Abstract: Systems, methods, and computer-readable medium storing instructions for using a machine learning to predict dwell times for shipments along routes are described herein. The method, system, or instructions may include training the machine learning model using training data, storing the machine learning model in a memory, accessing route data of a shipment of interest, analyzing the route data using the machine learning model, and, based on the analyzing of the route data, outputting a predicted dwell time at a stop of the shipment of interest.

Abstract: Systems and methods for using machine learning to dynamically determine shipping information are disclosed. According to certain aspects, an electronic device may receive location data for a set of vehicles that may be associated with a shipping agreement, wherein the electronic device may input the location data and shipping agreement parameters into a machine learning model which outputs a set of likelihoods of the respective set of vehicles actually transporting products associated with the shipping agreement. The electronic device may enable a customer computing device to access this information along with any determined updates to the shipping agreement.

Abstract: In examples, a computing system is configured to detect rotor imbalance at wind turbines by (1) obtaining sets of historical-vibration data for turbines, each set comprising vibration data captured by a given turbine's multi-dimensional sensor, (2) deriving a rotor-imbalance-detection model by: (a) for each turbine, (i) transforming time segments of the turbine's historical-vibration dataset into a frequency-domain representation, and (ii) for each time segment, using the frequency-domain representation for the time segment to derive a set of harmonic-mode values for at least one frequency-range of interest, thereby deriving a time-series set of harmonic-mode values for the turbine, and (b) performing an evaluation of the time-series sets for the turbines, thereby deriving the rotor-imbalance-detection model, (3) based on received vibration data for a given turbine from a reference time, executing the derived model, thereby detecting a rotor imbalance at the given turbine, and (4) transmitting a notification

Abstract: In examples, a computing system is configured to detect rotor imbalance at wind turbines by (1) obtaining sets of historical-vibration data for turbines, each set comprising vibration data captured by a given turbine's multi-dimensional sensor, (2) deriving a rotor-imbalance-detection model by: (a) for each turbine, (i) transforming time segments of the turbine's historical-vibration dataset into a frequency-domain representation, and (ii) for each time segment, using the frequency-domain representation for the time segment to derive a set of harmonic-mode values for at least one frequency-range of interest, thereby deriving a time-series set of harmonic-mode values for the turbine, and (b) performing an evaluation of the time-series sets for the turbines, thereby deriving the rotor-imbalance-detection model, (3) based on received vibration data for a given turbine from a reference time, executing the derived model, thereby detecting a rotor imbalance at the given turbine, and (4) transmitting a notification