3results about How to "Reduce the required power" patented technology

This application provides a fuel cell hydrogen circulation system and its regulation method and apparatus, belonging to the field of fuel cell technology. The system includes a hydrogen storage tank forming the anode circuit, a pressure reducing valve, a purge valve, a vapor-water separator, and a vacuum pump, and a fuel cell stack connected between the pressure reducing valve and the purge valve. The method includes: when the fuel cell stack starts up, acquiring the operating current of the fuel cell stack according to a sampling period; controlling the purge valve to open according to the operating current, the sampling period, and the purge period, so that the purge valve purges the generated water in the fuel cell stack to the vapor-water separator; when the purge valve closes, controlling the vacuum pump to start, so that the vacuum pump pumps the hydrogen in the vapor-water separator back to the fuel cell stack's air inlet; during the operation of the fuel cell stack, controlling the vapor-water separator to discharge the generated water according to a drainage period. This application aims to reduce the cost, noise, and parasitic power of the fuel cell hydrogen circulation system.

The application provides a wind power timing adaptive window adjustment method and device based on reinforcement learning, wherein the method comprises the following steps: collecting multi-source timing data from a wind turbine system or a database, and preprocessing the multi-source timing data to obtain a preprocessing data set; dividing the preprocessing data set according to a time sequence principle to obtain training data; training an initial LSTM model based on the training data to obtain a target LSTM model, and training a reinforcement learning model according to an output value of the target LSTM model and a reinforcement learning strategy; performing prediction based on the reinforcement learning model and the target LSTM model to obtain a prediction value, and inputting the prediction value and a real-time power feedback error into a discrete PID controller to obtain a control amount for driving a wind turbine actuator. The application combines the deep timing modeling capability of LSTM and the dynamic decision-making capability of reinforcement learning to intelligently adjust the length of a historical time window in wind power prediction.

This invention provides a high-temperature conductive silver paste for a microcrystalline glass thick-film heating plate, its preparation method, and sintering process. The high-temperature conductive silver paste for the microcrystalline glass thick-film heating plate, by mass percentage, comprises: silver powder: 75-85%; composite glass powder: 1-5%; organic carrier: 10-24%. The composite glass powder comprises component A and component B in a mass ratio of 1-3:1. Component B is silicon micropowder. Component A, by mass percentage, comprises: silicon oxide: 35-50%; boric acid: 20-30%; magnesium oxide: 10-15%; aluminum oxide: 5-10%; titanium oxide: 3-5%; and zirconium oxide: 1-2%. The high-temperature conductive silver paste for the microcrystalline glass thick-film heating plate prepared by this invention has high solderability, strong adhesion, a maximum operating temperature exceeding 450℃, strong resistance to high current impact, high re-firing stability, and excellent overall performance.