Resources

White Paper n°1: Get the keys to guide you towards Industry 4.0

Posted on: 10 February 2023

The decarbonization of industry appears today as a major issue, both for economic, geopolitical and environmental reasons. Energy renovation, use of renewable energies… what are the actions to be implemented to achieve this? How can manufacturers get support today?
To help you in this transition, we have written the Dametis White Paper, in 3 chapters, so that you get the keys to guide you towards industry 4.0!

The drafting of this White Paper was possible thanks to Dametis experts:

Julian Aristizabal
Co-founder, CEO

Jeremy Barrais
Product Manager

Nicolas Duran
Co-founder CTO

Sebastien Papouin
Technical Director

Cyril Quemeneur
Energy Engineer

Chapter 1: move towards industry 4.0 – data and human expertise, at the heart of your decarbonization strategy

I. Memory and environmental intelligence

If “the development of full artificial intelligence could mark the end of the human species” (Stephen Hawking, 2014), intelligent software can mark the end of energy waste in industry. For example, the energy data that comes into play in the manufacture of a product – from mascara to automobiles to puree sachets – far exceeds the storage and processing capacities of the human brain.

• An “energy memory” already outsourced

Naturally, the professionals therefore began by externalizing their “energy memory” in paper files and Excel tables. This is the case when an operator reads the meters on a printed sheet and puts it away in a filing cabinet, before a colleague possibly copies this data onto the computer, with more or less errors. Same phenomenon of outsourced storage when various software doze in a corner of the factory, keeping without doing anything data of all kinds, including energy.

• Limits of Excel tables

Julian Aristizabal, CEO of Dametis: “Today, many industrial sites manage their energy with simple Excel tables. This involves time-consuming and hazardous data recovery work – during tours5 of the factory, which in the absence of automated transmission can represent 30 minutes or even an hour per day – then integration, a lot of copying and pasting, rewriting errors, a stack of versions created by different users... This method takes away precious time to reflect on this data (which is in any case incomplete and unreliable compared to that which would be reported by a good EMS). "

• Humans and AI together in the face of the ecological challenge

A software measuring the environmental performance is therefore (among other things) a new factory memory. When this software is sufficiently sophisticated, the data in it is correct, tidy and easy to access, contextualized and non-redundant. The particularity is that this memory can be mobilized simultaneously by two categories of brains: human and algorithmic. If we have to worry that in general, in our societies, “the computer comes to represent an ideal in the light of which real thought perversely ends up appearing deficient” (Matthew B. Crawford)6, however, it must be recognized that the human mind cannot meet the challenge of energy saving in industry alone.

• "Environment" conductor software in the factory of the future

Already essential in current factories wishing to move towards the “minimum attainable energy” (MEA), software will gain in importance over the growing automation of production sites.

“Programmable machine tools, welding and painting robots, remote-controlled trucks, handling and assembly automatons have long been part of the factory and the storage warehouse, recalls Charles-Édouard Bouée in his book Confucius and automata ( ed. Grasset, 2014)7
.
But the new generation of this equipment will be nothing like the previous ones, because they will acquire more and more intelligence and, thanks to the Internet, they will be able to connect and communicate with each other. »

In Industry 4.0, environmental performance software will be the conductors of the ecological challenge in this “new cyber-physical reality”.

• The human remains essential

Julian Aristizabal, CEO of Dametis:
“The software is based on human-machine collaboration. Because in a factory, we always end up being confronted with exceptional situations, which require us to go through the human again. Software does not create expertise, it works from human expertise written in algorithmic form. There are also things it cannot do, such as (re)calibrating sensors8 – which inevitably drift over time, in other words the zero shifts and the data reported is false. »

II. Environmental expertise in software

• “Expert systems” at the service of manufacturers

A collaborative platform for environmental transition should ideally concentrate, in the hands of each user, global human expertise in industrial environmental efficiency. For this, it must be a true expert system.
“An expert system is an artificial intelligence (AI) computer tool, designed to simulate the know-how of a specialist, in a precise and well-defined field, thanks to the exploitation of a certain amount of knowledge provided explicitly by experts in the field. »

• Challenge factories with regard to the best global performance

In addition, the expertise provided must be sufficiently rich to integrate the best environmental scores (energy among others) at the global level, updated, all industries combined.
Le EMS software can thus challenge utilities and processes by comparing them to the best performances in the world. Of course, there is no pre-made reference framework that simply needs to be “poured” into the software… This data must come from cumulative field experience (factory visits and audits, implementation and monitoring of plans). measurement…) of the company providing the software, supplemented by specialized documentary research.

• Users of an EMS can increase their energy skills

By nature, expert software transfers to manufacturers increased knowledge traditionally held by employees, service providers and consultants. However, there is no risk of loss of energy skills internally, the software is not a "black box" from which strange recommendations and reports would come, but rather a transparent and intuitive tool at the service of the 'human.
Generally speaking, “software must allow user autonomy – particularly in France where we see fairly strong technical maturity, with very qualified operators – by being flexible and open. » (Julian Aristizabal, CEO of Dametis).
The Dametis expert system is defined by a double transfer of expertise: on the one hand (and by definition), a process of concentrating the knowledge of our experts in the platform, on the other, a process of disseminating this knowledge to of all users (especially on-site operators).
Our users, who invest themselves in using the software, continually increase their level of skills and gain autonomy on the topic of environmental performance.

III. 4.0 artisans of environmental data

Software must first collect, seconds after seconds, a large amount of data, wherever it is: PLCs, ERP, MES, sensors, virtual sensors with algorithms, etc.

And as a cabinetmaker studies his wood before working it – is it robust, irregular, knotty…? -, software must “understand” its material (the data) before doing anything with it. Is the data incorrect (sensor drift, configuration error, etc.) or correct?

• Reflect factory life and remove “technical debt”

“I have visited factories in which the software data was so disconnected from reality that the tool had become unusable”, underlines Julian Aristizabal, CEO of Dametis. These technical debts concern, to varying degrees, 90% of the software I encounter.

What some software designers forget is that manufacturers spend their time looking for solutions to concrete problems, and therefore modifying their installations. Software must reflect reality and take into account the most minor changes which, put together, over the months, shape the factory. »

• Examples of daily changes to take into account

The software must constantly have a critical look at the data but also eliminate “technical debt” by assimilating everyday changes (powering a process, configuring a utility, etc.).

A tap to interconnect two cold networks will change the performance of the two networks, an automation engineer can easily change an addressing to optimize communication between two automatons. Intelligent software must be able to follow these developments.

Would you like to obtain and read the rest of the White Paper in order to obtain all the keys to guide you towards Industry 4.0?

Fill out the form below ↓

White Paper No. 1