280results about How to "Achieving Adaptive Control" patented technology

The invention relates to the technical field of traffic control and artificial intelligence and provides a traffic signal self-adaptive control method based on deep reinforcement learning. The method includes the following steps that 1, a traffic signal control agent, a state space S, a motion space A and a return function r are defined; 2, a deep neutral network is pre-trained; 3, the neutral network is trained through a deep reinforcement learning method; 4, traffic signal control is carried out according to the trained deep neutral network. By preprocessing traffic data acquired by magnetic induction, video, an RFID, vehicle internet and the like, low-layer expression of the traffic state containing vehicle position information is obtained; then the traffic state is perceived through a multilayer perceptron of deep learning, and high-layer abstract features of the current traffic state are obtained; on the basis, a proper timing plan is selected according to the high-layer abstract features of the current traffic state through the decision making capacity of reinforcement learning, self-adaptive control of traffic signals is achieved, the vehicle travel time is shortened accordingly, and safe, smooth, orderly and efficient operation of traffic is guaranteed.

The invention discloses an air conditioner and a control method thereof. The control method comprises the following steps: after the air conditioner is powered on, the air conditioner is in communication connection with outdoor units of other air conditioners with the same communication protocol as the air conditioner within a coverage area through an outdoor unit; the air conditioner obtains the parameter information of the other air conditioners within the coverage area through the outdoor unit; the air conditioner generates an own control parameter according to the parameter information of the other air conditioners within the coverage area; the air conditioner controls the air conditioner according to the control parameter. According to the control method of the air conditioner, disclosed by the embodiment of the invention, the air conditioner is in communication connection with the other air conditioners within the coverage area through the outdoor unit, obtains the parameter information of the other air conditioners through a communications network, and generates the own control parameter according to the parameter information of the other air conditioners so as to control the air conditioner, so that the adaptive control of the air conditioner is realized, the intervention of a user for the control parameter of the air conditioner is reduced, and the use experience of users is improved.

The invention relates to a road surface self-adaptive driving anti-skid control method and system of a distributed driving electric automobile and belongs to the technical field of vehicle control. According to the road surface self-adaptive driving anti-skid control method of the distributed driving electric automobile, by estimating a current road surface peak adhesion coefficient in real time,a current road surface optimal slip rate is obtained according to a corresponding linear relation between the current road surface peak adhesion coefficient and the current road surface optimal slip rate; by combining a current wheel center speed, a current wheel reference wheel speed is determined; a difference between an actual wheel speed and the reference wheel speed is calculated; according to the wheel speed difference, the moment of a wheel, which slips in a driving state, is controlled by using a sliding mode variable structure controller; and therefore, it is guaranteed that the wheelslip rate is controlled to the current road surface optimal slip rate. According to the road surface self-adaptive driving anti-skid control method of the distributed driving electric automobile, thewheel slip rate is controlled to the current road surface optimal slip rate to realize self-adaptive control of anti-skid driving of the wheel.

The invention relates to an unmanned aerial vehicle (UAV) autonomous navigation method and system capable of being applied to a large-scale unfamiliar complex environment. The method includes the steps of obtaining the state of a UAV by using sensing equipment and positioning equipment of the UAV; then determining a control vector of the UAV; determining a revenue function according to the state of the UAV and the environment in which the UAV is located; performing deep enhanced learning based on the revenue function to train a control function from the UAV state mapping to control; and by using the control function through training, generating a corresponding control instruction according to the state of the UAV and controlling the autonomous navigation of the UAV in a large-scale unknown complex scene. According to the invention, a navigation task can be independently accomplished only by using the perception information and position information of the UAV on the surrounding environment and the adaptive control of the UAV in a large-scale unknown complex environment is realized.

An aviation lamination material variable-parameter adaptive hole drilling system is characterized by comprising a, an end executor; b, a force sensor or a current detector; c, an adaptive controller; d, a control unit. An electric spindle transducer of the end executor controls the rotation of an electric spindle. The force sensor or the current detector is arranged on the electric spindle to be used for detecting the axial force or the current of the electric spindle. The adaptive controller communicates with the force sensor or the current detector and the control unit to be used for receiving feedback signals of the force sensor or the current detector to send instructions to the control unit, and the control unit controls the end executor to perform corresponding actions. A drive motor of the end executor comprises an encoder to be used for recognizing and feeding back tool feeding positions, and the adaptive controller communicates with the encoder and the control unit to be used for receiving the feedback signals of the encoder to send instructions to the control unit which controls the end executor to perform corresponding actions.

The invention discloses a fill light lamp automatic control method based on video analysis. The fill light lamp automatic control method based on the video analysis achieves the automatic control over a fill light lamp according to the changing of brightness values in a monitoring area. The fill light lamp automatic control method based on the video analysis achieves the self-adaptive control over the fill light lamp according to the changing of ambient brightness, avoids electric energy waste and light pollution to the environment by the fill light lamp, avoids the phenomena that the definition of monitoring video images declines due to insufficient light and the fill light lamp may flicker, saves equipment investment, shortens mounting construction cycles, and improves the reliability of system working.

