Example embodiments allow for networks of hybrid controllers that can be computed efficiently and that can adapt to changes in the system(s) under control. Such a network includes at least one hybrid controller that includes a dynamic sub-controller and a learned system sub-controller. Information about the ongoing performance of the system under control is provided to both the hybrid controller and to an over-controller, which provides one or more control inputs to the hybrid controller in order to modify the ongoing operation of the hybrid controller. These inputs can include the set-point of the hybrid controller, one or more parameters of the dynamic controller, and an update rate or other parameter of the learned system controller. The over-controller can control multiple hybrid controllers (e.g., controlling respective sub-systems of an overall system) and can, itself, be a hybrid controller.

Techniques for predicting an amount of at least one biomaterial produced or consumed by a biological system in a bioreactor are provided. Process conditions and metabolite concentrations are measured for the biological system as a function of time. Metabolic rates for the biological system, including specific consumption rates of metabolites and specific production rates of metabolites are determined. The process conditions and the metabolic rates are provided to a hybrid system model configured to predict production of the biomaterial. The hybrid system model includes a kinetic growth model configured to estimate cell growth as a function of time and a metabolic condition model based on metabolite specific consumption or secretion rates and select process conditions, wherein the metabolic condition model is configured to classify the biological system into a metabolic state. An amount of the biomaterial based on the hybrid system model is predicted.

Disclosed is a process for creating an event prediction model that employs a data-driven approach for selecting the model's input data variables, which, in one embodiment, involves selecting initial data variables, obtaining a respective set of historical data values for each respective initial data variable, determining a respective difference metric that indicates the extent to which each initial data variable tends to be predictive of an event occurrence, filtering the initial data variables, applying one or more transformations to at least two initial data variables, obtaining a respective set of historical data values for each respective transformed data variable, determining a respective difference metric that indicates the extent to which each transformed data variable tends to be predictive of an event occurrence, filtering the transformed data variables, and using the filtered, transformed data variables as a basis for selecting the input variables of the event prediction model.

An HVAC system includes a compressor, condenser, and evaporator. A sensor measures a value associated with the refrigerant in the condenser or the evaporator, and a controller is communicatively coupled to the compressor and the sensor. The controller determines, based on an operational history the compressor, that pre-requisite criteria are satisfied for entering a sensor validation mode. After determining the pre-requisite criteria are satisfied, an initial sensor measurement value is determined. Following determining the initial sensor measurement value, the compressor is operated according to a sensor-validation mode. Following operating the compressor according to the sensor-validation mode for at least a minimum time, a current sensor measurement value is determined. The controller determines whether validation criteria are satisfied for the current sensor value. In response to determining that the validation criteria are satisfied, the controller determines that the sensor is validated.

A system comprising one or more memory devices having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to perform operations comprising receiving a request for a rating for a device of building equipment, the request for the rating including a plurality of attributes characterizing the device of building equipment including at least a first device characteristic, selecting, from a plurality of rating engines, a first rating engine for use in generating the rating based on the plurality of attributes characterizing the device of building equipment, communicating the first device characteristic to the first rating engine, receiving a first rating for the device of building equipment from the first rating engine, and using the first rating to at least one of generate a predictive model for the device of building equipment or control the device of building equipment.

Systems and methods for device monitoring. The method may include obtaining first measurement data relating to one or more first operating parameters of a target device, obtaining a correlation model corresponding to the target device, and predicting, based on the first measurement data and the correlation model, second measurement data relating to the one or more second operating parameters of the target device. The correlation model may be generated based on first sample measurement data relating to the one or more first operating parameters and one or more second operating parameters of a reference device. The reference device may be of a same type of device as the target device and equipped with one or more additional sensors compared with the target device, the one or more additional sensors being configured for collecting the first sample measurement data relating to the one or more second operating parameters.

System and method for improving operation of an industrial automation system, which includes a control system that controls operation of an industrial automation process. The control system includes a feature extraction block that determines extracted features by transforming process data determined during operation of an industrial automation process based at least in part on feature extraction parameters; a feature selection block that determines selected features by selecting a subset of the extracted features based at least in part on feature selection parameters, in which the selected features are expected to be representative of the operation of the industrial automation process; and a clustering block that determines a first expected operational state of the industrial automation system by mapping the selected features into a feature space based at least in part on feature selection parameters.

A chiller threshold management system for a building, including one or more memory devices and one or more processors. The one or more memory devices are configured to store instructions to be executed on the one or more processors. The one or more processors are configured to determine whether chiller fault data exists in chiller data used to generate a plurality of chiller prediction models. The one or more processors are further configured to generate a first threshold evaluation value for each of the plurality of chiller prediction models using a first evaluation technique in response to a determination that chiller fault data exists in the chiller data, and generate a second threshold evaluation value for each of the chiller prediction models using a second evaluation technique in response to a determination that chiller fault data does not exist in the chiller data. The one or more processors are configured to select a first threshold for each of the plurality of chiller prediction models based on the first threshold evaluation values in response to the determination that chiller fault data exists in the chiller data, and select a second threshold for each of the plurality of chiller prediction models based on the second threshold evaluation values in response to the determination that chiller fault data does not exist in the chiller data.

A method of generating a controller for a continuous process. The method includes receiving from a storage memory off-line stored values of one or more controlled variables and one or more manipulated variables of the continuous process over a plurality of time points. The off-line stored values are used to train a first neural network to operate as a predictor of the controlled variables. Then, the method includes training a second neural network to operate as a controller of the continuous process using the first neural network after it was trained to operate as the predictor for the continuous process and employing the second neural network as a controller of the continuous process.

Embodiments are directed towards controlling uncontrolled release of ammonia from an engine of a vehicle. An estimated status of the engine is determined prior to an event, such as an estimated load on the engine prior to the vehicle going up a hill. A predictive model of uncontrolled ammonia release is generated for the estimated status. At least one engine-related countermeasure is selected based on the predictive model. If the predictive model of uncontrolled ammonia release with the selected countermeasures satisfies a threshold condition, then the selected engine-related countermeasure is employed.