Digitally adjustable bale press cotton picker
By integrating onboard sensors, a machine-cloud management platform, and a fuzzy PID control system, real-time closed-loop intelligent control of cotton harvesters has been achieved, solving the problem of relying on driver experience in existing technologies and improving the stability and efficiency of the harvesting process.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHIHEZI UNIVERSITY
- Filing Date
- 2026-03-13
- Publication Date
- 2026-06-09
AI Technical Summary
Existing cotton harvesters rely heavily on the driver's experience for adjusting operating parameters, lacking intelligent decision-making and closed-loop control based on real-time operating data. This makes it difficult to maintain optimal conditions during the harvesting process, affecting operational efficiency and the consistency of cotton quality.
By employing vehicle-mounted sensors, a "machine-cloud" management platform, and a fuzzy PID control system, a real-time multi-parameter perception, cloud-based data collaboration, and intelligent adjustment of operational parameters are achieved, thus constructing a real-time closed-loop intelligent control system encompassing perception, decision-making, and execution.
It significantly improves the stability, harvesting efficiency, and intelligence level of cotton harvesters, ensuring efficient and high-quality cotton harvesting.
Smart Images

Figure CN122162608A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent control of agricultural machinery, and in particular to a digitally adjustable baling cotton harvester. Background Technology
[0002] Cotton, as an important economic crop, has achieved large-scale mechanized harvesting in major producing areas such as Xinjiang, with machine-harvested cotton accounting for over 90%. However, existing cotton harvesters still heavily rely on driver experience for adjusting operating parameters and lack intelligent decision-making and closed-loop control mechanisms based on real-time operating data. This makes it difficult to maintain optimal conditions throughout the harvesting process, affecting operational efficiency and the consistency of cotton quality.
[0003] In the existing technology, although some patents have attempted to solve the above problems, such as patent CN114486880B which proposes an integrated detection device for moisture regain and impurity content on a cotton harvester vehicle, and patent CN117465780A which discloses an active control method for the weight of cotton bales in a baling cotton harvester, neither of them has achieved integrated real-time monitoring of the field working environment, cotton harvester operating parameters and cotton harvesting quality, nor has it formed a closed-loop linkage with the cotton harvester control system.
[0004] In summary, existing cotton harvesters still have significant shortcomings in terms of operational stability, harvesting efficiency, and overall intelligence level. There is an urgent need for a baling cotton harvester system that can achieve real-time perception of multiple parameters, cloud-based data collaboration, and intelligent adjustment of operational parameters to improve the overall intelligence level and quality control capabilities of harvesting operations. Summary of the Invention
[0005] The purpose of this invention is to provide a digitally adjustable baling cotton harvester that can adaptively adjust its operating status according to actual harvesting conditions, thereby improving the stability, harvesting efficiency, and overall intelligence level of the cotton harvester, and achieving efficient and high-quality cotton harvesting.
[0006] To achieve the above objectives, the present invention provides the following solution: A digitally adjustable baling cotton harvester includes the harvester itself, an onboard sensor, a machine-to-cloud management platform, and a fuzzy PID control system mounted on the harvester. The onboard sensor collects data on the harvester's field operating environment, operating parameters, and key parameters related to cotton harvesting quality. The machine-to-cloud management platform receives and stores data from the industrial control computer and supports remote monitoring and quality traceability. The fuzzy PID control system automatically adjusts the harvester's operating parameters according to control commands from the industrial control computer.
[0007] Furthermore, the "machine-cloud" management platform also has data storage and analysis functions, which can learn from historical harvesting data, establish a correlation model between harvesting quality and operating parameters, and dynamically recommend the optimal combination of operating parameters based on the current cotton field environment and cotton status.
[0008] Furthermore, the fuzzy PID control system also includes a drive module that is compatible with the electro-hydraulic proportional valve and the electric regulating valve. The drive module receives control signals from the industrial control computer and converts them into corresponding current or voltage outputs to achieve precise driving of the actuator.
[0009] Furthermore, the harvesting site monitoring camera can capture the distribution of cotton plants in front of the cotton harvester in real time, and use image recognition technology to determine the cotton plant density and boll opening, providing a visual basis for adjusting the travel speed and harvesting head height.
[0010] Furthermore, the moisture regain detection sensor uses the resistance method to measure the moisture content of seed cotton with temperature and pressure compensation, and uploads the data to the cloud in real time to support real-time monitoring and early warning of moisture regain during the harvesting process.
