Abstract: Tools and techniques are described to automate creation of point mapping diagrams between controllers and controlled resources. After receiving a defined space diagram (which may be input using a graphical interface of the controller, or by other means), resource locations and resource wiring requirements (which may be done automatically), a wiring diagram including point mapping between the resources and any necessary controllers is generated. If resources need to be moved, a new wiring diagram and/or point mapping can be regenerated.

Abstract: Tools and techniques are described to automate line testing when wiring devices (such as equipment and sensors) to controllers. Controllers have access to databases of the devices that are controlled by them, including wiring diagrams and protocols, such that the controller can automatically check that each wire responds correctly to stimulus from the controller. After testing, a reporting device rapidly shows the results of the line testing.

Abstract: A controller is described that a building design can be input into, the building design comprising inputting a layout, predefined resources and positions for resources. within the layout. The resources may have a predefined physics nature that includes physics equations, allowable inputs and outputs, etc. The system then can determine how many controllers are needed of what type, and create a guided wiring system. In some implementations a user can control certain aspects of the wiring system, such as how full the individual controllers are and how much money is to be spent on labor versus money spent on equipment.

Abstract: Tools and techniques are described to create an interface that can translate a device language into an internal language, and describe the device to the controller in terms of actors and quanta such that when a device is attached to a controller, the controller can understand what the device does and why it does it. This internal language can then be translated back to a natural language, such as English. This allows the controller to track errors, determine what upstream or downstream device and action of the device caused the error, and to track many different facts of the system that allow for detailed reports.

Abstract: Controllers that control a building's state functions can be controlled by a master controller that the controllers choose themselves. The master controller communicates with the controllers and sensors to determine when a building state should change. When the building state should change, the maser controller or another controller determines the device or devices that need to modify state values of the building, and send messages to the devices so that they can change building state. If the master controller has a fault, the working controllers can choose another master controller. When a sensor indicates that a building state needs to be changed the master controller determines which device should change state, then tells the controller that is attached to the device.

Abstract: An interface is disclosed that allows a controller wiring diagram to be automatically created by understanding the nature of the building the controller is in as well as understanding the nature of the devices that are to be wired to it, and the location within the building of the devices. Users, using the user interface, can modify a depiction of the wiring diagram which may further modify the hardware of the controller device interface. Some embodiments further comprise modules that plug into the controller. The modules comprise the device connector that will be wired to the device. Some modules have hardware and memory that allow the module to physically modify the device connectors.

Abstract: Tools and techniques are described to create a controller wiring board. A user, using a user interface associated with a controller, can determine which devices will be attached to a controller. The features of the devices may be already known by the controller. The controller can change wiring terminal types depending on the requirements of the devices wired to the controllers. In some embodiments, a device is wired to a module associated with the controller. The controller can signal to the module to modify its wiring terminal to match the needs of the device to be wired to that location.

Abstract: A sensor is discloses that uses very little power by entering a sleep state, waking up, finding a sensor or other device to report to, then going back to sleep for the next sleep cycle. The sensor may need to add itself onto its network. To do so, keys are exchanged with the network provisioner, the sensor informs the network of its capabilities, and/or characteristics, etc, and the network determines which other sensors and other places in the network the sensor may talk with.

Abstract: A building controller with wiring terminals that has a moveable interactive screen is disclosed. The moveable interactive screen, when closed, covers the housing that holds the wiring terminals. The specific devices attached to specific terminals and the state of the devices can be displayed on the closed moveable interactive screen. Using the moveable interactive screen, a user can set up the expected devices and their protocols that will be attached to specific wiring terminals within the building controller. The controller wiring terminals can be viewed along with an interactive diagram of the the devices and the terminals that have been set up for the building controller can be viewed simultaneously when the moveable interactive screen is in the open position.

Abstract: Tools and techniques are described to automate commissioning of physical spaces. Controllers have access to databases of the devices that are controlled by them, including wiring diagrams and protocols, such that the controller can automatically check that each wire responds correctly to stimulus from the controller. Controllers also have access to databases of the physical space such that they can check that sensors in the space record the correct information for device activity, and sensors can cross-check each other for consistency. Once a physical space is commissioned, incentives can be sought based on commissioning results.

Abstract: Candidate function data can include data for multiple candidate functions that may indicate whether insurance claims are likely to involve certain issues, such as comparative negligence issues. A real-time claim identifier can use the candidate function data to determine, in near real-time, if claim data for a new insurance claim submitted to an insurance company satisfies at least one of the candidate functions. If the claim data satisfies at least one of the candidate functions, the insurance claim can be assigned to a corresponding destination in the insurance company, such as a department that processes comparative negligence claims, for further processing.

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: Processing methods and apparatus for increasing a reaction chamber batch size. Such a method of processing deposition substrates (e.g., wafers), involves conducting a deposition on a first portion of a batch of deposition wafers in a reaction chamber, conducting an interval conditioning reaction chamber purge to remove defects generated by the wafer processing from the reaction chamber; and following the interval conditioning mid-batch reaction chamber purge, conducting the deposition on another portion of the batch of wafers in the reaction chamber. The interval conditioning reaction chamber purge is conducted prior to exceeding a baseline for acceptable defect (e.g., particle) generation in the chamber and is performed while no wafers are positioned in the reaction chamber.

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: 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: 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: 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: 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: 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.