5results about How to "Improve interaction speed" patented technology

This invention provides an active flow control method and system based on intelligent algorithms. The method includes: determining the number of inlet parameter sets for a typical flight state point, constrained by simulation economy and sampling efficiency; performing numerical simulations according to the number of inlet parameter sets to obtain dataset 1, with inlet parameters as independent variables and flow field characteristics as dependent variables; obtaining dataset 2, with flight state as independent variables and flow field characteristics as dependent variables, through numerical simulation for a certain set of inlet parameters; constructing a proxy model of inlet flow field characteristics for a typical flight state point using deep learning based on dataset 1; constructing a proxy model of inlet flow field characteristics for a wide-speed-domain flight state based on the proxy model of inlet flow field characteristics for the flight state point, using a transfer learning algorithm and dataset 2; constructing an environment-agent interaction model based on a deep reinforcement learning algorithm, using the proxy model of inlet flow field characteristics for a wide-speed-domain flight state as the environment model for deep reinforcement learning; setting optimization termination conditions based on the environment-agent interaction model, and obtaining a control sequence with continuously optimal inlet performance under different flight states through deep reinforcement learning. This invention can stably adapt to flight scenarios with a wide speed range and a large airspace, and achieve real-time optimal control of the air intake flow field under a wide speed range, solving the problem of poor generalization ability of traditional methods under different operating conditions.

The present disclosure relates to an intelligent control cabinet, which belongs to the field of energy storage technology and can save the cost and space of wiring between boxes. An intelligent control cabinet includes a cabinet and a distribution circuit, a control circuit and a communication circuit located in the cabinet, wherein: the distribution circuit is connected to the mains power grid, converts the alternating current of the mains power grid into direct current for supplying power to the internal devices and external loads of the intelligent control cabinet, converts the high-voltage direct current output by the DC switch cabinet of the energy storage system into direct current for supplying power to the internal devices and external loads of the intelligent control cabinet, and protects the remote lines and the internal devices and external loads of the intelligent control cabinet; the control circuit obtains various switch quantity status information inside the intelligent control cabinet, and controls the on and off of the power supply circuits of the internal devices and external loads of the intelligent control cabinet based on the switch quantity status information; the communication circuit exchanges data with the SCADA outside the intelligent control cabinet.

The application relates to a kind of box-type substation monitoring data visualization method, belong to substation monitoring and visualization technical field.The application adds the required visualization primitive in box-type substation electrical vector diagram according to layer order, edits the ID, coordinate, animation, layer, group, relevant primitive and other properties of primitive, and is bound with the visualization information table of monitoring object primitive and monitoring data by electrical vector diagram;before the interaction of sensing data and visualization primitive, the address of monitoring data is used to replace the ID of monitoring object primitive;the many-to-one and one-to-many association between primitives is constructed according to the group, coordinate, relevant primitive properties and electrical transmission relationship of primitive by electrical vector diagram;the sensing data is directly pushed to the primitive of monitoring object from the address of monitoring data, so as to quickly realize data visualization expression according to the association between primitives.The application reduces the development difficulty of box-type substation monitoring data visualization, and improves the level of box-type substation digitization.

According to the battery box and the battery pack, the battery box comprises a box body and a controller cover, the box body comprises a box body and a beam body arranged on the box body, the beam body and the box body define a first cavity used for containing a battery, and the controller cover is connected with the beam body and can define a second cavity used for containing a control module with the beam body; moreover, a mounting opening is formed in the beam body, and the mounting opening is communicated with the first cavity and the second cavity, so that when the battery is arranged in the first cavity and the control module is arranged in the second cavity, the control module can be inserted into the first cavity from the second cavity through the mounting opening; the interaction speed of the control module and the battery in the first cavity can be improved to a certain degree, meanwhile, the controller cover is arranged on the side, away from the first cavity, of the beam body, so that the controller cover and the second cavity are both located on the outer side of the box body, the situation that the controller occupies the space in the first cavity can be avoided, and the service life of the controller is prolonged. And the influence on the energy density of the battery pack is reduced.

The present invention belongs to the field of active flow control technology, and discloses an active flow control method based on agent model and transfer learning, including the following steps: S1, data sampling based on model-free reinforcement learning; S2, training the neural network based on the interaction data between the intelligent agent module and the CFD environment module in step S1; S3, active flow control training based on the agent model; S4, based on the idea of ​​transfer learning, using the agent model reinforcement learning framework established in step S3 to perform active flow control training in complex environments. The present invention adopts the above-mentioned active flow control method based on agent model and transfer learning, trains the agent model based on model-free reinforcement learning interaction experience, reduces the time and computing power of pre-simulating data in advance, improves the interaction speed, and quickly implements the active flow control strategy in complex environments.