Abstract: Disclosed are techniques for querying a digital twin marketplace for digital twins relevant to a work order and delivering said digital twins to a mobile computing device. A query for digital twins on a digital twin marketplace is generated using a workorder, followed by an availability assessment to determine the availability of the queried digital twins to a querying user. When a queried digital twin is available to the querying user, the queried digital twin is provided to a mobile computing device associated with the querying user. Querying and providing digital twins in this manner streamlines the determination and provision of digital twin assets to work order responders in-situ.

Abstract: In an approach to predictive maintenance explanations based on a user profile, one or more computer processors receive a failure prediction associated with a physical asset of an organization. One or more computer processors receive a work order associated with the failure prediction and an assignment of a first user to the work order. One or more computer processors retrieve a profile associated with the first user. One or more computer processors determine a best match between a taxonomy node of a taxonomy of user expertise associated with the work order and the retrieved profile associated with the first user. Based on the determined best match, one or more computer processors generate an explanation of the failure prediction. One or more computer processors display the explanation to the first user.

Abstract: According to one embodiment, a method, computer system, and computer program product for identifying commercialization opportunities for digital twin resources captured on a sensor is provided. The present invention may include receiving digital content pertaining to a physical asset captured by the sensor; responsive to determining that no digital twin resources within a digital twin content store associated with the physical asset exceed a threshold level of similarity to the digital content, uploading the digital content to the digital twin content store based on a user response to one or more prompts.

Abstract: Methods, computer program products, and/or systems are provided that perform the following operations: obtaining asset data; determining an asset class associated with the asset data; initializing a new neural network model, wherein the new neural network model is initialized based on a pretrained model associated with the asset class; training the new neural network model based, at least in part, on the asset data to obtain a trained remaining useful life model; and deploying the trained remaining useful life model to generate prediction data for one or more assets as output of the trained remaining useful life model.

Abstract: Information about a technician is received, in which the information includes an area expertise, a skill level, qualifications, available tools and materials, a previously performed service history and a location of the technician. A plurality of service request candidates is received that includes information associated with respective service requests. A first set of service requests appropriate for the technician is identified by comparing the information about the technician and the current location of the technician to the plurality of service request candidates. A recommended order to perform the first set of service requests is determined, based on a distance between service request locations, urgency of performing the service request, and factors associated with the respective service request; and a map representation of relative locations and the recommended order of service request response for the first set of service requests is presented to the technician.

Abstract: Disclosed are techniques for querying a digital twin marketplace for digital twins relevant to a work order and delivering said digital twins to a mobile computing device. A query for digital twins on a digital twin marketplace is generated using a workorder, followed by an availability assessment to determine the availability of the queried digital twins to a querying user. When a queried digital twin is available to the querying user, the queried digital twin is provided to a mobile computing device associated with the querying user. Querying and providing digital twins in this manner streamlines the determination and provision of digital twin assets to work order responders in-situ.

Abstract: An approach to assigning health scores to physical assets based on digital twin resources. The approach can retrieve a digital twin with characteristics similar to a physical asset. The approach can predict a health score of the physical asset based on a first asset health formula associated with the digital twin.

Abstract: A method of expert peer identification includes receiving, from a user, a request for an expert peer for an asset type, and obtaining asset interaction data relevant to the request including a list of assets, and, for each asset on the list, values for each of a set of pre-defined interaction categories for each worker that has interacted with the asset. The method further includes, for each asset on the list, respectively multiplying the interaction category values by a corresponding set of category weights to obtain a set of weighted interaction values, and, for each worker, processing the sum of their weighted interaction values to obtain an overall centrality measure. The method also includes selecting one of the workers as the expert peer based, at least in part, on their overall centrality measure, and identifying the expert peer to the user.

Abstract: A method of expert peer identification includes receiving, from a user, a request for an expert peer for an asset type, and obtaining asset interaction data relevant to the request including a list of assets, and, for each asset on the list, values for each of a set of pre-defined interaction categories for each worker that has interacted with the asset. The method further includes, for each asset on the list, respectively multiplying the interaction category values by a corresponding set of category weights to obtain a set of weighted interaction values, and, for each worker, processing the sum of their weighted interaction values to obtain an overall centrality measure. The method also includes selecting one of the workers as the expert peer based, at least in part, on their overall centrality measure, and identifying the expert peer to the user.