Abstract: A building management system includes building equipment configured to operate in accordance with an input to alter a variable state or condition of a building, a feedback controller configured to generate the input as a function of a measured state of the building equipment, and an analytics circuit. The analytics circuit is configured to obtain and store a dataset comprising the measured state and the input for a plurality of time steps, determine, based on at least a portion of the dataset, a self-optimizing control function that defines a self-optimizing control variable as a function of the measured state, calculate a value of the self-optimizing control variable using the self-optimizing control function and the measured state, monitor the value of the self-optimizing control variable over time, and generate an indication of performance of the building equipment relative to optimal performance based on the value of the self-optimizing control variable.

Abstract: Disclosed is a system to control a climate of a space via a first control loop and a second control loop interacting with the first control loop. The system includes a first controller of the first control loop to generate a first control signal based on a first modified set point and a first feedback signal. The system further includes a second controller of the second control loop to generate a second control signal based on a second modified set point and a second feedback signal. The system further includes a decoupler configured to predict a first effect of the first control signal on the second control loop and a second effect of the second control signal on the first control loop, and generate the first modified set point and the second modified set point to reduce the first effect and the second effect.

Abstract: A controller for HVAC equipment of a plant includes a processing circuit configured to predict an impact of a time delay of the plant on a performance variable received as feedback from the plant. The processing circuit is configured to artificially increase or decrease a value of the performance variable using an adjustable time delay parameter to at least partially negate the impact of the time delay on the performance variable. The processing circuit is configured to use the artificially increased or decreased value of the performance variable in on-off feedback control to operate the HVAC equipment.

Abstract: A self-optimizing controller for equipment of a plant provides a manipulated variable as an input to the plant and receives an output variable as feedback. The controller generates a performance variable model defining the performance variable as a function of the manipulated variable and an output variable model defining the output variable as a function of the manipulated variable. The controller uses the performance variable model to determine a gradient of the performance variable, uses the output variable model to determine a gradient of the output variable, and generates a self-optimizing variable based on the gradient of the performance variable model and the gradient of the output variable model. The controller operates the equipment of the plant to affect a variable state or condition of the building based on the value of the self-optimizing variable from the self-optimizing variable model.

Abstract: Systems and methods for monitoring and controlling a plant using extremum-seeking control. The method includes perturbing a setpoint for a controller by applying a dither signal to the setpoint. The controller uses a perturbed setpoint to generate one or more control inputs for the building equipment. Receiving, from the building equipment, an output signal and obtaining values of a performance variable based on the output signal, the values of the performance variable resulting from operating the building equipment based on the perturbed setpoint. The method includes determining a gradient of the performance variable with respect to the perturbed setpoint and a Hessian of the performance variable affected by the building equipment with respect to the setpoint. The method includes determining an adjustment to the setpoint predicted to drive the performance variable to an extremum based on the gradient and the Hessian of the performance variable.

Abstract: Systems and methods for monitoring and controlling a plant using extremum-seeking control. The method includes perturbing a setpoint for a controller by applying a dither signal to the setpoint. The controller uses a perturbed setpoint to generate one or more control inputs for the building equipment. Receiving, from the building equipment, an output signal and obtaining values of a performance variable based on the output signal, the values of the performance variable resulting from operating the building equipment based on the perturbed setpoint. The method includes determining a gradient of the performance variable with respect to the perturbed setpoint and a Hessian of the performance variable affected by the building equipment with respect to the setpoint. The method includes determining an adjustment to the setpoint predicted to drive the performance variable to an extremum based on the gradient and the Hessian of the performance variable.

Abstract: A building management system includes building equipment configured to operate in accordance with an input to alter a variable state or condition of a building, a feedback controller configured to generate the input as a function of a measured state of the building equipment, and an analytics circuit. The analytics circuit is configured to obtain and store a dataset comprising the measured state and the input for a plurality of time steps, determine, based on at least a portion of the dataset, a self-optimizing control function that defines a self-optimizing control variable as a function of the measured state, calculate a value of the self-optimizing control variable using the self-optimizing control function and the measured state, monitor the value of the self-optimizing control variable over time, and generate an indication of performance of the building equipment relative to optimal performance based on the value of the self-optimizing control variable.

