Abstract: A computer-implemented method, computer program, and device for evaluating pipe condition of pipe sections of a pipe network are provided. To do so, the pipe sections are clustered into classes based on structural and environmental parameters; within each class a sample of pipe sections are selected to be inspected. The scores that are obtained through the inspection are used to train a model of pipe conditions of pipes in a class, in order to estimate the pipe conditions of pipes that have not been inspected.

Abstract: A method is provided for placing sensors in a fluid distribution network by simulating network operating scenarios; by determining candidate sets of sensor positions; by determining the measurements of each sensor in each scenario, and the detection of associated anomalies; by attributing a score to each candidate set of sensor positions, representing the capacity of the sensors placed in the positions of the set to accomplish a mission. Finally, the candidate sets are modified using so-called genetic algorithms until a stop criterion is validated. The genetic algorithms can for example consist in crossing over or mutating candidate sets.

Abstract: A method for determining an optimal dose of coagulant for raw water includes a step of determining a value, for the raw water, of a first organic parameter; a step of determining a value, for the raw water, of a second mineral parameter; a step of determining a class of water for the raw water, characterized by the value of the first organic parameter and the value of the second mineral parameter; a step of determining a value, for the raw water, of a third organic parameter; a step of defining a target value, for the clarified water, of the third organic parameter; a step of selecting a function between the third organic parameter and an added dose of coagulant, said function being selected for the class of water and for the value, for the raw water, of the third organic parameter; a step of using the function to determine a first dose of coagulant in order to reach the target value.

Abstract: A device for detecting and characterizing anomalies in a water continuum is provided. The device is configured to receive measurements of physical quantities on the basis of sensors situated in the water continuum. The measurements are thereafter transformed, and a detection of anomalies is performed by a detector of anomalies which is trained with transformed values arising from the same sensors. In parallel with the detection, predefined rules make it possible to characterize a possible anomaly. Thus, an anomaly detection can be optimized for a water continuum in particular, whilst characterization with predefined rules allows the device to be operational without each anomaly having needed to be detected in this water continuum in particular.

Abstract: A process for monitoring the concentration of bacteria in the water of a water distribution network, wherein the process includes the following steps: measuring the concentration of bacteria in the water by means of a first sensor positioned at a first location in the water distribution network, determining a variable instantaneous value of the expected concentration of bacteria in the water at the first location as a function of a parameter characteristic of the water, comparing the concentration of bacteria in the water measured by the first sensor to the variable instantaneous value, corrective action acting on the concentration of bacteria in the water if the concentration of bacteria in the water measured by the first sensor exeeds the variable instantaneous value. A device for monitoring the concentration of bacteria in the water of a water distribution network is also provided.