Renault is moving up a gear in terms of optimizing the manufacture of its vehicles by having created a virtual duplicate of its factories and its Supply Chain. The device that the manufacturer calls “industrial metaverse” calls on Google to globalize the data and activate artificial intelligence algorithms to optimize its processes.
Global centralization of data and artificial intelligence
A central platform brings together all data from factories, vehicle assembly lines and the supply chain. From there, the manufacturer implements supervision and optimization algorithms based on artificial intelligence and machine learning. Renault has chosen the OPC Unified Architecture (OPC UA) standard in order to have a cross-platform and open source description for the exchange of data between sensors and Cloud applications.” Thanks to the unique structuring of our data, we are now able to scale and process data at group level » welcomes Renault. ” When others strive to capture data, create and improve their digital twins [Jumeaux numériques], us today, we were able to link all this, all our digital twins. All of our equipment at group level works together digitally, this is called the industrial metaverse continues the automaker.
This is what Renault presented to the press on October 25 at its Flins plant. Patrice Haettel, director of industrial strategy and engineering, Eric Marchiol, director of industry 4.0 and François Lavernos, director of IS/IT industry detailed the challenges facing the manufacturer. The presentation goes through a dozen stands that illustrate the progress made. This “mini show” is also for internal use in order to communicate for two weeks with the teams of the car manufacturer on its industrial achievements. This ranges from the collection of data from the field, the connection of equipment and to the algorithms for the supervision of manufacturing chains and the optimization of the supply of factories, the delivery of customers, as well as additive manufacturing technologies. – 3D printing – and operator training in virtual reality.
Significant financial benefits
The cost of deploying the various technologies between 2016 and 2022 amounts to 780 million euros. Therefore, the objectives of the transformation towards a central virtual platform are high. This new approach should make it possible to achieve 320 million euros in savings on fixed and variable costs by 2025. Similarly, it should lead to the release of 260 million euros in savings by reducing inventories. ” Centralization reduces inventory because you know exactly what you have and where it is. It is not useful to have duplicates. This brings 20% to 30% savings “ underlines Renault.Another objective is to reduce by 60% the time between the order and the delivery of a vehicle vis-à-vis the customer and to contribute to the reduction of warranty costs by 50%. Renault Group has created a platform that brings together with a single standard description all the objects, screwdrivers, robots and even packaging. A standardized data model can be used to describe a pump whether it is in France or in Spain. Each object is modeled, identified, connected, and has its digital avatar.
Renault has thus created a digital twin faithful to the reality of all of its factories and its Supply Chain. There are 8,500 pieces of equipment connected in the factories, 4,400 operator stations connected (fixed screen, tablet and mobile) and 10,000 energy sensors have been installed. In 20 factories, 600 items of equipment are equipped with vibration sensors in order to anticipate maintenance work on the motors. These are presses (107), machining centers (472) and paint air extractors (15). Supervision of the vibration aspects of European factories is carried out from a control room located in Flins. Since 2019, 300 alerts have prevented production stoppages, generating 10 million euros in savings.
In all, 60 industrial processes are modeled. This concerns screwing, machining, welding, stamping, heat treatment, electric motor process, etc. One billion Datasets are collected every day. “ These are very rich data, such as curves or photos “says Renault. The Supply Chain, for its part, tracks 90% of delivery trucks in real time in Europe by GPS based on the company Shippeo and Renault tracks the delivery of vehicles to dealerships, 700,000 have thus been tracked while monitoring their data of “health”, ie the condition of their batteries and tires in order to maintain quality at the highest level until delivery to the end customer. The creation of this Supply Chain control tower in the Google Cloud has improved fill rates, saving 8,000 trucks.
Real-time simulation helps you adapt faster
The digital twin makes it possible to simulate in real time the entire ecosystem of Renault factories and the innumerable relationships between digital avatars in order to optimize their functioning in the physical world. Real time allows you to intervene in the right place at the right time. In the event of an unforeseen event, an accident or a disaster, real-time simulation makes it possible to adapt more quickly.Artificial intelligence is mobilized on many processes. For example, Renault works with the Lille startup Buawei to identify on the assembly line whether the vehicles are equipped with the same tire reference. This reference is written on the tire but difficult to read by an operator, hence the advantage of using computer vision to carry out the verification. In the event that the references differ between the tires, the vehicle is removed from the assembly line.
Renault has developed an image database with Google; dubbed MP4 AI. This platform facilitates the development of new vertical solutions. Buawei’s solution, for example, is a vision control system that uses artificial intelligence models trained in the Google Cloud and then executed in the field, the so-called “Edge”. Renault relies on Google equipment, “appliances”, installed in its factories for local execution of algorithms in its workshops.
Finally, all the technological know-how developed by Renault as part of this virtualization of its factories and their equipment is marketed by Atos under the name Data @ Scale. Renault and Atos are targeting a turnover of 49 million euros and 18 active customers in 2027.
Key information on this subject
We would like to say thanks to the author of this article for this awesome content
Renault creates a virtual duplicate of its factories in order to optimize them
Find here our social media profiles as well as other related pageshttps://www.ai-magazine.com/related-pages/