Abstract: A building management system includes connected equipment configured to measure a plurality of monitored variables and a predictive diagnostics system configured to receive the monitored variables from the connected equipment; generate a probability distribution of the plurality of monitored variables; determine a boundary for the probability distribution using a supervised machine learning technique to separate normal conditions from faulty conditions indicated by the plurality of monitored variables; separate the faulty conditions into sub-patterns using an unsupervised machine learning technique to generate a fault prediction model, each sub-pattern corresponding with a fault, and each fault associated with a fault diagnosis; receive a current set of the monitored variables from the connected equipment; determine whether the current set of monitored variables correspond with one of the sub-patterns of the fault prediction model to facilitate predicting whether a corresponding fault will occur; and determin

Abstract: A building management system includes connected equipment configured to measure a plurality of monitored variables and a predictive diagnostics system configured to receive the monitored variables from the connected equipment; generate a probability distribution of the plurality of monitored variables; determine a boundary for the probability distribution using a supervised machine learning technique to separate normal conditions from faulty conditions indicated by the plurality of monitored variables; separate the faulty conditions into sub-patterns using an unsupervised machine learning technique to generate a fault prediction model, each sub-pattern corresponding with a fault, and each fault associated with a fault diagnosis; receive a current set of the monitored variables from the connected equipment; determine whether the current set of monitored variables correspond with one of the sub-patterns of the fault prediction model to facilitate predicting whether a corresponding fault will occur; and determin

Abstract: A building management system includes a plurality of devices of building equipment configured to provide status data. The building management system also includes an equipment management server configured to assign and store parent-child relationships for the plurality of devices of building equipment. The equipment management server is also configured to monitor the status data to detect faults and generate a fault visualization interface. The fault visualization interface provides provide a list of the devices with detected faults, allows a user to select one or more of the devices from the list, and presents a parent-child relationship widget for the selected device. The parent-child relationship widget includes a list of parent devices for the selected device and a list of child devices for the selected device. Each device on the lists of parent devices and child devices has a status indicator indicating whether the device is in a fault condition.

Abstract: A building management system includes connected equipment configured to measure a plurality of monitored variables and a predictive diagnostics system configured to receive the monitored variables from the connected equipment; generate a probability distribution of the plurality of monitored variables; determine a boundary for the probability distribution using a supervised machine learning technique to separate normal conditions from faulty conditions indicated by the plurality of monitored variables; separate the faulty conditions into sub-patterns using an unsupervised machine learning technique to generate a fault prediction model, each sub-pattern corresponding with a fault, and each fault associated with a fault diagnosis; receive a current set of the monitored variables from the connected equipment; determine whether the current set of monitored variables correspond with one of the sub-patterns of the fault prediction model to facilitate predicting whether a corresponding fault will occur; and determin

Abstract: A building management system includes connected equipment configured to measure a plurality of monitored variables and a predictive diagnostics system configured to receive the monitored variables from the connected equipment; generate a probability distribution of the plurality of monitored variables; determine a boundary for the probability distribution using a supervised machine learning technique to separate normal conditions from faulty conditions indicated by the plurality of monitored variables; separate the faulty conditions into sub-patterns using an unsupervised machine learning technique to generate a fault prediction model, each sub-pattern corresponding with a fault, and each fault associated with a fault diagnosis; receive a current set of the monitored variables from the connected equipment; determine whether the current set of monitored variables correspond with one of the sub-patterns of the fault prediction model to facilitate predicting whether a corresponding fault will occur; and determin

Abstract: A building management system includes connected equipment configured to measure a plurality of monitored variables and a predictive diagnostics system configured to receive the monitored variables from the connected equipment; generate a probability distribution of the plurality of monitored variables; determine a boundary for the probability distribution using a supervised machine learning technique to separate normal conditions from faulty conditions indicated by the plurality of monitored variables; separate the faulty conditions into sub-patterns using an unsupervised machine learning technique to generate a fault prediction model, each sub-pattern corresponding with a fault, and each fault associated with a fault diagnosis; receive a current set of the monitored variables from the connected equipment; determine whether the current set of monitored variables correspond with one of the sub-patterns of the fault prediction model to facilitate predicting whether a corresponding fault will occur; and determin

Abstract: A building management system includes building equipment, a metric generation system, and a visualization engine. The building equipment is configured to generate data samples. The metric generation system is configured to collect the data samples and generate key performance indicators. The visualization engine is configured to create a scorecard that displays the key performance indicators. The scorecard comprises a building energy overview widget that displays total consumption of a building, a consumption by space widget that displays consumption of a plurality of subspaces of the building, and a consumption by commodity widget that displays consumption of the building categorized by commodity. In some embodiments, the scorecard also includes an energy density by space widget that displays consumption per unit area per day for the subspaces of the building.

Abstract: A building management system includes a plurality of devices of building equipment configured to provide status data. The building management system also includes an equipment management server configured to assign and store parent-child relationships for the plurality of devices of building equipment. The equipment management server is also configured to monitor the status data to detect faults and generate a fault visualization interface. The fault visualization interface provides provide a list of the devices with detected faults, allows a user to select one or more of the devices from the list, and presents a parent-child relationship widget for the selected device. The parent-child relationship widget includes a list of parent devices for the selected device and a list of child devices for the selected device. Each device on the lists of parent devices and child devices has a status indicator indicating whether the device is in a fault condition.

Abstract: A building management system includes building equipment, a metric generation system, and a visualization engine. The building equipment is configured to generate data samples. The metric generation system is configured to collect the data samples and generate key performance indicators. The visualization engine is configured to create a scorecard that displays the key performance indicators. The scorecard comprises a building energy overview widget that displays total consumption of a building, a consumption by space widget that displays consumption of a plurality of subspaces of the building, and a consumption by commodity widget that displays consumption of the building categorized by commodity. In some embodiments, the scorecard also includes an energy density by space widget that displays consumption per unit area per day for the subspaces of the building.

Abstract: A building management system includes connected equipment configured to measure a plurality of monitored variables and a predictive diagnostics system configured to receive the monitored variables from the connected equipment; generate a probability distribution of the plurality of monitored variables; determine a boundary for the probability distribution using a supervised machine learning technique to separate normal conditions from faulty conditions indicated by the plurality of monitored variables; separate the faulty conditions into sub-patterns using an unsupervised machine learning technique to generate a fault prediction model, each sub-pattern corresponding with a fault, and each fault associated with a fault diagnosis; receive a current set of the monitored variables from the connected equipment; determine whether the current set of monitored variables correspond with one of the sub-patterns of the fault prediction model to facilitate predicting whether a corresponding fault will occur; and determin