Who are you?
Laurent Truscello: I am Laurent Truscello, Head of Products and Innovation at Carl Berger-Levrault. All sectors of activity have started to instrument and monitor their assets in software such as the ones offered. 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 well beyond cmms?
Laurent Truscello: It's a bit old school to talk today about CMMS – computer-aided maintenance management – or EAM; sometimes we say Asset Management. There are different terminologies to finally translate traceability, knowledge of this equipment, and how we will optimize them within the process. As I told you in the introduction, it has been more than thirty years that companies have been equipping themselves: the largest, then the most modest in size have been equipped to be able to control their wells; and then, as a result, maximize their production.
To answer the question, are we still talking about CMMS? Today, we are going to talk about CMMS 4.0 to be in the trend of Industry 4.0. We will perhaps speak more generally of a digital platform for equipment. We will begin to integrate a set of other concepts. What will change is that the body of management remains necessary, and it is intended, graphically, in these technologies – the web, mobility. So there are things that have evolved anyway, while being called "maintenance management". That is to say, we bring information to technicians in the field, and in exchange, we will obviously share this information through mobility or other technologies.
But where I would say that the factor evolves over the years is from two angles. The first is management; we know it, we have already talked about it. The second is rather everything that will concern the digital representation of equipment. That is to say, just as we represent in 3D the parts that we manufacture, the equipment that is in the production line are also modeled by the manufacturers. And the idea is not only to have the understanding and traceability of the activity that is carried out on this equipment – their knowledge and the activity that happens on it – but also to understand where it happens on this equipment, to better understand the equipment that is more and more complex, where we must carry out the maintenance intervention. You need this valve, this transporter trolley, this motor, this robot – because we have a lot of equipment of this nature in the sectors of activity that we just talked about. And so, as the equipment is becoming more and more complex, we also need to have a representation to help us better understand them and to understand where failures may happen in order to better respond to them.
You talk about process control in cosmetic pharmacy. Right away, you said, "Knowledge of the equipment." A process cannot be mastered without equipment, without a detailed knowledge of what makes it possible to produce?
Laurent Truscello: What makes it possible to produce, usually, there are several things. There is the raw material, which is at the beginning of the process, which is going to be processed. You have the means. And the means, they are at that time of two main natures: the human means, the people who are there to control, to feed; and then the equipment, which will themselves perform a function of manufacture, packaging, control, whatever. And so, unless you're really in the sewing manufacturing business for example, and again, there would be equipment, today, it's clear that it's an important part of the process, which is an element, precisely, that communicates more and more. It is no longer simply a static element that produces something, it is an element that will speak, that will exchange much more with its human or machine environment.
So here too, your raw material is data?
Laurent Truscello: That's right. And these data, they come to be fed by the graphic aspect that I was talking about, the management aspect, and obviously, new data that arrives en masse: either by SCADA tools, supervision tools that are already in place, or thanks today to the democratization of connected objects. We complete the information thanks to these objects, which are already integrated more and more inside the machines themselves, or we add others when we are in particular contexts; since even if the machines are increasingly equipped with measuring elements, obviously, these machines are integrated into a more complex system. When you are in pharmacy or cosmetics, it is a set of end-to-end equipment that will be brought to produce or make a finished product. And so, in this context, we may still have to complete the instrumentation. So it's this set of additional and existing data that's going to bring this real vision of the equipment for analysis.
And where we're starting to switch to what we can call 4.0, it's really this ability to collect the measurement – that, we could already start to do it – but it's [this ability] to analyze it in the light of the history and understanding of current equipment, to propose operating models by detecting weak signals , in order to propose the maintenance prognosis. That is to say, no longer only and simply technical acts, but sometimes, it can also be adjustment in order to avoid increasing wear, a heating phenomenon, which will then lead to an unavailability of all or part of the process.
Can 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 be a flowmeter as well, which produce their own data. So you add an extra layer, you use that data. How does it work? Who has the truth in the end, who decides?
Laurent Truscello: So, in any case, the one who decides, it is still today someone who will make a human decision. That is to say, in any case, what we have is the maintenance prognosis that will lead to someone being alerted to an information, an act that he must perform. And it can be an act of control, sometimes, an act of verification – because you can also be supervised. We will nevertheless check, especially at the beginning, that what is being proposed is sometimes consistent. And we're really into this notion of alert.
After, what exists, on the other hand, what can be automated, already, is loops of autocorrection of the measurements. That is to say, when we come to collect information, not to mention the complexity of assembling this information – already just the raw data – if a detector, a sensor begins to malfunction, today, we ourselves have filter algorithms that will detect that the sensor itself is drifting, and that it is it that is giving erroneous information.
And so you put your finger on an essential element, which is that trust in data is an important element. And so you have to have systems that are able to partially self-control. Then there is also blind trust in the system. The goal is to analyze weak signals, it is to understand sometimes complex systems to help in certain situations. We are not on the total instrumentation of a line driven by maintenance assisted by artificial intelligence. Today, we are on isolated projects of critical machines or sets of critical systems to improve an extremely targeted productivity, with very precise results expected.
