Electric control suspension system of electric tractor and suspension height control method thereof
Through electric suspension system and digital twin technology, combined with multi-factor intelligent control, the problem of insufficient response speed and accuracy of traditional hydraulic tractor suspension systems is solved, and the precise adjustment of the suspension height of electric tractors is realized and the energy consumption optimization is optimized, which improves the quality and efficiency of operation .
Patent Information
- Application Number
- CN202411246213.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-09-06
AI Technical Summary
The traditional hydraulic tractor suspension system has shortcomings in response speed and accuracy, making it difficult to achieve precise control, and the complex structure increases cost and failure rate, making it difficult to directly apply to electric tractors.
Using electric suspension system, using electric push rods to drive the suspension mechanism, combined with digital twin technology, and based on multi-factor intelligent control method, the precise adjustment of suspension height and energy is achieved through GPS positioning, magnetostrictive displacement sensors and pin force sensors. Consumption optimization.
It realizes more efficient energy utilization, faster response speed and higher accuracy suspension height control, reduces maintenance costs and improves operation quality and efficiency.
Smart Images

Figure CN118927895A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of electric tractors, and in particular relates to an electric-controlled suspension system for an electric tractor and a suspension height control method thereof. Background Art
[0002] Electric tractors have opened up new paths for the development of green agricultural machinery technology and will play a vital role in future agricultural production. The suspension system of traditional fuel tractors is usually controlled by hydraulics. Due to the limited response speed and accuracy of hydraulic components, it is difficult to achieve precise control of the suspension system. At the same time, the structure of the hydraulic suspension system is relatively complex and requires a large number of hydraulic components and pipelines, which not only increases the manufacturing cost, but also increases the failure rate and maintenance cost of the system. These shortcomings make it difficult to directly apply the hydraulic suspension system to electric tractors.
[0003] Electric tractors have unique advantages when using electric suspension systems. The electric suspension system relies on the electric tractor's power battery pack to provide energy, does not require an additional hydraulic system, and also reduces system redundancy and complexity. The lifting force of the electric suspension system is provided by a separate power element, which is not coupled with the drive system, so it will not affect the tractor's traction during operation. The electric suspension system can also achieve faster response speed, making the adjustment speed of the mounted agricultural implements faster and smoother, and there is no noise during movement.
[0004] At present, the most commonly used tillage depth control methods of tractor suspension systems include position adjustment, force adjustment and force-position combined adjustment. Affected by many factors, the electric suspension system is a complex nonlinear system. In the actual tillage process, factors such as tillage position, tillage resistance, soil moisture, ambient temperature, soil type, equipment parameters and performance will affect the work quality and efficiency. In this case, the traditional force and position adjustment methods cannot effectively guarantee the work quality. Therefore, combined with the excellent response speed of the electronically controlled suspension system, it is urgent to develop an intelligent suspension height control method that comprehensively considers multiple factors. Summary of the invention
[0005] In view of the shortcomings of the prior art, the present invention provides an electric tractor electronically controlled suspension system and a suspension height control method thereof. The electronically controlled suspension system of the present invention has a compact structure and high reliability, and adopts an electric push rod to drive the suspension mechanism. For the new electronically controlled suspension system, an intelligent suspension height control method based on digital twins is designed to comprehensively consider multiple factors. The existing tractor suspension system overcomes the problems of high energy consumption, poor impact strength, high failure rate, and poor operation quality and agronomic level caused by poor tillage depth and position during farming.
