2results about How to "Ensure safe execution" patented technology

This invention relates to the field of flue gas pollution control technology in coal-fired power plants, and discloses a method for total pollutant emission reduction in an environmental protection island based on morphological transformation and residual compensation. The method includes: acquiring real-time operating data of a smart environmental protection island in a coal-fired power plant, generating a time-series feature vector, and setting inlet boundary conditions; constructing a pollutant morphological transformation mechanism model for each environmental protection subsystem, inputting relevant data and inlet boundary conditions, and calculating the theoretical baseline concentration of pollutants; using an LSTM as an error-compensated prediction model, after training with historical data, inputting the current operating condition time-series feature vector to obtain the concentration prediction residual value, obtaining the deviation between the historical training conditions and the current operating conditions, calculating the confidence factor, and generating a mixed pollutant prediction concentration; finally, using ammonia injection flow rate and other factors as optimization variables, setting constraints, and constructing an objective function with the lowest total cost to obtain the optimal control parameter set, thereby achieving optimized control and pollutant emission reduction of the environmental protection subsystem. This invention significantly improves the pollutant emission reduction effect.

The invention provides a motion trail optimization method for a mechanical arm and a storage medium. The method comprises the following steps that a charging mechanical arm model used for force control and an interaction dynamics model between a charging plug at the tail end of the charging mechanical arm and a vehicle charging jack are established; designing an optimization target and a constraint condition of a force position track of a charging plug at the tail end of the charging mechanical arm to obtain a force position track optimization problem of the charging mechanical arm; the force position trajectory optimization problem obtained in the problem description step is decoupled into an independent force position trajectory tracking problem and a mechanical arm trajectory planning problem with convex constraint, and an alternating direction multiplier method is adopted for solving; and a tail end force-position hybrid model prediction controller of the charging mechanical arm is designed, and a joint torque control instruction of the mechanical arm at the current moment is obtained by combining the current system state, so that each joint driver of the charging mechanical arm executes tail end force-position hybrid control according to the obtained control instruction.