[0011] Furthermore, the impurity detection camera is equipped with a supplementary light and a dust cover, which can still stably capture cotton flow images in working environments with insufficient light or high dust levels. The impurity content of the seed cotton is calculated in real time through image processing algorithms and fed back to the control system.
[0012] Furthermore, the locator is a Beidou positioning module, which can achieve centimeter-level positioning accuracy. Combined with a geographic information system, it can draw the cotton harvester's operating trajectory and cotton field harvesting progress map in real time.
[0013] Furthermore, the pressure sensor is installed on the hydraulic cylinder of the cotton picking machine's cotton support frame. The sensor converts the minute deformation of the elastic element inside the sensor into a recognizable electrical signal through a circuit and transmits it to the industrial control computer. After processing, accurate hydraulic pressure data is obtained for subsequent cotton bale weight calculation.
[0014] Furthermore, the vehicle-mounted barcode scanner is specifically installed above the packing film extraction mechanism at the rear of the cotton harvester's packing box. Its scanning angle is directly facing the cotton bale forming station, and it is used to automatically scan the QR code label of the cotton bale during the packing process to associate and record the identity information of the cotton bale.
[0015] Furthermore, the cotton bale identification information associated with the QR code label includes at least the harvest time, geographical coordinates, impurity content of seed cotton, moisture regain of seed cotton, and information about the plot to which it belongs.
[0016] Furthermore, the transmission layer adopts a dual-link redundancy design of 5G and 4G to ensure reliable data upload and real-time command delivery even in areas with unstable signals.
[0017] Furthermore, in the fuzzy PID control algorithm, the fuzzy inference module dynamically adjusts the proportional, integral, and derivative parameters of the PID controller based on real-time data fed back from the harvesting site monitoring camera, moisture regain sensor, and impurity content camera, thereby achieving adaptive and coordinated control of multiple variables such as harvesting head height, travel speed, and drum negative pressure.
[0018] Furthermore, the system is equipped with a manual / automatic switching function, allowing the driver to switch control modes at any time according to operational needs. In automatic mode, the system intelligently adjusts the parameters, while in manual mode, the driver can directly intervene in key parameters based on experience.
[0019] Furthermore, the "machine-cloud" management platform provides a visual monitoring interface, which supports real-time viewing of sensor data, operating parameters, cotton bale quality information and system alarm status on vehicle-mounted displays or remote terminals, and has data export and report generation functions.
[0020] The present invention achieves the following technical effects compared to the prior art: This invention, based on traditional cotton harvesters, integrates three parts: on-board sensors, a machine-cloud management platform, and a fuzzy PID control system, to construct a real-time closed-loop intelligent control system encompassing "perception-decision-execution." This invention achieves adaptive dynamic optimization of key operating parameters of the cotton harvester, significantly improving operational stability, harvesting efficiency, and intelligence, thereby ensuring efficient and high-quality cotton harvesting. Attached Figure Description
[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0022] Figure 1 This is a flowchart of the control process of the present invention; Figure 2 This is a schematic diagram of the structure of the present invention; Figure 3 This is a process flowchart of the "machine-cloud" management platform of the present invention.
[0023] 1. Laser rangefinder; 2. Electro-hydraulic proportional valve I; 3. Harvesting site monitoring camera; 4. Positioner; 5. Vehicle-mounted display; 6. Industrial computer; 7. Photoelectric sensor; 8. Electric regulating valve; 9. Vehicle-mounted barcode scanner; 10. Cleanliness camera; 11. Impurity detection camera; 12. Pressure sensor; 13. Moisture regain detection sensor; 14. Electro-hydraulic proportional valve II; 15. Differential pressure sensor Detailed Implementation
[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0025] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0026] refer to Figure 1 The vehicle-mounted sensing device includes a moisture regain detection sensor installed on the inner plate of the packing cavity of the cotton harvester, a impurity detection camera installed on the cotton support frame of the cotton harvester, a cleanliness camera installed behind the packing box of the cotton harvester, a pressure sensor installed on the hydraulic cylinder of the cotton support frame of the cotton harvester, a rotary encoder installed on the sprocket inside the packing cavity, a laser rangefinder installed on the cotton harvesting head of the cotton harvester, a locator installed on the roof of the cotton harvester, a differential pressure sensor installed in the air duct of the cotton harvesting head, a vehicle-mounted barcode scanner installed above the packing film extraction mechanism of the cotton harvester, an industrial control computer installed next to the driver's seat in the cab of the cotton harvester, and a vehicle-mounted display installed below the control area in the cab of the cotton harvester. refer to Figure 2 A digitally adjustable baling cotton harvester includes a baling cotton harvester, an on-board sensing device, a machine-cloud management platform, and a fuzzy PID control system installed on the baling cotton harvester.
