Seeding depth compensation method and system based on terrain prediction

Abstract

The invention relates to the technical field of mechanical position servo control, and solves the problem of seeding depth fluctuation caused by position response lag and linear compensation failure of a traditional profiling mechanism. The method comprises the following steps: acquiring curvature characteristics of a front terrain through a terrain detection sensor, and predicting vertical displacement offset of a ground contact point by combining structural parameters and speed of an execution mechanism; generating a drive actuator feed-forward position instruction based on the offset and a preset depth target value; a cutting edge load disturbance value is collected in real time, and output thrust (hard soil area nonlinear thrust increasing / soft soil area stepped thrust decreasing) is corrected in a graded mode according to the discrete disturbance gradient; and the position of the actuator is dynamically adjusted by combining ditching depth feedback. Through double closed-loop control of terrain-position feedforward and resistance-position feedback, independent pre-judgment and accurate position tracking of the mobile platform on the surface micro-terrain are realized, so that position output is consistent with a position target value.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical position servo control, and in particular to a sowing depth compensation method and system based on terrain prediction. Background Art

[0002] Traditional seed drills use mechanical contouring mechanisms (such as counterweighted linkages or integral contouring wheels) to maintain trenching depth. Essentially, these mechanisms achieve position tracking through the mechanism's gravity or spring force. This type of passive control has fundamental flaws: First, the mechanism responds passively only after the actuator encounters a sudden change in terrain, unable to anticipate changes in curvature ahead (such as a steep slope transitioning to a pit), causing the trenching depth to momentarily deviate from the set position. Second, soil resistance exhibits a discrete distribution (suddenly increasing resistance in hard, rocky areas and sharply decreasing resistance in soft areas). However, the passive mechanism only provides a constant or linearly varying downforce, leading to loss of depth control at extreme resistance levels. In hard soil, insufficient thrust causes the actuator to lift (undercompensation), while excessive thrust causes it to sink (overcompensation) in soft areas.

[0003] Although existing electro-hydraulic position control systems have attempted to introduce depth sensor feedback, they still have two major limitations: they rely solely on the current actuator position feedback and do not integrate the geometric features of the terrain ahead (curvature, slope) to predict the displacement offset; they use a fixed-gain PID to regulate the hydraulic thrust, which cannot adapt to the discontinuous gradient changes in soil resistance and will still produce depth oscillations in the resistance mutation zone. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a sowing depth compensation method based on terrain prediction to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above-mentioned object, the present invention provides a method for compensating sowing depth based on terrain prediction, comprising: The controlled object installed on the mobile platform obtains the terrain elevation data of the front working area; Extracting curvature change characteristics of the terrain elevation data, and converting the curvature change characteristics into a vertical displacement offset of the actuator's touchdown point based on the actuator's structural parameters and travel speed; Generating a displacement compensation instruction for driving the actuator in real time according to the vertical displacement offset and the preset position target value; In response to the displacement compensation instruction, the driving actuator is driven to output an initial thrust, and a load disturbance value of the actuator cutting edge is collected in real time; When the load disturbance value exceeds a preset disturbance threshold range, the output thrust of the driving actuator is adjusted in stages according to the disturbance gradient; The relative position of the actuator and the mobile platform is dynamically adjusted based on the output thrust so that the position output is consistent with the position target value.

[0006] In order to solve the above problems, the present invention also provides a sowing depth compensation system based on terrain prediction, the system comprising: A terrain elevation data acquisition module is used to obtain terrain elevation data of the front working area through a controlled object installed on a mobile platform; a displacement offset generating module, configured to extract curvature variation characteristics of the terrain elevation data and convert the curvature variation characteristics into a vertical displacement offset of the actuator's touchdown point based on the actuator's structural parameters and travel speed; A compensation instruction generating module, configured to generate a displacement compensation instruction for driving the actuator in real time according to the vertical displacement offset and the preset position target value; a load disturbance value generating module, configured to respond to the displacement compensation instruction, drive the driving actuator to output an initial thrust, and collect the load disturbance value of the actuator cutting edge in real time; A thrust graded adjustment module, configured to grade and adjust the output thrust of the drive actuator according to a disturbance gradient when the load disturbance value exceeds a preset disturbance threshold range; The position output and the position target value consistency adjustment module is used to dynamically adjust the relative position of the actuator and the mobile platform based on the output thrust so that the position output is consistent with the position target value.

