A smart window control device controls transmittance of a smart window provided as a window of a space where a temperature is controlled by an air conditioning system in accordance with a set temperature. The smart window control device includes a processor, and a memory storing program instructions that cause the processor to obtain a predicted value of external environment information about outside of the space in an interval between a first time and a second time, the second time being when a predetermined time period has elapsed from the first time, calculate transition of the temperature of the space in the interval based on the predicted value of the external environment information in the interval, and control the transmittance of the smart window so that the temperature of the space in the interval transitions based on the calculated transition of the temperature.

A method for determining an emission behaviour of a gas turbine engine. In order to provide a reliable operation of the gas turbine engine the method includes: parameterising the emission behaviour of the gas turbine engine for at least one selected first state variable of the gas turbine engine by using a model, which reflects a state behaviour of the gas turbine engine, and determining the emission behaviour of the gas turbine engine by using the parameterisation.

A method for controlling an environmental system may include defining a reference signal of an environmental variable in a greenhouse. The method may also include receiving renewable resource information related to the greenhouse. The method may further include receiving dynamic weather information of an environment external to the greenhouse. In addition, the method may include determining an optimization control scheme based on the reference signal, renewable resource information, and dynamic weather information. Further, the method may include regulating environmental conditions in the greenhouse according to the optimization control scheme.

Aspects of the invention include implemented method includes selecting an optimization algorithm for the control system of a processing plant based on whether the control system is guided by a linear-based predictive model or a non-linear-based predictive model, in which a gradient is available. Calculating set-point variables using the optimization algorithm. Predicting an output based on the calculated set-point variables. Comparing an actual output at the processing plant to the predicted output. Suspending a physical process at the processing plant in response to the actual output being a threshold value apart from the predicted output.

A method for evaluating a status of a vehicle, the method may include (i) obtaining sensed information during one or more driving sessions of the vehicle; (ii) determining, based on the sensed information, (a) multi-component-model (MCM) behavioral information regarding one or more MCM driving events, and (b) a component behavioral information regarding one or more component driving events; wherein a behavior of at least one first part of the vehicle during the one or more MCM driving events is indicative of a status of one or more MCMs; wherein a behavior of at least one second part of the vehicle during the one or more component driving event is indicative of a status of one or more components; (iii) determining the status of the one or more MCMs, based at least on the MCM behavioral information; and (iv) determining the status of the one or more components, based at least on the component behavioral information, the status of the component.

The present invention refers to an integrated operation method of conventional and residue FCC units that applies a model developed for predicting the catalytic performance of residue FCC units with any content and quality of flushing for the correct prediction and optimization of process simulators for residue FCC units and refining production planning models. The application can be for individual studies in process simulators or in digital twins to mitigate the unreliability in the prediction of the original simulator for studies with wide alteration in the content and quality of the flushing. The other application consists of modifying the refining production planning models based on the simulation result obtained in the modified process simulators to predict the performance of the waste units operating for any variation in the content and quality of the flushing catalyst used. The refining production planning model allows: 1. Indicative of potential profitability gain; 2. Optimum replacement of virgin and flushing catalysts in the conventional and residue FCC units; 3. Better distribution of the flushing content and flushing quality for FCC consumer units of the flushing system; 4. Quantifies the marginal value of flushing generated in the FCCs units that produce flushing; 5. Defines the best virgin catalyst budget and predicts the logistical costs of transporting flushing between the FCC units producing flushing and consuming flushing, considering all viable routes.

A variable refrigerant flow (VRF) system for a building includes an outdoor VRF unit, a plurality of indoor VRF units, a battery, and a predictive VRF controller. The outdoor VRF unit includes powered VRF components configured to apply heating or cooling to a refrigerant. The indoor VRF units are configured to use the heated or cooled refrigerant to provide heating or cooling to a plurality of building zones. The battery is configured to store electric energy and discharge the stored electric energy for use in powering the powered VRF components. The predictive VRF controller is configured to optimize a predictive cost function to determine an optimal amount of electric energy to purchase from an energy grid and an optimal amount of electric energy to store in the battery or discharge from the battery for use in powering the powered VRF components at each time step of an optimization period.

The invention discloses a MIMO different-factor full-form model-free control method with parameter self-tuning. In view of the limitations of the existing MIMO full-form model-free control method with the same-factor structure, namely, at time k, different control inputs in the control input vector can only use the same values of penalty factor and step-size factors, the invention proposes a MIMO full-form model-free control method with the different-factor structure, namely, at time k, different control inputs in the control input vector can use different values of penalty factors and/or step-size factors, which can solve control problems of strongly nonlinear MIMO systems with different characteristics between control channels widely existing in complex plants. Meanwhile, parameter self-tuning is proposed to effectively address the problem of time-consuming and cost-consuming when tuning the penalty factors and/or step-size factors. Compared with the existing method, the inventive method has higher control accuracy, stronger stability and wider applicability.

A control system includes an electric heater disposed within an exhaust fluid flow pathway, and a control device for receiving at least one input selected from the group consisting of temperature readings along the exhaust fluid flow pathway, alternator power/current/voltage, battery power/current/voltage/state of charge, IAT and EAT profiles, mass flow rate of an exhaust fluid flow, NH.sub.3 slip, TCR characteristics of the heater, alternator speed, engine speed, state of aging of an aftertreatment component, state of aging of engine, aging degradation characteristics, a dosing rate and a temperature of DEF, NH.sub.3 storage condition of aftertreatment system, an ambient temperature, and combinations thereof. The control device modulates power to the heater based on the at least one input such that the heater provides different power output as a function of the at least one input and a continuously variable power output during operation of the exhaust system.

The invention relates to a method for generating a control system for a target system, wherein: operational data is received; a first neural model component is trained with the received operational data for generating a prediction on a state of the target system based on the received operational data; a second neural model component is trained with the operational data for generating a regularizer for use in inverting the first neural model component; and the control system is generated by inverting the first neural model component by optimization and arranging to apply the regularizer generated with the second neural model component in the optimization. The invention relates also to a system and a computer program product.