System and method for identifying related events in a resource network monitoring system

Abstract

A computerized method for detecting related events in a water monitoring system. The method includes receiving event data from a plurality of sensors in a water network. The method also includes identifying at least two candidate events from the event data as being candidate events which are likely to constitute part of a common anomaly event, the candidate events each being substantially anomalous. An event combination rule is selected. One or more event characteristics are compared between the at least two candidate events based on the event combination rule. The at least two candidate events are determined whether they are related and associated with a common event causing the at least two candidate events on the basis of the comparison. The determination of the at least two candidate events are related and associated with a common event is reported to a user via a user interface.

1 - 85 . (canceled) 
     
     
         86 . A computerized method performed using a processor for identifying related events in a water network monitoring system, the related events represented by stored event data derived from data received from one or more sources including sensor data received from a plurality of sensors in a water network, each event data comprising data identifying an event and one or more characteristics of the event, the method comprising:
 identifying at least two events from the event data as being candidate events that are likely to constitute parts of a composite event, the identified candidate events each being determined by the water network monitoring system not to be statistically significant enough to be reported as events by themselves;   comparing one or more event characteristics between the at least two candidate events based on an event combination rule, the event combination rule including one or more criteria to determine whether the at least two candidate events are related and can be combined to form a composite event of a given event type; and   determining that the at least two candidate events are related and processible as a single event of the given event type based at least in part on the comparison.   
     
     
         87 . The method of  claim 86  further comprising determining whether the at least two candidate events have related locations using the event combination rule. 
     
     
         88 . The method of  claim 86  further comprising testing the at least two candidate events based on at least one of geographical proximity and temporal proximity. 
     
     
         89 . The method of  claim 86  further comprising determining a maximum distance between likely locations of the one or more event pairs; 
     
     
         90 . The method of  claim 86  further comprising determining a maximum distance per unit of magnitude of the one or more event pairs 
     
     
         91 . The method of  claim 86  further comprising determining whether events in the one or more event pairs should be located within a same region. 
     
     
         92 . The method of  claim 86  wherein the combination event combination rule includes at least one of: a simultaneous flow increase and flow decrease in two adjacent locations within the fluid network, a flow increase and one or more turbidity increases downstream; a reservoir level decrease and a turbidity increase at the reservoir's exit, a turbidity increase and a chlorine decrease, zero pressure in a plurality of neighboring sensors within the fluid network, a plurality of pressure decreases in supply zone, and a plurality of similar transmission failure events in a same area. 
     
     
         93 . The method of  claim 86  wherein the event data includes at least one of: a start time for a given event, an end time of the given event, a magnitude of the given event, and a total fluid loss associated with the given event. 
     
     
         94 . The method of  claim 86  wherein identifying at least two events from the event data further comprises correlating the at least two events on the basis of at least one of: likely physical or logical location, size, direction, time occurrence of the at least two events. 
     
     
         95 . The method of  claim 86  further comprising correlating the event data with asset management information. 
     
     
         96 . The method of  claim 95  wherein the asset management information includes at least one of: information concerning water network operations, acoustic surveys, repairs or improvements, maintenance made to the network, and access control information indicating when and where in the network technical personnel may be active. 
     
     
         97 . The method of  claim 86  further comprising analyzing a significance of deviations and a statistical likelihood that no relevant anomaly occurred during a given time period. 
     
     
         98 . The method of  claim 86  wherein the at least two candidate events identified from the event data includes a start of the single event and an end of the single event. 
     
     
         99 . The method of  claim 86  further comprising:
 determining a signature for each the at least two candidate events; 
 comparing the signatures of the at least two candidate events with a known signature of the given event type; and 
 determining the at least two candidate events are anomalies of the given event type. 
 
     
     
         100 . A system for identifying related events in a water network monitoring system, the system comprising:
 one or more sensors in the water network;   an event data store storing a plurality of event data derived from data received from the one or more sensors, the plurality of event data representing a plurality of events which have been processed from anomalies received from the water network monitoring system and which each contain a plurality of data fields including event start time and event magnitude; and   a composite event subsystem operative to:   identify at least two events from the event data as being candidate events that are likely to constitute parts of a composite event, the identified candidate events each being determined by the water network monitoring system not to be statistically significant enough to be reported as events by themselves;   compare one or more event characteristics between the at least two candidate events based on an event combination rule, the event combination rule including one or more criteria to determine whether the at least two candidate events are related and can be combined to form a composite event of a given event type; and   determine that the at least two candidate events are related and processable as a single event of the given event type based at least in part on the comparison.   
     
     
         101 . A method performed using a processor for identifying related events with matching anomaly directions in a water network monitoring system, the method comprising:
 selecting at least two events from event data as being candidate events that are likely to constitute parts of a composite event of a given event type, the event data derived from data received from one or more sources including sensor data received from a plurality of sensors in a water network;   comparing anomaly directions of change between the at least two candidate events based on an event combination rule, the event combination rule including one or more criteria to determine whether the at least two candidate events are related and can be combined to form a composite event of the given event type;   determining an anomaly direction relationship between the at least two candidate events including a permitted set of anomaly directions corresponding to the given event type between the candidate events based on criteria from the event combination rule for the given event type; and   determining the at least two candidate events are related and associated with the composite event of the given event type based on the searching.   
     
     
         102 . The method of  claim 101  wherein the set of anomaly directions of the at least two candidate events are associated with measurement increases. 
     
     
         103 . The method of  claim 101  wherein the set of anomaly directions of the at least two candidate events are associated with measurement decreases. 
     
     
         104 . The method of  claim 101  wherein the set of anomaly directions of the at least two candidate events includes one of exactly two candidates associated with a measurement increase and the other associated with a measurement decrease. 
     
     
         105 . A system for identifying related events with matching anomaly directions in a water network monitoring system, the system comprising:
 one or more sensors in the water network;   an event data store storing a plurality of event data derived from data received from the one or more sensors, the plurality of event data representing a plurality of events which have been processed from anomalies received from the water network monitoring system and which each contain a plurality of data fields including event start time and event magnitude; and   a composite event subsystem operative to:   select at least two events from event data as being candidate events that are likely to constitute parts of a composite event of a given event type, the event data derived from data received from one or more sources including sensor data received from a plurality of sensors in a water network;   compare anomaly directions of change between the at least two candidate events based on an event combination rule, the event combination rule including one or more criteria to determine whether the at least two candidate events are related and can be combined to form a composite event of the given event type;   determine an anomaly direction relationship between the at least two candidate events including a permitted set of anomaly directions corresponding to the given event type between the candidate events based on criteria from the event combination rule for the given event type; and   determine the at least two candidate events are related and associated with the composite event of the given event type based on the searching.