Abstract: A building management system includes one or more processors, and one or more computer-readable storage media communicably coupled to the one or more processors and having instructions stored thereon that cause the one or more processors to: define a state of a zone or space within a building; control an HVAC system to adjust a temperature of the zone or space corresponding to a first action; receive utterance data from a voice assist device located in the zone or space; analyze the utterance data to identify a sentiment relating to the temperature of the zone or space; calculate a reward based on the state, the first action, and the sentiment; determine a second action to adjust the temperature of the zone or space based on the reward; and control the HVAC system to adjust the temperature of the zone or space corresponding to the second action.

Abstract: A building management system includes one or more processors, and one or more computer-readable storage media communicably coupled to the one or more processors and having instructions stored thereon that cause the one or more processors to: receive utterance data from a voice assist device; determine a location of the voice assist device; analyze the utterance data to identify a sentiment relating to a temperature of the location; and control an HVAC system to adjust the temperature of the location based on the sentiment.

Abstract: A method includes collecting a first dataset of input-output data for a first building, training a deep learning model using the first dataset, initializing parameters of a target model for a second building using parameters of the deep learning model, collecting a second dataset of input-output data for a second building, training the target model for the second building using the initialized parameters of the target model and the second dataset, and controlling building equipment using the target model. Controlling the building equipment affects a variable state or condition of the building.

Abstract: A method for classifying an occluded object includes receiving, by one or more processing circuits, an image of the object that is partially occluded by a foreign object and classifying, by the one or more processing circuits, the object of the image into one of one or more classes of interest via an artificial neural network (ANN) by determining a plurality of neuron activations of neurons of the ANN for one or more foreign classes and the one or more classes of interest, subtracting one or more of the neuron activations of the one or more foreign classes from the neuron activations of the one or more classes of interest, wherein the foreign object belongs to one of the one or more foreign classes, and classifying the object of the image into the one of the one or more classes of interest based on the subtracting.

Abstract: A building system of a building including one or more memory devices configured to store one or more instructions that, when executed on one or more processors, cause the one or more processors to exercise a building entity causing building entity data to be generated associated with the building entity, the building entity data indicating a result of exercising the building entity and collect the building entity data. The instructions cause the one or more processors to identify, based on a relational model, one or more relationships between one or more building entities and the building entity, wherein the one or more relationships indicate that exercising the building entity affects operation of the one or more building entities and identify that the building is experiencing a performance issue by analyzing the building entity data and the one or more relationships.

Abstract: A building system including one or more memory devices configured to store instructions that, when executed on one or more processors, cause the one or more processors to collect building device data of a building device, the building device data comprising a plurality of data samples of a data point and generate a time correlated data stream for the data point, the time correlated data stream comprising values of the plurality of data samples of the data point. The instructions cause the one or more processors to generate a time correlated reliability data stream for the data point, the time correlated reliability data stream comprising a plurality of reliability values indicating reliability of the values of the plurality of data samples of the data point.

Abstract: A building schema mapping system, the system including one or more memory devices configured to store instructions, that, when executed by one or more processors, cause the one or more processors to receive strings in a first schema, each string representing at least one of a point, building equipment, or a building space, extract relationships from the strings, each relationship of the relationships indicating a particular relationship between a first string of the strings and a second string of the strings, label each of the strings based on characters of each of the strings, and generate a graph data structure of a second schema based on the relationships and the label of each of the strings.

Abstract: A building security system for a building includes one or more memory devices configured to store instructions. The instructions, when executed on one or more processors, cause the one or more processors to receive an access policy data structure for a building device, the access policy data structure indicating access policies for interactions of one or more other building devices with the building device, wherein the access policy data structure identifies the one or more other building devices with one or more building model queries, generate a dynamic access policy data structure for the building device by resolving the one or more building model queries with a building model to identify the one or more other building devices, wherein the dynamic access policy data structure comprises the access policies, and implement the access policies of the dynamic access policy data structure based on the one or more other building devices.

Abstract: A method for generating a human-like response to a voice or text command includes receiving an input sequence of words and processing the input sequence of words to generate a trigger word that is indicative of a desired nature of the human-like response. The method further includes encoding a neural network using the trigger word and generating the human-like response using an output of the neural network. The method enables implementation of voice command functionality in various types of devices with only a small amount of training data.

Abstract: A method for classifying an occluded object includes receiving, by one or more processing circuits, an image of the object that is partially occluded by a foreign object and classifying, by the one or more processing circuits, the object of the image into one of one or more classes of interest via an artificial neural network (ANN) by determining a plurality of neuron activations of neurons of the ANN for one or more foreign classes and the one or more classes of interest, subtracting one or more of the neuron activations of the one or more foreign classes from the neuron activations of the one or more classes of interest, wherein the foreign object belongs to one of the one or more foreign classes, and classifying the object of the image into the one of the one or more classes of interest based on the subtracting.

Abstract: Controlling product production in multi-stage manufacturing process automatically generates by machine learning causal relationships between the processing conditions and the product quality based on product genealogy data and product quality data. Real time sensor data from sensors coupled to processing units in a manufacturing facility implementing the multi-stage manufacturing process are received, and control rules are instantiated based on the real time sensor data. An instantiated control rule firing causes an actuator to automatically set a processing variable to a set point specified in the control rule.

