Rotor torque predictor
View Patent ↗A system is disclosed for determining the total torque required at the main and tail rotors of a helicopter for use in feed-forward rotor torque anticipation which includes a polynomial neural network adapted and configured to predict the aerodynamic torque at the main and tail rotors with the helicopter in motion based upon a plurality of pilot inputs and airframe inputs, a main rotor load map for determining the torque at the main rotor in hover out of ground effects based upon main rotor speed and collective stick position, a tail rotor load map for determining the torque at the tail rotor with the helicopter stationary based upon main rotor speed and pedal position, and a processor for calculating the required total torque at the main and tail rotors by summing the outputs of the polynomial neural network, and the main and tail rotor load maps.
1. A system for determining the total torque required at the main and tail rotors of a helicopter for use in feed-forward rotor torque anticipation, the total torque including the aerodynamic torque and static torque at the main and tail rotors, the system comprising:
a) means for predicting the aerodynamic torque at the main and tail rotors with the helicopter in motion;
b) means for determining the torque at the main rotor with the helicopter stationary;
c) means for determining the torque at the tail rotor with the helicopter stationary; and
d) means for calculating the required total torque at the main and tail rotors based upon the aerodynamic torque at the main and tail rotors with the helicopter in motion, the torque at the main rotor with the helicopter stationary, and the torque at the tail rotor with the helicopter stationary.
2. A system as recited in claim 1 , wherein the means for calculating the required total torque at the main and tail rotors includes means for summing the aerodynamic torque at the main and tail rotors with the helicopter in motion, the torque at the main rotor with the helicopter stationary, and the torque at the tail rotor with the helicopter stationary.
3. A system as recited in claim 2 , wherein the polynomial neural network is a full order polynomial neural network.
4. A system as recited in claim 3 , further comprising means for selecting between the full order polynomial neural network and a reduced order polynomial neural network.
5. A system as recited in claim 3 , wherein the full order polynomial neural network is adapted and configured to predict the aerodynamic torque at the main and tail rotors with the helicopter in motion based upon pilot input data including collective stick position data, pedal position data, rate of change of pedal position data, lateral stick position data and longitudinal stick position data, and airframe input data including main rotor speed data, engine torque data, true airspeed data and pitch attitude data.
6. A system as recited in claim 5 , wherein the full order polynomial network includes forty-nine interconnected nodes, each node having a quadratic polynomial associated therewith.
7. A system as recited in claim 5 , wherein the full order polynomial neural network is trained to predict the aerodynamic torque component of total torque on collective pitch and non-collective pitch maneuvers with equal weighting.
8. A system as recited in claim 2 , wherein the polynomial neural network is a reduced order polynomial neural network.
9. A system as recited in claim 8 , wherein the reduced order polynomial neural network is adapted and configured to predict the aerodynamic torque at the main and tail rotors with the helicopter in motion based upon pilot input data including collective stick position data and pedal position data, and airframe input data including main rotor set speed data and climb rate data.
10. A system as recited in claim 9 , wherein the reduced order polynomial network includes ten interconnected nodes, each node having a quadratic polynomial associated therewith.
11. A system as recited in claim 9 , wherein the reduced order polynomial neural network is trained to predict the aerodynamic torque component of total torque on primarily collective pitch maneuvers.
12. A system as recited in claim 1 , wherein the means for predicting the aerodynamic torque at the main and tail rotors with the helicopter in motion comprises a polynomial neural network.
13. A system as recited in claim 1 , wherein the means for determining the torque at the main rotor blades with the helicopter stationary is a main rotor load map.
14. A system as recited in claim 13 , wherein the main rotor load map is adapted and configured to determine the torque at the main rotor with the helicopter stationary based upon main rotor speed and collective stick position.
15. A system as recited in claim 1 , wherein the means for determining the torque at the tail rotor blades with the helicopter stationary is a tail rotor load map.
16. A system as recited in claim 15 , wherein the tail rotor load map is adapted and configured to determine the torque at the tail rotor with the helicopter stationary based upon main rotor speed and pedal position.
17. A system for determining the total torque required at the main and tail rotors of a helicopter for use in feed-forward rotor torque anticipation, the total torque including the aerodynamic torque and static torque at the main and tail rotors, the system comprising:
a) a polynomial neural network adapted and configured to predict the aerodynamic torque at the main and tail rotors with the helicopter in motion based upon a plurality of pilot inputs and airframe inputs;
b) a main rotor load map for determining the torque at the main rotor in hover out of ground effects based upon main rotor speed and collective stick position;
c) a tail rotor load map for determining the torque at the tail rotor with the helicopter stationary based upon main rotor speed and pedal position; and
d) means for calculating the required total torque at the main and tail rotors by summing the outputs of the polynomial neural network, and the main and tail rotor load maps.
18. A system as recited in claim 17 , wherein the polynomial neural network is a full order polynomial neural network.
19. A system as recited in claim 18 , wherein the full order polynomial neural network is adapted and configured to predict the aerodynamic torque at the main and tail rotors with the helicopter in motion based upon pilot input data including collective stick position data, pedal position data, rate of change of pedal position data, lateral stick position data and longitudinal stick position data, and airframe input data including main rotor speed data, engine torque data, true airspeed data and pitch attitude data.
20. A system as recited in claim 17 , wherein the polynomial neural network is a reduced order polynomial neural network.
21. A system as recited in claim 20 , wherein the reduced order polynomial neural network is adapted and configured to predict the aerodynamic torque at the main and tail rotors with the helicopter in motion based upon pilot input data including collective stick position data and pedal position data, and airframe input data including main rotor set speed data and climb rate data.