain works, and an output layer that provides classification/prediction. Deep learning neural networks are especially good at learning complex features and segmenting an image at different levels of abstraction (edges, different colors, shapes, objects), including noise and probabilistic information.

Traditional machine vision that does not use this approach typically processes images but does not learn from the data, such as thermal imaging cameras, motion detection sensors, light intensity sensors, among others.

Detection of defects in fresh and frozen fish loins

The DeepSight Loins™ system is capable of detecting numerous defects in fish loins such as bruises, blood stains, gapping (i.e. openings or tears in the musculature), skin remnants, superficial bones or other superficial foreign bodies that may reach the processing line. It also has built-in color measurement functionality under international CIELAB or L*a*b* standards, which is important as a quality parameter both on the surface and in relation to the freshness of the fish.

DeepSight Loins™ has a high IP protection for easy cleaning of the line and has a built-in anti-reflective and anti-humidity system that allows it to operate normally on both fresh and frozen fish loins.

Usability, Operation and Communication

The Visum DeepSight Loins™ system incorporates 2 user levels: “Administrator” for modifying settings, working mode, adjusting rejection sensitivity or taking references and “Operator” for automatic operation mode of the device.

The system is complemented by a trap door rejection that allows the ejection of non-conforming units for reprocessing or control by the operators.

The information and results of the analysis, such as the quantification of defects and rejects by class, lot information and the quantity of products inspected, can be viewed on the built-in computer module, on a computer connected to the network or on the plant’s own information management system. In addition, automatically generated reports can be exported in different formats.

The sensitivity adjustment functionality is an essential tool for calibrating the level of rejection of the device in the event of certain defects and thus regulating the system’s operating performance without causing any inconvenience to the line’s production capacity.

For more information about the device and inquiries write to info@iris-eng.com

By IRIS Technology Solutions
Environment, Industry-4-0 22 September 2022

Sorting and quantification of organic waste

biomethan
Share post

Sorting and control of organic waste in biogas production

In this article we will discuss how it is possible to optimize the treatment of organic municipal solid waste used for biogas production with hyperspectral technology to improve the quality and yield of biomethane, based on the application that IRIS Technology has developed for the Biomethanization Plant of Las Dehesas (FCC), in Madrid based on its Visum HSI™ organic waste sorting system.

The problem of organic waste separation

In the last year alone, the Spanish economy generated more than 138 million tons of waste, of which only 15% was reused to manufacture new products, by-products or raw materials. Moreover, Spain is still below the EU target of recycling 50% of Municipal Solid Waste (MSW) also stipulated in Law 22/2011 on waste and contaminated soils. Despite the fact that some communities have managed to achieve high recycling rates, organic waste remains one of the main headaches for the Administration and waste treatment and recycling plants.

This is because a large part of the organic fraction of municipal solid waste (MSW) is contaminated with inorganic materials, mainly packaging – another of the great challenges of recycling – and plastics, where optical sorting and spectroscopy technologies have become great allies.

Biogas production

One of the main destinations for the reuse and revaluation of organic waste is the production of biogas, which is converted in biomethanization plants into biomethane, a type of gas suitable for injection and commercialization in the gas network, complying with certain quality and safety standards. In these plants, such as the one in Las Dehesas in Madrid, the organic fraction of the solid waste is treated to avoid high percentages of “improper” (presence of inorganics) which, once in the biodigesters, cannot be used in the fermentation process and, consequently, the result is a suboptimal quality and performance of the process and the final product.

To this end, IRIS Technology, within the framework of the European Scalibur project, installed an HSI™ hyperspectral imaging system in the FCC line in order to quantify and classify waste according to whether it is organic or inorganic. Beyond the various intermediate controls, the removal of bulky waste, plastic bags, etc., knowing the percentage of organic waste is a key parameter for adjusting the biological process that takes place in the digesters.

FORS quality monitoring

Separation of organic and inorganic waste

The organic waste sorter Visum HSI™ based on hyperspectral technology allows to obtain real-time data on the percentage of organic and inorganic waste, as well as to locate the different components on the conveyor belt, to know the average composition of the waste, to monitor the evolution of the waste composition over time and to extract useful information for decision making in waste management, production and circularity.

Resultados Scalibu

The implementation of the HSI system has allowed FCC to monitor in real time the waste in order to improve the flow corresponding to the organic fraction and, consequently, a fermentation process with a lower level of impurities, maximizing the key parameters of the fermentation process.

