A system for analyzing operational data associated with a plant that has processing equipment configured and controlled to run a process involving at least one tangible material. Actual operational data corresponding to plant operations is received by a computing device that may relate to production, equipment, workforce, automation systems, safety, and/or cybersecurity of the plant. A model of the plant is generated based on the actual operational data, where the model indicates ideal plant operations including model operational data. The actual plant operational data and the model operational data are compared. Based on the operational data and the comparison of the operational data to model operational data, at least one recommendation for an action associated with the plant is determined.

Device and method using a neural network to detect and compensate an air vacuum effect. The device stores a predictive model comprising weights of a neural network. The device receives an area temperature measurement (representative of a temperature of an area where the device is located) from a temperature sensing module of the device. The device determines at least one other measurement related to the device. The device executes a neural network inference engine implementing a neural network, using the predictive model for inferring output(s) based on inputs. The inputs comprise the area temperature measurement and the at least one other measurement related to the device. The output(s) comprises a metric representative of an air vacuum effect in the device. The device determines if an adjustment of the area temperature measurement needs to be performed based on the metric representative of the air vacuum effect in the device.

A nonlinear dynamic control system is defined by a set of equations that include a state vector and one or more control inputs. Via a machine learning method, a sub-optimal controller is derived that stabilizes the nonlinear dynamic control system at an equilibrium point. The sub-optimal controller is retrained to be used as a stabilizing controller for the nonlinear dynamic control system under general operating conditions.

Embodiments provide techniques for datacenter power management using variable power sources. Power from the variable power sources is stored in a power cache. An optimization engine receives input criteria such as power availability from non-variable and variable power sources, as well as one or more power management goals. The optimization engine implements a dispatch strategy that dispatches stored energy from the power cache and feeds it to the datacenter, resulting in a mixture of non-variable and variable power sources used to achieve the power management goals, such as reduced power cost, increased power availability, and lowered carbon footprint for the datacenter.

The subject matter herein provides for AI-based prediction of production defects in association with a production system, such as a semiconductor manufacturing machine. In one embodiment, a method begins by receiving production data from the production system. The production data typically comprises non-homogeneous machine parameters and maintenance data, quality test data, and product and process data. Using the production data, a neural network is trained to model an operation of a given machine in the production system. Preferably, the training involves multi-task learning, transfer learning (e.g., using knowledge obtained with respect to a machine of the same type as the given machine), and a combination of multi-task learning and transfer learning. Once the model is trained, it is associated with the given machine operating environment, wherein it is used to provide quality assurance predictions.

The invention provides a method for controlling a wind turbine. The method predicts behaviour of the wind turbine components for the time stages over a prediction horizon using a wind turbine model describing dynamics of the wind turbine, where the time stages include a first set of time stages from an initial time stage and a second set of time stages subsequent to the first set. The method determines control outputs, e.g. individual blade pitch, for time stages based on the predicted behaviour. The method then transmits a control signal to implement only the control outputs for each of the second set of time stages so as to control the wind turbine. Advantageously, the invention reduces both average and peak computational loads relative to standard predictive control algorithms.

A method for reducing and/or managing energy-related stress in an electrical system includes processing electrical measurement data from or derived from energy-related signals captured by at least one intelligent electronic device (IED) in the electrical system to identify and track at least one energy-related transient in the electrical system. An impact of the at least one energy-related transient on equipment in the electrical system is quantified, and one or more transient-related alarms are generated in response to the impact of the at least one energy-related transient being near, within or above a predetermined range of the stress tolerance of the equipment. The transient-related alarms are prioritized based in part on at least one of the stress tolerance of the equipment, the stress associated with one or more transient events, and accumulated energy-related stress on the equipment. One or more actions are taken in the electrical system in response to the transient-related alarms to reduce energy-related stress on the equipment in the electrical system.

An embodiment includes duplicating an input dataset being input to a model predictive control (MPC) module for input to a first Hierarchical Temporal Memory (HTM) network. The embodiment also includes generating system behavior data using the MPC module for characteristic data of the input dataset. The embodiment also includes generating first HTM prediction data from the input dataset and the system behavior data using the first HTM network, the first HTM prediction data comprising predictions for respective dimensions of the system. The embodiment also includes generating second HTM prediction data from the first HTM prediction data and system output data using a second HTM network, the second HTM prediction data comprising a distinction between the first HTM prediction and the system output data. Finally, the embodiment includes determining that the distinction of the second HTM prediction data indicates an anomaly and adjusting system input data based on the anomaly.

A post-harvest crop management platform is provided for regulating conditions of an agricultural crop being dried and/or stored. The platform utilizes data collected from sensors positioned proximate to, or embedded within, an agricultural crop, and analyzes selected crop characteristics affecting the stored crop in multiple sections thereof. The platform identifies parameters relative to achieving a desired crop characteristic level in the agricultural crop, generates a profile of the selected crop characteristic across the multiple sections of the stored crop, and models an application of a fluid flow pattern to achieve the desired crop characteristic level in each section. The crop storage monitoring and management platform also actuates a multi-stack assembly, configured within the stored crop, to automatically apply the fluid flow pattern in one or more cycles that are adjustable to changing conditions within the stored crop in real time. The crop storage monitoring and management platform further integrates with, and connects to and communicates with, other systems within an autonomous field activity ecosystem.

Embodiments of systems and methods for delivering a medicament using a pump are provided. The methods comprise inserting a first cannula into subcutaneous tissue. Medicament is delivered from a medicament pump through the first cannula according to a dosing protocol. The first cannula can removed after a period of time and a second cannula can be inserted. The method comprises modifying the dosing protocol based upon a cannula change indicator, the modifying comprising performing neural network calculations utilizing previously calculated error data, resulting in a modified dosing protocol. Medicament is delivered from the medicament pump through the second cannula according to the modified dosing protocol.