Search

CN-115576326-A - Rice combine harvester aided navigation method and device

CN115576326ACN 115576326 ACN115576326 ACN 115576326ACN-115576326-A

Abstract

The embodiment of the invention provides an auxiliary navigation method, an auxiliary navigation device and electronic equipment for a rice combine harvester, belonging to the technical field of artificial intelligence, wherein the method comprises the following steps: the main controller receives positioning, image and angle information acquired by the vision sensor, the positioning module and the angle sensor through a serial port; the positioning module sends real-time positioning longitude, latitude and speed information to the main control module through a serial port, and a path planning and boundary prediction model is established; two vision sensors are adopted to respectively obtain operation images on the left side and the right side of the harvester, and the vision sensors are connected with a main controller module through serial ports and selected and called by a main controller; the angle sensor sends steering wheel angle information to the main control module in real time through a serial port to provide navigation control feedback information, and the steering actuator receives a steering control signal sent by the main controller to correct deviation of the harvester relative to an operation boundary line. By adopting the scheme, the rice harvesting efficiency can be improved, and the production cost is reduced.

Inventors

  • YANG YINGYING
  • LI XIAODONG

Assignees

  • UNIV HUAIHUA

Dates

Publication Date
20230106
Application Date
20221031
Priority Date
20221031

Claims (10)

  1. 1. An auxiliary navigation method of a rice combine harvester is characterized by comprising the following steps: the main controller receives positioning, image and angle information acquired by the visual sensor, the positioning module and the angle sensor through a serial port, and realizes positioning information analysis and processing, visual sensor selection and calling, image information acquisition and processing, angle sensor information acquisition, navigation control, man-machine interaction and information storage through software design; the positioning module sends real-time positioning longitude, latitude and speed information to the main control module through a serial port, and a path planning and boundary prediction model is established; two vision sensors are adopted to respectively obtain operation images on the left side and the right side of the harvester, and the vision sensors are connected with a main controller module through serial ports and selected and called by a main controller; the angle sensor sends steering wheel angle information to the main control module in real time through a serial port to provide navigation control feedback information, and the steering actuator receives a steering control signal sent by the main controller to correct deviation of the harvester relative to an operation boundary line so that the harvester runs along an expected straight line.
  2. 2. The method of claim 1, further comprising: the man-machine interaction module provides the latitude and longitude of the current operation, the operation path planning information and the image information acquired by the vision sensor for the driver, and assists the driver in completing the harvesting operation.
  3. 3. The method of claim 2, further comprising: the storage module is used for storing key information acquired by positioning, angle sensors and vision sensors so as to facilitate subsequent off-line analysis and research.
  4. 4. The method of claim 3, further comprising: the stress-strain relationship of the soil is expressed as Where σ is the normal stress, k c Is soilCohesive modulus of soil, k φ Is the modulus of frictional deformation of the soil, b c Is the track width, Z is the soil settlement, and Γ is the soil settlement index. The load borne by the two sides of the track type combine harvester is expressed as Wherein G is the mass of the crawler-type combine harvester, G1 is the mass borne by the crawler I, G2 is the mass borne by the crawler II, and B is the track gauge of the crawler.
  5. 5. The method of claim 4, further comprising: when the amount of deviation in the track longitudinal direction is equal to 0, the maximum ground specific pressure and the minimum ground specific pressure of the track I are respectively calculated as Wherein, ew is the ground plane modulus, gz is the offset along the longitudinal direction of the track; the theoretical turning radius of the rice combine body is calculated according to the following formula Wherein u is r1 And u r2 Track-winding speeds of low-speed side and high-speed side, R l The theoretical turning radius of the crawler-type combine harvester body; when the crawler vehicle turns, the crawler on the low-speed side slips, and the slip rate is delta 1 The track on the high-speed side is slipped at a slip ratio of delta 2 The corresponding expression is as follows Wherein v is r1 Is the implied speed v of the vehicle body on the low-speed side track to the ground r1 The implied speed of the vehicle body on the high-speed side track to the ground; the method for calculating the actual turning radius is Wherein, A 1 And A 2 Track offset for low and high speed sides; the theoretical steering angular velocity of the crawler-type combine harvester is calculated according to the following formula Wherein v is O1 Is the track relative to the car body 1 Implicit velocity of the point, v O2 Is the track relative to the car body 2 Implicit speed of points; the actual steering angular velocity is expressed as The shear force over the entire rail is calculated as follows Wherein, F m1 Is the x-direction component of the shear force over the entire track, F m2 Is the y-direction component of the shear force across the rail; the translation speed of the central point of the crawler-type combine harvester is calculated by the following formula
  6. 6. The method of claim 5, further comprising: in the path planning of the rice combine harvester, on the basis of an artificial fish school algorithm, the algorithm is improved from two aspects of parameters and a mechanism; the position of the artificial fish i at time t is marked And randomly selecting a position within its visual range Wherein Rand is a random number in the interval (0, 1) if The artificial fish is moved one step in the direction, i.e. If it is not Then X j Are reselected until the number of selections is greater than the maximum number of tests, and no higher food concentration is found, the artificial fish performs a random behavior.
  7. 7. The method of claim 6, further comprising: when an artificial fish tries to reach point IV, if no point with a large degree of fit is found in its field of view, a random action is performed, i.e. a random action is performed A larger visual range and a larger step length are adopted in the early stage, so that the algorithm is quickly converged near the optimal point, and the convergence speed is increased; and a smaller visual range and a smaller step length are adopted in the later period, so that the algorithm is carefully searched in the optimal area, the optimization precision is improved, and the synchronous self-adaptive method of the visual range and the step length comprises the following steps: Visual_ada＝Visual·f V (iter) Step_ada＝Step·f s (iter) wherein Visual _ ada is self-adaptive Visual range, step _ ada is self-adaptive Step length, f V (iter) is an adaptive function of the apparent distance, f s (iter) is an adaptive function of the step size, iter is the number of iterations.
  8. 8. An auxiliary navigation device of a rice combine harvester is characterized by comprising: the main controller receives positioning, image and angle information acquired by the visual sensor, the positioning module and the angle sensor through a serial port, and realizes positioning information analysis and processing, visual sensor selection and calling, image information acquisition and processing, angle sensor information acquisition, navigation control, man-machine interaction and information storage through software design; the sending module is used for sending the longitude, latitude and speed information positioned in real time to the main control module through the serial port by the positioning module and establishing a path planning and boundary prediction model; the connecting module is used for adopting two vision sensors to respectively obtain operation images on the left side and the right side of the harvester, and the vision sensors are connected with the main controller module through serial ports and selected and called by the main controller; and the execution module is used for sending steering wheel angle information to the main control module in real time through the serial port by the angle sensor, providing navigation control feedback information, receiving a steering control signal sent by the main controller by the steering actuator, correcting the deviation of the harvester relative to an operation boundary line, and enabling the harvester to run along an expected straight line.
  9. 9. An electronic device, characterized in that the electronic device comprises: at least one processor; and the number of the first and second groups, a memory communicatively coupled to the at least one processor; wherein, the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the rice combine assisted navigation method of any one of claims 1-7.
  10. 10. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the rice combine assisted navigation method of any one of claims 1 to 7.