For more information about this project and the technology, please visit Scalibur’s website or write to our mail: news@iris-eng.com

By IRIS Technology Solutions
Industry-4-0 5 September 2022

Real-time monitoring of biofuels with NIR spectroscopy

bioethanol and nir
Share post

In this post we will discuss NIR spectroscopy monitoring of the bioethanol production process and how on-line NIR is an important ally for real-time monitoring of fermentation results, final quality or purity, process inhibitors and other analytes of interest for the production of high value-added by-products for the industry.

Bioethanol and NIR

Bioethanol is a type of fuel obtained from the fermentation of organic matter rich in sugars and starch, such as corn, sugar beet, sugar cane, among the most popular ones used worldwide. It can even be produced from solid urban waste and biomass with no food value, known as “second generation” bioethanol or lignocellulosic bioethanol, which solves the added problem of giving a productive destination and added value to the organic waste we discard, converting it into biofuel.

As a result of the action of yeasts and enzymes in the fermentation process, and after distillation, bioethanol is obtained for use as biofuel and for blending with fossil fuels. From the rest of the components, by-products are obtained that can change depending on the raw material used in the process, for example, from dry milling, animal feed can be obtained due to its high protein content, or other by-products from wet milling such as corn oil, syrups, to mention a few. Also, from lignocellulosic biomass, by-products can be obtained for reuse in other industries, such as methanol and acetic acid.

Quality control of the bioethanol production process.

Bioethanol quality control is very important to ensure the purity of the product resulting from the process and the valorization of by-products for reuse in other industries. In most biorefineries, the control of reducing sugars (glucose) and ethanol is carried out using analytical techniques offline, i.e. in the laboratory, using high performance liquid chromatography (HPLC), which takes time and resources, or with benchtop NIR spectroscopy, which, unlike HPLC, provides accurate results in just seconds, but is still an unrepresentative and off-line sampling method.

Bioethanol and NIR in line

However, few biorefineries have bet on the introduction of in-line NIR technology to monitor the fermentation process, distillation, the action of process inhibitors or the control of by-products.

In this sense, IRIS Technology has developed several applications for process control in biorefineries using the Visum NIR In-Line ™ analyzer and the portable (handheld) Visum Palm™ NIR.

Table 1: Inline glucose and ethanol content prediction using a Visum NIR In-Line ™ analyzer.

Table 1 shows the main parameters, ranges and production stages in the manufacture of lignocellulosic bioethanol at IMECAL‘s Perseo Biotechnology plant, where municipal solid waste is transformed into bioethanol.

The lignocellulosic biomass delignification process was also monitored to free cellulose from hemicellulose and lignin and thus achieve depolymerization of carbohydrates to produce simple sugars and fermentation to produce ethanol.

Table 2: The pretreatment process consists of a combination of organosolvation with steam explosion (performed by LTU, Lulea Univ. of Technology). Parameters monitored: Lignin, cellulose and hemicellulose content.

Another application developed in the framework of this project was the monitoring by Visum NIR In-Line™ of the process of obtaining reducing sugars from hemicellulose present in lignocellulosic residues. In particular, it is shown that it is possible to control inhibiting factors of the fermentation process, such as acetic acid.

Table 3: Parameters monitored: xylose, glucose, acetic acid content.

The installations and tests carried out demonstrate the effectiveness and importance of introducing in-line NIR technology in biorefineries in order to have a more precise control of the different phases of the bioethanol production process, achieve higher quality and therefore increase biofuel efficiency.

By IRIS Technology Solutions
Industry-4-0 10 August 2022

Hyperspectral NIR: Applications in the Food Industry

Share post

In this article we will address cross-cutting applications of hyperspectral NIR technology in the food industry with the aim of questioning our current production process and considering effective ways to optimize it with in-line technology. We will not go into detail on each of the applications, but if you are interested in learning more, you can read the following post where we see a case of application in fried pastries to mitigate indeterminate fat variations in the process and optimize the use of raw material.

However, IRIS Technology’s hyperspectral NIR technology, Visum HSI™ opens a huge window of applications to the industry in process control, quality and food safety with an optical industrial system that is able to chemically monitor each product unit in real time and determine a large number of physical and chemical parameters simultaneously. A hyperspectral camera is equivalent, in practice, to having a spectrophotometer in every pixel.

Visum HSI™: pixel-by-pixel, spatially resolved chemical imaging

Food Industry

Fruit and vegetable industry

In this industry there are numerous non-destructive controls that can be performed with hyperspectral NIR technology. Among them we can mention ºBx, starch, dry matter that are relevant parameters to establish the degree of maturity and commercialization of fresh products, as well as pH, acidity, fat content, moisture or soluble solids that are part of the usual controls in the industry and that currently, as in most of the industry, are performed by traditional offline techniques (sampling and laboratory).

