Digitalization of waste recycling services: a great story… that concerns you! By Olivier Pagès

We can easily compare industrial sectors to gastronomic recipes: some of them are traditional, others are more contemporary. In terms of waste collection and recycling, we used to be more traditional. But this was way before the leader of the recycling sector, SUEZ Group, decided to force the sector to enter in the new era of digitalization.



When industry meets technology…

The story is edifying, and characteristic of a virtuous meeting between an industrial need and a technology. It is also a meeting with a start-up dedicated to B2B innovation through the creation of critical data for a worldwide leader in its sector. It all started with the presentation by ffly4u to Suez teams in Occitanie, of the connected drums solution developed by ffly4u. It is based on “Edge AI Low Power®” technology, allowing embedded processing (in our ffly4u device) of the data produced by the movement sensor through Artificial Intelligence, which means Machine Learning and Deep Learning. The demo consisted in showing how a connected drum is able to differentiate its rolling on the ground from its rolling on an axial drum. This identification of drum life phases makes it possible to accurately compute the daily length of unwound cable on each drum with a success rate close to 95%. At the end of 2020, this data had become a “must have” in the cable and telephone fiber sector – an indicator of the working site progress – which prevails today in most of the calls for tenders in Europe and Middle East. 


The skip filling alert, a key indicator of the work in progress 

The Suez teams were then convinced of the relevance of our technology to create new specific business data, more valuable than the geolocation of objects. To digitize their business, they came to the conclusion that their central and differentiating data was the skip filling alert. To do so, it was necessary to identify the number of compactions, consisting in compressing, by a roller at the end of an articulated arm, the contents of the skip. The embedded “Edge AI Low Power®” technology is essential in this use case. Thanks to this innovative technology, the skip is able to identify, through the recognition of the vibratory signature of the arm on the skip, the action of the compressor arm.  


5% reduction in greenhouse gas emissions (GHG)

After a validation test of the end-to-end service, integrating at dock/off dock geolocations, loading / unloading alerts, emptying and other presence on industrial sites, 2 types of dashboards have been designed, a daily and a weekly one. The deployment on 13 sites and more than 200 skips was then implemented very quickly at the end of 2020 allowing a reduction of 5% in (GHG).

This is an excellent example of the value created by a leader in a traditional sector through technologies linked to the production of critical data. Each industrial sector is or will be concerned in the near future: we have already digitized the cable/fiber and waste recycling sectors, and also returnable transit packaging in the aeronautics industry.


New business data for a quick ROI

Each industrial sector will be revisited through the production of data, for a double challenge: a new level of industrial performance by reducing costs, and above all, by the monetization of business data that brings value to your own customers. Thus, creating a new source of income for your benefit.

Believe me, your job is already impacted … whether you are Coq au vin or molecular cuisine, your job will change in a sustainable and virtuous way through the valuation of business data. That’s for sure!

Remember the story of Suez – ffly4u. Yours is on the way!


Skip filling alert: myth or reality? By Nghia Phan, CTO at ffly4u

SUEZ use case: our CTO gives you an overview of the technical challenges to compute the skip filling rate, real KPI of the work in progress in the recycling industry.


What were the technical challenges to meet SUEZ business needs?

Even though one may not  call it as a technical challenge, the most important for us in the beginning of this project was to fully and deeply understand the complete operations of a waste collection center and understand the gain in operational performance that our customer was looking for. Without such deep understanding, it was pointless to go any further. A recycling business operates a limited number of skips, manages different type of wastes/items to be recycled, has limited number of docks, and also shares common resources such as collecting trucks and special compacting equipments. A limited number of skips means that you have to rotate them between the waste collection center (where individuals or businesses would drop off their wastes) and the actual waste recycling/processing center where the wastes are further sorted and processed.

Eventually we came to the conclusion that the Return On Investment of this project was really based on our ability to optimize the collection of only fully filled and compacted skips and hence save thousands of gallons of gasoline.

So the overall technical challenge was to be able  to determine where and foremost when a skip is ready for collection.

What available information could you use to develop a customized solution?

The short answer is that there were no readily usable inputs. As explained earlier, we spent a fair amount of time with the operators in the field to understand the business operations: what information the operators was collecting manually? How this information was then processed and used? For which purposes? What were the decisions they would take based on the manually collected information?

Once we had this understanding, we had to figure out the right technologies and the right “IOT” device to collect this same information but in an automated and systematic manner and then, how to process and report the data and associated analytics to the operators so that the correct decisions could be effectively taken.