Embodiments of the invention provide a permission management method and apparatus, a medium and an electronic device. The permission management method comprises the steps of determining a position ofa user to be allocated with a permission in an organization; and allocating a position permission corresponding to the position to the user, wherein each position permission contains at least one rolepermission, each role permission contains at least one menu permission, and each menu permission contains an access permission of at least one business function. According to the technical scheme, fine-grained permission control can be realized; permissions in the organization can be conveniently and orderly managed; and the permission management efficiency can be improved.

The invention discloses a method for electromagnetic valve frequency conversion and current control of an automatic transmission. The method comprises control at a clutch/brake oil-way pressure regulation stage and control at a clutch/brake oil-way pressure maintenance stage, wherein an electromagnetic valve carrier valve control technology is adopted for the clutch/brake oil-way pressure regulation stage and current control is adopted for the pressure maintenance stage, and whole-course frequency conversion control of the electromagnetic valve is realized; the electromagnetic valve carrier valve control technology is adopted for the clutch/brake oil-way pressure regulation stage so that the response speed and the response precision of the electromagnetic valve are improved; the current control is adopted for the clutch/brake oil-way pressure maintenance stage, so that current change, caused by circuit voltage change, is avoided, and self-adaptive control of current is realized; besides, the current control is adopted for the clutch/brake oil-way pressure maintenance stage, so that extra heating or electromagnetic force reduction, caused by current change, of the electromagnetic valve is avoided, and the reliability of the electromagnetic valve during working is improved.

The invention discloses a volume control method of an automobile player and the automobile player. The method comprises the following steps of: acquiring an external environment sound signal of the automobile player, and extracting a loudspeaker sound signal from an automobile player output signal; reversely processing the loudspeaker sound signal; superposing the loudspeaker sound signal which is reversely processed with the environment sound signal, and thus obtaining an environment noise signal; and according to the environment noise signal which is obtained and a preset gear value, regulating the volume of the automobile player. By the invention, self-adaptive control over the volume of the automobile player according to different external environment noises is realized, and an experience effect of a user is improved.

The embodiment of the invention provides a planting environment self-adaptive control method and device. The method comprises the steps of acquiring environment monitoring data and crop growth processdata; inputting the environment monitoring data and the crop growth process data into a trained corrected growth prediction model to obtain crop growth stage prediction information; and determining an environment control scheme according to the crop growth stage prediction information and a preset growth stage and planting database. The trained corrected growth prediction model considers factorssuch as crop structure change caused by human factors in the plant growth process; the crop growth stage prediction information is more accurately obtained through the trained corrected growth prediction model, so that the optimal planting environment corresponding to the crop growth stage is determined, and the self-adaptive efficient management of the crop planting environment is realized.

The invention discloses a message flow control method and system. The message flow control method includes establishing a communication connection pool, a message buffer pool and a processing thread pool; detecting current using conditions of the communication connection pool, the message buffer pool and the processing thread pool in real time; adjusting capacity of the communication connection pool, the message buffer pool and the processing thread pool according to the current using conditions of the communication connection pool, the message buffer pool and the processing thread pool respectively; utilizing communication connection transceiving messages in the communication connection pool, and using messages in the message buffer pool and thread processing messages in the processing thread pool. In the message flow control method, the communication connection pool, the message buffer pool and the processing thread pool are established with the current using conditions under real-time monitoring, capacity of the pools can be adaptively adjusted, self-adaption control of the system on data communication flows is realized, and communication jamming and the like are avoided.

The invention provides a traffic signal control system and method based on edge side online calculation. The system comprises vehicle-mounted terminal equipment, a signal machine and a signal lamp controller, wherein the vehicle-mounted terminal equipment is used for acquiring vehicle information data of an installed vehicle in real time, combining the vehicle information data into a vehicle information data packet and sending the vehicle information data packet to the annunciator; the signal machine is used for calculating and obtaining road condition parameters of each road section of the intersection according to the plurality of collected vehicle information data packets, outputting a current road passing state through a fuzzy comprehensive evaluation model, adjusting a signal timing scheme and sending the signal timing scheme to the signal lamp controller; and the signal lamp controller is used for performing adaptive control on the signal lamp according to the received signal lamp timing scheme. The system can detect and comprehensively analyze the traffic operation state of the intersection in real time; and intersection signal coordination adaptive control is realized.