 

Likewise, hyperspectral NIR technology is effective for determining texture by levels, detecting and rejecting foreign bodies in the line and for sorting. In general terms, they are systems that can learn from a quantitative reference criterion or from a human expert when controlling a certain process. Therefore, as a non-destructive control method, it is an excellent alternative to classify and select products according to their composition in a fully automated way, providing greater value to the final product, for example, if you want to create a premium line.

Fish and seafood

Food safety controls for all seafood products are becoming increasingly stringent. In this context, the Visum HSI™ inline hyperspectral NIR technology facilitates the detection of foreign bodies coming from the seabed, such as shells, stones, other arthropods, net fragments, among others, which are visually little different from the product to be processed and can therefore escape visual inspection, or which, due to their low density, there are no useful detectors on the market. It is also possible to detect plastic packaging residues, even if they are transparent in fish fillets and slices. In addition to being able to quantitatively determine a large number of analytical parameters simultaneously (fats, proteins, acidity, among others), it is capable of detecting and classifying the application of sulfites or preservatives and the degree of freshness.

 

In case you are wondering, Hyperspectral NIR technology, at least as of 2022 and no other technology on the market that is in-line and continuous, is effective in quantifying histamine at the levels required by industry and regulations (<50 ppm).

 

In the next post you can read more about foreign body detection with our hyperspectral systems.

Nuts, grains and pulses

In nuts (almonds, pistachios, peanuts, among many others) it is possible to replace conventional laboratory analysis and combine these with in-line imaging spectroscopy vision techniques. This is useful for real-time control of chemical parameters such as moisture, fat, fibers, acidity, as well as to detect and separate foreign bodies: corn that appeared on the line, wood, plastics, stones. For visible defects such as spotting, moth-eaten, other grain defects or fruit with skin, it is required to complement with a machine vision system, such as Visum DeepSight™ .

Bread and pastries

We have covered this topic in our blog, focusing on fat control, a critical input for manufacturer costs, consumer trends and food taste and texture. However, Visum HSI™ technology can monitor unit by unit of product other critical parameters, such as moisture or sugar content and more importantly, interact through the line PLC with machinery and the plant management system.

In conclusion, hyperspectral technology, coupled with the breakthrough in optical systems in recent years, opens up a wealth of opportunities for food safety in industrial processes.

I hope this article on hyperspectral NIR technology in the food industry has been useful and applicable.  As always, we invite you to send us your questions, comments and suggestions to our e-mail address news@iris-eng.com.

By IRIS Technology Solutions
Industry-4-0 26 July 2022

Detection of foreign bodies in the production line

Detection of foreign bodies
Share post

In this post we will address a recurrent and transversal problem in the industry related to food safety: the presence of foreign bodies in the production line and we will see how we can prevent this from happening with viable techniques at industrial level such as imaging spectroscopy or also known as hyperspectral NIR or Hyperspectral Imaging (HSI).

Detection of foreign bodies

What do we mean by foreign bodies?

In general terms, for manufacturers, “foreign body” is anything that should not be in the production line, whether it is an organic element (bone, skin, shells, other foods that are not the product to be packed, pieces of wood, wood chips to mention a few) or inorganic elements such as metals, screws, plastics, cardboard, paper, etc. The rule is that everything that is not product should not be there, as it is a problem that can alter the quality of the final product and therefore generate economic losses, as well as being a risk for the health of consumers and the image of the company.

State of the art

Until now, foreign body control in the vast majority of industries, whether food or non-food, has been carried out by visual inspection. That is to say, with operators on the production line watching the product flow and extracting any foreign bodies that may have crept in during the manufacturing process. On the one hand, X-ray detection systems, which have already been implemented in practically all industries, guarantee that no conductive elements, i.e. metals, will pass through the line, but do not exempt us from the possibility of non-conductive, low-density elements such as plastics, paper, cardboard, stones, glass, rubber, among others, which may appear and which are undetectable with this technology.

On the other hand, traditional artificial vision, for the detection of foreign bodies, has significant limitations due to the enormous variability that may exist in terms of type, shape, colour or size, which results in a high false positive rate (rejected “good” product). However, on a more contemporary level, artificial vision assisted by deep learning or machine learning algorithms is a technology that has its benefits at certain points in the line, such as in packaging, where it is useful for detecting the presence of certain physical contaminants.