[0007] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention uses a laser rangefinder to collect real-time terrain elevation data ahead, extracting curvature variation characteristics. This model, combined with the actuator's surface inclination angle, mass inertia parameters, and travel speed, establishes a position offset prediction model. The system response lag is calculated based on travel speed, and phase compensation is performed on the curvature characteristics to eliminate mechanical delays. The compensated curvature value is mapped to the vertical displacement offset of the actuator's contact point, generating a feedforward compensation command for the actuator. This process quantifies terrain geometric characteristics into position control variables in real time, breaking through the open-loop response bottleneck and enabling the system to pre-adjust the actuator's position before it encounters sudden changes in terrain, eliminating errors inherent in depth fluctuations.

[0008] 2. Based on position feedforward control, the present invention constructs a thrust graded correction mechanism based on discrete resistance gradient: real-time monitoring of the actuator blade load disturbance value, dividing the disturbance threshold intervals of hard / soft soil; when the resistance value enters the hard interval, the hydraulic output thrust is increased according to a nonlinear increasing function to ensure the position maintenance capability; when the resistance value enters the soft interval, the thrust is reduced according to a step-by-step decreasing function to avoid position overadjustment; combined with the displacement sensor to feedback the trenching depth deviation in real time, the thrust readjustment mechanism is triggered. This dual closed-loop control breaks through the limitations of linear force control, allowing the system to maintain position tracking accuracy when the soil resistance jumps discretely, and ultimately achieves sowing depth consistency. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic flow chart of a method for compensating sowing depth based on terrain prediction provided by one embodiment of the present invention; Figure 2 A functional module diagram of a sowing depth compensation system based on terrain prediction provided by an embodiment of the present invention; The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0010] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0011] The embodiment of the present application provides a sowing depth compensation method based on terrain prediction. The execution subject of the sowing depth compensation method based on terrain prediction includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the sowing depth compensation method based on terrain prediction can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and big data and artificial intelligence platforms.

[0012] Reference Figure 1 FIG. 1 is a flow chart of a method for compensating sowing depth based on terrain prediction according to an embodiment of the present invention. In this embodiment, the method for compensating sowing depth based on terrain prediction includes: S1. Obtain the terrain elevation data of the front working area through the controlled object installed on the mobile platform.

[0013] In an embodiment of the present application, the mobile platform is a single functional unit on the seeder that can independently complete operations such as furrowing and sowing, can independently respond to terrain changes and make adjustments, and can be a sowing unit; the controlled object is a device for collecting surface height information, and its function is to obtain terrain data of the working area before the sowing operation, and can be a terrain detection sensor; the working area refers to the area of ​​the land where the mobile platform is about to perform sowing operations; the terrain elevation data is a set of numerical values ​​reflecting the height of each surface point in the working area relative to the set reference plane.

[0014] In some embodiments, obtaining terrain elevation data of the front working area by a controlled object installed on a mobile platform includes: A laser rangefinder is used to scan the working area in front of the mobile platform, and the scanned point cloud data is converted into terrain elevation data.

[0015] In an embodiment of the present application, a laser rangefinder is a device that measures distance by emitting laser light and receiving reflected signals, and can be used to scan the surface to obtain three-dimensional coordinate information; point cloud data is a data set consisting of the three-dimensional coordinates (including X-axis coordinates) of a large number of surface points scanned by the laser rangefinder, where the Z-axis coordinate reflects the height information of the point.

[0016] First, a laser rangefinder was installed in front of the mobile platform in the direction of travel, with the horizontal distance from the actuator set at 50 cm. This distance ensured that terrain could be detected in advance while avoiding large terrain prediction errors caused by excessive distance. The laser rangefinder's scanning parameters were set to: a scanning frequency of 40 Hz and a scanning width of 1.0 m. This means that it can scan a 1.0 m wide area in front 40 times per second, generating 3D coordinate data for 150 points with each scan. During the seeding operation, the laser rangefinder continuously emits a laser beam into the work area. The laser beam is reflected by the ground, and the laser rangefinder receives the reflected signal and calculates the 3D coordinates of each scanned point (with the mobile platform's forward direction as the X-axis, the Y-axis perpendicular to the forward direction as the Y-axis, and the Z-axis perpendicular to the ground upward as the Z-axis), forming point cloud data.

[0017] The acquired point cloud data is then transformed to extract the Z-axis coordinate value of each point. These Z-axis coordinates represent the height of the corresponding surface point relative to the reference surface, thereby obtaining the terrain elevation data of the work area. For example, in the point cloud data obtained from a certain scan, the three-dimensional coordinates of a point are (0.2m, 0.3m, 0.04m), of which the Z-axis coordinate of 0.04m is used as the terrain elevation data of the point; the coordinates of another point are (0.3m, 0.4m, 0.06m), and its terrain elevation data is 0.06m.

