Back to results
US 12,517,497 B2Granted
Solar board system
OwnerRobert A. Swaninventor
Life of this patent
Estimating the term…
Abstract
A method includes, responsive to first input, actuating a first plurality of valves of a solar board to be in an open position to provide cold water via a first manifold mounted to the solar board to first equipment and to receive hot water from the first equipment. The method further includes, responsive to second input, actuating a second plurality of valves of the solar board to be in the open position to provide the cold water via the first manifold and a second manifold mounted to the solar board to second equipment and to receive the hot water from the second equipment.
Claims18
A method comprising:
- receiving historical sensor data and historical performance data;
- training a machine learning model with data input comprising the historical sensor data and target output comprising the historical performance data to generate a trained machine learning model, the trained machine learning model being capable of generating one or more outputs indicative of one or more of a first input or a second input;
- responsive to the first input, actuating a first plurality of valves of a solar board to be in an open position to provide cold water via a first manifold mounted to the solar board to first equipment and to receive hot water from the first equipment for efficient use of energy;
- and
- responsive to the second input, actuating a second plurality of valves of the solar board to be in the open position to provide the cold water via the first manifold and a second manifold mounted to the solar board to second equipment and to receive the hot water from the second equipment for the efficient use of the energy, wherein:
- the first equipment comprises a natural gas water heater and the second equipment comprises an electric water heater;
- or
- the first equipment comprises the electric water heater and the second equipment comprises the natural gas water heater.
5 more elements
A solar board system comprising:
- a processing device configured to:
- receive historical sensor data and historical performance data;
- and
- train a machine learning model with data input comprising the historical sensor data and target output comprising the historical performance data to generate a trained machine learning model, the trained machine learning model being capable of generating one or more outputs indicative of one or more of a first input or a second input;
- a board;
- cold water inlet configured to receive cold water;
- hot water outlet configured to provide hot water;
- and
- a plurality of manifolds mounted to the board, the plurality of manifolds comprising:
- a first manifold configured to receive the cold water from the cold water inlet;
- and
- a second manifold configured to:
- receive the hot water from first equipment responsive to a first valve and a second valve being in an open position responsive to the first input for efficient use of energy, the first valve being disposed between the first manifold and a first equipment inlet, and the second valve being disposed between a first equipment outlet and the second manifold;
- and
- provide the cold water to second equipment responsive to a third valve and a fourth valve being in the open position responsive to the second input for the efficient use of the energy, the third valve being disposed between the first manifold and the second manifold, and the fourth valve being disposed between the second manifold and second equipment inlet, wherein:
- the first equipment comprises a natural gas water heater and the second equipment comprises an electric water heater;
- or
- the first equipment comprises the electric water heater and the second equipment comprises the natural gas water heater.
15 more elements
A non-transitory machine-readable storage medium storing instructions that when executed by a processing device, cause the processing device to perform operations comprising:
- receiving historical sensor data and historical performance data;
- training a machine learning model with data input comprising the historical sensor data and target output comprising the historical performance data to generate a trained machine learning model, the trained machine learning model being capable of generating one or more outputs indicative of one or more of a first input or a second input;
- responsive to the first input, actuating a first plurality of valves of a solar board to be in an open position to provide cold water via a first manifold mounted to the solar board to first equipment and to receive hot water from the first equipment for efficient use of energy;
- and
- responsive to the second input, actuating a second plurality of valves of the solar board to be in the open position to provide the cold water via the first manifold and a second manifold mounted to the solar board to second equipment and to receive the hot water from the second equipment for the efficient use of the energy, wherein:
- the first equipment comprises a natural gas water heater and the second equipment comprises an electric water heater;
- or
- the first equipment comprises the electric water heater and the second equipment comprises the natural gas water heater.
5 more elements
Dependencies are inferred from the claim text.