A method of operating a building management system is disclosed. The method includes determining, by a processing circuit, policy rankings for a plurality of control policies based on building operation data of a first previous time period, selecting, by the processing circuit, a set of control policies from among the plurality of control policies based on the policy rankings of the set of control policies satisfying a ranking threshold, generating, by the processing circuit, a plurality of prediction models for the set of control policies, selecting, by the processing circuit, a first prediction model of the plurality of prediction models based on building operation data of a second previous time period, and responsive to selecting the first prediction model, operating, by the processing circuit, the building management system using the first prediction model.

A system for controlling a boiler apparatus in a power plant to combust under optimized conditions, and a method for optimizing combustion of the boiler apparatus using the same are provided. The boiler control system may include a task manager configured to collect information on a current operating state of a boiler and determine whether to perform a combustion optimization operation for the boiler, a pre-processor configured to preprocess data collected from the boiler and supply the pre-processed data, a modeler configured to create a boiler combustion model on the basis of the pre-processed data received from the pre-processor, an optimizer configured to receive the boiler combustion model from the modeler and perform the combustion optimization operation for the boiler using the boiler combustion model to calculate an optimum control value, wherein the pre-processed data is supplied to the modeler and the optimizer by the pre-processor, and an output controller configured to receive the optimum control value from the optimizer and control an operation of the boiler by reflecting the optimum control value to a boiler control logic.

An operation path generation unit (210) generates an operation quantity time series for an actuator (111) based on a measurement state quantity output from a state sensor (101). A predictive model unit (220) generates a state quantity predictive time series by calculating a predictive model by using as an input the measurement state quantity and the operation quantity time series. A neural network unit (230) corrects the state quantity predictive time series by performing arithmetic operation of a neural network, by using as an input a measurement environment quantity output from an environment sensor (102) and the state quantity predictive time series. A state quantity evaluation unit (240) generates an evaluation result for the state quantity time series after the correction. The operation path generation unit outputs an operation quantity at the head of the operation quantity time series to the actuator when the evaluation result fulfils an appropriate criterion.

A system to generate scenarios by modifying values of machine learning features is provided. The system can present a first indication in a first coordinate space of a first performance generated by a model trained with a plurality of features using machine learning. The system can present a second indication in a second coordinate space of a first performance of the first feature. The system can receive a modification to a value in the second coordinate space of the first feature. The system can determine a second performance of the model using machine learning based on a first derived feature to output derived data points in the time period. The system can present in the first coordinate space, a third indication of the second performance of the model overlaid with the first indication of the first performance of the model.

The present invention provides an improved Smith predictive controller-based aero-engine H∞ algorithm, and belongs to the technical field of aero-engine control and simulation. The present invention first establishes a reasonable small deviation linear model for an aero-engine nonlinear model, and selects the state space model data of a certain operating condition as the controlled object for controller design; selects appropriate performance index weighting function parameters, solves the H.sub.∞ output feedback controller, and adjusts the parameters to basically meet the control requirements; and designs a Smith predictive compensator with an improved structure based on a closed-loop feedback control system designed according to the H.sub.∞ control law to constitute a compound controller, adds a deviation correction controller designed according to the PID control law to the control system to stabilize the controlled object in view that the prediction model and parameters of the controlled object have large deviations from the real model and parameters, and makes adaptive corrections by comparing the output signals of the controlled object and the model so as to further enhance the robustness of the system.

A system and approach for storing factors in a quadratic programming solver of an embedded model predictive control platform. The solver may be connected to an optimization model which may be connected to a factorization module. The factorization module may incorporate a memory containing saved factors that may be connected to a factor search mechanism to find a nearest stored factor in the memory. A factor update unit may be connected to the factor search mechanism to obtain the nearest stored factor to perform a factor update. The factorization module may provide variable ordering to reduce a number of factors that need to be stored to permit the factors to be updated at zero floating point operations per unit of time.

A model predictive controller for a performing stateless prediction. Using dosed form algebraic expressions for the step test in a dynamic matrix eliminates the requirement for individual calculation on each element. With both the dynamic matrix and the vector of predicted errors written in terms of discrete algebraic equations, the control law is written as a function of the current state of the system. The control law is then be reduced to its minimal form, which leaves the next control action to be a function of the system parameters, the past errors, and the past control actions. Since the system parameters are constant, this controller is then be reduced into a single discrete equation. This greatly reduces the computations required in each control loop iteration.

A multi-pump control system with a control module, a processing module, communication interface, and a storage module. The system is configured to change a number n of running pumps, and receive a signal indicative of a power consumption P and information about a speed ω of one of the n running pumps before and after two different changes of the number n of running pumps. The system is configured to determine, before and after at least two different changes of the number n of running pumps, without a measurement of a differential pressure Δp and of a flow Q, two approximated pump characteristics P.sub.n and Δ{tilde over (p)}.sub.n, wherein each of the approximated pump characteristics P.sub.n and Δ{tilde over (p)}.sub.n is unambiguously defined by a pair of parameters (θ.sub.1, θ.sub.2; θ.sub.3, θ.sub.4). The system is configured to store the pair of parameters (θ.sub.1, θ.sub.2; θ.sub.3, θ.sub.4) for each of the determined approximated pump characteristics P.sub.n and Δ{tilde over (p)}.sub.n.

Systems and methods for automatically generating solver code for a nonlinear model predictive controller are disclosed. In one embodiment, a method of automatically generating solver code for a nonlinear model predictive control solver includes receiving an optimal control problem code, wherein the optimal control problem code represents an optimal control problem comprising a cost function, one or more constraints, and a continuous time model representing dynamics of a system. The method further includes receiving a discretization method preference, a linearization point preference, and a parameter specification, and encoding the optimal control problem into an optimization problem by discretizing the optimal control problem according to the discretization method preference, and linearizing the optimal control problem according to the linearization point preference. The method further includes generating the solver code from the optimization problem.

A computer implemented method and related aspects for updating a perception function of a plurality of vehicles having an Automated Driving System (ADS) are disclosed. The method includes obtaining one or more locally updated model parameters of a self-supervised machine-learning algorithm from a plurality of remote vehicles, and updating one or more model parameters of a global self-supervised machine-learning algorithm based on the obtained one or more locally updated model parameters. Further, the method includes fine-tuning the global self-supervised machine-learning algorithm based on an annotated dataset in order to generate a fine-tuned global machine-learning algorithm comprising one or more fine-tuned model parameters. The method further includes forming a machine-learning algorithm for an in-vehicle perception module based on the fine-tuned global machine-learning algorithm, and transmitting one or more model parameters of the formed machine-learning algorithm for the in-vehicle perception module to the plurality of remote vehicles.