[0018] In the embodiment of the present application, this step uses a laser rangefinder to obtain the terrain elevation data of the working area ahead in advance, breaking the limitation that the traditional passive profiling mechanism needs to contact the surface before responding to terrain changes, and provides basic data for subsequent prediction and compensation of terrain changes, which helps to solve the problem of sowing depth fluctuations caused by uneven surface (such as small bumps or depressions).

[0019] S2. Extracting curvature change characteristics of the terrain elevation data, and converting the curvature change characteristics into a vertical displacement offset of the actuator's touchdown point based on the actuator's structural parameters and travel speed.

[0020] In the embodiment of the present application, the curvature change characteristic is an indicator reflecting the sudden change in the degree of terrain curvature, which is manifested by the abnormal change point of the terrain curvature radius; the actuator is a component on the mobile platform used to cut the soil to form a seed trench, which can be a furrow opener; the vertical displacement offset is the vertical deviation value of the actuator contact point relative to the reference position due to the terrain change.

[0021] In some embodiments, the structural parameters include an inclination angle of an action surface and a mass inertia parameter, wherein the inclination angle of the action surface is measured in real time by an angle sensor, and the mass inertia parameter is pre-set through a calibration test.

[0022] In the embodiment of the present application, the structural parameters are parameters that characterize the mechanical properties of the actuator; the inclination angle of the action surface is the angle between the blade edge of the actuator and the horizontal plane, which can be the blade angle inclination angle of the trench opener; the mass inertia parameter is the additional mass set to adjust the soil penetration pressure of the actuator, which can be the configuration mass of the trench opener; the travel speed is the forward speed of the mobile platform during the operation process.

[0023] In some embodiments, extracting curvature change characteristics of the terrain elevation data includes: Calculate the slope change rate between adjacent terrain elevation data points; generating a sequence of terrain curvature radii according to the slope change rate; The mutation points in the curvature radius sequence are extracted as curvature change features.

[0024] In the embodiment of the present application, the slope change rate is the ratio of the slope difference between two adjacent terrain elevation data points to the horizontal distance, which is used to reflect the severity of the change in terrain slope; the curvature radius sequence is an ordered set of curvature radii of multiple consecutive terrain points, and the curvature radius is a parameter that characterizes the degree of curvature of the curve. The smaller the value, the more severe the curvature; the mutation point is the point where the value in the curvature radius sequence suddenly changes significantly.

[0025] In this embodiment of the present application, the process of extracting curvature change features is as follows: Based on the terrain elevation data obtained in S1 (for example, the elevation values ​​of consecutive points in a certain area are 0.03m, 0.06m, 0.04m, and 0.10m), the slopes of adjacent points are first calculated. Taking two adjacent points A (elevation 0.03m, X-coordinate 0.1m) and B (elevation 0.06m, X-coordinate 0.2m), the slope is (0.06m-0.03m) / (0.2m-0.1m)=0.3; then taking points B and C (elevation 0.04m, X-coordinate 0.3m), the slope is (0.04m-0.06m) / (0.3m-0.2m)=-0.2. Next, we calculate the slope change rate, which is the ratio of the slope difference between two points to the horizontal distance. The slope change rate of point B relative to point A is (-0.2-0.3) / (0.3m-0.1m) = -2.5. We then calculate the radius of curvature based on the slope change rate. The radius of curvature is the ratio of 1 to the absolute value of the slope change rate, i.e., 1 / |-2.5| = 0.4m. This generates a sequence of curvature radii (e.g., 0.5m, 0.4m, 0.2m). We then identify the abrupt change point. When the curvature radius of a point in the sequence suddenly drops from 0.4m to 0.2m (a change exceeding 50%), this point is considered a sudden change in the curvature change characteristic.

[0026] In some embodiments, converting the curvature change characteristic into a vertical displacement offset of the actuator's contact point based on the actuator's structural parameters and travel speed includes: calculating a response lag time of the actuator based on a travel speed of the actuator; performing soil cutting resistance phase compensation on the curvature variation characteristic according to the response lag time and the inclination angle of the action surface to generate a compensated curvature characteristic value; The compensated curvature characteristic value is multiplied by the mass inertia parameter to generate a vertical displacement offset of the actuator touchdown point.

[0027] In the embodiment of the present application, the response lag time is the time required from the terrain detection sensor detecting the terrain change to the actuator actually contacting the terrain; the soil cutting resistance phase compensation is a correction made to eliminate the synchronization between the soil cutting resistance and the terrain change caused by the actuator response lag; the compensated curvature characteristic value is the value that can accurately reflect the terrain curvature when the actuator actually contacts after phase compensation.