Abstract: A self-optimizing controller for equipment of a plant provides a manipulated variable as an input to the plant and receives an output variable as feedback. The controller generates a performance variable model defining the performance variable as a function of the manipulated variable and an output variable model defining the output variable as a function of the manipulated variable. The controller uses the performance variable model to determine a gradient of the performance variable, uses the output variable model to determine a gradient of the output variable, and generates a self-optimizing variable based on the gradient of the performance variable model and the gradient of the output variable model. The controller operates the equipment of the plant to affect a variable state or condition of the building based on the value of the self-optimizing variable from the self-optimizing variable model.

Abstract: A thermostat for a conditioned space includes a sensor that measures a value of a performance variable of the conditioned space, a user interface that receives a setpoint value from a user and displays information to the user, and a controller. The controller receives values of the performance variable from the sensor over a time period, stores the values of the performance variable, receives the setpoint value from the user interface, and determines a value of a manipulated variable based on the setpoint value and the values of the performance variable. The controller is configured to adjust an operation of HVAC equipment that affect the conditioned space based on the value of the manipulated variable. The controller is configured to determine a smoothed value of the performance variable based on the values of the performance variable and cause the user interface to display the smoothed value.

Abstract: A building management system includes sensors configured to measure a plurality of monitored variables and fault detection and diagnosis (FDD) system configured to identify an operating state associated with the monitored variables. The FDD system includes a communications interface configured to receive samples of the monitored variables from the plurality of sensors. The FDD system includes a direction extractor configured to use locations, in a multidimensional modeling space, of a plurality of stored operating states to extract a direction from each of the stored operating states to each of the other stored operating states. The FDD system includes a fault diagnoser configured to use the extracted directions in a voting-based diagnosis to determine an operating state for each of the samples of the monitored variables.

Abstract: A thermostat for transmitting data wirelessly to a controller in a building includes a temperature sensor, a processing circuit, and a wireless radio. The processing circuit is configured to receive a measured temperature value from the temperature sensor, determine a current temperature error based on the current measured temperature value and a setpoint temperature, and determine whether a difference between the current temperature error and a previous temperature error is greater than an error threshold. The processing circuit is configured to determine whether a minimum amount of time has passed since transmitting a previous measured temperature value and transmit the current measured temperature value to the controller via the wireless transmitter in response to determining that both the difference between the current temperature error and the previous temperature error is greater than the error threshold and the minimum amount of time has passed since transmitting a temperature value.

Abstract: A building management system includes connected equipment and a predictive diagnostics system. The connected equipment is configured to measure a plurality of monitored variables. The predictive diagnostics system includes a communications interface, a principal component analysis (PCA) modeler, and a fault predictor. The communications interface is configured to receive samples of the monitored variables from the connected equipment. The PCA modeler is configured to construct PCA models for a plurality of operating states of the connected equipment using the samples of the monitored variables. Each PCA model defines a location of one of the operating states in a multidimensional modeling space. The fault predictor is configured to determine a proximity of a new sample of the monitored variables to one or more of the operating states using the PCA models and to predict a fault occurrence based on the proximity.

Abstract: An on-off control system includes on-off equipment configured to operate in either an on state or an off state, an on-off controller configured to cause the equipment to transition between the on state and the off state based on a setpoint value and a deadband value to drive a control variable toward the setpoint value, and a deadband controller, according to some embodiments. In some embodiments, the deadband controller is configured to generate the deadband value used by the on-off controller. In some embodiments, the deadband controller is configured to generate the deadband value by obtaining a cost function that defines a cost based on at least a set of control values and the deadband value and selecting the deadband value that results in an optimal value of the cost function over a range of possible deadband values, the selected deadband value defining an optimal deadband value.

Abstract: A method for performing extremum-seeking control of a plant includes determining multiple values of a correlation coefficient that relates a control input provided as an input to the plant to a performance variable that characterizes a performance of the plant in response to the control input. The performance variable includes a noise-free portion and an amount of noise. The method includes determining an adjusted correlation coefficient by scaling a first value of the correlation coefficient selected from the multiple values relative to a second value of the correlation coefficient selected from the multiple values. The adjusted correlation coefficient relates the noise-free portion of the performance variable to the control input. The method includes using the adjusted correlation coefficient to modulate the control input provided as an input to the plant.

