Abstract: A method of acoustic echo suppression using a recurrent neural network, performed by at least one processor, is provided. The method includes receiving a microphone signal and a far-end reference signal, estimating an echo suppressed signal and an echo signal based on the microphone signal and the far-end reference signal, estimating enhancement filters for the microphone signal based on the echo suppressed signal and the echo signal, generating an enhanced signal based on the enhancement filters, and adjusting the enhanced signal using automatic gain control (AGC) and outputting the adjusted signal.

Abstract: A semiconductor structure includes a substrate and a word line (WL) structure. The WL structure includes: a work function stacking structure located in the substrate, where the work function stacking structure includes multiple sequentially and alternately stacked first work function layers and second work function layers, and a work function of the first work function layer is greater than a work function of the second work function layer; a WL conductive layer located in the substrate, and located on an upper surface of the work function stacking structure; and a gate oxide layer located between the work function stacking structure and the substrate as well as between the WL conductive layer and the substrate.

Abstract: Systems and methods for generating a load model having composite load components for electric power systems are disclosed which include acquiring state information at a bus of the electric power system, acquiring a training event record, and generating the load model by sequentially executing steps of determining a final load component composition for a predetermined composite load model structure referencing to both the state information and the training event record, and determining a plurality of final load parameters corresponding to the final load component composition and the predetermined load model structure also referencing to both the state information and the training event record.

Abstract: A displaying base plate includes an opening region, an adjacent region surrounding the opening region, and a displaying region surrounding the adjacent region, and the displaying base plate located within the adjacent region includes: a substrate base plate; a flat layer and a passivation layer that are provided on one side of the substrate base plate, wherein the passivation layer is provided on one side of the flat layer that is further away from the substrate base plate, a surface of the one side of the flat layer that is further away from the substrate base plate includes at least an inclined plane adjacent to one side of the opening region, and the flat layer includes a first protrusion provided on the inclined plane; and a first isolating groove that at least partially overlaps with the first protrusion and extends throughout the passivation layer and extends into the first protrusion.

Abstract: Systems and methods for processing measurement data in an electric power system include acquiring the measurement data by a phasor measurement unit (PMU) coupled to a line of the electric power system, and inputting a plurality of the measurement data within a predetermined time window into a K-nearest neighbor (KNN) for identifying bad data among the plurality of the measurement data, wherein when one of the plurality of measurement data contains a bad datum, the machine learning module sends the bad datum to a denoising autoencoder module for correcting the bad datum, wherein the denoising autoencoder module outputs a corrected part corresponding to the bad datum, and when one of the plurality of measurement data contains no bad datum, the machine learning module bypasses the denoising autoencoder module and outputs the one of the plurality of measurement data as an untouched part.

Abstract: A displaying base plate includes an opening region, an adjacent region surrounding the opening region, and a displaying region surrounding the adjacent region, and the displaying base plate located within the adjacent region includes: a substrate base plate; a flat layer and a passivation layer that are provided on one side of the substrate base plate, wherein the passivation layer is provided on one side of the flat layer that is further away from the substrate base plate, a surface of the one side of the flat layer that is further away from the substrate base plate includes at least an inclined plane adjacent to one side of the opening region, and the flat layer includes a first protrusion provided on the inclined plane; and a first isolating groove that at least partially overlaps with the first protrusion and extends throughout the passivation layer and extends into the first protrusion.

Abstract: Systems and methods are disclosed for control voltage profiles, line flows and transmission losses of a power grid by forming an autonomous multi-objective control model with one or more neural networks as a Deep Reinforcement Learning (DRL) agent; training the DRL agent to provide data-driven, real-time and autonomous grid control strategies; and coordinating and optimizing power controllers to regulate voltage profiles, line flows and transmission losses in the power grid with a Markov decision process (MDP) operating with reinforcement learning to control problems in dynamic and stochastic environments.

Abstract: State estimation in an electric power system includes acquiring electrical measurements from the electric power system at a reporting rate of the electrical measurements, processing the electrical measurements into sequence data including positive sequence data, processing positive sequence data by an observable state estimator to generate a plurality of estimated states including a plurality of estimated observable states, parameters of the observable state estimator being updated by a first training module in a first time thread, processing the plurality of estimated states by an unobservable state estimator to generate a plurality of estimated unobservable states, parameters of the unobservable state estimator being updated by a second training module in a second time thread independent of the first time thread, and outputting a plurality of final estimated states generated by concatenating the plurality of estimated observable states and the plurality of estimated unobservable states.

Abstract: A method is disclosed for identification of the mechanism of power system low-frequency oscillations and distinguish natural oscillations and forced oscillations using machine learning or neural network.

Abstract: Systems and methods manage electrical loads in a grid by applying Robust principal component analysis (R-PCA) to decompose annual load profiles into low-rank components and sparse components; extracting one or more predetermined features; constructing a similarity graph; selecting submodular cluster centers through the constructed similarity graph; determining a cluster assignment based on selected centers; and applying the clustering assignment for load analysis.