[0028] In the embodiment of the present application, the process of converting the curvature change characteristics into vertical displacement offset is as follows: First, the response lag time is calculated. It is known that the horizontal distance between the terrain detection sensor and the actuator is 0.6m, and the travel speed is 1.2m / s. The response lag time is the ratio of the horizontal distance to the travel speed, that is, 0.6m / 1.2m / s=0.5s. Secondly, the soil cutting resistance phase compensation is performed. The angle sensor measures the inclination angle of the action surface as 25° in real time. The compensation amount is the product of the response lag time, the travel speed and the sine value of the inclination angle of the action surface, that is, , the compensation amount is added to the position parameter of the curvature mutation point to obtain the compensated curvature characteristic value (for example, the original curvature radius of 0.2m corresponds to a curvature of , the curvature characteristic value after compensation is Finally, the compensated curvature characteristic value is multiplied by the mass inertia parameter (20kg) set in advance through the calibration test to generate the vertical displacement offset, that is, (calibration coefficient, determined by field soil property tests) ≈ 1.21m. This value is the vertical deviation that needs to be adjusted for the actuator's touchdown point due to terrain changes.

[0029] In the embodiment of the present application, this step realizes the early prediction of surface microtopography changes by converting the geometric characteristics of the terrain into physical displacement parameters of the actuator, provides a quantitative basis for subsequent depth compensation, and solves the problem of depth adjustment lag caused by the inability of traditional passive profiling mechanisms to predict the terrain.

[0030] In the embodiment of the present application, this step breaks through the limitation that the traditional contour-matching mechanism can only passively respond to the terrain. By combining the change in terrain curvature with the structural parameters and motion parameters of the actuator, a quantitative mapping relationship from terrain characteristics to physical displacement is established, and the basis for active predictive depth adjustment is realized, providing an innovative solution for the precise control of sowing depth.

[0031] S3. Generate a displacement compensation instruction for driving the actuator in real time according to the vertical displacement offset and the preset position target value.

[0032] In an embodiment of the present application, the preset position target value is an ideal furrowing depth reference value set according to crop growth requirements, which can be a sowing depth target value; the drive actuator is a hydraulic drive device that receives control instructions and drives the actuator to perform vertical displacement adjustment, which can be a hydraulic actuator; the displacement compensation instruction is a signal used to control the action of the drive actuator, which contains displacement information that the actuator needs to adjust.

[0033] In some embodiments, the generating of a displacement compensation instruction for driving the actuator in real time based on the vertical displacement offset and the preset position target value includes: Superimpose the vertical displacement offset to the reference stroke value corresponding to the position target value to generate a compensation stroke value for driving the actuator; Generate a PWM control signal for driving the hydraulic proportional valve according to the compensation stroke value as a displacement compensation instruction for driving the actuator.

[0034] In the embodiments of the present application, the reference stroke value is the initial telescopic length required for driving the actuator to achieve the preset position target value; the compensation stroke value is the telescopic length actually required for driving the actuator after superimposing the vertical displacement offset on the reference stroke value; the hydraulic proportional valve is a control valve capable of proportionally adjusting the hydraulic flow and pressure according to the input electrical signal, used for controlling the action of the driving actuator; and the PWM control signal is a pulse signal capable of adjusting the output by changing the pulse width, which can be used to control the opening degree of the hydraulic proportional valve.

[0035] In some embodiments, the preset position target value is determined by selecting a reference depth interval according to the work object type, the work object type including a crop type, adjusting the reference depth interval based on a field calibration test, and generating a position target value.

[0036] In the embodiments of the present application, the specific process of determining the preset position target value is as follows: taking corn seeding as an example, according to the characteristics of corn crops, the reference depth interval is selected as 5-8 cm; then a field calibration test is carried out, and corn is seeded at depths of 5 cm, 6 cm, 7 cm and 8 cm in different areas of the test field respectively, the emergence rate and seedling growth of each depth are counted, and it is found that the emergence rate is the highest and the seedlings grow healthily at a depth of 6 cm, so the preset position target value is determined as 6 cm. The reference stroke value corresponding to the target value is calibrated by test, that is, when the driving actuator is telescoped by 4 cm, the execution mechanism can reach a furrowing depth of 6 cm, so the reference stroke value is set to 4 cm.

[0037] In the embodiments of the present application, the compensation stroke value for driving the actuator is generated by superimposing the vertical displacement offset of 1.21 cm obtained in S2 on the reference stroke value, i.e. compensation stroke value = 4 cm + 1.21 cm = 5.21 cm.

