Development of new spectrometric methods for the characterization of uranium-bearing ore
This subject aims at developing new methods of X/gamma-ray spectrum analysis for the characterization of uranium-bearing ore, enabling to process data obtained in the framework of nuclear mining activities. This subject will be developped into two parts. The first part will concern the processing of complex gamma-ray spectra, obtained using different types of medium-resolution scintillators (such as NaI or LaBr3 detector). The main purpose of this part will be related to the processing of complex regions of interest using deconvolving methods by non-parametric Bayesian inference, notably by using the SINBAD code, initially developed by CEA LIST for the processing of HPGe spectra. The second part of the subject will concern the analysis of low-resolution spectra obtained using a NaI detector in order to obtain a spectrometric information. In this case, a traditional approach based on the analysis of photoelectric peaks is not conceivable. The problem will be studied in the form of an inverse problem using a model of the detector response and a reconstruction, using an approach analogous to computed tomography. The performances of different types of reconstruction algorithms will be studied (EM analysis, non-parametric Bayesian approach).
Planning energy consumption within an eco-district
Energy consumption and production are changing, and the birth of eco-districts is now a reality which is a continuation of these changes. Eco-districts consists in grouping within the same territory entities which consume or produce energy and in managing these resources locally.
Alongside these developments, homes, shops and even offices are increasingly equipped with communicating sensors and intelligent devices that can be controlled remotely. It is therefore possible to control these devices taking into account several factors: the financial or environmental cost of energy consumed, the respect of comfort desired by the people and the intent of the directors of the eco-district. Many algorithms have been developed in order to plan and control devices more or less autonomous, while expert systems have often been excluded because of their lack of expressiveness in this area. The goal of this postdoctoral fellowship is to check if fuzzy expert systems can be used to plan devices which consume a source of energy.
Distributed multiagent resources allocation. Application to district heating
Heating district networks in France fed more than one million homes and deliver a quantity of heat equal to about 5% of the heat consumed by the residential and tertiary sector. Therefore, they represent a significant potential for the massive introduction of renewable and recovery energy. However, heating networks are complex systems that must manage large numbers of consumers and producers of energy, and that are distributed in extended and highly branched geographical zones. The aim of the SIGMA project, realized in collaboration among the CEA-LIST and the CEA-LITEN, is to implement an optimal and dynamic management of heating networks. We propose a multidisciplinary approach, by integrating the advanced network management using Multi-Agent Systems (MAS), by taking into account spatial constraints using Geographic Information Systems (GIS) and by considering simplified physical models of transport and recovery of heat.
The post-doc’s goal is to design mechanisms for dynamically allocating resources that consider the geographical information from the GIS and the predictions of consumption, production and losses calculated with the physical models. In this way, several characteristics of the network will be considered: the continuous and dynamic aspect of the resource; sources with different behaviors, capabilities and production costs; the dependence of consumption / production to external aspects (weather, energy price); the internal characteristics of the network (losses, storage capacity). The coupling with a GIS should allow implementing self-configuration mechanisms for the management of different networks and different levels of granularity obtained by reduction of the original GIS. The MAS should dynamically establish the link between the suitable simplified models and the desired level of granularity and then it will create the agents needed to represent the system.
Unsupervised Few-Shot Detection of Signal Anomalies
Our laboratory, located at Digiteo in CEA Saclay, is looking for a postdoc candidate working on the subject of anomaly detection in manufacturing processes, for a duration of 18 months starting from Feburary 2022. This postdoc is part of HIASCI (Hybridation des IA et de la Simulation pour le Contrôle Industriel), a CEA LIST project in an internal collaboration which aims at building a platform of AI methods and tools for manufacturing applications, ranging from quality control to process monitoring. Our laboratory contributes to HIASCI by developping efficient methods of anomaly detection in acoustic or vibrational signals, operating with small amounts of training data. In this context, the detection of signal anomalies (DSA) consists of extracting from data the information about the physical process of manufacturing, which is in general too complex to be fully understood. Moreover, real data of abnormal states are relatively scarce and often expensive to collect. For these reasons we privilege a data-driven approach under the framework of Few-Shot Learning (FSL).
