CARL Berger-Levrault: software solutions to help make decisions.
Interview with Mr. Laurent Truscello, Head of Products and Innovation at CARL Berger-Levrault.
Who are you?
Laurent Truscello: I am Laurent Truscello, product and innovation manager at CARL Berger-Levrault. All business sectors have started to instrument and monitor their assets in software such as the ones we offer. Two years ago, we joined a larger group, in particular to support our international development.
Are we still talking about maintenance today, or are we going way beyond CMMS?
Laurent Truscello: It’s a bit old school to talk about CMMS – computer-assisted maintenance management – today, or EAM; sometimes we say Asset Management (asset management in the broad sense). There are different terminologies to translate the traceability, the knowledge of these equipments, and how we are going to do to optimize them within the process. As I told you in the introduction, companies have been equipping themselves for more than thirty years: the largest, then the smallest in size have seen themselves equipped to be able to control their assets; and then, as a result, maximize their production.
To answer the question, are we still talking about CMMS? Today, we’re going to talk about CMMS 4.0 in keeping with the trend of industry 4.0. We will perhaps talk more generally about a digital platform for equipment. We will begin to integrate a set of other concepts. What will change is that management remains necessary, and it is wanted, graphically, in these technologies – the web, mobility. So there are things that have nevertheless evolved, while still being called “maintenance management.” That is to say that we provide information to the technicians in the field, and in exchange, we will obviously share this information through the mobility or other technologies.
But where I would say that the factor has shifted over the years is from two angles. The first is management; we know it, we’ve already talked about it. The second is everything that concerns the digital representation of equipment. In other words, just as we represent in 3D the parts we manufacture, the equipment in the production chain is also modelled by the manufacturers. And the idea is to have not only the understanding and traceability of the activity that takes place on this equipment – their knowledge and the activity that takes place on them – but also to understand where it takes place on this equipment, to better understand the equipment that is increasingly complex, where maintenance work must be carried out. You need this valve, this conveyor truck, this motor, this robot – because we have a lot of equipment of this nature in the sectors of activity that we have just talked about. And so, as the equipment becomes more and more complex, we also need a representation to help us understand it better and to understand where the failures may occur in order to respond better.
You were talking about process control in cosmetic pharmacy. Right away, you answered “understanding the equipment”. A process cannot be understood without equipment, without detailed knowledge of what makes it possible to manufacture?
Laurent Truscello: There are generally several things that make it possible to manufacture. There is the raw material, which is at the start of the process, which will be transformed. You have the resources. And there are two types of those: the human resources, the people who are there to control, to feed; and then the equipment, which will itself fulfill a function of manufacturing, packaging, control, whatever. And so, unless you are really in the manufacturing business of sewing for example, and again, there would be equipment, today, it is clear that it is an important element of the process, which is an element, in fact, which communicates more and more. It is no longer simply a static element that produces something, it is an element that will speak, which will exchange much more with its human or machine environment.
Could there be a misunderstanding in the data, or even a competition on who decides, who interprets? You were talking earlier about an instrumented valve, it can also be a flow meter, which themselves produce their own data. So you add an additional layer, you use this data. How does this work? Who has the truth in the end, who decides?
Laurent Truscello: So, in any case, the person who decides is still someone who will make a human decision. That is to say that, in any case, what we have is the maintenance prognosis which will lead to someone being alerted to information, to an act which he must perform. And this can be an act of control, sometimes, or a check – because we can also be supervised. We’re going to check, especially at the beginning, that what is being suggested is coherent. There is this idea of a warning.
Afterwards, what exists, on the other hand, what can be automated, already, is self-correction loops for the measures. That is to say that when we collect information, without talking about the complexity of assembling this information – just the raw data – if a detector, a sensor starts to malfunction, today we have our own filter algorithms which will detect that the sensor itself is drifting, and that it is the one which is giving false information.
So you have put your finger on an essential element, which is that confidence in the data is indispensable. And so we need to have systems that are capable of being partly self-monitoring. And then there is also blind trust in the system. The aim is to analyse weak signals, to understand sometimes complex systems in order to help in certain situations. We are not talking about the total instrumentation of a line controlled by maintenance assisted by artificial intelligence. Today, we are working on isolated projects for critical machines or sets of critical systems to improve extremely targeted productivity, with very precise results expected.
So here as well your raw material is data?
Laurent Truscello: That’s right. And this data is fed by the graphical aspect I was talking about, the management aspect, and obviously, new data which arrives en masse: either by SCADA or supervision tools which are already in place, or today thanks to the popularity of connected objects. We complete the information thanks to these objects, which are already increasingly integrated into the machines themselves, or we add others when we are in particular situations; because even if the machines are increasingly equipped with measurement tools, obviously these machines are integrated into a more complex system. When we are in the pharmaceutical or cosmetics industry, it is a set of equipment that is brought together to produce or make a finished product. And so, in this context, we may have to complete the instrumentation. So it is this set of additional and existing data that will provide this very real vision of the equipment for analysis purposes.
And where we are starting to move into what we can call 4.0 is really this capacity to collect measurements – we could already start doing that – but it is [this capacity] to analyse them in the light of the history and understanding of current equipment, to put forward operating models by detecting weak signals, in order to suggest maintenance prognoses. That is to say, not only and simply technical acts, but sometimes it can also be adjustment in order to avoid increasing wear and tear, such as overheating, which will then lead to the unavailability of all or part of the process.