[0006] In order to achieve the above object, the present invention provides the following technical solutions:
[0007] An electric controlled suspension system for an electric tractor, wherein the electric controlled suspension system comprises a low voltage servo motor 1, a lower enclosure plate 2, a frame 3, an upper enclosure plate 4, a first cylindrical pin 5, an electric push rod 6, an "L" shaped sliding frame 7, a diagonal tie rod 8, a connecting pin 9, a suspension frame 10, a GPS locator 11, a main controller 12, a tillage depth controller 13, an electric push rod driver 14, a second cylindrical pin 15, a connecting pin 16, a pin shaft force sensor 17 and a speed reduction mechanism 18;
[0008] The frame 3 is a rectangular frame structure, including a left column and a right column arranged on the left and right sides, and a top plate arranged between the upper ends of the left column and the right column;
[0009] The "L"-shaped sliding frame 7 includes a bottom rectangular frame, a left vertical beam and a right vertical beam, wherein the bottom rectangular frame includes a front beam, a rear beam, a left vertical beam and a right vertical beam; the left vertical beam and the right vertical beam are perpendicular to the bottom rectangular frame and extend upward, and the bottoms of the left vertical beam and the right vertical beam are connected to the rear ends of the left vertical beam and the right vertical beam; the front ends of the left vertical beam and the right vertical beam are connected to the lower end of the suspension frame 10;
[0010] The upper ends of the two inclined rods 8 are connected to the upper end of the suspension frame 10 through the connecting pin 9, and the lower ends of the two inclined rods 8 are respectively hinged to the rear parts of the left beam and the right beam of the "L"-shaped sliding frame 7 through the connecting pin 16; the pin shaft force sensor 17 is arranged at the connection between the left beam and the right beam of the "L"-shaped sliding frame 7 and the suspension frame 10;
[0011] The upper end of the electric push rod 6 is hinged to the top plate of the frame 3 through the first cylindrical pin 5, and the lower end of the electric push rod 6 is hinged to the rear beam of the "L"-shaped sliding frame 7 through the second cylindrical pin 15;
[0012] The electric push rod 6 has a built-in magnetostrictive displacement sensor 23;
[0013] The lower baffle plate 2 is located in front of the frame 3 and is connected to the left and right columns of the frame 3 respectively; the upper baffle plate 4 is located in front of the frame 3 and is connected to the left and right columns of the frame 3 respectively; the upper baffle plate 4 is located above the lower baffle plate 2;
[0014] The left and right vertical beams of the "L"-shaped sliding frame 7 are located between the left and right vertical columns of the frame 3 and the lower and upper enclosure plates 2 and 4;
[0015] The low voltage servo motor 1, the speed reduction mechanism 18 and the vehicle frame 3 are connected in sequence;
[0016] The GPS locator 11 is installed on the vehicle body and connected to the main controller 12 via a cable;
[0017] The main controller 12 collects data from the GPS locator 11, the magnetostrictive displacement sensor 23 built into the electric push rod 6, and the pin force sensor 17 through a dedicated signal line to obtain the tillage position and the current status information of the electric control suspension system;
[0018] The data transceiver device 24 is connected to the main controller 12; the data transceiver device 24 remotely transmits and receives the data collected by the main controller 12;
[0019] The main controller 12 , the tillage depth controller 13 , the electric push rod driver 14 are connected to the electric push rod 6 in sequence.
[0020] The electronically controlled suspension system further comprises a long nylon pad 19 and a short nylon pad 22 ; the long nylon pad 19 is fixed to the front surface of the left and right pillars of the frame 3 ; the short nylon pad 22 is fixed to the rear surface of the lower enclosure plate 2 and the upper enclosure plate 4 .
[0021] Among them, the electronically controlled suspension system also includes a bent plate 20 and a rolling bearing 21; the bent plate 20 is fixed on the left and right columns of the frame 3, and the rolling bearing 21 is installed on the bent plate 20; the bearing 21 contacts the left and right beams of the "L"-shaped sliding frame 7, playing a guiding and limiting role, ensuring that the "L"-shaped sliding frame 7 is smoothly lifted and lowered in the vertical direction.
[0022] The extension and retraction of the electric push rod 6 can drive the "L"-shaped sliding frame 7 to achieve lifting within a range of 37 cm.
