Disclosed herein are systems, devices, and methods related to assets and asset operating conditions. In particular, examples involve defining and executing predictive models for outputting health metrics that estimate the operating health of an asset or a part thereof, analyzing health metrics to determine variables that are associated with high health metrics, and modifying the handling of abnormal-condition indicators in accordance with a prediction of a likely response to such abnormal-condition indicators, among other examples.

Asset Health Score

Disclosed herein are computer systems, devices, and methods for improving the technology related to asset condition monitoring. In accordance with the present disclosure, an asset data platform may be configured to receive data related to asset operation, ingest, process, and analyze the received data, and then provide a set of advanced tools that enable a user to monitor asset operation and take action based on that asset operation. The set of advanced tools may include (1) an interactive visualization tool, (2) a task creation tool, (3) a rule creation tool, and/or (4) a metadata tool.

Computer systems and methods for creating asset-related tasks based on predictive models

Adaptive handling of operating data

A service planning engine may predict the future wind speed at a wind farm as well as the future price of energy of the utility grid coupled to the wind turbines. Based on the predicted values, the service planning engine identifies times to perform maintenance when lost revenue is minimized—e.g., when the predicted price of energy is low. Furthermore, the service planning engine may calculate a service priority associated with the turbine to determine when to perform service. The service priority may be based on a status signal associated with the component to be serviced or the time window stipulated in the service contract for performing the maintenance. In one embodiment, the service planning engine also considers resource constraints such as labor costs (e.g., work schedules, overtime costs, availability of technicians with certain skills, availability of components, shipping costs, and the like).

Wind turbine maintenance optimizer

The astronomical growth of data has necessitated the need for educating well-qualified data scientists to derive deep insights from large and complex data sets generated by organizations. In this paper, we present our interdisciplinary approach and experiences in teaching a Data Science course, the first of its kind offered at the Wright State University. Two faculty members from the Management Information Systems (MIS) and Computer Science (CS) departments designed and co-taught the course with perspectives from their previous research and teaching experiences. Students in the class had mix backgrounds with mainly MIS and CS majors. Students' learning outcomes and post course survey responses suggested that the course delivered a broad overview of data science as desired, and that students worked synergistically with those of different majors in collaborative lab assignments and in a semester long project. The interdisciplinary pedagogy helped build collaboration and create satisfaction among learners.

/pdf/teaching-the-foundations-of-data-science-an-145bux8yqc.pdf

Teaching the Foundations of Data Science: An Interdisciplinary Approach

A computer-implemented system and method for predictive and diagnostic analysis of an electrical transmission, generation and distribution asset health includes a computer with a non-transient computer readable medium able to receive data regarding an asset, its components, component subsystem and parameters related thereto. Instructions stored on the non-transient computer readable medium execute instructions that predictively calculate overall asset health and also calculated the states of subsystems and component parameters, providing a diagnostic of the causes of poor asset health.

System and method for power transmission and distribution asset condition prediction and diagnosis

Among other things, one or more techniques and/or systems are provided for predicting an oil temperature of a transformer for a desired load and/or predicting a load that a transformer can support for a desired time. A machine learning algorithm may be developed using historical data of a power system. After the algorithm is developed, historical data corresponding to the transformer may be input into the algorithm to develop a profile of the transformer. Using the profile, an oil temperature of the transformer may be estimated or predicted for a desired load. In this way, a prediction may be made as to whether and/or for how long a transformer may support a desired load before the oil temperature reaches a specified threshold and/or before the transformer fails due to the load.

Profiling transformer of power system

Among other things, one or more techniques and/or systems are provided for assessing power system equipment of a power system. Historical sensor data and/or historical field test data collected from the power system equipment may be utilized to develop a health profile of the power system equipment. The health profile is indicative of a predicted health (e.g., or probability of failure) of the power system equipment. In one embodiment, the health profile further comprises a health index score which evaluates that health of the power system equipment in terms of the importance of the power system equipment to the power system. Using the health profiles developed for a plurality of power system equipment, a maintenance strategy for at least a portion of the power system may be developed.

Assessment of power system equipment for equipment maintenance and/or risk mitigation

As the world population grows, recent climatic changes seem to bring powerful storms to populated areas. The impact of these storms on utility services is devastating. Hurricane Sandy is a recent example of the enormous damages that storms can inflict on infrastructure, society, and the economy. Quick response to these emergencies represents a big challenge to electric power utilities. Traditionally utilities develop preparedness plans for storm emergency situations based on the experience of utility experts and with limited use of historical data. With the advent of the Smart Grid, utilities are incorporating automation and sensing technologies in their grids and operation systems. This greatly increases the amount of data collected during normal and storm conditions. These data, when complemented with data from weather stations, storm forecasting systems, and online social media, can be used in analyses for enhancing storm preparedness for utilities. This paper presents a data analytics approach that uses real-world historical data to help utilities in storm damage projection. Preliminary results from the analysis are also included.

/pdf/data-analytics-for-power-utility-storm-planning-fds5jzugoo.pdf

Data Analytics for Power Utility Storm Planning

This paper describes a novel application of probabilistic Bayesian networks for the identification of faulty conditions in power transformers, based on the well-known fault tree analysis procedure. The proposed technique emulates human judgment by the construction of a Bayesian net which closely resembles the structure of a typical expert-built power transformer fault tree. The proposed solution will be exemplified with test data from real cases.

http://ieeexplore.ieee.org/iel7/6855589/6863147/06863177.pdf

Lan Lin

Papers

System and method for power transmission and distribution asset condition prediction and diagnosis

Profiling transformer of power system

Assessment of power system equipment for equipment maintenance and/or risk mitigation

Data Analytics for Power Utility Storm Planning

Probabilistic transformer fault tree analysis using Bayesian networks