So if we want to be concrete, now you have customers in pharmacies, in cosmetics. What do they expect from you? What have you developed for them? What products do they get from you?
Laurent Truscello: Already, they are using – and they have very quickly adopted it – what is called CMMS 2.0 or 3.0; which means, the fact of already having traceability, data, and a history of their equipment. This is what we will find more generally, in any case for all the stakeholders of a certain size, although there are still some who have Excel files, and who are starting to centralize them, or to share information when they have several sites. So we’ll say, the fairly classic things, the electronic signature, the traceability of information.
Because as we were saying, you asked me the question: is the equipment part of the process? Well, the equipment is part of the process because when they have certification audits – there are some in the pharmaceutical industry in particular – the equipment and the processes linked to maintenance are audited in the same way as the production processes. We have to guarantee who worked at what time, on what product, in relation to what batch. So obviously this concept is important. Today, there is a trend, which is still growing, to move towards technologies based on connected objects, but it is a trend which is arriving gradually. That’s it, and we hear a lot about it, but between hearing about it….
What is that in concrete terms?
Laurent Truscello: In concrete terms, this will mean acting on pieces of line or pieces of process – because we have judged that this specific equipment is critical – and monitoring them to determine the weak signals. The objective of these strategies is twofold. It is to increase the performance of the equipment while reducing preventive maintenance. Because, if you like, it’s quite easy to prevent a complex system from breaking down. You just have to go and look at it every day, every hour, every minute, and act on it constantly. And so you will maximise your rounds, maximise your lubrication, maximise your maintenance. So it’s this whole idea of balance. And so when we are looking to optimise costs and quality, we are going to go towards this type of technology.
But as I was saying, today we have a few projects which are pilot projects. Here, we are going to be on very specific and precise things, to optimise what I have just given you. The pharmaceutical or cosmetic industries are cutting-edge industries, so they already have management tools, they already have supervision tools. So often, we will use what already exists, and we will improve it to take a new step forward and move from curative maintenance to preventive or programmed maintenance, assisted – I’ll call it that – by artificial intelligence, because we want to optimise, we want to be very precise, and at that point we need to use certain technologies.
This is not yet the case, but I think a lot about energy savings in the future. In the building industry, for example, in other business sectors, we feel that there is a will, because the energy challenge is strong. But I am convinced that we will have this problem to address, or this will to address energy consumption in equipment.
In the cosmetic pharmacy sector, are there any particularities specific to this sector?
Laurent Truscello: Compared to other business sectorsty, it is this very, very strong desire for traceability. It’s really very, very important to guarantee this ability to log everything. And so, this also means that if tomorrow elements are controlled by the computer, well, this idea of guaranteeing what was done, how it was done, is an element which is perhaps stronger and more overarching than in other business sectors – on the equipment itself… No, because clean rooms can be found in other business sectors. I would say that this whole “equipment” aspect can be found in other business sectors, it is not specific to them. What I would really note is this idea of traceability, and obviously I didn’t highlight it, but of safety. And so, on this point, this idea of quality, control and safety is obviously of great importance.
Traceability, safety, are we going as far as liability?
Laurent Truscello: This raises questions if the algorithm is the one controlling the equipment. Today, we haven’t gone that far. The algorithm puts forward something to the technical teams and helps them to understand better. But we are not in the business of algorithms that automatically act on the equipment’s actuators. This can already create a barrier and avoid this type of response right away.
How fast will this evolve? It’s difficult to say, especially if we start to move towards complete systems in a chain, which interlock with each other. As long as we are dealing with very targeted problems… But for the moment, we have chosen to be in the assistance business, really – that’s the clear word – and not in the action business. This means that it is not the algorithm that acts on the system. The algorithm informs, provides suggestions, that is its purpose. But on the other hand, it does not act
What comes next?
Laurent Truscello: I think there may be a new element, and one that needs to be taken into consideration. Today, we are in the continuity of data acquisition, data processing, making proposals, I will not go back on that. Perhaps what will evolve is with the first mobile applications. We have started to bring this information closer to the field, and we have started to give tools to the technicians, the agents in the field. It is clear that with these new approaches, there are new technologies which will also help the agents in the field, in real time, if only for their safety. So it could be augmented reality that assists with certain complex missions. It can be communicating in real time on the fact that when he is in front of an installation, he can see if it is supplied, we can see if there is a remaining load in certain networks, we can tell him “watch out for the valve”. Sometimes, on complex systems, we have valves in the vicinity, so “watch out, it’s not valve A, it’s valve B that needs to be turned”. And we’ll be able to give him real assistance tools for complex missions.
And so I think that these ideas of digital twins, data on the ground, and not just having curves or that kind of thing, but in overlay of reality or in a real situation facing the equipment, this will be what we talk about in the future because the equipment is increasingly sophisticated. How do we bring this technology, this information to the agents in the field? So that, for example, is one of the subjects on which CARL Berger–Levrault works a lot, particularly in connection with what can be called increased maintenance. How we find technologies to bring this information closer to the agents.
Journalist: Nicolas Gosse
