5results about How to "Avoid the modeling process" patented technology

The invention discloses an efficient regulation and control system and method for plateau low-oxygen environment damage, and relates to the technical field of human body low-oxygen damage analysis, detection and regulation and control, and the system comprises a data monitoring module, a signal screening module, a decision oxygen distribution module and a monitoring interaction module; the data monitoring module is used for acquiring a physiological state related to the plateau hypoxia adaptive capacity in real time; acquiring physiological data with high modeling value through an optimization algorithm by using a signal screening module based on test data, and constructing a discrete state space model of a physiological state; an oxygen distribution concentration decision is determined through a predictive control algorithm by utilizing a decision oxygen distribution module, so that oxygen supply regulation and control are realized; and the monitoring interaction module is used for storing, recording and displaying data, issuing an alarm and predicting dangerous conditions. Therefore, by means of the method, effective oxygen supply, blood oxygen dynamic monitoring and real-time alarming can be achieved, and health and safety of individuals in oxygen-deficient environments such as high-altitude areas and the like are guaranteed.

The invention provides a surface clutter real-time generation method and device, and the method comprises the steps: determining a target time domain range and a target frequency domain range of a to-be-generated surface clutter signal according to the real-time motion state parameter of a carrier carrying a radar seeker and the beam pointing parameter of the radar seeker; generating a random clutter sequence covering the target time domain range and the target frequency domain range according to a preset amplitude statistical distribution model and a preset power spectrum model; a surface clutter signal is generated by modulating a reference radar signal, the modulation including convolving the reference radar signal using a random clutter sequence, and parameter adjusting the convolved signal to match dynamic characteristics of a carrier. According to the invention, the problem of insufficient fidelity of clutter simulation signals in the prior art is solved.

The invention relates to a mother-type ship database-based ship noise forecasting method, which comprises the following steps of: collecting mother-type ship noise actual measurement data, performing arrangement by taking each place as a dimension, and establishing a mother-type ship database; carrying out statistical processing on the data, and calculating statistical indexes of noise measured values of all rooms of all mother type ships; the measured values of the same place of each mother ship are regarded as different results repeatedly measured for the same experiment, and a normal distribution model is established; adding the average value of the noise measured values at all positions and the standard deviation of a certain multiple of the normal distribution model as the noise basic value of the new ship; comparing the difference between a noise source and a propagation path between the predicted ship and the mother ship, establishing a function relationship between a single difference and a noise level by using an empirical formula or an actual measurement result similar to new ship equipment arrangement, and superposing all change influence results to obtain a total influence result of the noise at the place; and obtaining a predicted value of the noise of the new ship based on a superposition result of the noise basic value and the total influence result.

The application discloses a heavy-load combined train cooperative communication consistency braking control method and device. In the train braking process, the braking controller combines the strict constraints of the actuator and the relative displacement between the carriages, and adopts a distributed model predictive control method to design a cooperative braking controller according to the state variables such as the speed, acceleration and position information of each sub-node; the train consistency braking force control method is designed to solve the performance index of minimizing the speed inconsistency and the relative displacement difference between the carriages. The application reduces the relative displacement and the speed inconsistency between the carriages during train braking, reduces the size of the train hook force during braking, effectively reduces the damage of the carriage structure, and improves the comfort during train driving.

The embodiment of the invention relates to a multi-unmanned-aerial-vehicle close-range fighting method based on an opponent coding network, and the method comprises the steps: inputting the historical action information of a task collected by each unmanned aerial vehicle into the opponent coding network according to the task environment of the multi-unmanned-aerial-vehicle close-range fighting, and carrying out the center average calculation, thereby obtaining the opponent coding information; the opponent coding information is combined in parallel and input to a leader network to obtain indication information; the indication information is combined and input into the evaluation network to obtain evaluation information, the action network outputs actions according to the evaluation information, the leader network, the opponent coding network, the evaluation network and the action network are optimized until the leader network and the opponent coding network converge, and a multi-unmanned-aerial-vehicle close-range combat strategy is generated. According to the embodiment of the invention, the method reduces the cost of behavior modeling of the unmanned aerial vehicle, solves a problem that a conventional algorithm cannot be suitable for a sequential decision-making task of multiple unmanned aerial vehicles through the introduction of the opponent coding network, and solves a problem that the environment is not stable in a training process of multiple unmanned aerial vehicles.