[0023] A suspension height control method for an electric tractor electronically controlled suspension system, wherein the method comprises the following steps:
[0024] Step S1: Establish a digital twin system, which includes an electronically controlled suspension system, farmland monitoring equipment, a digital twin, twin data, a digital twin service platform, and connections between various parts of the digital twin system;
[0025] The electric control suspension system includes a magnetostrictive displacement sensor 23 built into the electric push rod 6, a GPS locator 11, a pin force sensor 17, the electric push rod 6 as a suspension height actuator, and a data transceiver device 24;
[0026] The GPS locator 11 can measure the tractor position information and tillage position; the pin force sensor 17 can measure tillage resistance; the electric push rod 6 can perform lifting and lowering actions; the data transceiver device 24 can complete the remote transmission and reception of information;
[0027] The farmland monitoring equipment collects weather condition information and soil information in real time, and transmits the weather condition information and soil information to the digital twin service platform;
[0028] The weather condition information includes rain, snow and temperature;
[0029] The soil information includes soil moisture, soil temperature, soil type and soil hardness;
[0030] The digital twin is a dynamic simulation model of the plowing process built in the server;
[0031] Based on the real-time status information of the electric tractor and its suspension system, the collected weather conditions and soil information, the digital twin is driven to run synchronously in the virtual world. The digital twin simulates and generates dynamics and soil model data, and supports data query and status review.
[0032] Twin data is a collection of historical data and real-time data generated by the electronically controlled suspension system, digital twin, and digital twin service: including the tillage depth data measured by the magnetostrictive displacement sensor 23 built into the electric push rod 6, the geographic location information provided by the GPS locator 11, the force data obtained by the pin force sensor 17, and the dynamics and soil model data simulated by the digital twin. These data are fused and stored in the server for subsequent analysis and decision-making;
[0033] The pin pressure measured by the pin force sensor 17 is converted into the tillage resistance of the electric tractor in real time; the displacement signal of the magnetostrictive displacement sensor 23 built into the electric push rod 6 is converted into the tillage depth in real time;
[0034] The digital twin service platform runs on the server and can provide real-time monitoring and data collection functions, prediction and simulation functions, and support remote monitoring and management;
[0035] The connection between the various parts of the digital twin system is completed through TCP / IP and MQTT protocols;
[0036] Step S2: Suspension height control: Based on the historical weather condition information, soil information, and tillage depth data collected and recorded in step S1, an online control problem model of the electronically controlled suspension system is established, and the optimal tillage depth is obtained by training with a deep deterministic policy gradient algorithm. The suspension height of the electric tractor's electronically controlled suspension system is set to the tillage depth, thereby achieving a control strategy with consistent tillage depth and low energy consumption.
[0037] Step S2.1: Establishing the control strategy model of the electronically controlled suspension system
[0038] The online control problem model of the electronically controlled suspension system is established as follows:
[0039] s t =[xy FrθT S lv] Formula 1
[0040] a t =[h] Formula 2
[0041] In formula 1 and formula 2, s t is the state observation at time t; a t is the action amount at time t; x and y are the horizontal and vertical coordinates of the tillage position at the current moment in the geodetic coordinate system, in m; Fr is the current tillage resistance, in N; θ is the soil moisture, in %mass; T is the soil temperature, in ℃; S is the soil type; l is the current tillage depth, in cm, which is an important constraint in suspension control; v is the current vehicle speed, in m / s; h is the current suspension lifting height, in cm;
[0042] Step S2.2: Use the deep deterministic policy gradient algorithm to train the electronic suspension system control strategy model established in step S2.1
[0043] The deep deterministic policy gradient algorithm adopts a dual-network mode. Both the Actor network and the Critic network are equipped with a target network with the same structure. Therefore, there are four networks in the deep deterministic policy gradient algorithm. The existence of the target network reduces the fluctuation of network parameters, makes the learning process more stable, and makes the model easier to converge.