Abstract: A building management system includes building equipment configured to operate in accordance with an input to alter a variable state or condition of a building as a process function of the input while incurring a cost of operating the equipment as a cost function of the input. The building management system also includes a controller configured to calculate a value of a self-optimizing control variable as a function of a measured state of the building equipment and drive the value of the self-optimizing control variable towards a setpoint value by generating the input based on the self-optimizing control variable and providing the input to the building equipment. The function comprises multiplying the measured state by a matrix and adding an offset vector. Values of elements of the matrix and the offset vector are determined using a non-optimal reference.

Abstract: A pressure disturbance rejection valve assembly is provided. The valve assembly includes a valve, a flow rate sensor, and an actuator. The actuator includes a motor, a drive device configured to be driven by the motor and coupled to the valve for driving the valve within a range of positions, and a position sensor configured to measure a rotational position of the drive device. The actuator further includes a communications mechanism configured to receive a flow rate setpoint and a processing circuit. The processing circuit is configured to determine an actuator position setpoint using a feedback control mechanism based on the flow rate setpoint and the flow rate measurement, operate the motor to drive the drive device to the actuator position setpoint, detect a fault condition based at least in part on the rotational position measurement or the flow rate measurement, and perform a fault mitigation action in response to detection of the fault condition.

Abstract: A plant includes equipment that operate to affect a variable state or condition of the plant in response to a control signal. A feedback controller monitors a process variable received via a feedback signal from the plant and uses an error signal representing a setpoint error between the process variable and a setpoint to generate the control signal for the plant. An exponentially-weighted moving average (EWMA) calculator generates EWMA values based on the setpoint error. A normalized index generator uses the EWMA values to calculate a normalized performance index. A threshold generator generates a threshold based on a first alarm parameter ? representing a normalized magnitude of the setpoint error and a second alarm parameter ? representing a normalized duration that the setpoint error has persisted. An alarm manager generates an alarm in response to the normalized performance index crossing the threshold.

Abstract: A building management system includes connected equipment and a predictive diagnostics system. The connected equipment is configured to measure a plurality of monitored variables. The predictive diagnostics system includes a communications interface, a steady state detector, a controller. The communications interface is configured to receive samples of the monitored variables from the connected equipment. The steady state detector is configured to recursively update a mean and a variance of the samples each time a new sample is received, identify whether each of the samples reflects a steady state or a transient state of operation of the connected equipment using the mean and the variance, and associate each of the samples to the steady state or the transient state as identified. The controller is configured to adjust an operation of the connected equipment based on the steady state or the transient state as identified.

Abstract: A control system is configured to operate a multiple-input system to achieve an optimal value for a performance variable of the multiple-input system. The control system includes a mapper configured to generate a mapping from a first number of manipulated variables to a second number of latent variables. The second number is smaller than the first number and each of the latent variables includes a linear combination of the manipulated variables. The control system also includes an extremum-seeking controller configured to receive the performance variable from the multiple-input system as a feedback and modulate values of the second number of latent variables to drive the performance variable to the optimal value. The mapper is further configured to use the mapping to translate modulated values of the second number of latent variables to modulated values of the first number of manipulated variables and provide the modulated values of the first number of manipulated variables to the multiple-input system.

Abstract: A system for monitoring and controlling flow rate of a fluid through a valve is disclosed. The system includes a flow rate sensor to measure the flow rate of the fluid through the valve, and a controller. The controller is configured to receive the measured flow rate from the flow rate sensor, and determine if the measured flow rate is equal to a predetermined flow rate value. The controller is further configured to, in response to a determination that the measured flow rate is equal to the predetermined flow rate value, determine a minimum valve position threshold (xmin). Additionally, the controller is configured to determine a minimum flow rate threshold (ymin) corresponding to xmin, and configured to generate a PWM signal and calculate a corrected flow rate (?f) using the PWM signal. The controller controls a valve operation using ?f. The PWM signal switches between zero and ymin.