Abstract: The disclosure relates to chiller systems and, more particularly, to chiller systems that employ electrically driven desiccant regenerators. In some examples, a chiller system includes a heat and mass exchanger and an electrically driven desiccant regenerator in fluid communication with the heat and mass exchanger. The heat and mass exchanger is configured to dehumidify a flow of air, and provide the dehumidified flow of air to a cooling tower. Further, the electrically driven desiccant regenerator is configured to provide concentrated liquid desiccant to the heat and mass exchanger for dehumidifying the flow of air.

Abstract: The disclosure relates to heat and mass exchangers. In some examples, a heat-mass exchanger includes a plurality of regeneration fins extending generally vertically, and a plurality of desiccant feed tubes extending generally horizontally. The heat-mass exchanger also includes a plurality of regenerator heating tubes extending generally horizontally. The plurality of desiccant feed tubes are positioned above the plurality of regenerator heating tubes. In addition, the plurality of desiccant feed tubes and the plurality of regenerator heating tubes extend through the plurality of regeneration fins. Further, the plurality of desiccant feed tubes include feed tube openings adapted for delivering liquid desiccant onto surfaces of the plurality of regeneration fins.

Abstract: The disclosure relates to machine learning and artificial intelligence based control systems for heating ventilation and cooling systems. In some examples, a computing device receives flow data characterizing flow rates of a first fluid over a time range. The computing device also receives humidity data characterizing humidity levels over the time range. Further, the computing device receives temperature data characterizing temperatures over the time range. The computing device also generates a training set of features based on the flow data, the humidity data, and the temperature data. The computing device further trains a machine learning process based on the training set of features. The computing device stores machine learning model data characterizing the trained machine learning process in a data repository.

Abstract: The disclosure relates to parallel plate and manifold assemblies for heat exchangers. In some examples, a plate assembly includes at least one plate. The plate includes a first side defining a side of a conditioning channel, where the first side is configured to receive desiccant. The plate also includes a second side that is opposite the first side. The second side defines a side of an exhaust channel. In addition, at least one of the first side and the second side include a plurality of support structures that are distributed in a predetermined pattern and are configured to maintain a predetermined width of the respective conditioning channel or exhaust channel.

Abstract: The disclosure relates to mass transfer assemblies for heating ventilation and cooling systems. In some examples, a mass transfer apparatus includes a stack of plates, where the stack defines channel pairs, and each channel pair has one conditioning channel and one exhaust channel. An upstream edge of the conditioning channels and a downstream edge of the exhaust channels define an upstream portion of the stack and extend laterally. In addition, the mass transfer apparatus is adapted to feed a fluid feed stream to the conditioning channels, and feed a first portion of the conditioned fluid feed stream to the exhaust channels. For each channel pair, an open portion of the upstream edge of the conditioning channel is open for receiving the fluid feed stream, and an open portion of the downstream edge of the exhaust channel is open for exhausting the conditioned fluid feed stream.

Abstract: The disclosure relates to control systems for heating ventilation and cooling systems. In some examples, a controller for a heating ventilation and cooling system receives, from a first temperature sensor, a first temperature of a first air flow entering a conditioner system. The controller also receives, from a first humidity sensor, a first dew point of the first air flow, and also receives, from a thermostat, a desired temperature for a conditioned space. The controller generates adjustment data characterizing an adjustment to at least one of: (1) an exhaust air flow, (2) a desiccant flow rate, (3) a water flow rate, (4) a total air flow rate, and (5) a liquid desiccant concentration of the conditioner system based on at least one of the first temperature, the first dew point, and the desired temperature. The controller transmits the adjustment data to the conditioner system to cause the adjustment.

Abstract: The disclosure relates to mass transfer assemblies for heating ventilation and cooling systems. In some examples, a mass transfer apparatus includes a stack of plates defining alternating conditioning channels and exhaust channels. The mass transfer apparatus also includes a fluid distribution system that includes a conditioning supply line defined in part by a first hole in an upper portion of each of the plates, and a working supply line defined in part by a second hole in the upper portion of each of the plates. The conditioning supply line supplies a conditioning fluid to the conditioning channels and the working supply line supplies a working fluid to the exhaust channels. The fluid distribution system also includes a conditioning return line that collects the conditioning fluid, and a working return line that collects the working fluid, each collection at a lower portion of each of the plates.

Abstract: The disclosure relates to fin inserts for heat and mass exchangers and corresponding methods. For instance, in some examples, a fin insert to a heat and mass exchanger includes a generally rigid, longitudinally-extending member that includes a top portion and side portions. The side portions may be disposed on opposite sides of the top portion, and may include a concave shape facing away from one another. The side portions may further are each be positioned around a portion of a respective heat transfer tube.

Abstract: This application relates to apparatus and methods for generating, and executing, surrogate models. In some examples, a computing device generates and evaluates correlations between input and output variables for a system to identify highly correlated input and output parameters. In addition, weights for one or more of the parameters may be determined. The computing device identifies a mathematical relationship between input and output variables to generate a physics model. The computing device may also identify other features not captured by the physical relationship that are highly correlated to each other, and generates a feature model that is based on the highly correlated features. The computing device may optimize the feature model based on a culling process that reduces the computational resources required to execute the feature model. The physics model is then combined with the feature model to generate a system output model that can simulate the system.

Abstract: This application relates to apparatus and methods for generating, and executing, surrogate models. In some examples, a computing device generates and evaluates correlations between input and output variables for a system to identify highly correlated input and output parameters. In addition, weights for one or more of the parameters may be determined. The computing device identifies a mathematical relationship between input and output variables to generate a physics model. The computing device may also identify other features not captured by the physical relationship that are highly correlated to each other, and generates a feature model that is based on the highly correlated features. The computing device may optimize the feature model based on a culling process that reduces the computational resources required to execute the feature model. The physics model is then combined with the feature model to generate a system output model that can simulate the system.

Abstract: The disclosure relates to plate-fin and manifold assemblies for heat exchangers. In some examples, an assembly includes a first plate and a second plate. The assembly also includes a plurality of fins disposed between the first plate and the second plate. In addition, the plurality of fins are spaced apart by a width large enough adapted for counter-flow of a plurality of fluids between adjacent fins of the plurality of fins. Further, the plurality of fins are configured to direct fluid flow across a length of the first plate and the second plate.

Abstract: The disclosure relates to fin inserts for heat and mass exchangers and corresponding methods. For instance, in some examples, a fin insert to a heat and mass exchanger includes a generally rigid, longitudinally-extending member that includes a top portion and side portions. The side portions may be disposed on opposite sides of the top portion, and may include a concave shape facing away from one another. The side portions may further are each be positioned around a portion of a respective heat transfer tube.

Abstract: This application relates to apparatus and methods for generating, and executing, surrogate models. In some examples, a computing device generates and evaluates correlations between input and output variables for a system to identify highly correlated input and output parameters. In addition, weights for one or more of the parameters may be determined. The computing device identifies a mathematical relationship between input and output variables to generate a physics model. The computing device may also identify other features not captured by the physical relationship that are highly correlated to each other, and generates a feature model that is based on the highly correlated features. The computing device may optimize the feature model based on a culling process that reduces the computational resources required to execute the feature model. The physics model is then combined with the feature model to generate a system output model that can simulate the system.