4results about How to "Avoid control error" patented technology

This invention discloses a method for generating sickle bend control strategies based on deep reinforcement learning, comprising: collecting intermediate slab data during the hot roughing and rolling process of strip steel as sample data and performing data preprocessing; establishing and training a sickle bend amount prediction model based on the XGBoost algorithm to build an intelligent agent environment for generating the sickle bend control strategy model; establishing a sickle bend control strategy generation model based on a deep deterministic policy gradient algorithm; training the sickle bend control strategy generation model and saving the model parameters; inputting the intermediate slab data from the hot roughing and rolling process of strip steel into the trained sickle bend control strategy generation model, and outputting the intermediate slab sickle bend adjustment strategy. This invention, through automatic control, can effectively avoid control errors caused by current reliance on human experience, reduce manual intervention, and lower labor intensity. Simultaneously, controlling the straightness of the roughing slab provides a strong guarantee for the stability of finishing rolling production.

The application provides a wing parachute track tracking method for complex environment, and belongs to the technical field of wing parachute track tracking control, and comprises the following steps: a six-degree-of-freedom model of the wing parachute is established to describe the position and posture of the wing parachute in the movement process; a reasonable structure and loss function are selected, and a long short-term memory network (LSTM) for predicting instantaneous speed is trained through a back propagation algorithm; the error between the actual track and the expected track is calculated through a lateral track error method to realize lateral control of the wing parachute; and the predicted instantaneous speed, the expected track and the actual track error are taken as inputs to realize tracking control of the wing parachute through a sliding mode controller. In the case that the measurement information is limited, the instantaneous speed of the wing parachute is predicted through the LSTM, and the track tracking of the wing parachute is realized in combination with the sliding mode control. Compared with the traditional control method, the method provided by the application has higher reaction speed and robustness, and can realize fast and stable track tracking of the wing parachute.

The embodiment of the invention discloses a water level detection control method for a heat preservation tank of a water purifier, and relates to the technical field of water purifiers, and the method comprises the following steps: under the triggering of a water supplementing signal and / or a water taking signal, collecting a real-time water level height sequence of the heat preservation tank within a preset time, and fitting the real-time water level height sequence to obtain a real-time water level height sequence; determining an incidence relation model of the water level height and the water level change time; and when the heat preservation tank is in the water supplementing process or the water taking process, the operation parameters of the water pump and / or the heating body are / is controlled according to the incidence relation model. The real-time real flow velocity can be dynamically measured through the incidence relation model of the water level height and the water level change time, and control errors caused by flow velocity fluctuation are avoided; under the dynamic operation working condition, the operation parameters of the execution mechanism are adjusted in real time through the incidence relation model, the technical problem that the water taking amount is inaccurate in the water taking process is solved, the water level rising trend can be monitored in real time according to the model during water supplementing, and water level overflow is effectively prevented.

This invention discloses a fault control method and system for distribution networks, belonging to the field of fault control technology. The method comprises: acquiring the voltage and current signals of the converter grid connection point based on the distribution network to be controlled, and determining the operating state of the distribution network to be controlled; if it is an asymmetrical fault operating state, then blocking the active and reactive power loops of the distribution network to obtain the positive-sequence voltage component, the negative-sequence voltage component, and the positive and negative-sequence virtual internal potentials of the converter; calculating the positive and negative-sequence virtual impedance coefficients based on the above data; calculating the positive and negative-sequence virtual impedances based on the above data; and inputting the positive and negative-sequence virtual impedances into the distribution network to be controlled and reacquiring the voltage and current signals of the converter grid connection point to redetermine the operating state of the distribution network to be controlled until it is in a normal operating state. The fault control method for distribution networks provided by this invention can achieve stable control of new distribution networks under fault scenarios, ensuring the safe and efficient operation of new distribution networks.