Processes and systems for controlling operation of a commercial refinery distillation column and/or splitter operable to separate hydrocarbons. An automated process controller (APC) receives signal from at least one analyzer that provides information about the concentration of at least a first chemical in a first fraction and a second chemical in a second fraction obtained from the distillation column. The APC comprises programming in the form of an algorithm that calculates real-time monetary values for the first chemical and the second chemical and alters the operation of the distillation column to change either the percentage of the first chemical in the second fraction or the percentage of the second chemical in the first fraction, thereby maximizing overall operational profit for the distillation column.

A heating, ventilation, and air conditioning (HVAC) control device is configured to record a plurality of actual occupancy statuses, to determine a plurality of corresponding predicted occupancy statuses, and to compare the plurality of predicted occupancy statuses to the plurality of actual occupancy statuses. The device is further configured to identify conflicting occupancy statuses based on the comparison. A conflicting occupancy status indicates a difference between an actual occupancy status and a corresponding predicted occupancy status. The device is further configured to identify timestamps corresponding with the conflicting occupancy statuses, to identify historical occupancy statuses corresponding with the identified timestamps, and to update the conflicting occupancy statuses in the predicted occupancy schedule with the historical occupancy statuses.

A system and method for real world autonomous vehicle trajectory simulation may include: receiving training data from a data collection system; obtaining ground truth data corresponding to the training data; performing a training phase to train a plurality of trajectory prediction models; and performing a simulation or operational phase to generate a vicinal scenario for each simulated vehicle in an iteration of a simulation. Vicinal scenarios may correspond to different locations, traffic patterns, or environmental conditions being simulated. Vehicle intention data corresponding to a data representation of various types of simulated vehicle or driver intentions.

A method and computing device for inferring an airflow of a controlled appliance operating in an area of a building. The computing device stores a predictive model. The computing device determines a measured airflow of the controlled appliance and a plurality of consecutive temperature measurements in the area. The computing device executes a neural network inference engine using the predictive model for inferring an inferred airflow based on inputs. The inputs comprise the measured airflow and the plurality of consecutive temperature measurements. The inputs may further include at least one of a plurality of consecutive humidity level measurements in the area and a plurality of consecutive carbon dioxide (CO2) level measurements in the area. For instance, the controlled appliance is a Variable Air Volume (VAV) appliance and a K factor of the VAV appliance is calculated based on the inferred airflow.

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 first in-situ sensor detects a characteristic value as a mobile machine operates at a worksite. A second in-situ sensor detects a material dynamics characteristic value as the mobile machine operates at the worksite. A predictive model generator generates a predictive model that models a relationship between the characteristic and the materials dynamics characteristic based on the characteristic value detected by the first in-situ sensor and the material dynamics characteristic value detected by the second in-situ sensor. The predictive model can be output and used in automated machine control.

The present technology addresses the problem of quickly and safely improving policies in online reinforcement learning domains. As its solution, an exploration strategy comprising diverse exploration (DE) is employed, which learns and deploys a diverse set of safe policies to explore the environment. DE theory explains why diversity in behavior policies enables effective exploration without sacrificing exploitation. An empirical study shows that an online policy improvement algorithm framework implementing the DE strategy can achieve both fast policy improvement and safe online performance.

A process and system for efficiently producing reference data that can be fed into a predictive model for predicting quality attribute concentrations in cell culture processes. A perfusion bioreactor is operated at pseudo-steady-state conditions and one or more attribute influencing parameters are manipulated and changed over time. As the one or more attribute influencing parameters are manipulated, one or more quality attributes are monitored and measured. In one embodiment, multiple quality attributes are monitored and measured in parallel. The quality attribute information is recorded in conjunction with the changes in the attribute influencing parameters. This information is then fed to the predictive model for propagating cell cultures in commercial processes and maintaining the cell cultures within desired preset limits.

A disclosed example includes: a resource utilization analyzer to determine 1) first workloads of a first workload type deployed in a first server room in a data center, and 2) second workloads of a second workload type deployed in the first server room; a workload authorizer to determine that first virtual machines executing the first workloads and second virtual machines executing the second workloads cause a first server rack to generate an amount of heat; and a migrator to migrate the first virtual machines from the first server rack of the first server room to a second server rack of a second server room in the data center to reduce a temperature in the first server room based on the amount of heat, the migrator to migrate the first virtual machines to the second server rack without migrating the second virtual machines to the second server rack.

A training method of a semiconductor process prediction model, a semiconductor process prediction device, and a semiconductor process prediction method are provided. The training method of the semiconductor process prediction model includes the following steps. The semiconductor process was performed on several samples. A plurality of process data of the samples are obtained. A plurality of electrical measurement data of the samples are obtained. Some of the samples having physical defects are filtered out according to the process data. The semiconductor process prediction model is trained according to the process data and the electrical measurement data of the filtered samples.