Predictive modelling

A system for predicting maintenance events, the system comprising one or more processors or special-purpose computing hardware configured to perform:

• determining, based on an ontology, first data associated with a first maintenance event of a first resource;
• retrieving from the first data, first historic maintenance data in relation to the first resource, the first historic maintenance data originating from a time period preceding a first time of the first maintenance event;
• identifying a first subset of the retrieved first historic maintenance data as being indicative of the first maintenance event;
• storing the first subset as one or more precursor signals of a type of the first maintenance event;
• determining, based on the ontology, second data associated with a second maintenance event of the first resource or a second resource;
• retrieving second historic maintenance data in relation to the first resource or the second resource, the second historic maintenance data originating from a time period preceding a second time of the second maintenance event;
• identifying a second subset of the retrieved second historic maintenance data as being indicative of the second maintenance event;
• updating the one or more precursor signals based on the second subset;
• and
• monitoring subsequent maintenance data from the first resource, the second resource, or a third resource to predict, based on the one or more precursor signals, a subsequent occurrence of the maintenance event in the first resource, the second resource, or a third resource.

A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:

• determining, based on an ontology, first data associated with a first maintenance event of a first resource;
• retrieving from the first data, first historic maintenance data in relation to the first resource, the first historic maintenance data originating from a time period preceding a first time of the first maintenance event;
• identifying a first subset of the retrieved first historic maintenance data as being indicative of the first maintenance event;
• storing the first subset as one or more precursor signals of a type of the first maintenance event;
• determining, based on the ontology, second data associated with a second maintenance event of the first resource or a second resource;
• retrieving second historic maintenance data in relation to the first resource or the second resource, the second historic maintenance data originating from a time period preceding a second time of the second maintenance event;
• identifying a second subset of the retrieved second historic maintenance data as being indicative of the second maintenance event;
• updating the one or more precursor signals based on the second subset;
• and
• monitoring subsequent maintenance data from the first resource, the second resource, or a third resource to predict, based on the one or more precursor signals, a subsequent occurrence of the maintenance event in the first resource, the second resource, or a third resource.