Abstract: A module is described which is slidably attachable to a controller. Resource wires are connected to the module through resource connectors, The module has a circuit board that can perform actions. The module can modify the function of its resource connectors. These modifications may be to meet the requirements of resources that are to be connected to the module. The module may be able to monitor voltage, current, or power, or check for faults on the wire. The results of such monitoring may be displayed on a screen associated with the controller.

Abstract: The amount of state over time (demand curves) that needs to be injected into a structure over time to achieve desired state values over time (desired comfort curves) at locations are determined by using a neural network that models the structure. Possibly random demand curves are fed into the neural network model at areas, such as the outside, state source locations (such as heaters), and are fed forward though the model, diffusing the state throughout the model. Comfort curves at chosen locations within the neural net representing physical locations are output. The comfort curves are compared with the desired comfort curves using cost function. Machine-learning methods are used to incrementally improve the demand curves until the output comfort curves are sufficiently close the desired state values.

Abstract: Personal comfort information for individuals (such as characteristics such as height and weight, and preferences such as preferred temperature, etc) can be gathered and stored in a controller that controls a controlled space. The location of these individuals can be tracked as they move around the controlled space. The personal comfort information of the individuals can be used to modify the state of the current space the individual is in.

Abstract: Heterogenous neural networks are disclosed that have activation functions that hold multi-variable equations. These variables can be passed from one neuron to another. The neurons may be laid out in a topologically similar fashion to a physical system that the heterogenous neural network is modeling. A neural network may have inputs of more than one type. Only a portion of the inputs (a subdomain) may be optimized In such an instance, the neural network may run forward, backpropagate to all inputs, and then perform optimization only on those inputs which will be optimized.

Abstract: A model receives a target demand curve as an input and outputs an optimized control sequence that allows equipment within a physical space to be run optimally. A thermodynamic model is created that represents equipment within the physical space, with the equipment being laid out as nodes within the model according to the equipment flow in the physical space. The equipment activation functions comprise equations that mimic equipment operation. Values flow between the nodes similarly to how states flow between the actual equipment. The model is run such that a control sequence is used as input into the neural network; the neural network outputs a demand curve which is then checked against the target demand curve. Machine learning methods are then used to determine a new control sequence. The model is run until a goal state is reached.

Abstract: A neural network in one embodiment is built by decomposing a structure into different building materials creating neurons that represent building materials and open spaces in a structure. Subsystems in the building have their neurons concatenated together to create same length neuron strings. In some embodiments, neurons in a short neuron string are split to make longer neuron strings. In some embodiments, neurons are added to some neuron strings to represent inside features, air features, and outside features.

Abstract: A structure thermodynamic model, which models the physical characteristics of a controlled space, inputs a constraint state curve which gives constraints, such as temperature, that a controlled space is to meet; and outputs a state injection time series which is the amount of state needed for the controlled space to optimize the constraint state curve. The state injection time series curve is then used as input into an equipment model, which models equipment behavior in the controlled space. The equipment model outputs equipment control actions per control time (a control sequence) which can be used to control the equipment in the controlled space. Some embodiments train the models using training data.

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.

Abstract: An unknown state value in a structure neuron value in a neural network, in one embodiment, is determined by using the difference between known values and output at an equivalent model location. The accuracy of model produced values with known values are determined compared to the known values. How much the known model produced locations were used to determine the unknown state value is determined. These amounts and accuracy of the model produced values are used to determine accuracy of the model produced value of the unknown state value.

Abstract: Using processes and methods described herein, a digital twin of a physical space can train itself using sensors and other information available from the building. In some embodiments, a system to be controlled comprises a controller that is connected to sensors. This controller also has a thermodynamic model of the system to be controlled within memory associated with the controller. The thermodynamic model has neurons that represent distinct pieces of a controlled space, such as a piece of equipment or a thermodynamically coherent section of a building, such as a window. The neurons represent these distinct pieces of the controlled space using parameter values and equations that model physical behavior of state with reference to the distinct piece of the controlled state. A machine learning process refines the thermodynamic model by modifying the parameter values of the neurons, using sensor data gathered from the system to be controlled as ground truth to be matched by behavior of the thermodynamic model.