PartnershipPressEOLANE Launch BOB Assistant

15 October 2019by Joel Rubino


Cartesiam and éolane announce a breakthrough innovation in the industry: Bob Assistant TM, the first predictive maintenance assistant for industrial equipment, integrating artificial intelligence directly into the sensors.

Cartesiam, a B2B software publisher specializing in artificial intelligence embedded in objects, and éolane, a leader in industrial services in electronics and connected solutions, announce their partnership for the launch of Bob.

bob-assistant with NanoEdge AI Studio
Bob is the world’s first maintenance assistant to integrate artificial intelligence embedded directly in sensors. This assistant enables predictive maintenance in an industrial environment of all sensitive equipment, in total autonomy, based on machine vibrations.

According to Markets and Markets’ analysis, the predictive maintenance market is expected to grow from $1,404.3 million in 2016 to $4,904.0 million in 2021, with an average annual growth rate of 28.4% between 2016 and 2021. Bob is the solution likely to revolutionize this market with, for the first time, artificial intelligence functionalities directly integrated into a sensor capable of autonomous learning, without any specific link to an “intelligent” cloud. This technological feat, which reduces the cost of access to industrial predictive maintenance solutions, is the result of a partnership between éolane, for the electronic hardware and IoT solutions, and Cartesiam for the Software/IA part.


Imagine having a highly qualified predictive maintenance assistant in your factory, permanently available, listening to the machines, and able to warn you of any abnormal behavior before a problem impacts the production line! It is now possible: Bob fulfills this mission and performs a real-time diagnosis of the health of the equipment to be monitored.

The assistant is made up of vibration and temperature sensors which, thanks to its powerful embedded machine learning algorithms, allows it to understand its environment in a completely autonomous way. The sensor builds up his reference knowledge, and then monitor the behavior of the equipment on which it has been installed 24 hours a day.

At regular intervals, Bob sends by LoRaWan radio a report on the activity and health of the monitored equipment, as well as alerts in case of suspected anomalies (present or future). Bob is thus able to recognize the signature of normal or abnormal vibrations, just as Shazam* would do for music. As soon as spots a problem or a drift, Bob immediately transmits an alert, i.e. the result of its analysis, to a supervision console, an IoT platform on the Internet or an operator’s smartphone. Bob does not transmit data, only communicates the result of its analysis. So production data is never sent to the cloud.


Is it necessary to send more and more data to the cloud or to add intelligence to the connected objects? Bob can compute and analyze directly at the source, where the data is generated and then transforms it into useful information.

Completely autonomous, Bob also interfaces, if necessary, to the power of the cloud, thus making it possible to add context to the information that is feedback. Compatible with LoRa networks (LoRaWan protocol), Bob sends to the cloud, not data for analysis like a simple sensor, but on the contrary value-added information from embedded artificial intelligence, making the solution unique in this sector. After a period of validation at major manufacturers (EDF, Véolia), but also in SMEs such as SJD décolletage, Bob is now available for industrial testing. Bob will be marketed in the form of a monthly subscription in the coming weeks.

NanoEdge™ AI is the only learning machine engine capable of operating in learning and inference directly on all Cortex M type microcontrollers.

Thus, industrialists no longer have to resort to these increasingly rare expert profiles and data sets that are difficult to build up to develop machine learning solutions in the “Edge.” Semiconductor manufacturers have understood this. They are investing more and more in this type of technology, and several of them have formed partnerships with Cartesiam. They enable their customers to keep control of their data by having it analyzed directly at the source (Edge), where the signal is transformed in data, rather than in the cloud.

Gaining in productivity and competitiveness: a vital issue

The signals analyzed at the source can be diverse and varied. It can be, as Bob, the intelligent wind turbine assistant, does, learning and then monitoring the vibrations of a machine. The aim is to detect anomalies and carry out predictive maintenance operations as soon as necessary. This solution, which is based on NanoEdge™ AI from Cartesiam, is already being massively deployed in European companies of all sizes and, more recently, in the USA. Other Cartesiam customers, both design offices and end customers, are working on solutions based on NanoEdge™ AI but using different signals such as sound, magnetometry, pressure, or air pollutants.

A sine qua non for the success of the IoT

Every year, 40 billion microcontrollers are sold, 15 billion of which are connected.
These components are integrated in everyday objects, from coffee machines to air conditioners to cars and, of course, in all connected objects. It is in this embedded AI market that Cartesiam aims to become the world leader.

“Being identified in the Gartner Hype Cycle 2019 as one of the three suppliers of the Edge AI brick is a great honor and recognition for the entire Cartesiam team. Our technology is the result of several years of research and development where we chose to rewrite, from algebra, all the machine learning algorithms so that they can run in an environment as frugal as that of a microcontroller. “commented Joël Rubino, CEO, and co-founder of Cartesiam.

He adds, “That’s how we created NanoEdge™ AI, a next-generation Machine Learning engine. With our technology, we enable design offices and manufacturers to easily integrate Machine Learning functions into everyday objects. We are several years ahead of our global competitors, wich explains the speed of our international development and the recognition by the Gartner Group.

At the proposal of Cartesiam :

Founded in 2016 and headquartered in Toulon with offices in Paris and New York (USA), Cartesiam is a French software publisher whose mission is to develop artificial intelligence solutions on microcontrollers. NanoEdge™ AI, an innovation developed by Cartesiam, provides cognitive functions (Machine Learning) to microcontrollers embedded in connected objects. Whatever their industry, Cartesiam thus brings immeasurable benefits to its customers involved in projects integrating microcontrollers: Simplicity of deployment, secure environment, rich analysis and reduced energy expenditure. The company has around twenty employees. The company, co-founded by Marc Dupaquier, François de Rochebouët, Michel and Joël Rubino, is located in Toulon for R&D  Paris and New York for the sales and marketing part.

NanoEdge™ AI studio