Foreign body detection with hyperspectral NIR

If we have to say that by 2022 there is a sufficiently mature, easily integrated inline and economically viable technology for foreign body detection, it is hyperspectral NIR technology.

This technology is an extension of traditional artificial vision in two ways: Firstly, instead of the usual three colour channels in artificial vision, hyperspectral imaging uses up to hundreds of channels, making it possible to see very subtle differences. Secondly, hyperspectral cameras incorporating these systems often have an extended spectral range beyond the visible, i.e. into the infrared, where chemical composition is much more evident than in the visible range.

Hyperspectral imaging can therefore be seen as a paradigm shift in vision systems and as a source of abundant, high-quality data to feed vision systems based on artificial intelligence algorithms. In practice, having a hyperspectral camera is equivalent to having a spectrophotometer in each pixel, i.e. it allows obtaining chemical information on the composition of the product pixel by pixel and product unit by product unit, providing a clear image of the whole inspected area and distinguishing according to its chemical composition what is product and what is not, regardless of its shape, size or typology. It has a limitation; as it works with light and as this has a minimum penetration in the material, everything that is not superficial will not be detected. To prevent this from happening, at IRIS Technology, we integrate vibration or velocity to generate dispersion of the product in the section where the hyperspectral detection system is located.

The Visum HSI™ system can work at a speed of up to 50 m/min detecting foreign bodies up to 3 mm² and with a minimum density of 0.7g/cm³. It is therefore a “compromise” solution between line speed, processing power and minimum detectable size.

Detection of foreign bodies

Visible NIR and chemical composition

IRIS Technology’s turnkey systems, such as the Visum HSI™ analyser, can operate in two spectral ranges, Vis-NIR (400 to 1000 nm) or SWIR (900-1700 nm). The application of one camera or the other in the hyperspectral system will depend on the manufacturer’s need. If it is only a question of detecting foreign bodies, a Vis-NIR camera will be used, since in this range there is enough chemical information to detect what is a product and what is not. On the other hand, if you also want to quantify or classify product composition parameters other than moisture, such as fats, proteins, fibres, acidity or other parameters, a camera working in the SWIR range will be used to obtain reliable and robust results like those of the laboratory.

Some final clarifications

It is important to note that hyperspectral technology is not useful for detecting foreign bodies inside the product, regardless of the product in question, because as mentioned above, the light has minimal penetration.

Although it is not the subject of this article, we believe it is important to clarify that hyperspectral technology is also not useful for the detection of microbiological activity at the concentrations and limits required by regulatory bodies (ppm), where the only viable analytical technique is still the swap or Elisa.

Therefore, at IRIS Technology we are constantly investing in R&D to increase the analytical capabilities of our systems, as well as to develop advanced solutions that are reliable and feasible to integrate into the production line.

By IRIS Technology Solutions

More than 60% of the films used in food packaging are transparent multilayer films

In recent years, multilayer film structures have made it possible to extend their applications in the packaging of food products, allowing the organoleptic and nutritional qualities of the product to be optimally preserved. Today, more than 60% of the films used in food packaging are transparent multilayer films obtained from coextrusion, where the different polymeric layers respond to certain needs: barrier against water, water vapor, temperature, sealability, mechanical resistance, among others.

Film thickness and its uniformity is a critical parameter to control changes in the structure without compromising the performance requirements of the same and therefore the on-line control of thickness is of great importance for designers and manufacturers of multilayer films. Up to now, this control has been done with offline methods that are not compatible with continuous production, such as using a micrometer or optical microscopy. There are also sensors on the market to control the uniformity of single-layer films, but there is no tool that is really effective in industrial and technological terms for controlling the thickness of multilayer films and guaranteeing their uniformity.

The patented Visum Thickness™ sensor technology is a tool for single or multipoint thickness control of thin translucent multilayer films, layer by layer, total thickness and in real time, which makes it suitable for different color coatings on substrates of different nature and therefore has potential uses in multilayer barrier packaging, but also coated textiles, metals, among others.

Some additional features of Visum Thickness™:

  • No calibration required.
  • Number of layers: unlimited.
  • Spot size: 5 mm. 
  • Inspection: single or multi-point.
  • Probe-to-film distance range: 5-30 cm.
  • Dimensions: 300 x 200 x 150 mm3 
  • Weight: 7 kg 
  • Power supply: 240 VAC, 100 W 
  • Operation: slave or continuous.
  • Communication: Wifi / Ethernet / Profinet / Profibus
  • Visum ® software
  • Embedded computer

 

IRIS Technology is a European leader in the development and manufacturing of industrial solutions with applied photonic technologies.