[0044] Step S2.3: Set the reward function to evaluate the performance of the electronic suspension system control strategy model trained in step S2.2
[0045] The reward variable R is used to evaluate the characteristics of the electronically controlled suspension system and establish the reward function:
[0046] R=[lv] Formula 3
[0047] In Formula 3, R is the reward variable; l is the tillage depth in cm, which is an important constraint in suspension control; v is the vehicle speed in m / s;
[0048] The immediate reward function is expressed as follows:
[0049] r=-(k1|l-l0| 2 +k2|v-v0| 2 ) Formula 4
[0050] In formula 4, r is the immediate reward; k1 and k2 are the weight coefficients of tillage depth and vehicle speed respectively; l is the expected tillage depth, in cm; l0 is the target tillage depth, in cm; v is the expected vehicle speed, in m / s; v0 is the target vehicle speed, in m / s;
[0051] The model is trained using the historical weather condition information, soil information, and tillage depth data collected and recorded in step S1. During the training process, the model learns the optimal suspension height control strategy through interaction with the digital twin system to maximize the cumulative reward of the reward function.
[0052] Step S2.4: setting the suspension height of the electric tractor's electronically controlled suspension system to the tillage depth of the electronically controlled suspension system control strategy model obtained after training in step S2.3, so as to achieve a control strategy with consistent tillage depth and low energy consumption;
[0053] Step S3: Apply the digital twin system in actual farming to determine the optimal tillage depth based on real-time environmental parameters and historical data; continuously collect actual farming data for iterative improvement of the digital twin system and reinforcement learning model to improve the accuracy of suspension height prediction and operation efficiency;
[0054] Step S4: In actual farming, the optimal hanging height is predicted and determined by real-time monitoring of environmental parameters and farming resistance, and combining the iteratively improved digital twin system in step S3 and the reinforcement learning model trained by the deep deterministic policy gradient algorithm.
[0055] Among them, in step S1, the digital twin is constructed in the following way:
[0056] Step S1.1: Use MATLAB to construct a dynamic model of the electric suspension actuator, including a motor model, a transmission system model, and a load model of the electric push rod 6;
[0057] Step S1.2: Using the soil information data measured by the farmland monitoring equipment, a soil mechanical property model is established in MATLAB, including the shear stress-strain relationship of the soil;
[0058] Step S1.3: Use Unity3D to build a visualization model to present the real-time status and operation of the electric tractor and its suspension system. The visualization model is synchronized with the plowing process and updated in real time to ensure that the model's prediction is consistent with the actual operation.
[0059] Among them, in step S2.2, the Actor network adopts a six-layer neural network; the input is the system state s, and the input layer has 8 nodes; the activation function of the first hidden layer uses the ReLU function, and the number of nodes is 240; the activation function of the second hidden layer also uses the ReLU function, and the number of nodes is 200; the output layer is action a, with 1 node; the learning rate of the network is set to 0.001; the Critic network also adopts a four-layer neural network; the input is a set of system state s and action a, so the input layer contains 9 nodes; the number of nodes in the two hidden layers are 200 and 150 respectively; the activation function of the hidden layer uses the ReLU function; the output layer is the value function Q(s,a), with 1 node, and the learning rate of the network is set to 0.002.
[0060] Wherein, in step S3, the iterative improvement steps include: data collection and analysis, model evaluation, model update and iterative cycle;
[0061] Data collection and analysis: Collect real-time tillage data, including tillage depth, tillage resistance, soil moisture, soil temperature, soil type, and vehicle speed; clean and pre-process the collected data to remove outliers and noise, and perform feature extraction and dimensionality reduction for subsequent analysis;
[0062] Model evaluation: Using tillage depth consistency and energy consumption as indicators to evaluate model performance, the prediction accuracy and control effect of the digital twin system and reinforcement learning model are evaluated;
[0063] Model update: Adjust the model parameters of the digital twin system and the reinforcement learning model parameters trained by the deep deterministic policy gradient algorithm based on the model evaluation results and problem diagnosis;
[0064] Iteration loop: Use the updated model to train with the deep deterministic policy gradient algorithm, and continuously collect new data for iterative training and optimization; through the data feedback loop, continuously optimize the reinforcement learning model control strategy to improve the model's prediction accuracy and control effect;
[0065] Through the above iterative improvement steps, the digital twin system and the reinforcement learning model trained by the deep deterministic policy gradient algorithm are continuously optimized to achieve more efficient suspension height control and operational efficiency.
