Automated ground leveling using artificial neural network

A surface grading system comprising:

• a traction unit including a three-point hitch system having an actuator selectively controllable between a plurality of different positions;
• a scraper implement attached to the three-point hitch system, the scraper implement including a cutting edge configured for shaping a ground surface, wherein a position of the cutting edge relative to the traction unit is adjustable in response to movement of the actuator;
• an angle sensor operable to sense data related to a pitch angle of the traction unit;
• a controller in communication with the angle sensor and the actuator, and including a processor and a memory having a grading control algorithm stored thereon, wherein the processor is operable to execute the grading control algorithm to:
• receive a desired elevation of the ground surface;
• receive a pitch angle of the traction unit at a current location of the traction unit from the angle sensor;
• calculate a leveling variation, wherein the leveling variation is a numerical difference between a current elevation of the cutting edge of the scraper implement and the desired elevation of the ground surface at a current location of the cutting edge of the scraper implement;
• generate a hitch control signal based on the pitch angle of the traction unit and the leveling variation;
• and
• apply the hitch control signal to the actuator of the three-point hitch system to adjust a vertical position of the cutting edge of the scraper implement relative to the traction unit.

A surface grading system comprising:

• a traction unit having a scraper implement attached thereto, the scraper implement including a cutting edge configured for shaping a ground surface;
• an actuator selectively controllable between a plurality of different positions and interconnecting the traction unit and the scraper implement, whereby movement of the actuator adjusts a position of scraper implement relative to the traction unit;
• an angle sensor operable to sense data related to a pitch angle of the traction unit;
• a position sensor operable to sense data related to a location of the traction unit;
• a controller in communication with the angle sensor, the position sensor, and the actuator, wherein the controller includes a processor and a memory having a grading control algorithm stored thereon, wherein the processor is operable to execute the grading control algorithm to:
• receive a desired elevation of the ground surface;
• receive a pitch angle of the traction unit at a current location of the traction unit from the angle sensor;
• calculate a leveling variation, wherein the leveling variation is a numerical difference between a current elevation of the cutting edge of the scraper implement and the desired elevation of the ground surface at a current location of the cutting edge of the scraper implement;
• generate a hitch control signal based on the pitch angle of the traction unit and the leveling variation;
• and
• apply the hitch control signal to the actuator to adjust a vertical position of the cutting edge of the scraper implement relative to the traction unit;
• and
• wherein the controller includes an Artificial Neural Network configured to receive the pitch angle and the leveling variation as input values, and output the hitch control signal as an output value.