Catherine Cadet

Learn More
This paper presents a recurrent neural observer to estimate substrate and biomass concentrations in an activated sludge wastewater treatment. The observer is based on a discrete-time high order neural network (RHONN) trained on-line with an extended Kalman filter (EKF)-based algorithm. This observer is then associated with a hybrid intelligent system to(More)
The objective of this work is to improve the power management subsystem of a hybrid fuel cell / supercapacitor power generation system. The predictive approach is a relevant available control strategy that can explicitly handle constraints including soft ones and that can also deal with multiple control inputs. Some improvements are presented to shorten the(More)
Sedimentation is central activated sludge process, and its performance has a major impact on that of the whole wastewater treatment process. Nevertheless, there is still no satisfying model for secondary settling tanks. This paper explores the reasons why the existing one dimensional models are not relevant, from the lack of knowledge on the physical(More)
In this work, a neural control scheme to regulate carbon monoxide (CO) and nitrogen oxides (NO<sub>x</sub>) emissions for a solid waste incinerator is proposed. Carbon monoxide emissions are avoided by oxygen regulation in the incinerator; nevertheless nitrogen oxides emissions are difficult to control because the sludge composition varies continuously. The(More)
In this paper, the authors propose a discrete-time neural control scheme to regulate nitrogen oxides (NOx) emissions for a fluidized bed sludge combustor. This scheme ensures carbon monoxide (CO) regulation without decreasing combustion efficiency. In order to obtain the sludge combustion model, it is proposed to use a recurrent high order neural network(More)
This paper presents neuronal network identification of a wastewater treatment prototype. This identification is based on a discrete-time high order neuronal network (RHONN). The neuronal network is trained with an extended Kalman filter (EFK) algorithm. The neuronal identification performance is illustrated via simulations.
This paper presents a neural network identification scheme to estimate substrate, biomass and dissolved oxygen concentrations in an activated sludge wastewater treatment. This scheme is based on a discrete-time high order neural network (RHONN) trained on-line with an extended Kalman filter (EKF)-based algorithm. Then, the identification scheme is(More)
In this paper, we explore the combination of two control strategies for activated sludge wastewater treatment plants. From the plant configuration proposed by the Benchmark of the European group COST 624, first a fuzzy supervisory control which adequate the parameters of two local controllers is described and applied, then it is combined with a control(More)
  • 1