[0066] Compared with the prior art, the present invention has the following beneficial effects:
[0067] The present invention provides an electric-controlled suspension system for an electric tractor, which adopts an electric push rod to drive an "L"-shaped sliding frame, can use electric energy more efficiently and reduce energy waste; can achieve precise suspension height adjustment through digital control, and can make precise adjustments according to different operating conditions and requirements; compared with traditional hydraulic suspension systems, the electric-controlled suspension system of the present invention has higher energy efficiency, faster response speed and higher accuracy; the electric suspension system does not require hydraulic oil, reducing the risk of hydraulic oil pollution to the environment, and the electric components are relatively simple and the maintenance cost is lower.
[0068] At the same time, the present invention proposes a suspension height control method that takes into account multiple factors. The control method based on digital twins comprehensively considers multiple factors such as tillage position, tillage resistance, soil moisture, ambient temperature, soil type, etc., and predicts the optimal suspension height through the digital twin model; this enables the suspension system to be adaptively adjusted according to different operating environments and requirements, and combines historical tillage data and environmental parameters to achieve intelligent suspension height control. Compared with the traditional force and position adjustment method, it can more accurately respond to the needs under different farming conditions, and improve the farming efficiency and operation quality.
[0069] Before using electric tractors for farming, a digital twin system was first established, which includes an electric suspension system, a digital twin, twin data, and a digital twin service platform. The digital twin is a dynamic simulation model of the plowing process built in the server, which includes a dynamic model of the electric suspension actuator, a soil mechanical property model, and a visualization model. Secondly, the reinforcement learning model was trained to obtain the best suspension height control strategy using the reinforcement learning algorithm based on the data of tillage position, tillage resistance, soil moisture, ambient temperature, soil type, tillage depth, and vehicle speed recorded in previous years. During the farming process, the digital twin service platform monitors and analyzes real-time data, and adjusts the "L"-shaped sliding frame 7 in real time through the electric push rod 6 based on the suspension height control strategy obtained through historical data and reinforcement learning algorithm training, thereby achieving the purpose of adjusting the suspension height. The digital twin system uses real-time data to drive the digital twin to run synchronously in the virtual world, while supporting data query and status playback.
[0070] In order to further optimize the suspension height control strategy, the prediction function of the digital twin system can also be used to understand the operating effect of the tractor under different suspension heights by viewing the prediction results of the virtual model. In this way, the suspension height can be adjusted according to the prediction results to achieve the best operating effect. BRIEF DESCRIPTION OF THE DRAWINGS
[0071] Figure 1 It is a schematic diagram of the overall structure of the electric-controlled suspension system of the electric tractor of the present invention;
[0072] Figure 2 It is a structural schematic diagram of the frame 3;
[0073] Figure 3 It is a structural schematic diagram of an "L"-shaped sliding frame that can be electrically controlled to rise and fall;
[0074] Figure 4 Schematic diagram of the suspension height control method.
[0075] The accompanying drawings are denoted as follows:
[0076] 1. Low voltage servo motor 2. Lower baffle
[0077] 3. Frame 4. Upper baffle
[0078] 5. First cylindrical pin 6. Electric push rod
[0079] 7. "L" shaped sliding frame 8. Diagonal tie rod
[0080] 9. Hitch pin 10. Suspension bracket
[0081] 11. GPS locator 12. Main controller
[0082] 13. Tillage depth controller 14. Electric push rod driver
[0083] 15. Second cylindrical pin 16. Connecting pin
[0084] 17. Pin force sensor 18. Speed reduction mechanism
[0085] 19. Long nylon pad 20. Bend plate
[0086] 21. Rolling bearing 22. Short nylon pad
[0087] 23. Magnetostrictive displacement sensor 24. Data transceiver equipment DETAILED DESCRIPTION
[0088] The specific implementation of the present invention will be further described below in conjunction with the accompanying drawings.