[0038] In the embodiments of the present application, the PWM control signal is generated by: the duty cycle of the PWM control signal of the hydraulic proportional valve is linearly corresponding to the compensation stroke value, and it is determined by pre-calibration that when the compensation stroke value is 0 cm, the duty cycle is 0%; and when the compensation stroke value is 10 cm, the duty cycle is 100%. Therefore, the duty cycle corresponding to 5.21 cm is (5.21 cm / 10 cm) x 100% = 52.1%, and the PWM control signal with a duty cycle of 52.1% is generated, which is the displacement compensation instruction for driving the actuator.

[0039] In the embodiment of the present application, this step converts the displacement requirement obtained by terrain prediction into specific action instructions to drive the actuator, so that the actuator can adjust its position in advance to adapt to terrain changes, solving the depth adjustment lag problem caused by passive response of traditional profiling mechanisms, and helping to maintain the stability of sowing depth.

[0040] In the embodiments of this application, this step combines the vertical displacement offset with a preset target value to generate compensation instructions. This overcomes the limitation of traditional passive contouring mechanisms, which can only adjust based on real-time contact terrain, and provides a key instruction generation mechanism for precise control of seeding depth. This control method, which directly links terrain prediction results with crop growth requirements, enables the mobile platform to more intelligently adapt to changes in surface microtopography.

[0041] S4. In response to the displacement compensation instruction, the driving actuator is driven to output an initial thrust, and a load disturbance value of the cutting edge of the actuator is collected in real time.

[0042] In the embodiment of the present application, the initial thrust is the driving force that the actuator outputs for the first time according to the displacement compensation instruction, which is used to push the actuator to cut into the soil; the actuator cutting edge is the sharp edge of the actuator in direct contact with the soil, which is used to cut the soil; the load disturbance value, specifically the soil resistance value, is the soil reaction force received by the actuator cutting edge when it cuts into the soil.

[0043] In the embodiment of the present application, the specific process of implementing the steps is as follows: First, the actuator is driven to receive the displacement compensation instruction generated by S3 (such as a PWM control signal with a duty cycle of 52.1%), and the signal is converted into the corresponding hydraulic flow and pressure through the hydraulic proportional valve. The hydraulic cylinder inside the actuator is driven to expand and contract under the action of hydraulic pressure, and outputs an initial thrust. The magnitude of the initial thrust is related to the compensation stroke value, and the corresponding relationship between the two is determined by pre-calibration. For example, a compensation stroke value of 5.21cm corresponds to an initial thrust of 7.815kN (calculation basis: thrust = hydraulic pressure × piston area, where the hydraulic pressure is controlled by the PWM signal duty cycle and the piston area is a preset fixed value).

[0044] Secondly, a strain gauge force sensor is installed at the cutting edge of the actuator. Rigidly connected to the cutting edge, it senses the soil's force on the cutting edge in real time. The sensor's measurement range covers the possible load disturbance values ​​in the operating area (e.g., 5-20 kN), and the sampling frequency is set to 100 Hz to ensure that instantaneous changes in resistance are captured. The sensor converts the mechanical signal into an electrical signal, which is amplified and filtered before being transmitted to the control system, generating real-time load disturbance value data. For example, when the actuator passes through an area of ​​soil containing small clods of debris, the resistance value recorded by the sensor may suddenly increase from 6.5 kN to 9.2 kN.

[0045] In the embodiment of the present application, this step ensures that the actuator cuts into the soil at a preset depth by outputting an initial thrust, and at the same time collects the load disturbance value in real time, providing a basis for subsequent adjustment of the thrust according to soil conditions, thereby solving the problem that traditional profiling mechanisms cannot adapt to differences in soil looseness due to fixed thrust.

[0046] In the embodiment of the present application, this step combines the action of the actuator with real-time resistance detection, breaking through the limitation of the traditional contour-matching mechanism that only relies on the passive adaptation of the mechanical structure.

[0047] S5. When the load disturbance value exceeds a preset disturbance threshold range, the output thrust of the driving actuator is adjusted in stages according to the disturbance gradient.

[0048] In the embodiment of the present application, the disturbance gradient grading is a method of dividing the load disturbance values ​​into different levels according to their size differences and matching a specific thrust adjustment strategy for each level.

