Hyperspectral cameras for a sustainable future

White paper: waste no more
Recycling with hyperspectral camera

How recycling can be more efficient

How a spectral camera can improve recycling

Examples of applications and benefits

According to statistics, collected waste percentages in many European countries appear to be far above 80%. Germany, for example, gives recycling rates of 67% for household waste, around 70% for production and commercial waste, and almost 90% for construction and demolition waste. At the same time, there are countries where the recovery rate is less than 40%.

However, a closer look shows that most of the collected waste is currently used for energy production and burnt in power plants. In other words, waste is changing the format, not reused - we are still far away from our recycling targets. We are not exploiting maximum recycling potential, and much of the recyclable materials do not get recycled.

The benefits of efficient recycling are clear: recycling conserves natural resources and reduces greenhouse gases and pollution, as well as the use of fossil fuels in energy production: it reduces energy consumption for about 70% for plastics, 60% for steel, 40% for paper and 30% for glass.

What is more, it is not only about the ecological benefits:

Significant value lies in the material we waste. Efficient sorting and recycling of different materials can turn into profit with proper material handling methods.

Also, recycling and reusing of materials need to be cheaper and easier than using virgin materials. This potential is yet to be uncovered, as in many cases using natural resources in production is less expensive than using recycled material.

With political will in place and clear benefits listed, why are the recycling numbers still as low as they are?

Recycling can be more efficient

A typical waste management process includes the collection of waste to a recovery facility, segregation to different waste fractions, necessary cleaning and final classification to separate products which are then either incinerated to produce energy, recycled based on product type and purity, or placed to landfill.

The sorting process is a critical step in many types of recycling, from pallets to plastics, and more. Better accuracy means better separation of different grades of material, which results in higher value recovery. A typical sorting process is based on a mix of techniques and cannot rely on just one detection technology. In many cases, the available detection technology limits the types and the amount of the collected material that we can sort.

Today, most of the recovery or recycling plants use different technologies from bar code readers and RGB cameras to x-ray and eddy current systems. While they are capable technologies to a certain extent, they are not perfect solutions as they cannot recognise the material. For example, if a plastic bottle is missing a label with the printed barcode, it is not possible to say if it is PET or HDPE. Eddy current detector can sort out conductive metals but not separate plastics or pulp. RGB camera can sort bottles to transparent, black and coloured but is still missing the actual material information. Consequently, we lose recyclable material to landfill or energy production, while the recycled portion is not pure enough for possible reuse. The poor result can also cause a loss of profits, which makes recycling impractical or dependent on public support.

As different waste streams require different detection and processing methods to be recycled efficiently, current recycling methods are not flexible, efficient, and informative enough to tackle the challenge.

Currently, to make up for inadequate detection technologies, human labor must be used to make classification on materials based on their earlier experience and learning capability. Although this creates jobs, they are by far not the safest and most desirable of professions. What is more, picking waste from the stream by hand is slow, inaccurate, and expensive and yet, separating dangerous materials or plastic types in clear plastics bottles is still impossible. There is also the question of ethics: waste is shipped to lower cost countries where people - also child labor – is used to sort materials from conveyor belts manually.

A recycling plant must have sensors capable of separating different materials reliably and with high purity, and this is where spectral imaging can make a difference.

Examples of applications and benefits

Plastic recycling

Out of all the plastic manufactured, only 9% gets recycled. 12% is incinerated for energy, and 79% goes to landfills or nature. It is estimated that by 2050 there will be more plastic in the oceans than fish.

Majority of non-recyclable plastic waste comes from not being able to separate different plastic types from each other reliably.

When we sort and separate the collected plastic, we can re-use the high-quality and valuable polymers. The main objective in sorting is to reduce the quantity of non-targeted plastic polymers and to reduce the number of non-plastics like paper, metal, glass, oil, soil, or other contaminants. There may also be unwanted additives like flame retardants within the plastic, that can be detected, identified, and sorted with spectral cameras.

Most polymers have identifiable signatures in the NIR spectral region and can thus be sorted. However, many of the spectral signatures are close to each other. Here, the spectral camera’s high spectral resolution is a key to high sorting accuracy. With PP, PE, and PET plastics, for example, close to 99% purity can be achieved.

Sorting of black plastics

A large fraction of recyclable plastic constitutes of black plastics, used in particular in the automotive and electronics industries, which have added carbon-based pigment to produce the dark grey or black colour. Black plastic types have been notoriously difficult to identify, and so far, there has been no reliable sensor technique to sort these materials for reuse. Even NIR cameras struggle, as the black carbon-based pigment absorbs practically all the NIR light.

Development in spectral camera technology is changing this situation as well. In addition to NIR region, different plastics have characteristics spectral features in the longer infrared region (called mid-wave infrared, MWIR) where most black pigments are ‘less black’ (less absorbing) than in the NIR region. Thus, MWIR light can penetrate in and reflect from black materials, making their spectral identification possible. Spectral cameras operating in the MWIR region with required speed, resolution, and sensitivity for industrial in-line use are now available.

With a spectral camera that operates on MWIR region, we can sort black ABS plastics with close to 99% purity.

Below is an example of black plastics sorting measured in a laboratory with an MWIR range hyperspectral camera Specim FX50. Twelve pieces of ABS and PE were measured together with ten pieces of PS (34 altogether). For each sample group, half of the samples were shiny, and the second half with diffuse surface. The figure below shows that samples made of ABS, PS, and PE could be accurately sorted.

Material characterization for incineration

Although material recycling percentage is increasing, it will still be necessary to incinerate some part of non-recyclable material. These “waste-to-energy” power plants receive material from various sources like commerce, construction, household and industry and use this for generating power in Refuse Derived Fuel (RDF) power plants.

The value of RDFs is derived from the calorific content (Image KK) – which is determined by material type. Certain materials like glass, rock, or dirt, have zero calorific value. Water content and ice will also affect the process.

Precise combustion process control and calorific values can only be calculated based on proper material recognition. Hyperspectral imaging in the NIR spectral region is capable of providing an in-line solution for this.

Conclusion

We need to increase the percentage of waste that is recycled and not just collected and burned for energy production. To achieve this target, we need better detection systems. For instance, robots can work 24/7 accurately and efficiently without fatigue, handle hazardous waste, and operate flexibly for different waste streams - yet they need a visual aid to help them reliably identify the materials. Using hyperspectral imaging together with other technologies and sensors is a crucial step that will help us towards our goal.

Hyperspectral camera technology as well as analysis software are already available and in use in industrial surroundings, and their use is expected to grow at the significant market share. In the future, they will be extensively used and implemented due to the growing need to solve previously unfeasible sorting tasks.

Improved sorting accuracy increases the purity of the recycled material and as a result, the value. The percentage of waste that can be reused will also increase as a result. All this, with the support of political decisions, may yet bring a solution to the overuse of our natural resources.

As the hyperspectral camera hardware has improved and will continue to do so, it will also need algorithms, analysis software, spectral libraries, and other machine vision sensors
to produce a complete solution that will be the future of recycling industry.