[0089] like Figure 1 to Figure 3 As shown, an electric-controlled suspension system for an electric tractor includes a low-voltage servo motor 1, a lower enclosure plate 2, a frame 3, an upper enclosure plate 4, a first cylindrical pin 5, an electric push rod 6, an "L"-shaped sliding frame 7, a diagonal tie rod 8, a coupling pin 9, a suspension frame 10, a GPS locator 11, a main controller 12, a tillage depth controller 13, an electric push rod driver 14, a second cylindrical pin 15, a connecting pin 16, a pin shaft force sensor 17, a speed reduction mechanism 18, a long nylon pad 19, a bent plate 20, a rolling bearing 21 and a short nylon pad 22.
[0090] like Figure 2 As shown, the frame 3 is a rectangular frame structure, including a left column and a right column arranged on the left and right sides, and a top plate arranged between the upper ends of the left column and the right column.
[0091] like Figure 3 As shown, the "L"-shaped sliding frame 7 includes a bottom rectangular frame, a left vertical beam and a right vertical beam, and the bottom rectangular frame includes a front beam, a rear beam, a left beam and a right beam. The left vertical beam and the right vertical beam are perpendicular to the bottom rectangular frame and extend upward, and the bottom of the left vertical beam and the right vertical beam are connected to the rear ends of the left beam and the right beam. The front ends of the left beam and the right beam are connected to the lower end of the suspension frame 10.
[0092] The upper ends of the two inclined rods 8 are connected to the upper end of the suspension frame 10 through the connecting pin 9, and the lower ends of the two inclined rods 8 are respectively hinged to the rear of the left beam and the right beam of the "L"-shaped sliding frame 7 through the connecting pin 16. The pin force sensor 17 is arranged at the connection between the left beam and the right beam of the "L"-shaped sliding frame 7 and the suspension frame 10.
[0093] like Figure 1 and Figure 3As shown, the upper end of the electric push rod 6 is hinged to the top plate of the frame 3 through the first cylindrical pin 5, and the lower end of the electric push rod 6 is hinged to the rear beam of the "L"-shaped sliding frame 7 through the second cylindrical pin 15. The extension and retraction of the electric push rod 6 can drive the "L"-shaped sliding frame 7 to achieve a lifting range of 37 cm.
[0094] The electric push rod 6 has a built-in magnetostrictive displacement sensor 23, which can detect the displacement change of the push rod to obtain the corresponding tillage depth value.
[0095] The lower baffle plate 2 is located in front of the frame 3 and is respectively connected to the left column and the right column of the frame 3. The upper baffle plate 4 is located in front of the frame 3 and is respectively connected to the left column and the right column of the frame 3. The upper baffle plate 4 is located above the lower baffle plate 2.
[0096] The left vertical beam and the right vertical beam of the “L”-shaped sliding frame 7 are located between the left vertical column, the right vertical column of the frame 3 and the lower enclosure plate 2 and the upper enclosure plate 4 .
[0097] The long nylon pad 19 is fixed to the front surface of the left column and the right column of the frame 3. The short nylon pad 22 is fixed to the rear surface of the lower enclosure plate 2 and the upper enclosure plate 4. During the tillage process, the long nylon pad 19 and the short nylon pad 22 are used for shock absorption and buffering between the frame 3 and the "L"-shaped sliding frame 7.
