32 results about "Adaptive control theory" patented technology

The invention relates to an optimal control system for subway traffic flow. According to the system, a topological structure diagram of a rail transit network is generated according to planned operating parameters of trains; controllability and sensitivity of train flow are analyzed on the basis of the topological structure diagram; a multi-train conflict-free operating track is generated according to the planned operating parameters of each train; at each sampling moment, the advancing position of each train in the future time is predicted according to the current operating state and the historical position observation sequence of the train, an observer from continuous dynamics to discrete conflict logics of the train is established, and the continuous dynamics are mapped into conflict states expressed by discrete observation values; when the system possibly breaks the traffic control rule, hybrid dynamic behaviors of a subway traffic hybrid system are monitored, and alarm messages are provided for a control center; finally, when the alarm messages appear, the train operating track is subjected to robust bi-level programming with a self-adaptive control theoretical method, and a program result is transmitted to each train.

The invention relates to a navigation control method based on rolling planning strategies. The method includes the following steps: obtaining real-time and historical position information of ships through sea surface radar; at each sampling time, carrying out rolling prediction of trajectories of the ships within a future period of time according to the real-time and historical position information of the ships; observing sequences on the basis of current running states and historical positions of the ships, and obtaining a value of a sea wind field variable; on the basis of the running states of the ships and a safety rule set the requirement of which a set ship needs to meet when the set ship is running within the sea, monitoring dynamic behaviors of the ships and providing timely warning information to a sea traffic control center; and when the warning information appears, adopting an adaptive control theoretical method to conduct rolling planning for ship collision-prevention trajectories by setting an optimization index function and merging the wind field variable value under a condition that the ship physical performance and sea traffic rules are satisfied, and transmitting a planning result to the ships for implementation.

The invention discloses an adaptive welding method and system based on cloud platform big data. The adaptive welding method establishes a big data storage and an intelligent rule library through a cloud platform server, and uses the main theory of dynamic resistance control to perform welding adaptive control. Coupled with the optimized welding process evaluation and energy control ideas, it provides all-round guidance, process monitoring and quality control for the welding quality controlled by DSP. It has not only forward adaptive control theory, but also post-processing process evaluation and quality compensation optimization, coupled with the system configuration of automatic trusteeship process, it is a complete and comprehensive production process method and system. Its establishment and Perfection and maturity will provide the mechanical welding industry with high process quality and automatic production level, which can directly greatly improve social labor efficiency and ultimately bring extremely high economic value and social benefits.

This invention, relating to automatic measure technology realm, discloses a control system for automatic batch weighing powdered solid dye in textile dyeing and finishing industry, which is composed by an upper machine, a lower machine and a high-precision electronic scale, also defines as high-precision and automatic batching and dyeing control apparatus adopting modern automatic control technology to make the batching course supermatic. Wherein, the lower machine comprises multi-axis motion control card and electric control cabinet; the upper machine is linked to multi-axis motion control card via PCI bus, and forms a closed-loop feedback system with said scale; upper machine and the scale are separately connected to A.C. regulated power supply. The system adopts advanced control means based on machine learning, optimality principle, adaptive control theory and computer net technology to solve problem of precision in batching and dynamic weighing powder dye.

The invention discloses an ARX-based online modeling method of a water supply pipe network. The invention first establishes the real-time operation data of the pipe network system, and establishes the input and output process model of the system. The real-time operation database includes the real-time input data and real-time output data of the system; the input data includes the water supply pressure of the water plant, the water supply volume of the water plant, the pressure and flow of the booster pump station in the pipeline network, and the opening degree of the controllable valve on the pipeline; the output data includes The pressure of the pressure monitoring point, the flow rate of the flow detection point, and the water level of the reservoir. Then, based on the real-time process operation data set of the water supply network, an ARX model in the form of discrete difference equations is established. Finally, the model parameters are estimated in real time. The invention can estimate model parameters online in real time, track the state changes of the water supply pipe network in real time and make predictions; the model has simple structure and strong robustness, and combines predictive control and adaptive control theory to realize real-time optimal scheduling of the water supply pipe network.

The invention discloses a servo motor control method integrating sliding mode control and fractional order neural network control. The servo motor control method comprises the following steps of A, establishing a numerical model of a servo motor, and describing the numerical model of the servo motor, so as to obtain the output, speed error and speed error derivative of the servo motor; B, according to the speed error and the speed error derivative of the servo motor, designing a fractional order sliding mode controller, so as to obtain a sliding mode control rule for inhibiting the buffet of the system; C, adopting a neutral network approximating algorithm to approximate the obtained sliding mode control rule, so as to obtain the approximated sliding mode control rule; D, adopting a self-adaptive control method to adjust the approximated sliding mode control rule on line, so as to obtain a final control rule of the servo motor; according to the final control rule, controlling the servo motor. The servo motor control method has the advantages that the sliding mode control theory and the fractional order neural network adaptive control theory are integrated, the robustness is high, and the tracking property is good; the servo motor control method can be widely applied to the field of industrial control.