[0049] In some embodiments, when the load disturbance value exceeds a preset disturbance threshold range, adjusting the output thrust of the driving actuator in stages according to the disturbance gradient includes: Measure the load disturbance extreme values ​​in the hard rocky area and the soft pit area, and divide the disturbance threshold interval according to the load disturbance extreme value distribution; When the load disturbance value enters the hard soil area, the output thrust is increased according to a linear increasing function; When the load disturbance value enters the soft soil area, the output thrust is reduced according to a step-down function.

[0050] In the embodiment of the present application, the hard clod area is an area in the soil containing hard clods or compacted layers, which has a greater resistance to the actuator; the soft pit area is an area with loose soil structure or depressions, which has a smaller resistance to the actuator; the load disturbance extreme value is the maximum resistance value measured in the hard clod area and the minimum resistance value measured in the soft pit area; the disturbance threshold interval is a continuous numerical range divided based on the load disturbance extreme value, which is used to judge whether the soil resistance is normal.

[0051] In the embodiment of the present application, a linear increasing function refers to a mathematical relationship in which the output thrust increases linearly with time or resistance value. A step decreasing function refers to a mathematical relationship in which the output thrust decreases in stages according to a fixed amplitude.

[0052] First, the load disturbance extremes in hard, cloddy areas and soft, pitted areas were measured. This involved selecting typical hard, cloddy areas and soft, pitted areas within the plot to be sown, and performing multi-point measurements using a strain gauge force sensor mounted on the cutting edge of the actuator. For example, the maximum resistance value measured in the hard, cloddy area was 18kN, while the minimum resistance value measured in the soft, pitted area was 5kN. Based on these two extreme values, disturbance threshold ranges were established: 8-15kN for normal soil (the optimal resistance range determined through field trials), 15-18kN for hard soil, and 5-8kN for soft soil.

[0053] When the load disturbance value collected in S4 enters the hard soil region (e.g., 16 kN), the output thrust is adjusted according to a linearly increasing function. This linear increasing function is set to F = F0 + k × t, where F0 is the current thrust (e.g., 7.815 kN output in S4), k is the increasing coefficient (0.4 kN / s, determined by soil hardness testing), and t is the duration that the resistance value remains in this region. If the duration is 3 seconds, the adjusted thrust is 7.815 + 0.4 × 3 = 9.015 kN. This gradual increase in thrust ensures that the actuator can penetrate the hard soil and avoids shallowing the trenching depth due to excessive resistance.

[0054] When the load disturbance value enters the soft soil range (e.g., 6kN), the output thrust is adjusted using a step-by-step decreasing function. Set to a 1.2kN decrease per level, with an initial thrust of 7.815kN, the thrust after the first level adjustment is 6.615kN. If the resistance remains within this range, the second level adjustment is 5.415kN. This staged reduction in thrust prevents the actuator from over-entering the soil due to insufficient resistance, thus avoiding excessive trenching depth.

[0055] In the embodiment of the present application, this step matches the output thrust of the driving actuator with the soil resistance through a targeted thrust adjustment strategy, thereby solving the problem that the traditional profiling mechanism cannot adapt to differences in soil looseness due to fixed thrust, and reducing the sowing depth fluctuations caused by abnormal resistance.

[0056] In the embodiments of this application, this step overcomes the limitations of single-force thrust control in conventional contouring mechanisms. By dividing the thrust into intervals based on measured extreme values ​​and adjusting the thrust using a differentiation function, dynamic adaptation of the thrust to soil resistance is achieved. This graded adjustment strategy avoids both shallow trenching due to insufficient thrust in hard areas and deep trenching due to excessive thrust in soft areas. It provides a precise power control solution for the mobile platform to cope with complex soil conditions and is a key step in achieving independent, real-time, and precise closed-loop control.

[0057] S6. Dynamically adjust the relative position of the actuator and the mobile platform based on the output thrust so that the position output is consistent with the position target value.

[0058] In the embodiment of the present application, the relative position refers to the positional relationship of the actuator relative to the mobile platform frame in the vertical direction; the trenching depth is the vertical distance from the cutting edge to the ground surface after the actuator cuts into the soil.

[0059] In some embodiments, dynamically adjusting the relative position of the actuator and the mobile platform based on the output thrust so that the position output is consistent with the position target value includes: The displacement sensor is used to detect the pressing depth of the actuator in real time; When it is detected that the deviation between the depression depth and the position target value exceeds a tolerance threshold, the readjustment of the output thrust is fed back.

[0060] In the embodiment of the present application, the displacement sensor is a device that can measure the position change of an object in real time, and is used to monitor the vertical movement distance of the actuator; the downward pressure depth is the actual depth to which the actuator cuts into the soil under the action of thrust; the tolerance threshold is the maximum deviation range allowed between the downward pressure depth and the preset position target value; and readjustment refers to readjusting the output thrust of the driving actuator according to the depth deviation.