The invention discloses a switching state control circuit and control method and a fly-back converter. A first voltage sampling signal characterizing the input voltage information is obtained, and theconduction time of a synchronous rectifier tube is adjusted according to the change state of the first voltage sampling signal so as to adjust the absolute value of a negative current flowing througha secondary winding, wherein the negative current is used to discharge a junction capacitor of a main power tube so as to reduce the drain-source voltage of the main power tube. The main power tube can be switched on in a ZVS (Zero Voltage Switching) mode under different input voltages. The magnitude of the negative current is appropriate, and no extra circulating current will be generated. Adaptive control is realized.

The invention provides a method for controlling participation of a battery energy storage system in power grid secondary frequency modulation. An adjustment coefficient of participation of the battery energy storage system in the power grid secondary frequency modulation and a relation between the adjustment coefficient K2 and the amount of unbalance [delta]P of a load and generated power in a power grid are determined through the amount of unbalance [delta]P of the load and generated power in the power grid, after the amount of unbalance [delta]P of the load and generated power in the power grid goes through a generator-load frequency characteristic link, a frequency difference value [delta]f of a system is obtained, after a PI link of each power supply participating in the power grid secondary frequency modulation, to-be-changed-power of each power supply is obtained. The method can change the final output magnitude of participation of the battery energy storage system in the power grid secondary frequency modulation, the battery energy storage system realizes participation in the power grid secondary frequency modulation process through charging and discharging control, fire coal loss of a traditional unit can be reduced, and thus frequency modulation cost is reduced; and a balance between power supply power generation and load power utilization can be maintained rapidly.

The invention aims to provide a traffic control method and device. A wide-area microwave radar is adopted, multi-lane and wide-range traffic information of each phase of intelligent traffic control can be obtained, the method is not affected by environment or weather, large-area laying is not needed, and the installation and maintenance cost is low. The traffic flow of each lane and the traffic flow of each phase can be balanced by using an equisaturation control mechanism, and the phase saturation degree of each phase is controlled to be within an idea range; an adaptive control method can sufficiently coordinate traffic requirements between the phases, the green light duration is fully utilized, and then adaptive control over traffic circulation is achieved.

The invention discloses a three-phase four-bridge-arm dual-closed-loop control method based on emotional intelligence and a passivity theory. A three-phase four-bridge-arm state equation under a d-q-0 coordinate is established; an Euler-Lagrange model is established, and a passivity-based controller (PBC) is designed according to a system passivity theory; the passivity-based controller is designed to serve as a nonlinear controller; compared with a conventional PI linear controller, the passivity-based controller is more applicable to a D-STATCOM linear system; the passivity-based controller has the advantages of high control response speed and good output current waveform and can serve as a current closed-loop controller; in addition, a simplified emotional intelligent controller is adopted; a corresponding link of orbitofrontal cortex in conventional emotional control is reduced, so that the emotional controller is simplified; meanwhile, a self-learning capability which is better than conventional PI control is still kept; the stability of a direct current side voltage can be well maintained; the anti-interference capability of the system is enhanced; and due to the dual-closed-loop control method, the three-phase four-bridge-arm D-STATCOM has good, rapid and stable compensation performance at a user side of a low-voltage three-phase four-wire system power supply system.

The invention relates to a microgrid energy optimization scheduling method based on adaptive control. The microgrid energy optimization scheduling method comprises the steps of S1, obtaining a randomlinear control system; S2, constructing an adaptive microgrid optimization scheduling model according to the random linear control system obtained in the step S1; S3, performing MPC optimal schedulingon the adaptive microgrid optimal scheduling model constructed in the step S2. The beneficial effects of the method are that: according to the microgrid energy optimization scheduling method based onadaptive control, under a combined optimization scheduling framework of a random energy and an energy storage system, an optimization strategy based on adaptive random model predictive control is provided; the method is compared with a robust model predictive control method based on scene construction, different self-adaptive updating strategies and comparison models of different adjusting parameters are designed, the scheduling performance of the system and the self-adaptability of the model can be effectively improved, and the conservative property of the system is reduced.

The invention discloses a traffic signal lamp control method and system based on reinforcement learning, and the method comprises the steps: firstly building a signal lamp control Agent model, then building a road and road intersection model, enabling the road traffic state information to be represented as a speed, position and current signal lamp state matrix, then, on the basis of traditional Q-Learning, establishing a traffic signal lamp control algorithm based on Deep Q Network (DQN) according to the road environment information; and finally, obtaining real-time road condition information through interaction between the Agent and the environment, performing search self-learning in a behavior space, estimating Q values for executing all possible actions in the current state, and selecting the action with the larger Q to be executed by utilizing an epsilon-greedy strategy. An existing traffic signal lamp control method is improved, the waiting time of vehicles at the intersection is minimized, the effective green light time of a signal control period is maximized, the vehicles are assisted to rapidly pass through the intersection, the passing time is shortest, meanwhile, the maximum traffic flow exists at the intersection, and thus the purpose of relieving traffic jam is achieved, and adaptive control of the traffic signal lamp is realized.