4 results about "Motor variable" patented technology

The embodiment of the invention provides a dual-motor seamless variable stiffness control method based on deep reinforcement learning and related equipment, and belongs to the technical field of intelligent control. The method comprises the following steps: modeling a dual-motor variable stiffness control task into a Markov decision process to obtain a state space, an action space and a variable stiffness reward function; performing near-end strategy optimization on the strategy network through the state space, the action space and the variable stiffness reward function, so that the strategy network learns and generates a motor torque instruction for realizing variable stiffness behavior balance according to the environment, and an intelligent control network is obtained; the current state vectors of the double motors are collected in each control period, the current state vectors are input into the intelligent control network for control decision making, and an optimal motor torque instruction is obtained; and according to the optimal motor torque instruction, driving the double motors to carry out variable-stiffness cooperative motion. The embodiment of the invention can get rid of dependence on an accurate mathematical model, actively and autonomously learn the optimal control strategy through interaction with the environment, and realize a variable stiffness control behavior.

The application belongs to the technical field of asynchronous motor variable frequency speed regulation, and particularly relates to a power factor optimal control method based on vector control of a large-inertia asynchronous motor, which comprises the following steps: step one, calculating a rotor flux given initial value Flux0; step two, determining a slip angular velocity w corresponding to optimal power factor operation sy ; step three, reading a real-time speed difference e value; step four, motor overspeed determination; step five, when the motor overspeed value -e in step four reaches a set value A, reading a real-time torque current Is q , and performing step six; when the motor overspeed value -e in step four does not reach the set value A, directly performing step seven with the rotor flux given value Flux set = Flux0; step six, calculating a rotor flux given value given value Flux set ; step seven, calculating and outputting an excitation current constant value given value Isd set .

This invention discloses a multi-sensor fusion-based tunneling guidance control method. The method includes: constructing a motor variable cleaning model; receiving a set of motor sensor data and importing it into the motor variable cleaning model to obtain a final set of motor sensor data; constructing a motor variable pre-control algorithm model; inputting the final set of motor sensor data into the model to obtain a fused motor variable sensor model data set; obtaining temporary tunneling state data for motor variables based on the motor variable control data set and analyzing its validity; constructing a motor variable optimization control model; pre-setting motor control parameters; inputting the final set of motor sensor data and motor control parameters into a dynamic adjustment model for motor variables to output optimal temporary tunneling guidance control data for motor variables; analyzing the set of motor control parameters based on the temporary tunneling guidance data to obtain motor parameter sensitivity; constructing a motor parameter optimization priority model; analyzing and determining the optimization priority of motor control parameters based on motor parameter sensitivity; and inputting the optimized set of motor control parameters into the motor variable optimization control model to obtain the final tunneling motor variable guidance control data.

The invention provides a multifunctional experiment bench supporting motor overwater and underwater amphibious environment test, and belongs to the technical field of motor performance detection, and the multifunctional experiment bench comprises a main body support frame which is placed in a water tank with test liquid; a load simulation module, a torque sensing module and a tested motor module are sequentially mounted on the main body support frame from top to bottom; one ends of the two transmission shafts are respectively connected with an output shaft of the load simulation module and a motor flange coupling of the tested motor module through couplings, and the other ends of the two transmission shafts are respectively connected with a rotating shaft of the torque sensing module through couplings. According to the invention, under the condition that the motor and a transmission device are not disassembled and assembled, the motor twin trawling experiment and the motor variable load experiment of the motor on the water and under the water are realized, and the load applied by dragging the motor during the motor twin trawling experiment and the specific numerical value of the externally applied load during the motor variable load experiment are read through the torque sensor on the water; the experimental measurement efficiency is improved, and the measurement requirement of the underwater motor is met.