[0027] refer to Figure 3 The machine-cloud management platform includes a terminal layer, a transmission layer, and a cloud layer in the intelligent system of the digitally adjustable baling cotton harvester. All vehicle-mounted sensors communicate with the industrial control computer via wired or wireless means. The industrial control computer then transmits the data to the cloud platform through the communication network for in-depth analysis and storage, enabling data integration and remote uploading.
[0028] The specific workflow of this invention is as follows: The workflow of this invention begins with the system's power-on self-test. Operators can preset basic operating parameters through the human-machine interface, such as the moisture regain, impurity content, plot type, and crop density estimation of the target cotton. Based on these preset parameters, the control system calls upon the built-in database to provide initial values for the membership function, fuzzy rule base, and initial PID parameters (Kp0, Ki0, Kd0) in the fuzzy PID controller. This ensures that the system can quickly reach a near-optimal operating starting point, rather than adaptively starting from zero.
[0029] During operation, the system collects data from multiple sensors in real time. The industrial control computer filters, fuses, and extracts features from the data to calculate the input variables for fuzzy PID control.
[0030] (1) Install and arrange the harvesting site monitoring camera, harvesting rate camera, locator, engine speed sensor, fuel consumption sensor, mileage sensor, industrial control computer, vehicle display, moisture regain detection sensor, impurity content detection camera, pressure sensor, laser rangefinder, photoelectric sensor, differential pressure sensor, and vehicle barcode scanner; and connect them to the industrial control computer through the line, and start the cotton harvester engine to power on the industrial control computer.
[0031] When the locator transmits the current geographical location to the industrial control computer, it searches the network for information such as the current location's time, weather, and air humidity. The industrial control computer then controls a relay via a digital output module. The relay is connected in series in the cotton harvester's starting circuit. When the conditions are met, the relay engages, activating the starting circuit. The machine is only allowed to start when the daytime humidity is ≤60%, avoiding losses caused by night harvesting or open-air harvesting, which can lead to a decrease in cotton quality, an increase in impurity content, increased machine malfunction risk, and safety hazards.
[0032] (2) Install and arrange laser rangefinder sensors and electro-hydraulic proportional valve I for controlling the height of the mining head.
[0033] After receiving the head height data, the industrial control computer uses the height deviation e_h and its rate of change ec_h as input to the fuzzy PID controller in the head height control loop. The fuzzy inference engine makes decisions based on preset fuzzy rules, and corrects the proportional, integral, and derivative parameters (ΔKp, ΔKi, ΔKd) of the PID controller online in real time. Unlike the fixed parameters of traditional PID controllers, this invention can dynamically adjust the controller's response speed and damping characteristics through fuzzy logic when the ground is uneven. When encountering a steep slope (large e_h, large ec_h), the controller will rapidly increase Kp and Kd, generating a fast and powerful lifting action to prevent head collision; in flat areas, it maintains a small Kp and an appropriate Ki, achieving smooth fine-tuning and avoiding system oscillation. This achieves terrain tracking, significantly reducing missed harvesting and damage to cotton plants.
[0034] Connect an electro-hydraulic proportional valve in parallel with the existing manual hydraulic control valve. This valve can proportionally control the flow and direction of the hydraulic oil based on the PWM signal sent by the controller, thereby precisely controlling the speed and position of the lifting cylinder.
[0035] (3) Install and arrange the speed control electro-hydraulic proportional valve II.
[0036] When machine vision detects sparse cotton plants ahead, even if the current cotton flow rate is normal, fuzzy rules will predictively issue a moderate acceleration instruction. This is achieved by adjusting PID parameters to guide positive output, thus maintaining consistently high-efficiency operation. Conversely, when entering a dense area or when the cotton flow rate surges, indicating a risk of blockage, the system will intelligently reduce speed to ensure harvesting efficiency and prevent roller blockage. This process works in conjunction with the head height and negative pressure adjustment: during speed reduction, the system can correspondingly fine-tune and lower the head height and negative pressure to accommodate more precise harvesting; during acceleration, the head height and negative pressure are appropriately increased to ensure harvesting efficiency. This multi-variable coordination is key to improving the overall harvesting efficiency of this invention.
[0037] The above method is achieved by controlling the hydraulic speed control system of the cotton harvester. The controller sends the calculated speed command to the hydraulic proportional valve, thereby precisely controlling the speed of the travel motor.
[0038] (4) Install differential pressure sensors and electric regulating valves for adjusting the negative pressure of the drum.