[0061] First, a displacement sensor is installed at the connection between the actuator and the mobile platform. The sensor's measurement range covers the actuator's possible movement range (e.g., 0-20 cm), and the sampling frequency is set to 100 Hz to ensure real-time performance. During the seeding operation, the displacement sensor continuously detects the actuator's downward pressure and transmits this data to the control system. For example, the preset position target value is 6 cm, with a tolerance threshold of ±0.5 cm (determined through field trials to ensure that seedling emergence rate is not significantly affected).

[0062] When the displacement sensor detects a downward pressure depth of 6.7 cm, the calculated deviation from the target value is 0.7 cm, exceeding the tolerance threshold (0.5 cm). The control system feeds this deviation signal back to the thrust adjustment process, triggering a readjustment of the output thrust. If the deviation is positive (the depth is too deep), the output thrust of the actuator is proportionally reduced based on the deviation, for example, from the current 9.015 kN to 8.215 kN, reducing the actuator's earth pressure. If the detected downward pressure depth is 5.3 cm and the deviation is -0.7 cm (the depth is too shallow), the output thrust is proportionally increased, for example, from 7.815 kN to 8.615 kN, increasing the earth pressure until the downward pressure depth returns to within the range of 6 cm ± 0.5 cm.

[0063] In the embodiment of the present application, this step forms a complete closed-loop control by detecting depth deviation in real time and adjusting the thrust through feedback, ensuring that the trenching depth is not affected by terrain undulations and changes in soil resistance, and solving the depth fluctuation problem caused by the lack of precise feedback in traditional profiling mechanisms.

[0064] In the embodiments of this application, this step achieves dynamic correction of seeding depth through a closed-loop design combining depth detection and thrust readjustment. This real-time feedback mechanism rapidly responds to subtle changes in terrain and soil conditions, enabling the mobile platform to independently adapt to micro-topography and ultimately ensuring precise closed-loop control. By directly linking depth deviation to thrust adjustment, the control process is ensured to be both timely and accurate, further enhancing seeding depth stability.

[0065] like Figure 2 , which is a functional module diagram of a sowing depth compensation system based on terrain prediction provided by an embodiment of the present invention.

[0066] The terrain prediction-based seeding depth compensation system 100 of the present invention can be installed in an electronic device. Depending on the functionality implemented, the terrain prediction-based seeding depth compensation system 100 can include a terrain elevation data acquisition module 101, a displacement offset generation module 102, a compensation instruction generation module 103, a load disturbance value generation module 104, a thrust grading adjustment module 105, and a position output and position target value consistency adjustment module 106. The module of the present invention, which can also be referred to as a unit, refers to a series of computer program segments that can be executed by an electronic device processor and can perform fixed functions, and is stored in the memory of the electronic device.

[0067] In this embodiment, the functions of each module / unit are as follows: The terrain elevation data acquisition module 101 is used to obtain terrain elevation data of the front working area through the controlled object installed on the mobile platform; The displacement offset generating module 102 is configured to extract curvature variation characteristics of the terrain elevation data and convert the curvature variation characteristics into a vertical displacement offset of the actuator's touchdown point based on the actuator's structural parameters and travel speed; The compensation instruction generating module 103 is used to generate a displacement compensation instruction for driving the actuator in real time according to the vertical displacement offset and the preset position target value; The load disturbance value generating module 104 is configured to respond to the displacement compensation instruction, drive the driving actuator to output an initial thrust, and collect the load disturbance value of the actuator cutting edge in real time; The thrust graded adjustment module 105 is configured to grade and adjust the output thrust of the driving actuator according to the disturbance gradient when the load disturbance value exceeds a preset disturbance threshold range; The position output and the position target value consistency adjustment module 106 is used to dynamically adjust the relative position of the actuator and the mobile platform based on the output thrust to make the position output consistent with the position target value.

[0068] In the several embodiments provided by the present invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the module division is merely a logical function division, and other division methods may be used in actual implementation.

[0069] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0070] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0071] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0072] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A sowing depth compensation method based on terrain prediction, characterized in that: The method comprises: The controlled object installed on the mobile platform obtains the terrain elevation data of the front working area; Extracting curvature change characteristics of the terrain elevation data, and converting the curvature change characteristics into a vertical displacement offset of the actuator's touchdown point based on the actuator's structural parameters and travel speed; Generating a displacement compensation instruction for driving the actuator in real time according to the vertical displacement offset and the preset position target value; In response to the displacement compensation instruction, the driving actuator is driven to output an initial thrust, and a load disturbance value of the actuator cutting edge is collected in real time; When the load disturbance value exceeds a preset disturbance threshold range, the output thrust of the driving actuator is adjusted in stages according to the disturbance gradient; The relative position of the actuator and the mobile platform is dynamically adjusted based on the output thrust so that the position output is consistent with the position target value.