Abstract: A building energy system includes an energy storage system (ESS) configured to store energy received from an energy source and provide the stored energy to one or more pieces of building equipment. The system includes a local building system configured to collect building data and communicate the building data to a cloud platform and the cloud platform configured to receive the building data from the local building system via the network, determine whether to retrain a trained load prediction model based on at least some of the building data, retrain the trained load prediction model based on at least some of the building data in response to a determination to retrain the trained load prediction model, determine a load prediction for the building based on the retrained load prediction model, and cause the local building system to operate.

Abstract: A building energy system for a building includes an energy storage system (ESS) configured to store energy received from an energy source and provide the stored energy to one or more pieces of building equipment to operate the one or more pieces of building equipment. The system includes a processing circuit configured to collect building data, determine whether to retrain a trained load prediction model based on at least some of the building data, retrain the trained load prediction model based on the building data in response to a determination to retrain the trained load prediction model, determine a load prediction for the building based on the retrained load prediction model, and operate the ESS to store the energy received from the energy source or provide the stored energy to the one or more pieces of building equipment to operate the one or more pieces of building equipment.

Abstract: Detecting equipment failure risk in industrial process may include distributing equipment operations data to a cluster of nodes based on a range of time and operation specified in maintenance data associated with the equipment. From a record entry in the maintenance data, an operation, installation and maintenance time may be determined. A plurality of nodes storing equipment operations data associated with the operation during a time range between the installation and the maintenance time are selected. Operation features may be determined by distributed processing operation in the plurality of nodes. The operation features are aggregated and added as an entry in a target table. Equipment failure risk is detected by risk failure analysis performed based on the target table. A signal may be sent to automatically adjust or correct one or more operation features.

Abstract: Detecting equipment failure risk in industrial process may include distributing equipment operations data to a cluster of nodes based on a range of time and operation specified in maintenance data associated with the equipment. From a record entry in the maintenance data, an operation, installation and maintenance time may be determined. A plurality of nodes storing equipment operations data associated with the operation during a time range between the installation and the maintenance time are selected. Operation features may be determined by distributed processing operation in the plurality of nodes. The operation features are aggregated and added as an entry in a target table. Equipment failure risk is detected by risk failure analysis performed based on the target table. A signal may be sent to automatically adjust or correct one or more operation features.

Abstract: A chiller threshold management system for a building, including one or more memory devices and one or more processors. The one or more memory devices are configured to store instructions to be executed on the one or more processors. The one or more processors are configured to determine whether chiller fault data exists in chiller data used to generate a plurality of chiller prediction models. The one or more processors are further configured to generate a first threshold evaluation value for each of the plurality of chiller prediction models using a first evaluation technique in response to a determination that chiller fault data exists in the chiller data, and generate a second threshold evaluation value for each of the chiller prediction models using a second evaluation technique in response to a determination that chiller fault data does not exist in the chiller data.

Abstract: A chiller fault prediction system for a building, including one or more memory devices and one or more processors. The one or more memory devices are configured to store instructions to be executed on the one or more processors. The one or more processors are configured to receive chiller data for a plurality of chillers, the chiller data indicating performance of the plurality of chillers. The one or more processors are configured to generate, based on the received chiller data, a plurality of single chiller prediction models and a plurality of cluster chiller prediction models, the plurality of single chiller prediction models generated for each the plurality of chillers and the plurality of cluster chiller prediction models generated for chiller clusters of the plurality of chillers.

Abstract: A model management system for a building, including one or more memory devices and one or more processors. The one or more memory devices are configured to store instructions to be executed on the one or more processors. The one or more processors are configured to determine whether chiller fault data exists in chiller data used to generate a plurality of chiller shutdown prediction models. The one or more processors are further configured to generate a first performance evaluation value for each of the plurality of chiller shutdown prediction models using a first evaluation technique in response to a determination that chiller fault data exists in the chiller data, and generate a second performance evaluation value for each of the plurality of chiller shutdown prediction models using a second evaluation technique in response to a determination that chiller fault data does not exist in the chiller data.

Abstract: A building management system includes one or more processors, and one or more computer-readable storage media communicably coupled to the one or more processors and having instructions stored thereon that cause the one or more processors to: receive utterance data from a voice assist device; determine a location of the voice assist device; analyze the utterance data to identify a sentiment relating to a temperature of the location; and control an HVAC system to adjust the temperature of the location based on the sentiment.

Abstract: A building management system includes one or more processors, and one or more computer-readable storage media communicably coupled to the one or more processors and having instructions stored thereon that cause the one or more processors to: define a state of a zone or space within a building; control an HVAC system to adjust a temperature of the zone or space corresponding to a first action; receive utterance data from a voice assist device located in the zone or space; analyze the utterance data to identify a sentiment relating to the temperature of the zone or space; calculate a reward based on the state, the first action, and the sentiment; determine a second action to adjust the temperature of the zone or space based on the reward; and control the HVAC system to adjust the temperature of the zone or space corresponding to the second action.