3results about How to "Advanced" patented technology

The application belongs to the technical field of image processing, and discloses an RGB-T saliency target detection method based on cross-modal interaction and full-scale aggregation, realizes fusion between RGB image features and thermal infrared image features, fully utilizes feature information of different depths, and can also completely detect targets of different scales in an outdoor scene disturbed by interference, and improves detection precision. The application uses a cooperative incentive learning module as a cross-modal interaction mode to make two different modes use effective information features of each other in a targeted manner, maximally suppresses interference information of both sides, that is, information on an image background will not be acquired as effective information, and a detection result with high accuracy can be obtained under the condition of scene interference.

The present invention relates to the technical field of agricultural machinery, and in particular to an implement adjustment device of a three-point suspension mechanism, comprising an implement hydraulic system and a vehicle body for towing the implement, the hydraulic system comprising a lifting cylinder, an oil inlet pipeline of the hydraulic system and the lifting cylinder being connected via a reversing valve, a piston rod of the lifting cylinder being connected to the implement, a handle of the reversing valve being connected to a driving mechanism for driving the same, the content of this patent realizes servo control of tractor implements, realizes the correspondence between the position of the control handle and the height position of the tractor implements, the position where the handle operating rod is placed corresponds to the height position of the implement, there is no need to manually supervise the implement position during the adjustment process, and the efficiency is high.

The present invention relates to electric vehicle charging technology, and aims to provide a method for orderly charging of electric vehicles in substations based on load forecasting and deep reinforcement learning. It includes: according to the historical charging remaining capacity information of the substation, a fully connected feedforward neural network is used to predict the future remaining charging capacity; according to the flexible electricity price mechanism and the predicted future remaining charging capacity, a DQN-based deep reinforcement learning algorithm is used to adjust the electric vehicle charging strategy and control the number of electric vehicles connected to the charging pile. The present invention introduces the load forecasting method into the orderly charging operation of electric vehicles, and uses the predicted future remaining charging capacity as the basis for the charging scheduling of electric vehicles, which is more real-time and advanced than traditional methods. By introducing deep reinforcement learning into the orderly charging operation of electric vehicles, the predicted future information is used to pre-schedule the orderly charging of electric vehicles, and it has real-time self-learning and updating capabilities, which is more flexible and effective than traditional algorithms, and further improves the economy and efficiency.