The invention relates to a planning method for ship conflict release. The method comprises the steps that firstly, shape tracks, speculated at each sampling moment, of all ships in a future time period are acquired through a maritime traffic control center; sequences are observed on the basis of current operation states and historic positions of the ships, and sea area wind field variables are obtained; then at on the basis of the operation states of all the ships and a set safety rule set which is required to be met by the ships in the sea area during the operation each sampling moment, when a condition which might violate safety rules occurs among the ships, dynamic behaviors of the ships are monitored, and timely warning information is provided for the maritime traffic control center; finally, when the warning information occurs, on the premise that ship physical properties and sea area traffic rules are met, rolling planning is performed on a ship collision avoidance track with a self-adaption control theory method by setting an optimization indicator function and infusing wind field variables, and a planning result is transmitted to all the ships to be executed.

The present invention relates to a navigation traffic control method, which includes the following steps: first, the real-time and historical position information of the ship is obtained through the sea surface radar; Then, based on the current operating state of the ship and the observation sequence of historical positions, the value of the wind field variable in the sea area is obtained; and based on the operating state of each ship and the set of safety rules that the ship needs to meet when operating in the sea area, Monitor the dynamic behavior of the ship and provide timely warning information for the maritime traffic control center; when the warning information appears, on the premise of meeting the physical performance of the ship and the sea area traffic rules, by setting the optimization index function and integrating the value of the wind field variable , using the adaptive control theory method to carry out rolling planning for ship collision avoidance trajectories, and transmit the planning results to each ship for execution. The present invention predicts and plans the track in real time, and has good safety.

The invention belongs to the field of radio communication, and discloses a channel self-adaptive estimation method based on multi-model weighted soft handover. Firstly, the channel system model is established, the time-frequency dual channel is selected, and the channel parameters are determined. Then based on the channel model and estimation method, the channel estimation sub-model and multi-model channel estimation library are established, and the model error and estimation error of the channel estimation model are analyzed and calculated. Finally, according to the switching index combining model error and estimation error, the model switching is completed through the weighted multi-model adaptive estimation algorithm of LUMV. The present invention proposes that under the condition of uncertain transmission channel model, combined with channel model and estimation method, the multi-model idea in multi-model adaptive control theory is introduced into channel estimation, and a weighted multi-model with minimum variance of linear error is adopted An adaptive estimation method is used to complete the switching, so that the channel estimation method has high robustness and accuracy in the complex channel range.

The invention discloses a predictive control method and device of a piezoelectric ceramic actuator on the basis of the neural network. The predictive control method includes modeling the piezoelectric ceramic actuator by the multilayer neural network to obtain a neural network model of the piezoelectric ceramic actuator; adopting the neural network model to obtain a synchronous linearized model in each sampling period; adopting the synchronous linearized model to obtain a predictive controller and optimizing the predictive controller; controlling displacement of the piezoelectric ceramic actuator on the basis of the synchronous linearized model and the corresponding predictive controller. On the basis of relevant content of the self-adaption control theory, displacement of the piezoelectric ceramic actuator is controlled in real time by means of a plurality of linear approximate models and the predictive controller on the basis of the neural network, the inherent problem of delay of the piezoelectric ceramic actuator is overcome, and displacement of the piezoelectric ceramic actuator is tracked and controlled in real time.

The invention relates to a subway traffic flow optimization control method. The method comprises the following steps that a topology structural chart of a track traffic network is generated according to planned running parameters of trains; controllability and sensitivity of a train flow are analyzed based on the topology structural chart; a multi-train non-collision running track is generated according to the planned running parameters of the trains; the running positions of the trains at some time are predicted at each sampling time based on the current running state and the historical position observation sequence of the trains, an observer from the continuous dynamic state of the trains to the discrete collision logic is established, and the continuous dynamic state is mapped into the collision state expressed through the discrete observation value; when it is possible for a system to violate the traffic control rule, the hybrid dynamic behavior of the subway traffic hybrid system is monitored, and alarm information is provided for a control center; and finally when the alarm information occurs, the robustness double-layer planning is carried out on the train running track through a self-adaptation control theory method, and a planning result is transmitted to the trains.