# US 2026/0310969 A1 · Neural Network Initialization

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0310969 A1
- Document ID: US20260310969A1
- Status: Published application
- Kind: A1
- Application number: 19/717,397
- Filed: 2026-06-23
- Published: 2026-10-08
- Earliest claimed: 2020-06-05
- Assignees: PassiveLogic, Inc.
- Applicants: PassiveLogic, Inc.
- Inventors: Troy Aaron Harvey; Jeremy David Fillingim
- Web page: https://patentgrep.com/patent/US20260310969A1

## CPC

- G06N 3/084: Backpropagation, e.g. using gradient descent
- B60H 1/00285: {for vehicle seats}
- F24F 11/64: using pre-stored data
- F24F 11/65: for selecting an operating mode
- G05B 13/027: {using neural networks only}
- G05B 13/04: involving the use of models or simulators
- G05B 19/042: using digital processors (G05B19/05 takes precedence)
- G06F 17/16: Matrix or vector computation {, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization (matrix transposition G06F7/78)}
- G06F 30/18: Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling (circuit design at the physical level G06F30/39; network planning tools for wireless communication networks H04W16/18)
- G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/048: Activation functions
- G06N 3/063: using electronic means
- G06N 3/08: Learning methods
- G06Q 10/067: Enterprise or organisation modelling
- G06Q 50/163: Real estate management
- F24F 2120/10: Occupancy
- F24F 2120/20: Feedback from users
- F24F 2140/50: Load
- G05B 2219/2614: HVAC, heating, ventillation, climate control
- G06F 2119/06: Power analysis or power optimisation
- G06F 2119/08: Thermal analysis or thermal optimisation
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- B60H: ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
- F24F: AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING (removing dirt or fumes from areas where they are produced B08B15/00; vertical ducts for carrying away waste gases from buildings E04F17/02; tops for chimneys or ventilating shafts, terminals for flues F23L17/02)
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A neural network representing a controlled space can be initialized by collecting state time series data that affects the controlled space such as weather, and also collecting sensor data from the controlled space at the same time. The time series data is used as input to a neural network that models the controlled space until an area in the neural network equivalent to the sensor is at or near the sensor state at a given time.

## Claims

### Claim 1

A computer-implemented method for reducing compute time required to operate a thermodynamic model of a controlled space, the method comprising:
receiving, by one or more processors, time-series state data representing a physical state that affects the controlled space during a historical time period ending at a reference time;
receiving, by the one or more processors, sensor data from a sensor located in the controlled space, the sensor data representing a measured state of a portion of the controlled space at the reference time;
storing, in memory, a thermodynamic neural network representing the controlled space, the thermodynamic neural network comprising a plurality of neurons arranged to correspond to physical portions of the controlled space; and
before running the thermodynamic neural network to determine a control operation for equipment of the controlled space, performing a warmup process to establish initialized transient state values for the thermodynamic neural network, wherein the initialized transient state values represent internal thermodynamic states, the warmup process comprising:
selecting a first portion of the time-series state data;
propagating the first portion of the time-series state data through the thermodynamic neural network to update transient state values of the plurality of neurons;
determining whether an updated transient state value of a sensor-corresponding neuron satisfies a stopping condition relative to the measured state represented by the sensor data, the sensor-corresponding neuron corresponding to the portion of the controlled space in which the sensor is located;
when the stopping condition is not satisfied, selecting a second portion of the time-series state data having a different historical duration than the first portion and propagating the second portion of the time-series state data through the thermodynamic neural network; and
when the stopping condition is satisfied, storing current transient state values of the plurality of neurons as initialized transient state values of the thermodynamic neural network, and using the initialized transient state values as starting values for a later run of the thermodynamic neural network, thereby reducing a number of iterations or processor cycles required for the later run to reach a modeled state corresponding to the controlled space.

### Claim 2 (depends on 1)

The method of claim 1, wherein each neuron of at least some of the plurality of neurons comprises an activation function representing heat transfer or state transfer through a corresponding physical portion of the controlled space.

### Claim 3 (depends on 2)

The method of claim 2, wherein each neuron of the at least some of the plurality of neurons comprises a permanent state value representing a physical property of the corresponding physical portion.

### Claim 4 (depends on 3)

The method of claim 3, wherein each neuron of the at least some of the plurality of neurons comprises a transient state value representing an internal thermodynamic state of the corresponding physical portion.

### Claim 5 (depends on 1)

The method of claim 1, further comprising determining, using the later run of the thermodynamic neural network, an operating state of equipment configured to modify the physical state of the controlled space.

### Claim 6 (depends on 5)

The method of claim 5, further comprising causing the equipment to operate according to the determined operating state.

### Claim 7 (depends on 1)

The method of claim 1, wherein the first portion and the second portion of the time-series state data each end at the reference time, and wherein the second portion includes a longer historical duration than the first portion.

### Claim 8 (depends on 1)

The method of claim 1, wherein the time-series state data is divided into a plurality of sections, each section including a plurality of timesteps, and wherein selecting the second portion comprises changing an index identifying a number of the plurality of sections to be propagated through the thermodynamic neural network.

### Claim 9 (depends on 1)

The method of claim 1, wherein the stopping condition is satisfied when the updated transient state value of the sensor-corresponding neuron is within a threshold range or margin of error of the measured state represented by the sensor data.