 

For more information, write to info@iris-eng.com

By IRIS Technology Solutions
Industry-4-0 14 July 2022

WhiteCycle: Europe’s big bet to recycle more than 1.8 million tonnes of plastic textile waste annually.

WhiteCycle
Share post

What is WhiteCycle?

On 1st of July, the WhiteCycle project was launched with the aim of developing a circular solution to convert plastic textile waste into high added-value products. This unprecedented European project is coordinated by Michelin and is made up of a consortium of 17 public and private entities, co-funded by the European Commission’s Horizon Europe programme. IRIS Technology is a key member of the consortium as a European leader in the design of advanced optical systems.

WhiteCycle's objectives

By 2030, WhiteCycle is expected to adopt and deploy a circular solution to recycle more than 2 million tonnes of textile plastic waste annually, particularly the third most used plastic PET (Polyethylene Terephthalate). This is expected to reduce CO2 emissions by around 2 million tonnes per year and avoid the landfilling or incineration of more than 1.8 million tonnes of plastic each year.

Currently, complex textile-containing waste (PET) from various sources, such as multi-layer clothing, hoses or tyres, is difficult to recycle. However, soon all these products could be recyclable thanks to the results of the project. Thanks to the WhiteCycle project, PET 2 feedstock could be reused to create high-performance products. This would be possible thanks to a viable circular value chain.

This project will develop processes needed throughout the industrial value chain.

  • Develop and/or use innovative sorting technologies. This would allow an increase of the PET plastic content of complex waste streams in order to be able to process them better.
  • The recovered PET would be pre-treated for its content. This would be followed by an innovative process based on recycling enzymes to break down into pure monomers and pure monomers in a sustainable way.
  • Repolymerisation of the recycled monomers into a new plastic.
  • Manufacturing and verifying the quality of new products produced from recycled plastic materials.

WhiteCycle has an overall budget of ¤9.6 million and receives European funding of approximately ¤7.1 million. The companies participating in the project are located in five countries:

  • Germany: DITF, Estato, IPoint
    Spain: IRIS Technology Solutions, Inditex
    France: Axelera, Carbios, Dynergie, ERASME, IFTH, Michelin, PPRIME, Synergies TLC,UNIV POITIERS
    Norway: HVL, Mandals
    Turkey: Kordsa

IRIS Technology's role in White Cycle

There has long been an urgent need to develop a final circular solution for the industry to transform complex textile plastic waste into higher value-added products (new plastic for hoses, tyres and clothing).

As Europe’s leading designer of advanced optical systems, IRIS Technology will lead the development of a system capable of real-time monitoring and identification of textile PET waste for recycling. For this purpose, IRIS will implement hyperspectral NIR technology using the Visum HSI™ industrial analyser, which employs 2D imaging spectroscopy and extracts pixel-by-pixel and unit-by-unit chemical information from product passing over the line to detect chemical composition, content and spatial distribution. Finally, the HSI system for the detection and sorting of plastic textile waste will be validated on an industrial scale to facilitate its incorporation into recycling lines across Europe.

By IRIS Technology Solutions
Digitalization, Environment, Industry-4-0 22 June 2022

Identification and characterization of polymers with portable NIR technology

polymers
Share post

The plastic recycling industry presents an enormous complexity for the separation of the different types of polymers and among the most widespread techniques for this purpose are the spectroscopic ones. We will not discuss all of them in this article, as it would imply diving into the world of R&D, new in-line detection technologies and their practical or economic limitations in trying to reach the aspirational standards in terms of recycling and circularity of the European Union.

However, following an eminently practical approach, an agile and effective way to identify different compounds or plastic mixtures for recycling or industrial reuse is through NIR spectroscopy. This technique is based on the interaction of light with matter and makes it possible to observe the different absorbances produced by the vibrations of the bonds between the atoms of the polymers. As a result, a characteristic spectrum of each type of plastic is obtained, which can be quantified and classified by means of a predictive machine learning model.

The Visum Palm™ handheld NIR analyzer.

The Visum Palm™ analyzer, a portable NIR instrument operating in the SWIR range (1-1.7 μm), is particularly suitable for successful quantitative (composition) and qualitative (identification and classification) characterization of a wide variety of materials and mixtures. For this reason, the use of the Visum Palm leads to significant savings in analytical workload and substantial reductions in waiting time.

