G05B13/00

Neural network, computer readable medium, and methods including a method for training a neural network
11263528 · 2022-03-01 ·

The present disclosure provides an artificial neural network communicatively-coupled to at least one computer having one or more processors, including a plurality of neurons arranged in layers. The artificial neural network is arranged to receive a new neuron into a layer of the artificial neural network during training; the new neuron is added to the neural network when no other neuron in that layer for a selected output can learn a relationship associated with an input vector of a data set being learnt. The new neuron is updated with both the relationship which could not be learnt by any other neuron in that layer and a modified data set from a last trained neuron in that layer that contributes to the selected output of the neural network. Methods and computer-readable media are also disclosed.

Mobile energy management system

A system includes a network device installed at a site, the network device including an operating condition configured to be altered by an input initiated external to the site. The system also includes at least one multi-user configurable geographical boundary capable of being established about the site to alter the operating condition in response to a location based information of a user relative to the site and the geographical boundary. A method of managing a site includes detecting a network device installed at a site, the network device having an operating condition configured to be altered by an input initiated external to the site. The method also includes enabling configuration of at least one multi-user configurable geographical boundary capable of being established about the site to alter the operating condition in response to a location based information of a user relative to the site and the geographical boundary.

Laundry machine and online system including the same
09800430 · 2017-10-24 · ·

The present invention relates to a home appliance which can communicate with an outside of the home appliance and an online system including the same. According to embodiments of the present invention, an online system may be provided, including a server, a home appliance provided with remote control activation input means and connected to the server to enable communication therewith, and an external terminal having application for remote control of the home appliance through the server, wherein the home appliance is remotely controlled through the external terminal only if the remote control activation input means is selected.

Data center with air flow control
09801312 · 2017-10-24 · ·

A data center that houses an electronic device, the data center includes a plurality of air-current-supply-sections that supply an air current to the electronic device, a plurality of shields that are provided for the air-current-supply-sections to shield corresponding air-current-supply-sections, and a control section that acquires status information indicative of a status of the electronic device from the electronic device, controls a flow rate of the air current supplied from each of the air-current-supply-sections in accordance with the acquired status information, checks the air-current-supply-sections to locate an air-current-supply-section whose air current flow rate is not higher than a predetermined value, checks the shields to locate a shield corresponding to the air-current-supply-section whose air current flow rate is not higher than the predetermined value, and causes the located shield to shield the located air-current-supply-section.

Building management system with linked thermodynamic models for HVAC equipment

A building management system (BMS) includes one or more sensors that measure a variable state or condition in the BMS and a plurality of BMS devices that operate to affect the variable state or condition measured by the one or more sensors. Each of the BMS devices stores a thermodynamic block that models the BMS device. Each of the thermodynamic blocks includes a list of connections and a list of stats. The connections define one or more inputs to the thermodynamic block and one or more outputs from the thermodynamic block. The stats define one or more relationships between the inputs and the outputs. Each of the BMS devices includes a solver configured to perform calculations using the stats and connections defined by the thermodynamic block stored within the BMS device.

Plasma processing method

Method for carrying out plasma processing on a wafer under Run-to-Run control by using a plasma processing apparatus having a plasma processing chamber, a process monitor which monitors a condition in the plasma processing chamber, and an actuator which controls parameters which are constituent elements of a plasma processing condition. The method includes the steps of making one of the parameters a (N−1)th manipulated variable, calculating a first difference between a process monitor value in the plasma processing obtained by the process monitor and a desired value of the process monitor value in the plasma processing, calculating a correction amount of the (N−1)th manipulated variable on the basis of the first difference and a previously obtained correlation between the process monitor value in the plasma processing and the (N−1)th manipulated variable, wherein N is a natural number equal to or larger than 2.

Plasma processing method

Method for carrying out plasma processing on a wafer under Run-to-Run control by using a plasma processing apparatus having a plasma processing chamber, a process monitor which monitors a condition in the plasma processing chamber, and an actuator which controls parameters which are constituent elements of a plasma processing condition. The method includes the steps of making one of the parameters a (N−1)th manipulated variable, calculating a first difference between a process monitor value in the plasma processing obtained by the process monitor and a desired value of the process monitor value in the plasma processing, calculating a correction amount of the (N−1)th manipulated variable on the basis of the first difference and a previously obtained correlation between the process monitor value in the plasma processing and the (N−1)th manipulated variable, wherein N is a natural number equal to or larger than 2.

Systems and methods for managing smart alarms

A method of analyzing events for an electrical system includes: receiving event stream(s) of events occurring in the electrical system, the events being identified from captured energy-related signals in the system; analyzing, an event stream(s) of the events to identify different actionable triggers therefrom, the different triggers including a scenario in which a group of events satisfies one or more predetermined triggering conditions; analyzing, over time, the different actionable triggers to identify a combination of occurring and/or non-occurring actionable triggers which satisfies a predefined trigger combination condition and an analysis time constraint; and in response to the observation of the combination, taking one or more actions to address the events. The analysis time constraint can be a time period duration and/or sequence within which time-stamped data of events in the event stream(s) and the associated actionable triggers are considered or not considered in the analysis to identify the combination.

Systems and methods for managing smart alarms

A method of analyzing events for an electrical system includes: receiving event stream(s) of events occurring in the electrical system, the events being identified from captured energy-related signals in the system; analyzing, an event stream(s) of the events to identify different actionable triggers therefrom, the different triggers including a scenario in which a group of events satisfies one or more predetermined triggering conditions; analyzing, over time, the different actionable triggers to identify a combination of occurring and/or non-occurring actionable triggers which satisfies a predefined trigger combination condition and an analysis time constraint; and in response to the observation of the combination, taking one or more actions to address the events. The analysis time constraint can be a time period duration and/or sequence within which time-stamped data of events in the event stream(s) and the associated actionable triggers are considered or not considered in the analysis to identify the combination.

Irrigation system with ET based seasonal watering adjustment and soil moisture sensor shutoff

An irrigation system includes at least one environmental sensor, such as a solar radiation sensor that is installed on an irrigation site, and a soil moisture sensor that is also installed on the irrigation site. Programming allows an estimated ET value to be calculated based at least in part on the output signal of the environmental sensor. A pre-programmed watering schedule is automatically modified based on the estimated ET value to thereby conserve water while maintaining the health of plants on the irrigation site. The system automatically inhibits irrigation when an output signal of the soil moisture sensor indicates an amount of moisture in the soil is above a predetermined threshold.