[0039] If the cotton harvesting rate is too low or the impurity content is too high, the cotton harvester automatically adjusts the negative pressure of the rollers. The airflow generated by the negative pressure of the rollers is responsible for sucking the cotton on the cotton plants towards the picking spindle, where it is picked. If the negative pressure is insufficient, the airflow suction is not strong enough, and the cotton cannot be effectively adsorbed and picked, resulting in a large amount of cotton remaining on the cotton plants or falling to the ground, causing direct economic losses. Once the sensor detects an abnormally low negative pressure, the system will immediately remind the operator to check and clean any blockages (such as the cotton picking head outlet, pipe bends, etc.). When the industrial control computer receives a signal that the negative pressure is too high, it will send a signal to the electric regulating valve. The valve motor will rotate, causing the valve plate to close slightly, reducing the air intake and thus lowering the negative pressure. Conversely, when the negative pressure is insufficient, the valve plate will open wider, increasing the air intake and increasing the suction.
[0040] When the system determines that the risk of blockage is increasing through fuzzy logic, even if the current negative pressure deviation is very small, the controller will actively and slightly reduce the target negative pressure or increase the integral action to effectively draw the cotton toward the picking spindle in order to resolve potential blockages, rather than waiting until the blockage is complete before taking drastic action.
[0041] (5) The pressure of the hydraulic cylinder under the cotton picker frame is obtained by the pressure sensor, and the weight of the cotton bale is calculated by the controller in combination with the weight of the cotton picker frame and the tilt angle of the cylinder, etc., according to the preset formula; the impurity detection camera is automatically triggered according to the program to obtain the impurity image on the side of the cotton bale; at the same time, the moisture regain detection sensor is used to obtain the moisture regain information of the seed cotton by squeezing the moisture regain detection sensor with the moving seed cotton.
[0042] (6) At the same time, during the entire cotton harvesting process, the data other than the cotton bale information in the above information will be uploaded to the cloud server on a regular basis to provide data support for the subsequent cotton quality traceability information process.
[0043] Specific examples have been used to illustrate the principles and implementation methods of this invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this invention. Furthermore, those skilled in the art will recognize that, based on the ideas of this invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this invention.
[0044] Example 1: Joint control of head height and negative pressure based on real-time impurity content When the machine vision system detects that the impurity content of the cotton flow is >11%, the head height adjustment mechanism responds immediately. According to the fuzzy PID controller, the head height is increased by 3cm-18cm from the standard operation of 14-16cm to reduce the picking up of impurities on the ground. At the same time, the negative pressure of the fan is reduced to reduce the suction force on light impurities. This coordinated strategy successfully suppresses the impurity content and restores it to the qualified level of 11% within a 60-meter travel distance.
[0045] Example 2: Closed-loop feedback and travel speed regulation based on cotton flow anomalies During the packing process, the control system monitors in real time through photoelectric sensors and estimates the current weight of the cotton bale to be 1950kg, which is significantly lower than the target weight of 2200kg and exceeds the tolerance range. The system immediately judges this anomaly as insufficient feeding due to local sparse cotton plants and triggers the control mechanism: based on the weight deviation value, the fuzzy PID controller instantly reduces the travel speed to increase the harvest per unit area. This adjustment allows the weight of the subsequent cotton bale to return to the normal trajectory of 2150kg in the middle of the forming process, ensuring that the final bale weight meets the standard.
[0046] Example 3: Coordinated Control of Travel Speed and Negative Pressure Based on Real-Time Moisture Regain Rate After the locator collects the current location information, it automatically locks the machine and stops supplying power to the picking head if it is nighttime or rainy. When the moisture regain detection sensor detects that the cotton moisture regain exceeds the preset upper limit of 10%, the fuzzy PID controller decides to output a control quantity based on this deviation. On the one hand, it reduces the cotton harvester's travel speed to increase the effective drying time of the cotton on the plant; on the other hand, it increases the negative pressure of the rollers to enhance the adsorption force and overcome the adhesion of wet cotton. After this adjustment, the moisture regain drops and stabilizes within the normal range of less than 10% within about 90 seconds.
[0047] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A digitally adjustable baling cotton harvester, characterized in that, It includes a baling cotton harvester, an on-board sensing device installed on the baling cotton harvester, a "machine-cloud" management platform, and a fuzzy PID control system. The vehicle-mounted sensing device is responsible for integrated real-time monitoring of the field working environment, cotton harvester operating parameters, and cotton harvesting quality. The "machine-cloud" management platform performs multi-source transmission and integrated calculations on the data obtained by the vehicle-mounted sensing device to generate real-time control schemes for key operating parameters such as harvester head height, travel speed, and roller negative pressure. The fuzzy PID control system, based on the control scheme generated by the vehicle-mounted sensing device, realizes dynamic and precise adjustment of cotton harvester operating parameters, forming a closed-loop control system integrating "perception-decision-execution".