In addition, its ubiquitous nature -due to its portability- and the possibility of programming it to determine multiple parameters at the same time, allows it to be used in a wide variety of analytical tasks at the production line, in logistics warehouses and even for applied research studies and the development of proprietary models carried out by AIMPLAS, a reference in the plastics sector in Spain.

Main features and generic advantages of SWIR spectroscopy:

  • Determination of multiple parameters with a single instrument.
  • Real-time and continuous analysis for automatic and instantaneous correction of process parameters.
  • Non-destructive determinations without sample preparation.
  • Excellent repeatability.
  • Use does not require skilled operators.

Although there are several portable NIR instruments on the market, it is essential to take into account the spectral range with which the instrument works and the size of the spot (measuring point) to ensure representativeness of the reading with respect to the sample. The Visum Palm™ System introduces a 10mm spot and a powerful spectrophotometer that works in the range 900-1700 nm.

Identification and classification of polymers in the industry

The Visum Palm™ instrument includes a library of models for reading and determination at the line, without sample preparation and in a few seconds that allows characterization of a large number of polymers, including PET (polyethylene terephthalate), HDPE (high density polyethylene), LDPE (low density polyethylene), PP (polypropylene), PS (polystyrene), PVC (vinyl or polyvinyl chloride), PC (polycarbonate), ABS (acrylonitrile butadiene styrene), to name a few, including more complex mixtures.

Identification and separation is important in polymer manufacturing, since in order to reprocess plastic waste, manufacturers must ensure that the plastic materials are as pure and clean as possible and, of course, the price manufacturers pay recyclers for the plastic waste they supply depends on this. In addition, low levels of impurities can already considerably affect the quality and yield of a complete recycling batch. In this context, spectroscopy techniques combined with machine learning models make it possible to introduce important automatisms and quality controls sensitive to the needs of the industry.

By IRIS Technology Solutions

The wood industry, and in particular the manufacture of wood panels, has enormous advantages for the introduction of photonic techniques such as near infrared spectroscopy (NIRS) in the different phases of the production process that are currently controlled mechanically, randomly or simply escape from traditional control and manufacturing techniques.

 

IRIS Technology is the most important European supplier of advanced control systems with spectroscopy and artificial intelligence applied to production processes in different industries, including manufacturers of wood or particle boards. These boards consist of shavings of different sizes that form a multilayer structure and that, finally, may or may not be coated with decorative paper impregnated with melamine resin. Undoubtedly, particleboard has many applications in the furniture, furnishing, construction and interior finishing industries.

 

As a specialised supplier in the control of particleboard manufacturing, IRIS Technology has launched several applications in its Visum™ line of analysers using hyperspectral technology, which we will tell you about below:

 

Chipping process

Wood chips make up the raw material in the manufacture of particleboard and can be of different kinds or origins. At the production line, IRIS Technology’s hyperspectral imaging system Visum HSI is able to determine in real time the proportion (quantification) of each class or type of chips, as well as to determine the average moisture content of the chips passing through the conveyor belt and to detect surface foreign bodies that are not controlled by X-rays such as rubber, plastics, or others of lower density.

 

As the raw material is mainly cut into chips in a wet state and according to the origin and type of wood there is variability in terms of moisture content, having accurate and objective information in real time is a useful tool to adjust the subsequent processes of defibration and drying.

 

Gluing – Urea formaldehyde content Quantification or Classification

print_urea

Numerous adhesives, binders or resins such as urea formaldehyde, among the most widespread for their enormous advantages in particleboard production, are applied in the gluing process. The mixture of the wood chips together with the adhesives determines the consistency and quality of the board resulting from pressing.

The Visum HSI analyzer allows real-time monitoring, classification, quantification and determination of the spatial distribution of this adhesive compound without the need for destructive or laboratory techniques and thus detects anomalies to optimize the gluing process or formulation. 

 

Pressing and curing of boards

The pressing process is not a uniform process since to a large extent, the curing will depend on the variability that exists in the subsequent stages of the manufacturing process. Here at IRIS Technology, we find that the wood industry uses different scales to determine the quality of the curing of the boards and that it currently extends to a few samples produced per batch and destructive.