2. The method for compensating sowing depth based on terrain prediction according to claim 1, wherein: The method of obtaining terrain elevation data of the front working area by the controlled object installed on the mobile platform includes: A laser rangefinder is used to scan the working area in front of the mobile platform, and the scanned point cloud data is converted into terrain elevation data.

3. The method for compensating sowing depth based on terrain prediction according to claim 1, wherein: The step of extracting curvature change characteristics of the terrain elevation data includes: Calculate the slope change rate between adjacent terrain elevation data points; generating a sequence of terrain curvature radii according to the slope change rate; The mutation points in the curvature radius sequence are extracted as curvature change features.

4. The method for compensating sowing depth based on terrain prediction according to claim 1, wherein: The structural parameters include an action surface inclination angle and a mass inertia parameter, wherein the action surface inclination angle is measured in real time by an angle sensor, and the mass inertia parameter is pre-set through a calibration test.

5. The method for compensating sowing depth based on terrain prediction according to claim 4, wherein: The step of converting the curvature change characteristic into a vertical displacement offset of the actuator's contact point based on the actuator's structural parameters and travel speed includes: calculating a response lag time of the actuator based on a travel speed of the actuator; performing soil cutting resistance phase compensation on the curvature variation characteristic according to the response lag time and the inclination angle of the action surface to generate a compensated curvature characteristic value; The compensated curvature characteristic value is multiplied by the mass inertia parameter to generate a vertical displacement offset of the actuator touchdown point.

6. The method for compensating sowing depth based on terrain prediction according to claim 1, wherein: Generating a displacement compensation instruction for driving the actuator in real time according to the vertical displacement offset and the preset position target value includes: Adding the vertical displacement offset to the reference stroke value corresponding to the position target value to generate a compensation stroke value for driving the actuator; A PWM control signal for driving the hydraulic proportional valve is generated according to the compensation stroke value, which serves as a displacement compensation instruction for driving the actuator.

7. The method for compensating sowing depth based on terrain prediction according to claim 6, wherein: The preset position target value is determined by selecting a reference depth interval according to the type of the work object, adjusting the reference depth interval based on a field calibration test, and generating a position target value.

8. The method for compensating sowing depth based on terrain prediction according to claim 1, wherein: When the load disturbance value exceeds a preset disturbance threshold range, adjusting the output thrust of the driving actuator in stages according to the disturbance gradient includes: Measure the load disturbance extreme values ​​in the hard rocky area and the soft pit area, and divide the disturbance threshold interval according to the load disturbance extreme value distribution; When the load disturbance value enters the hard soil area, the output thrust is increased according to a linear increasing function; When the load disturbance value enters the soft soil area, the output thrust is reduced according to a step-down function.

9. The method for compensating sowing depth based on terrain prediction according to claim 1, wherein: The dynamically adjusting the relative position of the actuator and the mobile platform based on the output thrust so that the position output is consistent with the position target value includes: The displacement sensor is used to detect the pressing depth of the actuator in real time; When it is detected that the deviation between the depression depth and the position target value exceeds a tolerance threshold, the readjustment of the output thrust is fed back.

10. A sowing depth compensation system based on terrain prediction, characterized in that: The system comprises: A terrain elevation data acquisition module is used to obtain terrain elevation data of the front working area through a controlled object installed on a mobile platform; a displacement offset generating module, configured to extract curvature variation characteristics of the terrain elevation data and convert the curvature variation characteristics into a vertical displacement offset of the actuator's touchdown point based on the actuator's structural parameters and travel speed; A compensation instruction generating module, configured to generate a displacement compensation instruction for driving the actuator in real time according to the vertical displacement offset and the preset position target value; a load disturbance value generating module, configured to respond to the displacement compensation instruction, drive the driving actuator to output an initial thrust, and collect the load disturbance value of the actuator cutting edge in real time; A thrust graded adjustment module, configured to grade and adjust the output thrust of the drive actuator according to a disturbance gradient when the load disturbance value exceeds a preset disturbance threshold range; The position output and the position target value consistency adjustment module is used to dynamically adjust the relative position of the actuator and the mobile platform based on the output thrust so that the position output is consistent with the position target value.

Images