The information to be collected was:

  • Very accurate location of each skip, especially when they are located on a specific dock in a waste collection center or when they are located in a waste processing center
  • Type of waste collected in each skip
  • Number of compacting events
  • Number of loading and unloading of skips
  • Duration of stay of a skip on a given dock
  • Number of emptying of skips. Emptying a skip allows us to reset the number of compacting events
  • Number of trips of a skip

The key differentiating and proprietary technology that ffly4u has developed and has applied in this specific use case is called EDGE AI Low Power®: we are processing the data locally within the device (aka “on the EDGE”) using Machine Learning / Deep Learning while minimizing the power consumption of such processing. In standard IOT devices, the processing usually takes place in the cloud with limited and poor data set because the IOT devices usually connect to the cloud using LPWAN network which has very limited bandwidth.


How do you compute a skip filling rate based on this combination of information?

Getting the exact filling level of a skip is the ultimate information that everyone in IOT is looking for. But the reality is that there is currently no affordable technology which is economically compatible with this type of low-value waste recycling business.

Nevertheless, at ffly4u, we managed to get a sufficiently accurate estimation of this filling level by combining the following information, obtained and enriched via EDGE AI LP®:

  • Type of waste: one can hence determine the volume density of the waste. Each dock is dedicated to a specific type of waste. Thanks to our technology, we are able to also assign / associate dynamically in real-time the type of waste to each skip.
  • Number of compacting events for a given skip: the lower the volume density of the waste is, the more you need to perform compacting to optimize the filling of the skip. This data is continuously adjusted by machine learning and our EDGE AI LP® technology.
  • Duration of stay of a skip on a given dock for a given type of waste. This data is continuously adjusted by machine learning and our EDGE AI LP® technology.
  • Number of loading, unloading and emptying operations which helps determining when to reset the number of compacting events between each rotation of skips between the waste collection center and the waste processing center.

The skip filling rate is a key indicator for Suez and more generally for the recycling industry as it has a direct impact on the skips rotation and eventually, on the quality of customer service. 

Interview of Thibault Goulin, Head Of digital solutions at Nexans.

What is the impact of COVID-19 crisis on the cable drum sector?

In the cable drum sector, we noticed an acceleration in the digitalization of activities. This acceleration comes from the need of improving cash-flow through the reduction of stock and a better management of capital assets. Our clients who have been affected by the crisis need to limit losses but also optimize the assets turnaround rate.

This crisis also had an impact on Nexans as we decided to equip all the drums whose size would be superior to 1.90 m with the same objective of reducing drums losses and optimize the turnaround rate. It is also very important in term of sustainable impact to optimize the whole flow of drums and make it more efficient.

Despite the crisis, we did not really notice a reduction of activities as the construction sites have been maintained and companies quickly went back to work after the confinement period. So, what we can say is that the digitalization of activities in the cable sector has been confirmed and accelerated during the crisis.

What specific needs from the cable industry do you address through your connected drums solution?

Nexans has developed its presence in 34 countries in multiple sectors. The client’s needs are very different from a country to another so our work is to provide a solution which is adapted to our client’s specificities.

As for example, more than 5 000 drums have been equipped by Nexans with ffly4u’s sensors in Switzerland. On this specific geographical zone, our client is more focused on the financial aspect which means the reduction of idle times, the monitoring of drums flow in real time, a better management of stock, optimize activities etc. All this information make possible to automize the whole chain from production to the end of the construction site but also monitor activities in real time, which is especially interesting in town where the regulation is particularly tough. This is a full solution as we also offer services of collecting and recycling drums which is part of a circular economy model.

We also address business needs of global players (metro project in Dubai, oil platforms in Russia etc.). We help the leaders of the sector to monitor complex flows between multiple actors. It also facilitates the follow-up of subcontractor’s activities who might be involved in the whole process.

Thanks to our work with emerging countries, we also developed a new function as there is a huge demand to avoid the theft of cable drums. We implemented an alert system to identify any suspect movements during the night for example which reduced significantly the number of thefts.

In a few words, we provide this solution to very different markets but we are able to adapt our services to each use case with the same technology.

What do you plan for the next 3 years in term of deployment of your solution?

So far, the connected drum solution has been deployed in 11 countries. There is a real business need which has been clearly identified in the cable industry and Nexans is the leader on the market. On a short-term basis, we plan to duplicate the solution to reach 15 000 connected drums by the end of 2020, and 100 000 units in the next 3 years on a global level.

Tomorrow, we will focus more on the data. We actually make the cable drum smart by creating data which increases significantly value on construction sites. The technology allows our clients to know, as for example, the residual cable length on a drum at the end of the day.

Another important point is the platform which is used by our clients to collect the data. So far, this platform has been managed by Nexans but tomorrow, we want our customers to be able to manage it and customize it on their side depending on their specific needs.

To sum up, Nexans addresses very different markets so our role is to provide a customized solution which is adapted to our clients’ specific business needs.

Discover more about Nexans :

What is temporarily delaying the massive development of the Industrial Internet of Things (IIoT)?

Many observers, even some actors in the digitalization and/or transformation of the Industry 4.0 are somewhat questioning about the difficulty, particularly in the industrial IoT sector, of deploying significant volumes consistent with the forecasts of Gartner and other Roland Berger on the masterful potential of the IoT.