2. The vehicle-mounted sensing device according to claim 1, characterized in that, The cotton harvester is equipped with the following devices for monitoring the field working environment: a harvest site monitoring camera, a harvesting rate camera, and a locator; The cotton harvester is equipped with the following devices for monitoring its operating parameters: engine speed sensor, fuel consumption sensor, mileage sensor, industrial control computer, and vehicle-mounted display. The cotton harvester is equipped with an integrated real-time monitoring device for cotton harvesting quality, which includes: a moisture regain detection sensor, a dirt content detection camera, a pressure sensor, a laser rangefinder, a photoelectric sensor, a differential pressure sensor, and a vehicle-mounted barcode scanner.
3. The "machine-cloud" management platform according to claim 1 includes a terminal layer, a transmission layer, and a cloud layer in the intelligent system of the digitally adjustable baling cotton harvester.
4. The fuzzy PID control system according to claim 1 includes an electro-hydraulic proportional valve and an electric regulating valve installed in the control system of the digitally adjustable baling cotton harvester.
5. The vehicle-mounted sensing device according to claim 2, characterized in that: A harvesting site monitoring camera for acquiring images of the harvesting site is installed on the top outside the cab of the cotton harvester. A camera used to obtain the cotton harvesting rate in cotton fields is installed at the rear of the cotton harvester's packing box; A locator used to obtain the geographical location information of the cotton harvester and the vehicle speed is installed at the rear end of the monitoring camera at the cotton harvesting site. The engine speed sensor, fuel consumption sensor, and mileage sensor used to collect operating status data of the cotton harvester are installed inside the vehicle. An industrial control computer used to collect and preprocess data from various sensors is installed in the cab of the cotton harvester. An on-board display for real-time display of cotton harvester operating parameters, sensor data and control status is installed in the cab of the cotton harvester. A moisture regain detection sensor for acquiring seed cotton moisture regain information is installed inside the packing box of the cotton harvester; A camera for detecting the impurity content of cotton is installed in a fixed housing on the cotton picker's support frame. A weighing module for obtaining the weight of cotton bales from a cotton harvester includes a pressure sensor and is installed on the hydraulic cylinder of the cotton harvester's cotton support frame. A laser rangefinder sensor for obtaining the height of the picking head of a cotton harvester is installed on both sides of the picking head of the cotton harvester. A photoelectric sensor is used to monitor the changes in light flux below the cotton harvesting drum in real time, thereby monitoring the cotton flow rate in the cotton conveying pipe. Combined with a positioner, a cotton flow distribution map can be generated. To prevent blockage, it is installed inside the air duct of the cotton harvester. A differential pressure sensor for acquiring negative pressure information of the cotton harvester drum is installed on the harvesting head air duct near the air inlet of the cotton harvester fan. A vehicle-mounted barcode scanner, used to scan the QR code on the cotton bale film to associate it with the cotton bale's identity information, is installed above the packing film extraction mechanism at the rear of the cotton harvester's packing box.
6. The "machine-cloud" management platform according to claim 3, characterized in that: Terminal layer: Integrated into the industrial control computer of the cotton harvester, used to collect and preprocess the raw data collected by each sensor in the vehicle-mounted sensing system. The preprocessing includes at least data filtering, format unification and data packaging. Transmission layer: Using a 5G wireless communication module, the operation parameters, environmental data and multi-source cotton quality data preprocessed by the terminal layer are uploaded to the cloud layer in real time; Cloud layer: Deployed on a cloud server, it receives and stores all data from the transport layer, including operation parameters, environmental data, and multi-source data on cotton quality; it correlates information such as moisture regain, impurity content, cleanliness, and geographical location, and performs real-time analysis based on historical data models to obtain various status indicators and performance parameters of the cotton harvester, and generates a visual management interface.
7. The fuzzy PID control system according to claim 4, characterized in that, Receive decision parameters from the cloud layer (desired picking height, appropriate travel speed, negative pressure of the pneumatic conveying system in the drum area), calculate how the hydraulic system needs to act by running a fuzzy PID control algorithm, and amplify the signal through the drive circuit to provide sufficient current and voltage to achieve automatic adjustment of the picking head height, vehicle travel speed, and drum negative pressure.