So if we want to be concrete, now you have customers in pharmacy, in cosmetics. What do they expect from you? What did you develop for them? What do they use at home?
Laurent Truscello: Already, what they are using – and they seized very quickly – what is called CMMS 2.0 or 3.0; that is to say, the fact of already having traceability, data, and a history of their equipment. That's what we're going to find in a generalized way, at least on all actors of a certain size, although there are always some who have Excel files, and who begin to centralize them, or to share information when they have several sites. So we're going to say, the fairly classic things, the electronic signature, the traceability of information.
Because as they said, you asked me the question: is the equipment part of the process? Well, the equipment is part of the process since when they have certification audits – there are some in the pharmacy in particular – the equipment and processes related to maintenance are audited in the same way as the production processes. We must guarantee who has worked at what time, on what product, in relation to what batch. So obviously this notion is important. Today, we have a trend, which is still progressive, to move towards technologies around connected objects, but it is a trend that is coming gradually. That's it, and we hear a lot about it, but come to hear about it...
In concrete terms, what is it?
Laurent Truscello: Concretely, it's going to be to instrument pieces of lines, or pieces of process – because we judged that these precise equipments were critical – and to monitor them to determine the weak signals. The objective when we are in these strategies is twofold. This means increasing the performance of equipment while reducing preventive maintenance. Because if you want to, it's pretty simple on a complex system to prevent it from crashing. Just go and watch it every day, every hour, every minute and constantly act on it. And so you're going to maximize your tours, maximize your lubrication, maximize your maintenance. So it's this whole notion of balance. And so when we are in the search for cost optimization and quality, we will go towards this type of technology.
However, as I said, today we have a few projects that are pilot projects. There, we are going to be on very specific and very precise things, to optimize what I have just given you. The pharmaceutical or cosmetic industries, they are still cutting-edge industries, so they already have management tools, they already have supervision tools. So often, we will use the existing, and we will improve it to take a new step and move from curative maintenance to preventive or programmed maintenance, assisted – I'll call it that – by artificial intelligence; because we want to optimize, we want to be very precise, and we need at that time to have use of certain technologies.
This is not too much the case today, but I think a lot about the future, too, about energy gains. In the building industry, for example, in other sectors of activity, we feel that there is a will, because the energy stakes are high. But I am convinced that we will have this problem to address, or this desire to address energy consumption on equipment.

In the cosmetic pharmacy sector, are there any peculiarities specific to this sector?
Laurent Truscello: Compared to other sectors of activity, it is this very, very strong desire for traceability. That is really very, very important to guarantee this historisation. And so, it also means, if tomorrow elements are driven by the computer, well this notion of guarantee of what was done, how it was done, it is an element perhaps stronger, predominant compared to other sectors of activity – on the equipment itself ... No, because clean rooms can be found in other sectors of activity. I would say that all this "equipment" aspect, we will find it a little in other sectors of activity, it is not a specificity. What I would really note is this notion of traceability; and obviously, I did not note it, but security. And so, on this point, this notion of quality, control and safety is obviously eminently important.
Traceability, safety, do we go as far as responsibility?
Laurent Truscello: It raises questions. Indeed, if the algorithm is the one that drives the equipment. Today, we have not crossed that threshold. The algorithm offers something to technical teams and helps them understand better. But we are not in the algorithm that acts automatically on the actuators of the equipment. This can already for the moment create a barrier and avoid this type of response right away.
How quickly will this evolve? It's hard to say, especially if we start to move towards complete chain systems, which intertwin with one another. As long as we are on very targeted issues... But we, at least for the moment, have made the choice to be in the audience, really – that's the clear word – and not in the action. This means that it is not the algorithm that acts on the system. The algorithm, it informs, it feeds the reflection. He can also propose things, that is his goal. But on the other hand, it does not act.
What's next, then?
Laurent Truscello: I think that there may be a new element, and that must be taken into consideration. Today, we are in the continuity of the acquisition of data, the processing of this data, to make a proposal, I am not going to go back over that. Maybe what will evolve is with the first mobile apps. We have started to bring this information as close as possible to the field, and we have begun to give instruments to the technicians, the agents in the field. It is clear that with these new approaches, there are new technologies that will also help officers in the field, in real time, if only for their safety. So it can be augmented reality that assists on some complex missions. It can be communicate in real time about the fact that when he is in front of an installation, he sees if it is powered, we can see if there is any rest of charge in certain networks, we can tell him "be careful, the valve". In fact, sometimes, on complex systems, we have valves nearby, so "be careful, it's not valve A, it's valve B that you have to turn." And we will be able to give him real tools to assist on complex missions.
And so I think that bringing these notions of digital twins, data in the field, and not just having curves or that kind of thing, but in the inlay of reality or in situation facing the equipment, it's going to be an issue of tomorrow because the equipment itself is more and more sophisticated. How do we bring this technology, this information to the agents in the field? So that's one of the topics on which Carl Berger-Levrault is working a lot, particularly in relation to what we can call augmented maintenance. How we find technologies to conduct this information as close as possible to the agents.
Interview by Nicolas Gosse
www.carl-software.fr