 

Also through IRIS hyperspectral systems, it is possible to observe and classify the curing factor of complete boards, unit by unit, obtaining chemical and spectral information of each pixel observed by the system, becoming a crucial instrument in the final quality control of the particle board.

curado

Impregnation – Moisture Control In-Line

Finally, impregnation is the process by which the paper layer that acts as a decorative coating for the particleboard is impregnated. Moisture is the main quality factor here, as it will ultimately affect the quality and durability of the impregnation. The hyperspectral systems imaging Visum HSI at this point is able to determine the homogeneity and quantify the moisture so as to be able to detect and correct deviations or anomalies that will result in losses, claims and returns.

print_humedad

For further information about us and our hyperspectral systems, and applications please contact us at info@iris-eng.com.

By IRIS Technology Solutions
Industry-4-0, Pharma-4-0 31 March 2022

NIR technology and Raman spectroscopy: introduction and applications in the pharmaceutical industry

NIR technology and raman spectroscopy
Share post

In the following article we will address the main applications with NIR technology and Raman spectroscopy, in real time, for the control of manufacturing and quality processes both for pilot plant – in tune with the Quality by Design (QbD) concept – and for industrial scale-up. In addition, this article is intended to be a starting point for industry professionals to raise questions about how to optimize control with process analytical technologies (PAT) for efficient management and implementation of a continuous manufacturing model.

 

Raman and NIR Spectroscopy

 

Both technologies have in common that they are photonic techniques – they take advantage of the properties of photons or light and their interaction with matter – diagnostic and non-destructive, allowing chemical and structural information to be obtained in seconds from almost any organic or inorganic material or compound. Hence, their use in laboratories is widespread in different industries and they are analytical techniques known by quality control professionals.

 

For those who are not laboratory professionals or are just entering the field, it is essential to start with a few brief concepts and examples to understand its applications.

 

Raman spectroscopy is a technique based on the inelastic scattering of light. Inelastic or Raman scattering occurs when the energy changes during the collision between the monochromatic light and the molecule and, therefore, the frequency of the scattered light also changes. These changes provide information about the molecular identity and structure of the samples or material being analyzed.

 

Near infrared spectroscopy (NIR) is a technique based on the interaction between electromagnetic radiation and matter, within the wavelength range of 780-2500 nm. These absorbed radiations can be related to different properties of the sample, providing qualitative and quantitative information. The near-infrared range is characterized by weak overtones and combined bands arising from the strong fundamental vibrations of O-H, C-H, C-O, C=O, C=O, N-H bonds and metal-OH groups in the mid-infrared range.

 

However, both Raman and NIR spectroscopy devices in real time are optical (vision) devices that work with artificial intelligence. The information they collect from the spectrum of the analyzed object is interpreted by a mathematical model – chemometrics – called a “predictive model” that tells the system what it is looking at. A very simple example: if we want to control the Paracetamol content of a 1mg. form, the mathematical model that analyzes the process must know how to correlate the spectrum corresponding to that value and for that it must know what is 0.8 – 0.9 – 1.1 and so on in the range of interest to be controlled. The predictive model is a mathematical model that essentially correlates a spectrum with a reference value. This reference value comes out of the traditional laboratory analysis.

 

Let’s get down to the important: What use are these systems in my factory?

 

Applications of real-time NIR technology:

 

1) Raw material identification: Identification of raw materials is a routine task in the pharmaceutical industry. These tests are carried out before the materials are processed, in order to avoid errors as much as possible and thus save time and money. This material testing applies not only to purchased materials (e.g. excipients), but also to some internal material transfers, e.g. APIs manufactured in another plant. The latter is very important to take into account when wondering why we have problems in mixing some formulations with certain raw materials.

2) Homogenization: Once identified and weighed, raw materials usually require homogenization of the different components. This is a critical step in the manufacture of solid-state pharmaceutical products, as it has a direct impact on the quality and homogeneity of the final product. The homogenization process is mainly affected by physical properties such as particle size, shape and density. Mixing endpoint and homogenization are not the same, not in terms of regulation according to the European Medicines Agency (EMA). From IRIS Technology we try to raise awareness on this point, which is sometimes confused, to provide in-line control solutions that are homologous to the control protocols established by the EU and Spanish regulations.

3) Granulation and sizing: Sometimes the different ingredients of the formulation do not mix well and segregate during homogenization. Therefore, it is desirable to granulate powdered ingredients by compression, dry granulation or in the presence of a binder under wet conditions. Most spectroscopic uses focus on the determination of water during wet granulation or drying after granulation.

4) Extrusion: NIR spectroscopy has been widely used in hot extrusion to monitor both API content and solid state of extrudates and to identify interactions between ingredients.

5) Tableting: This stage of the process is the closest to the final product. Therefore, it is sometimes easier to control the quality of the product directly in the press, especially if there is a subsequent coating step. At this point, NIR can also play an important role.