### Claim 10 (depends on 4)

The method of claim 4, wherein propagating the first portion of the time-series state data through the thermodynamic neural network comprises feedforwarding the first portion through the plurality of neurons to update the transient state value of each neuron of the at least some of the plurality of neurons using the activation function and the permanent state value of that neuron, the permanent state value remaining unchanged during the propagating, and without adjusting any weight of the thermodynamic neural network by backpropagation.

### Claim 11

A system for reducing compute time required to operate a thermodynamic model of a controlled space, the system comprising:
one or more processors;
memory in operational communication with the one or more processors; and
instructions stored in the memory that, when executed by the one or more processors, cause the one or more processors to:
receive time-series state data representing a physical state that affects the controlled space during a historical time period ending at a reference time;
receive sensor data from a sensor located in the controlled space, the sensor data representing a measured state of a portion of the controlled space at the reference time; and
store, in the memory, a thermodynamic neural network representing the controlled space, the thermodynamic neural network comprising a plurality of neurons arranged to correspond to physical portions of the controlled space;
before running the thermodynamic neural network to determine a control operation for equipment of the controlled space, perform a warmup process to establish initialized transient state values for the thermodynamic neural network, wherein the initialized transient state values represent internal thermodynamic states, the warmup process comprising:
select a first portion of the time-series state data;
propagate the first portion of the time-series state data through the thermodynamic neural network to update transient state values of the plurality of neurons;
determine whether an updated transient state value of a sensor-corresponding neuron satisfies a stopping condition relative to the measured state represented by the sensor data, the sensor-corresponding neuron corresponding to the portion of the controlled space in which the sensor is located;
when the stopping condition is not satisfied, select a second portion of the time-series state data having a different historical duration than the first portion and propagate the second portion of the time-series state data through the thermodynamic neural network; and
when the stopping condition is satisfied, store current transient state values of the plurality of neurons as initialized transient state values of the thermodynamic neural network, and use the initialized transient state values as starting values for a later run of the thermodynamic neural network, thereby reducing a number of iterations or processor cycles required for the later run to reach a modeled state corresponding to the controlled space.

### Claim 12 (depends on 11)

The system of claim 11, wherein the instructions further cause the one or more processors to run an eventual model operation of the thermodynamic neural network using the initialized transient state values as starting values rather than default starting values.

### Claim 13 (depends on 12)

The system of claim 12, wherein running the eventual model operation using the initialized transient state values reduces processor cycles required for the eventual model operation to reach a modeled state corresponding to the controlled space.

### Claim 14 (depends on 12)

The system of claim 12, wherein the instructions further cause the one or more processors to determine, using the eventual model operation, an operating state of equipment configured to modify the physical state of the controlled space.

### Claim 15 (depends on 14)

The system of claim 14, wherein the operating state comprises an on state, an off state, an intermediate operating state, a setpoint, a flow rate, or a time-based control state of the equipment.

### Claim 16 (depends on 14)

The system of claim 14, wherein the instructions further cause the one or more processors to cause the equipment to operate according to the determined operating state.

### Claim 17

A non-transitory computer-readable storage medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations for reducing compute time required to operate a thermodynamic model of a controlled space, the operations comprising:
receiving time-series state data representing a physical state that affects the controlled space during a historical time period ending at a reference time;
receiving sensor data from a sensor located in the controlled space, the sensor data representing a measured state of a portion of the controlled space at the reference time;
storing, in memory, a thermodynamic neural network representing the controlled space, the thermodynamic neural network comprising a plurality of neurons arranged to correspond to physical portions of the controlled space;
before running the thermodynamic neural network to determine a control operation for equipment of the controlled space, performing a warmup process to establish initialized transient state values for the thermodynamic neural network, wherein the initialized transient state values represent internal thermodynamic states, the warmup process comprising:
selecting a first portion of the time-series state data;
propagating the first portion of the time-series state data through the thermodynamic neural network to update transient state values of the plurality of neurons;
determining whether an updated transient state value of a sensor-corresponding neuron satisfies a stopping condition relative to the measured state represented by the sensor data, the sensor-corresponding neuron corresponding to the portion of the controlled space in which the sensor is located;
when the stopping condition is not satisfied, selecting a second portion of the time-series state data having a different historical duration than the first portion and propagating the second portion of the time-series state data through the thermodynamic neural network; and
when the stopping condition is satisfied, storing current transient state values of the plurality of neurons as initialized transient state values of the thermodynamic neural network, and using the initialized transient state values as starting values, rather than default starting values, for a later run of the thermodynamic neural network, thereby reducing a number of iterations or processor cycles required for the later run to reach a modeled state corresponding to the controlled space.

### Claim 18 (depends on 17)

The non-transitory computer-readable storage medium of claim 17, wherein the operations further comprise running an eventual model operation of the thermodynamic neural network using the initialized transient state values as starting values rather than default starting values.

### Claim 19 (depends on 18)

The non-transitory computer-readable storage medium of claim 18, wherein the operations further comprise determining, using the eventual model operation, an operating state of equipment configured to modify the physical state of the controlled space.

### Claim 20 (depends on 19)

The non-transitory computer-readable storage medium of claim 19, wherein the operations further comprise causing the equipment to operate according to the determined operating state.