There are objective reasons for this temporary delay in deployment. We are going to develop two of them, that we think are major:

1 – Core business and innovation, a difficult combination

IIoT creates its market around new value creations that generally have as their scope the core business of customers. There are many examples: embedding data on connected drums, on IBCs/handling equipment, modify the business model of project leaders. The scope of action of the Industrial Internet of Things (IIoT) is the customer’s business. It is both its strength and its weakness

It’s strenght

Because if we prove that, through POCs first deployments, our customers’ business is durably enriched, the adoption of these new technologies goes from the “nice to have” to the “must to have” stage and definitively redefines the scope of the business. This is what we have done with cable drums and other assets such as handling equipment, waste bins, connected craddles (used to carry motorcycles).

This is the future of IIoT : a virtuous change in the business. Not at the margin, in depth. And in this case, the future is more than promising!

It’s weakness, too

decision-making in large organizations is by nature difficult in professions where the Business Model has been fixed for several decades, even several centuries… Even if we are approaching a “must to have”, changing our ways of thinking to the point of selling data when our revenues until now come exclusively from the sale of products, is not an easy task. And betting on the status quo in some key accounts (or SMEs) is less hypothetical than on the rapid implementation of change…

2 – Ploughing the value in surface is not sufficient

We dreamt up IIoT in the years 2014/2017: we believed that with 40 million of standard devices from China or Thailand, the business problems would all be solved! This is obviously not true! Pushed, it must be said, by some connectivity providers who launched the idea that the device would quickly become a commodity acquired in very large volumes, the actors of the IIot in Europe have often ignored the analysis of business issues! Similar to telephone subscription vendors, they considered that a GPS tracker, combined with a 3D Accelerometer, would be sufficient to meet all needs.

As a result, deployments are delayed because the business lines do not find the answer to the true value they are entitled to expect!

The Industrial Internet of Things (IIoT) market is in fact very fragmented: it must be organized by business-verticals both in terms of the value produced and its cost. We cannot provide the same service to the Aeronautic and the Retail sector: not the same sophistication, not the same volumes, not the same acceptable costs… and yet we are still talking about a base for geolocation of indoor or outdoor assets…
This implies going through a precise needs’ analysis phase, and above all adapting the device/data platform pair to the vertical-business concerned, even if it means adding specific functions:

Calculation of the residual cable length,

washing time of a plastic container in Cosmetics and Pharmacy,

predictive maintenance of rotating machines, etc.

It is for these reasons that ffly4u invented the Edge AI Low Power, through Artificial Intelligence and Machine Learning technologies embedded in the device… To stick as closely as possible to business needs and reduce the time of adoption of these new valuable parts.

And it works!
Have a good week.
Let’s ffly4u!


Industrial IoT Asset tracking: what about talking about the client’s business?

Whatever the type of technological services involved, it is always difficult to avoid the pleasure of explaining the “how”!

We always tend to talk more about technology, rather than the customer’s need or job. It’s in the DNA of the “engineer’s companies”! Especially in France, where culture is more “technological” than “market”. This is less the case in our Anglo-Saxon neighbours.

The field of industrial IoT, particularly in its asset-tracking component, is no exception.

Just look at the literature on the subject, both on social networks and on print, everyone is very happy to delight their interlocutors with more or less abstruse technical terms. We are entitled to wonder what our prospects really get out of all these details about the technical choices of our systems.

There are at least 3 reasons why our industry should focus on the “why” rather than the “how”:

  1. Our industry is young, we have to make the market understand the kind of value it can get from our technologies. Evangelization is necessary, and for it to be as effective as possible, it is necessary to talk about business value.
  2. The Industrial Internet of Things is a major innovation of this early century. To move from a POC phase to a real deployment, the stakes involved must be much higher than the constraints linked to change. The more we talk about the scope of the business, the better our understanding of internal resistance will be, the more effective our responses will be.
  3. More generally, talking about our customers’ business refocuses our concerns on the customer, not on technologies. This pushes our services to be more multi-technologies to meet increasingly diverse and multiform needs. For ffly4u, it is thanks to our customers that we have integrated new sensors into our devices, increased the requirement of our Software, integrated for the first time in the LPWan world, the Edge AI (Embedded Artificial Intelligence).
    Let us remain on this last point: it is surprising to note, particularly in our industrial IoT sector, that the “customer driven” approach pushes us to make our technological offer more complex, so that it “fits” as closely as possible with customer needs. This is the key, but it is also a real danger for us, asset tracking players: letting ourselves be led towards more integration of technologies by our market without strategic thinking is dangerous.

In fact, it is necessary to balance integration and specialization. This can be the beginning of defining a good strategic positioning in our sector.

Let’s ffly4u.

Have a good weekend.