The present invention relates to a substrate cleaning apparatus, a polishing apparatus, a buffing apparatus, a substrate processing apparatus, a machine learning apparatus used for any of these apparatuses, and a substrate cleaning method, which are improved in terms of both performance and throughput. The substrate cleaning apparatus (16) includes: a cleaning tool (77) configured to clean a substrate (W) held by a substrate holder (71, 72, 73, 74); a surface-property measuring device configured to obtain surface data of the cleaning tool (77); and a controller (30) configured to determine a replacement time of the cleaning tool (77) based on the surface data. The surface-property measuring device is configured to obtain surface data of the cleaning tool (77) at at least two measurement points (PA, PB) of the cleaning tool (77) each time a predetermined number of substrates (W) are scrubbed, and the controller (30) is configured to determine the replacement time of the cleaning tool (77) based on a difference in the surface data obtained.

A method for producing a well includes receiving production information associated with wells within a field; deriving a field specific model from the production information; receiving production information associated with the well; projecting production changes associated with installing artificial lift at the well at a projected date, the projecting using a production analysis engine applied to the field specific model, the projecting including determining a set of artificial lift parameters; and installing the artificial lift at the well in accordance with the artificial lift parameters.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, that control devices in an aquaculture environment. One of the methods includes determining a particular objective for a robot that is operating in an aquaculture environment and determining one or more sensed conditions that are associated with the aquaculture environment. The particular objective is provided to an anti-fish-startling model evaluation engine that is configured to output actions, for a given objective, that accomplish the given objective while reducing a startling effect on nearby fish. Based on providing the particular objective to the anti-fish-startling model evaluation engine, one or more particular actions for accomplishing the particular objective are determined. The one or more particular actions are transmitted to another device.

A method includes determining motion imitation information for causing a system to imitate a physical task using a first machine learning model that is trained using motion information that represents a performance of the physical task, determining a predicted correction based on the motion information and a current state from the system using a second machine learning model that is trained using the motion information, determining an action to be performed by the system based on the motion imitation information and the predicted correction; and controlling motion of the system in accordance with the action.

A device is configured to operate a Heating, Ventilation, and Air Conditioning (HVAC) system. The device is further configured to determine that the speed of a combustion air inducer exceeds a speed threshold value. The device is further configured to receive an audio signal from a microphone while operating the HVAC system and to determine an audio signature for the combustion air inducer is not present within the audio signal. The device is further configured to determine whether an audio signature for the integrated furnace controller is present within the audio signal. The device is further configured to determine a fault type based on the determination of whether the audio signature for the integrated furnace controller is present within the audio signal, to identify a component identifier for a component of the HVAC system that is associated with fault type, and to output a recommendation identifying the component identifier.

A device is configured to operate a Heating, Ventilation, and Air Conditioning (HVAC) system. The device is further configured to determine that the amount of time to close a pressure switch exceeds a time threshold value. The device is further configured to receive an audio signal from a microphone while operating the HVAC system, to identify an audio signature for the combustion air inducer, and to determine the audio signature for the combustion air inducer is present within the audio signal. The device is further configured to determine a fault type based on the determination that the audio signature for the combustion air inducer is present within the audio signal, to identify a component identifier for a component of the HVAC system that is associated with fault type, and to output a recommendation identifying the component identifier.

Cracks in foundations may be detected by sensing motion within the foundation. Sensors may be applied to a foundation, and the positions of the sensors may be read. At subsequent points in time the positions of the sensors may be read again. If the positions of the sensors are changing in a way that suggests that portions of the foundation are moving apart from each other, then it may be inferred that a crack is forming in the foundation. The formation of cracks may be used to take various actions. For example, the owner of the building that rests on the foundation may be information of the crack so that he or she may take remedial action.

Methods and systems described herein concern machine-learning-assisted materials discovery. One embodiment selects a candidate sample set including a plurality of compositions and performs the following operations iteratively: (1) selects an acquisition sample set, (2) performs a dark electrocatalyst experiment or a photo-electrocatalyst experiment on the compositions in the acquisition sample set to determine one or more properties, (3) trains a machine learning model using the one or more properties, and (4) predicts, based at least in part on one or more outputs of the machine learning model, the one or more properties for one or more compositions in a test sample set including compositions on which an experiment has not yet been performed. When one or more predetermined termination criteria have been satisfied, the embodiment also identifies one or more compositions in the candidate sample set for which the one or more properties satisfy predetermined performance criteria.

Systems for self-organizing data collection and storage in a refining environment are disclosed. An example system may include a swarm of mobile data collectors structured to interpret a plurality of sensor inputs from sensors in the refining environment, wherein the plurality of sensor inputs is configured to sense at least one of: an operational mode, a fault mode, a maintenance mode, or a health status of a plurality of refining system components disposed in the refining environment, and wherein the plurality of refining system components is structured to contribute, in part, to refining of a product. The self-organizing system organizes a swarm of mobile data collectors to collect data from the system components, and at least one of a storage operation of the data, a data collection operation of the sensors, or a selection operation of the plurality of sensor inputs.

Methods and systems for sensor fusion in a production line environment are disclosed. An example system for data collection in an industrial production environment may include an industrial production system comprising a plurality of components, and a plurality of sensors each operatively coupled to at least one of the components; a sensor communication circuit to interpret a plurality of sensor data values in response to a sensed parameter group; and a data analysis circuit to detect an operating condition of the industrial production system based at least in part on a portion of the sensor data values; and a response circuit to modify a production related operating parameter of the industrial production system in response to the detected operating condition.