Gas sensors based on diamond nanoparticles and nanoporous materials
The aim is to develop surface acoustic wave sensors (SAW) with high sensitivity and high selectivity to gaseous compounds (< 100 ppb). The development strategy involves the use of diamond nanoparticles based guiding layers deposited on the piezoelectric substrate and chemically modified to tune the specificity of the sensors. In order to increase further the selectivity, the sensors will be coupled to specific filters placed before the sensors and based on probe molecules trapped in porous sol-gel based materials and able to react non-reversibly with interferent molecules. The topic includes 4 mains sections: 1) synthesis and functionalisation of diamond nanoparticles, 2) study of probe molecules and immobilisation in porous matrices, 3) study of the filtering capacity of the filters toward relevant interferent species, 4) metrology and calibration of the sensors. This work will be carried out in the "Diamond Sensors Laboratory" as well as laboratoire Francis Perrin both located in CEA Saclay.
Machine learning technics and knowledge-based simulator combined for dynamic process state estimation
This project aims to estimate the real state of a dynamic process for liquid-liquid extraction through the real data record. Data of this kind are uncertain due to exogenous variables. They are not included inside the simulator PAREX+ dedicated to the dynamic process. So, the first part of the project is to collect data from simulator. By this way the operational domain should be well covered and the dynamic response recorded. Then, the project focuses to solve the inverse problem by using convolutionnal neural networks on times series. Maybe a data enrichment could be necessary to perfect zones and improve estimations. Finally, the CNN will be tested on real data and integrate the uncertainty inside its estimations.
At the end, the model built needs to be used in operational conditions to help diagnosis and improve the real-time control to ensure that the dynamic observed is the one needed.
Combinatorial optimization of base materials for the design of new materials
The design of new materials is a field of growing interest, especially with the emergence of additive manufacturing processes, thin film deposition, etc. In order to create new materials to target properties of interest for an application area, it is often necessary to mix several raw materials.
A physicochemical modeling of the reactions that occur during this mixing is often very difficult to obtain, especially when the number of raw materials increases. We want to free ourselves as much as possible from this modeling. From experimental data and business knowledge, the goal of this project is to create a symbolic AI capable of groping for the optimal mixture to achieve one or more given properties. The idea is to adapt existing methods of operations research, such as combinatorial optimization, in a context of imprecise knowledge.
We will focus on different use cases such as electric batteries, solvents for photovoltaic cells and anti-corrosion materials.
Within the project, you will:
• Study the state of the art,
• Propose one or several algorithms to prototype, and their evaluation,
• Disseminate the resulting innovations to the consortium and the scientific community, through presentations, contributions to technical reports and / or scientific publications.
Maximum duration: 18-24 months (regarding your experience).
New nanostructurated fluorescent materials for the detection of volatile organic compounds.
The presence in indoor environments of many substances and (geno-)toxic, allergenic and infectious agents with pathogenic effects is well known. The on-site detection of these
substances has become a strong need, related to public health concerns. To respond to this need and enable the development of sensitive and selective ’field-deployable chemical sensors’, different technological solutions are being considered (conductimetric, electrochemical, piezoelectric, electro-mechanical, optical based systems…). Among all these methods, those based on the use of fluorescence phenomena are particularly interesting because of the inherently high sensitivity (lower limit of detection) of the technique and the possibility it offers to develop low cost, small size and low
energy consuming devices.
The proposal falls into this context and aims at evaluating the potentialities of new nanostructurated organic materials for the detection of indoor air trace pollutants by fluorescence change monitoring. This work will be done in straight collaboration with the Laboratoire Chimie des Polymères (UMR7610-CNRS/UPMC Paris VI) specialized in the synthesis
of functionalized organogels. More precisely, we propose to develop new highly porous supramolecular materials serving either as substrate for the sensitive fluorescent polymer or functionalised so as to directly detect and recognize the vapor pollutant.
The physico-chemical properties of these new materials will be examined by different techniques. Their performances in the presence of target pollutants (formaldehyde, acetaldehyde) and potentially interferants will be evaluated. Finally, the most interesting materials will be integrated into a functional prototype.