Description

Auxiliary navigation method and device for rice combine harvester Technical Field The invention relates to the technical field of artificial intelligence, in particular to an auxiliary navigation method and device for a rice combine harvester and electronic equipment. Background The crop rotation rice is a rice planting mode which enables harvested rice stubbles to sprout into ears again through special cultivation measures. It has the advantages of double-end harvesting, labor saving, time saving, seed saving, good rice quality and the like. When the paddy rice in the terrace is harvested for the first time, the problems of high rolling rate of manual operation, poor harvesting stability and the like seriously restrict the development of the paddy rice in the terrace. In addition, in the first harvesting process of the affine cudweed, due to insufficient drying, the field surface is moist and soft, and the requirement on the traffic of the chassis of the harvester is high. With the continuous improvement of the automation and intelligence degree of agricultural machinery, advanced navigation positioning technology and control technology are widely applied to combine harvesters. In order to reduce labor intensity and improve the harvesting effect of rice in one season, an intelligent crawler-type combine harvester driven by electric power is an important development direction in the future. The crawler-type combine harvester is usually used for harvesting rice because the contact area between the crawler-type chassis and the ground can be increased, the grounding pressure is small, the whole machine has good traffic performance and stronger maneuverability and steering capacity in a paddy field environment. In order to take the harvesting quality and the working efficiency into consideration, a driver needs to dynamically adjust the advancing direction, the working speed, the height of a machine head, the position of the harvester and the operation parameters of working parts in real time according to the growth condition of rice in the harvesting process. High operation requirement and high labor intensity. The navigation system can realize the autonomous planning and tracking of the operation path, improve the operation efficiency and quality of agricultural equipment, reduce the labor intensity of a driver and prolong the operation time. However, some key technologies are not effectively broken through, and the navigation system is not widely applied to the crawler-type rice combine harvester. For example, key navigational information such as forward speed, heading angle, etc. of a tracked combine is difficult to directly measure. The harvesting path needs to be planned in real time according to the shape of the boundary of the area to be harvested. The creeper easily sinks and skids in the paddy field, which causes great control error, and the steering of the prior crawling type combine harvester completely depends on manual operation and can not be controlled by electric signals. During the operation of the crawler-type rice combine harvester, the advancing speed of the machine and the operation parameters (such as the machine head height, a winding drum, a threshing roller, the cleaning fan rotating speed and the like) of main working components need to be dynamically adjusted by a driver according to actual conditions. The navigation system realizes the autonomous identification and tracking of the operation path of the crawler-type rice combine harvester, and belongs to the category of auxiliary navigation. The research on the auxiliary navigation system of the crawler-type rice combine harvester is beneficial to changing the current situation that the crawler-type rice combine harvester widely used for harvesting rice in China operates in a pure manual mode, improving the operation efficiency and the harvesting quality, reducing the labor intensity of a driver, providing reference for the design and optimization of a navigation system of agricultural equipment, and having important significance for improving the agricultural production efficiency. The agricultural machinery automatic navigation mode based on satellite differential positioning is not dependent on operation environment information and crop growth state, and is mainly used for links such as cultivation, sowing, pesticide application and the like; the detection mode based on laser is affected by installation accuracy, sensor vibration and actual measurement range, so that the stability is insufficient, and the anti-interference capability is low. The contact-based navigation device is limited to different row spacing standards and different straw types, and the practical application of the contact-based navigation device is quite special; the visual navigation method based on the crop harvest boundary is mainly used for detecting the harvest boundaries of wheat and corn, and the detection and tracking research on the rice harvest bound