[0098] The bent plate 20 is fixed on the left and right uprights of the frame 3, and the rolling bearing 21 is installed on the bent plate 20. The bearing 21 contacts the left and right beams of the "L"-shaped sliding frame 7, plays a guiding and limiting role, and ensures that the "L"-shaped sliding frame 7 is smoothly lifted and lowered in the vertical direction.
[0099] The low voltage servo motor 1 and the speed reduction mechanism 18 are sequentially connected to the vehicle frame 3. The low voltage servo motor 1 and the speed reduction mechanism 18 serve as auxiliary power output devices of the electric tractor.
[0100] The GPS locator 11 is installed on the vehicle body and connected to the main controller 12 via a cable.
[0101] The main controller 12 collects data from the GPS locator 11, the magnetostrictive displacement sensor 23 built into the electric push rod 6, and the pin force sensor 17 through a dedicated signal line to obtain the tillage position and the current status information of the electric control suspension system.
[0102] The data transceiver device 24 is connected to the main controller 12. The data transceiver device 24 remotely transmits and receives data collected by the main controller 12. For example, the data transceiver device 24 performs remote communication with a remote server.
[0103] The main controller 12, the tillage depth controller 13, and the electric push rod driver 14 are connected to the electric push rod 6 in sequence. The electric push rod 6 controls the displacement of the push rod by receiving the signal of the electric push rod driver 14. When the push rod of the electric push rod 6 moves, the "L"-shaped sliding frame 7 is driven to rise and fall, thereby driving the agricultural implement to rise and fall.
[0104] The working process of the present invention is:
[0105] The main controller 12 sends a control signal to the electric push rod 6 through the electric push rod driver 14 based on the optimal tillage depth information provided by the digital twin system; after receiving the control signal, the electric push rod 6 drives the push rod to extend and retract; the extension and retraction of the push rod drives the "L"-shaped sliding frame 7 to rise and fall, and then drives the agricultural implement to rise and fall, thereby realizing the adjustment of the suspension height.
[0106] The magnetostrictive displacement sensor 23 built into the electric push rod 6 monitors the displacement changes of the push rod in real time; the magnetostrictive displacement sensor 23 converts the displacement of the push rod into an electrical signal and transmits it to the main controller 12; the main controller 12 calculates the current tillage depth based on the displacement signal and uses it as tillage depth feedback information for closed-loop control.
[0107] The pin force sensor 17 is installed at the connection between the "L"-shaped sliding frame 7 and the suspension frame 10; when the agricultural implement is subjected to soil resistance, the pin force sensor 17 detects the corresponding force change, converts it into an electrical signal, and transmits it to the main controller 12; the main controller 12 calculates the current tillage resistance based on the force signal, and uses it as tillage resistance feedback information for closed-loop control.
[0108] like Figure 4 As shown, a suspension height control method according to the electric tractor electronically controlled suspension system comprises the following steps:
[0109] Step S1: Establish a digital twin system, which includes an electronically controlled suspension system, farmland monitoring equipment, a digital twin, twin data, a digital twin service platform, and connections between various parts of the digital twin system;
[0110] The electric control suspension system includes a magnetostrictive displacement sensor 23 built into the electric push rod 6 , a GPS locator 11 , a pin force sensor 17 , the electric push rod 6 as a suspension height actuator, and a data transceiver 24 .
[0111] The GPS locator 11 can measure the tractor's position information and tillage position; the pin force sensor 17 can measure tillage resistance and other data; the electric push rod 6 can perform lifting actions; and the data transceiver device 24 can complete the remote transmission and reception of information.
[0112] The farmland monitoring equipment collects weather condition information and soil information in real time, and transmits the weather condition information and soil information to the digital twin service platform.
[0113] The weather condition information includes rain, snow and temperature.
[0114] The soil information includes soil moisture, soil temperature, soil type and soil hardness.
