Anomaly detection and evaluation for smart water system management

A non-transitory electronic device readable medium having instructions stored thereon that when executed on one or more processors of one or more electronic devices are operable to:

• receive time series data that includes both flow and pressure measurements at a plurality of time steps from one or more sensors of a water distribution system;
• detect, using a statistical process control (SPC) algorithm, outliers of the time series data;
• classify sensor events in response to flow or pressure of detected outliers exceeding high or low thresholds for at least a given number of time steps;
• classify anomaly events by correlating one or more sensor events related to flow with one or more sensor events related to pressure;
• determine a quantitative score for each of the detected anomaly events that indicates a level of significance or importance based on a density of sensor events for the anomaly event and a spread of the sensor events for the anomaly event;
• and
• provide at least the detected anomaly events and their respective quantitative scores.

A method for detecting and evaluating anomaly events in a water distribution system, comprising:

• using one or more sensors of the water distribution system to collect time series data that includes both flow and pressure measurements at a plurality of time steps;
• decomposing, by a decomposition algorithm of an application executing on one or more computing devices, the time series data to remove seasonality and render the time series data stationary;
• detecting, by one or more statistical process control (SPC) algorithms of the application, outliers of the stationary time series data;
• classifying, by the application, sensor events in response to flow or pressure of detected outliers exceeding high or low thresholds for at least a given number of time steps;
• classifying, by the application, anomaly events by correlating one or more sensor events related to flow with one or more sensor events related to pressure;
• and
• based on the classification of at least one anomaly event, deploying maintenance or repair personnel to the at least one anomaly event.