Abstract: Systems and methods are disclosed for control voltage profiles, line flows and transmission losses of a power grid by forming an autonomous multi-objective control model with one or more neural networks as a Deep Reinforcement Learning (DRL) agent; training the DRL agent to provide data-driven, real-time and autonomous grid control strategies; and coordinating and optimizing power controllers to regulate voltage profiles, line flows and transmission losses in the power grid with a Markov decision process (MDP) operating with reinforcement learning to control problems in dynamic and stochastic environments.

Abstract: Systems and methods are disclosed for power management by estimating power contingency of a grid at a cloud control center; performing decentralized real-time measurement and making local decisions at one more computer controlled outlets connected to the grid; and aggregating distributed loads to provide emergency frequency support to the grid.

Abstract: The present disclosure provides a method for performing clustering on operation modes of a power system based on a sparse autoencoder. The method includes: obtaining related data of the power system; setting a training parameter, a number of hidden layers, and a number of neurons; training an autoencoder model using the related data and extracting a topological structure and a weight matrix from the model; performing cluster analysis to obtain a number of typical scenarios; and performing decoding to obtain original data at centers of respective scenarios. The present disclosure can achieve fast selection and dimensionality reduction of feature vectors representing operation modes of a power system. In view of this, the present disclosure provides a novel idea and method for selecting a feature vector representing an operation mode of a power system and generating a typical operation scenario.

Abstract: Systems and methods are disclosed to control the power grid frequency by capturing the frequency change using an extended Kalman filter method with the distributed smart outlet devices at the low-voltage distribution level; and locally control the relay that provides power to the appliance by comparing the captured frequency with the threshold sent from the cloud control center.

Abstract: A heating/heat-retaining device, particularly to a heating/heat-retaining device used in the forging process, and more particularly to an opening-and-closing type heater and a wind generator shaft forging process using the same. The opening-and-closing type heater comprises a base, a tube body mounted on the base and a tube body opening-and-closing mechanism; the tube body comprises a fixed tube body and a movable tube body, the fixed tube body and the movable tube body are arc-shaped shells, and form a hollow shape when the openings thereof match with each other; the tube body opening-and-closing mechanism is connected to the movable tube body for realizing the opening-and-closing of the movable tube body and the fixed tube body. The invention solves heat retaining and heating problems during the forging process of the main shaft forgings and avoids internal defects due to rapid temperature drop of the main shaft forgings.

Abstract: Systems and methods for processing measurement data in an electric power system include acquiring the measurement data by a phasor measurement unit (PMU) coupled to a line of the electric power system, and inputting a plurality of the measurement data within a predetermined time window into a K-nearest neighbor (KNN) for identifying bad data among the plurality of the measurement data, wherein when one of the plurality of measurement data contains a bad datum, the machine learning module sends the bad datum to a denoising autoencoder module for correcting the bad datum, wherein the denoising autoencoder module outputs a corrected part corresponding to the bad datum, and when one of the plurality of measurement data contains no bad datum, the machine learning module bypasses the denoising autoencoder module and outputs the one of the plurality of measurement data as an untouched part.

Abstract: State estimation in an electric power system includes acquiring electrical measurements from the electric power system at a reporting rate of the electrical measurements, processing the electrical measurements into sequence data including positive sequence data, processing positive sequence data by an observable state estimator to generate a plurality of estimated states including a plurality of estimated observable states, parameters of the observable state estimator being updated by a first training module in a first time thread, processing the plurality of estimated states by an unobservable state estimator to generate a plurality of estimated unobservable states, parameters of the unobservable state estimator being updated by a second training module in a second time thread independent of the first time thread, and outputting a plurality of final estimated states generated by concatenating the plurality of estimated observable states and the plurality of estimated unobservable states.

Abstract: Systems and methods for generating a load model having composite load components for electric power systems are disclosed which include acquiring state information at a bus of the electric power system, acquiring a training event record, and generating the load model by sequentially executing steps of determining a final load component composition for a predetermined composite load model structure referencing to both the state information and the training event record, and determining a plurality of final load parameters corresponding to the final load component composition and the predetermined load model structure also referencing to both the state information and the training event record.

Abstract: Systems and methods are disclosed for controlling a power system by formulating a voltage control problem using a deep reinforcement learning (DRL) method with a control objective of training a DRL-agent to regulate the bus voltages of a power grid within a predefined zone before and after a disturbance; performing offline training with historical data to train the DRL agent; performing online retraining of the DRL agent using live PMU data; and providing autonomous control of the power system below a sub-second after training.

Abstract: Provided are an accurate load shedding system, and a communication method and an access apparatus thereof. The access apparatus includes: two E1 interfaces, eight optical fiber interfaces, a CPU and an FPGA. The two E1 interfaces are respectively connected to a control apparatus A and a control apparatus B of a control substation. The eight optical fiber interfaces are respectively connected to eight control terminals. The FPGA includes eight optical fiber transceivers respectively connected to the eight optical fiber interfaces through serial interfaces, and two E1 transceivers respectively connected to the two E1 interfaces through serial interfaces. Each optical fiber transceiver includes a reset submodule. Each E1 transceiver also includes a reset submodule. The CPU is connected to the FPGA through a parallel bus.