Abstract: A system with a plurality of operator stations, a first sub-system for operating an industrial process, a second sub-system for assisting with the operation, a first duplicated communication network that manages exchanges in the first sub-system, a second duplicated communication network that manages exchanges in the second sub-system, and a separating device that manages exchanges between the first and the second sub-systems. The first sub-system includes an interface module that collects data items each associated with one acquisition time; a first processing module that sorts the data and computes first information items; a first module that manages operator stations and sends each first information item to the operator stations. The sub-system includes a second processing module that computes second information items from the data items and from the first information items; a second module that manages operating stations and sends each second information item to the operator stations.

Abstract: A high-availability control system for an industrial process including operator stations displaying information, and an interface including a pair of computers for each model, each collecting each item of data received by each controller having the model and eliminating the duplicates, wherein the computers operate in asynchronous redundancy. The system also includes a processor including a pair of computers that each receive the collected data, sort the data received as a function of their acquisition time, eliminate the duplicates and calculate an information group by acquisition time, wherein the computers operate in active redundancy. The system also includes managing the operator stations including one computer per operator station, each receiving each calculated information group and sending to the operator station each information group corresponding to the subset of information.

Abstract: The invention relates to a method for estimating an electricity production of a set of production sites, comprising for each of said sites: acquiring an optimized set of parameters relating to the site, providing these parameters to a neural network associated with said site in order to obtain an estimated production said estimation being determined based upon the productions estimated by each of said neural networks; each of said neural networks being previously determined by: training on a training set corresponding to the site associated with said neural network and based on an extended set of parameters relating to the site, and according to a loss function; a first optimization phase consisting of selecting an optimized set of parameters among the extended set of parameters based upon the influence of the parameters on the training of said neural network; a second optimization phase consisting of iteratively modifying at least one structural parameter of the neural network in order to select at least

Abstract: One aspect of the invention relates to a high-availability control system (100) for an industrial process comprising: A plurality of operator stations (108) displaying a subset of information; An interface module (105) including a pair of computers (104) for each model, each collecting each item of data received by each controller (103) having the model and eliminating the duplicates, the computers (104) operating in asynchronous redundancy; A processing module (106) including a pair of computers (104) each receiving the collected data, sorting the data received as a function of their acquisition time, eliminating the duplicates and calculating an information group by acquisition time, the computers (104) operating in active redundancy, A module for managing the operator stations (107) including one computer (104) per operator station (108), each receiving each calculated information group and sending to the operator station (108) each information group corresponding to the subset of information; A duplica

Abstract: A system for monitoring industrial processes using an evolving set of iso-functional smart nodes, for a distributed mesh network, each node comprising a Linux or Linux-compatible computer hardware architecture and a software stack. Each node receives an execute statement from a program hosted by another node in the mesh and, by execution on the computer hardware architecture of each node, the program is responsible for: two-way communication with other nodes or a central platform (Big Data Management), control of sensors or programmable automatons for monitoring a process or actuators, acquisition and logging of data from the latter, formatting of data and decentralized calculations, the central platform allowing the acquisition, management and storing of a data lake and comprising nodes for synchronous or asynchronous communication with the distributed mesh network.