6) Coating: The coating process is a crucial step in the manufacture of solid oral preparations. In fact, the coating can act as a physical screen to avoid the effects of oxidation, moisture and lighting conditions in order to improve the stability of the final product or intermediate products in the process. The coating can also play an active role in the protection (gastroresistance) and release (modified release) of the drug in vivo. The homogeneity and thickness of the coating are important in controlling the timing of drug release. Many offline techniques are available to control the coating thickness, such as changes in weight, height or diameter of the coated granule/tablet cores during processing. In-line NIR technology is especially useful for monitoring water-based coatings and is a technique that saves hours of analysis, which we have discussed in particular in this other article.

7) Final product control: An important part of final product quality control includes the analysis of all batches produced to avoid out-of-specification results. This control point, although it is too late to avoid losses, can also be performed with portable (handheld) NIR tools and in just seconds analyze dozens of units (homogeneity, concentrations or other parameters) at the line.

 

Real-time Raman spectroscopy applications

 

As we will see below, this analysis technique has some applications similar to NIR spectroscopy and others very different because it is a technique with a much higher precision than NIR and that IRIS Technology uses in the systems we manufacture when we work with APIs with very low concentrations (typically <0.5) or in aqueous matrices where the amount of water generates a lot of noise in the analysis with NIR equipment.)

 

1) Raman spectroscopy for API identification: As each API has its own Raman characteristics, Raman spectroscopy can quickly and accurately identify the active ingredients, has a very low prediction error and in some cases has a detection limit as low as ppm.

2) Raman spectroscopy for the quantitative and qualitative analysis of formulations: The composition of pharmaceutical preparations is relatively complex; however, Raman spectroscopy remains one of the rapid detection methods if the excipients are simple or just an aqueous solution.

3) Raman spectroscopy for detection of illicit substances: Raman spectroscopy can be used for trace detection due to its sensitivity, speed and accuracy. In general, small amounts of illicit drugs cause drug safety incidents, and Raman spectroscopy can be used for illicit drug detection.

 

Benefits of applying NIR and Raman technology in production lines

 

In general, there are two fundamental advantages of Raman spectroscopy and NIR technology on production lines over traditional laboratory methods:

 

The first advantage would be the monitoring of continuous manufacturing. The pharmaceutical industry works mainly in such a way that the final drug is the result of several independent production steps. These can also take place in different geographical areas, which entails shipping and storing the different intermediate products in containers until the next manufacturing facility. This increases the risk of degradation over time or due to environmental conditions (light, humidity, etc.). One way to address this problem is to move from independent batch work to continuous manufacturing with the help of monitoring technologies such as real-time analytical control equipment.

A continuous process or continuous manufacturing is one in which materials are continuously loaded into the system, while the final product is continuously unloaded. Unlike stand-alone batch manufacturing, this concept involves the total connection of production units, with the use of PAT systems, along with process control systems to monitor and control the integrated manufacturing plant. Continuous process units are usually more efficient, more productive, with reduced volumes and less waste compared to classical process units. Therefore, these types of production units can respond more quickly to drug shortages or sudden changes in demand or needs (such as in a pandemic). In addition, their small size allows them to be transported directly to where the drugs are needed. However, a thorough understanding of the process, including the different connections between its processing units, is necessary.

The second major advantage is to reduce sampling and analysis time, and this is very important in biotech processes in their research, development and production phases. So far, most of the data are obtained with off-line instruments and methods.

 

Specifically for Raman, Raman spectroscopy is a powerful instrumental technique used in various types of pharmaceutical analysis. The superiority of the technique depends on the molecule of interest, the concentration level, the matrix or solution, other interfering species present and the desired sampling method. For many applications, Raman spectroscopy may be the best answer for identification and spectroscopic control needs. The role of Raman spectroscopy as a quantitative analytical tool is increasing due to the simplicity of sampling, ease of use and applicability to aqueous systems.

 

As manufacturers and system integrators of systems that operate with Raman and NIR spectroscopy, IRIS Technology collaborates with numerous pharmaceutical, foodstuffs, chemicals, among others, companies in the development of analytical solutions and the implementation of control systems, in turnkey projects ranging from technology, adaptations that may be necessary, data modeling, installation, validation and even homologation.

Here you can find the complete range of Visum® analytical equipment.

We hope this article has been of interest to you and as always, if you have any questions or even suggestions, you can write to us at news@iris-eng.com.

By IRIS Technology Solutions