Abstract: A method, apparatus, and computer program product provide for improving performance of a condition monitoring system by combining rules and anomaly detection. In the context of a method, the method receives plurality of telemetry data from a monitored system. The method processes the plurality of telemetry data to generate an anomaly score set. The method also processes the plurality of telemetry data in accordance with the predefined rule data object set to generate a rule-based result set. The method determines whether the plurality of telemetry data is associated with an undetected fault of the monitored system and generates an extracted rule data object based on the telemetry data. The method also monitors performance of the machine learning anomaly detection model and determines whether retraining is necessary.

Abstract: Various embodiments described herein relate to automated asset strategy selection for assets via cloud-based supervisory control. In this regard, one or more baselines for asset strategy data related to an asset is estimated based on a regression analysis process associated with the asset. Additionally, a maximum uncertainty level for the one or more baselines is determined, one or more conditions related to energy optimization for an environment associated with the asset is estimated for a future period of time, and a predicted uncertainty level for the one or more conditions related to the energy optimization is determined. Based on a comparison between the maximum uncertainty level and the predicted uncertainty level, a predetermined asset strategy or an energy optimization asset strategy for the future period of time is then selected.

Abstract: Various embodiments described herein relate to automated setpoint generation for assets via cloud-based supervisory control. In this regard, a request to perform supervisory control with respect to an asset is received. The request comprises an asset identifier indicating an identity of the asset. In response to the request, one or more setpoints for the asset is determined based on the asset identifier. Also in response to the request, comfort constraint data indicative of one or more comfort constraints for an environment associated with the asset is determined based on the asset identifier. Furthermore, the one or more setpoints for the asset is adjusted based on the comfort constraint data.

Abstract: An approach for measuring health of a system using benchmarks. The approach may incorporate defining benchmarks with sensors providing data of selected conditions of a system, collecting a predetermined amount of most recent data from the sensors for one or more modes of the system, training a model that represents the system, the model having a response variable that is a function of the predetermined amount of the most recent data from the sensors, applying the model trained, to the benchmarks to get a response of the model in a form of the response variable that is the function of the predetermined amount of the most recent data from the sensors, and comparing the response of the model of the most recent time window with a response of the model of a previous time windows to determine health of the system.

Abstract: An approach for measuring health of a system using benchmarks. The approach may incorporate defining benchmarks with sensors providing data of selected conditions of a system, collecting a predetermined amount of most recent data from the sensors for one or more modes of the system, training a model that represents the system, the model having a response variable that is a function of the predetermined amount of the most recent data from the sensors, applying the model trained, to the benchmarks to get a response of the model in a form of the response variable that is the function of the predetermined amount of the most recent data from the sensors, and comparing the response of the model of the most recent time window with a response of the model of a previous time windows to determine health of the system.

Abstract: A method, apparatus, and computer program product provide for improving performance of a condition monitoring system by combining rules and anomaly detection. In the context of a method, the method receives plurality of telemetry data from a monitored system. The method processes the plurality of telemetry data to generate an anomaly score set. The method also processes the plurality of telemetry data in accordance with the predefined rule data object set to generate a rule-based result set. The method determines whether the plurality of telemetry data is associated with an undetected fault of the monitored system and generates an extracted rule data object based on the telemetry data. The method also monitors performance of the machine learning anomaly detection model and determines whether retraining is necessary.

Abstract: An approach for measuring health of a system using benchmarks. The approach may incorporate defining benchmarks with sensors providing data of selected conditions of a system, collecting a predetermined amount of most recent data from the sensors for one or more modes of the system, training a model that represents the system, the model having a response variable that is a function of the predetermined amount of the most recent data from the sensors, applying the model trained, to the benchmarks to get a response of the model in a form of the response variable that is the function of the predetermined amount of the most recent data from the sensors, and comparing the response of the model of the most recent time window with a response of the model of a previous time windows to determine health of the system.