[0115] The digital twin is a dynamic simulation model of the plowing process built in the server. The digital twin is built as follows:
[0116] Step S1.1: Use MATLAB to construct a dynamic model of the electric suspension actuator, including a motor model, a transmission system model, and a load model of the electric push rod 6;
[0117] Step S1.2: Using the soil information data measured by the farmland monitoring equipment, a soil mechanical property model is established in MATLAB, including the shear stress-strain relationship of the soil;
[0118] Step S1.3: Use Unity3D to build a visualization model to present the real-time status and operation of the electric tractor and its suspension system. The visualization model is synchronized with the plowing process and updated in real time to ensure that the model's prediction is consistent with the actual operation;
[0119] Based on the real-time status information of the electric tractor and its suspension system, the collected weather conditions and soil information, the digital twin is driven to run synchronously in the virtual world. The digital twin simulates and generates dynamic and soil model data. At the same time, it supports operations such as data query and status playback.
[0120] Twin data is a collection of historical data and real-time data generated by the electronically controlled suspension system, digital twin, and digital twin service: including the tillage depth data measured by the magnetostrictive displacement sensor 23 built into the electric push rod 6, the geographic location information provided by the GPS locator 11, the force data obtained by the pin force sensor 17, and the dynamics and soil model data simulated by the digital twin. These data are fused and stored in the server for subsequent analysis and decision-making.
[0121] The pin pressure measured by the pin force sensor 17 is converted into the tillage resistance of the electric tractor in real time; and the displacement signal of the magnetostrictive displacement sensor 23 built into the electric push rod 6 is converted into the tillage depth in real time.
[0122] The digital twin service platform runs on the server and can provide real-time monitoring and data collection functions, provide prediction and simulation functions, and support remote monitoring and management.
[0123] The connection between the various parts of the digital twin system is completed through protocols such as TCP / IP and MQTT.
[0124] Step S2: Suspension height control: Based on the many years of historical weather conditions, soil information, and tillage depth data collected and recorded in step S1, an online control problem model of the electronically controlled suspension system is established. The deep deterministic policy gradient algorithm is used for training to obtain the optimal tillage depth, and the suspension height of the electric tractor's electronically controlled suspension system is set to the tillage depth, thereby achieving a control strategy with consistent tillage depth and low energy consumption.
[0125] Step S2.1: Establishing the control strategy model of the electronically controlled suspension system
[0126] The core of this method is to use digital twins as a dynamic learning environment to verify the feasibility and performance of suspension height control. The strategies learned from the digital twin environment reduce the gap between simulation and reality, thereby achieving more realistic suspension height control strategy learning.
[0127] In order to improve the convergence speed of reinforcement learning training in a digital twin system with higher degrees of freedom (larger state-action space), a suspension control height and vehicle speed control strategy based on a deep deterministic policy gradient algorithm is proposed. Considering the observability of the digital twin system and the control characteristics of the electronically controlled suspension system in a real environment, the online control problem model of the electronically controlled suspension system is established as follows:
[0128] s t =[xy FrθT S lv] Formula 1
[0129] a t =[h] Formula 2
[0130] In formula 1 and formula 2, s t is the state observation at time t; a t is the action amount at time t; x and y are the horizontal and vertical coordinates of the tillage position at the current moment in the geodetic coordinate system, in m; Fr is the current tillage resistance, in N; θ is the soil moisture, in %mass; T is the soil temperature, in ℃; S is the soil type; l is the current tillage depth, in cm, which is an important constraint in suspension control; v is the current vehicle speed, in m / s; h is the current suspension lift height, in cm.
[0131] Step S2.2: Use the deep deterministic policy gradient algorithm (DDPG) to train the electronic suspension system control strategy model established in step S2.1
[0132] DDPG adopts a dual network mode. Both the Actor network and the Critic network are equipped with target networks of the same structure, so there are four networks in DDPG. The existence of the target network reduces the fluctuation of network parameters, makes the learning process more stable, and makes the model easier to converge. The Actor network adopts a six-layer neural network. The input is the system state s, and the input layer has 8 nodes; the activation function of the first hidden layer uses the ReLU function, with 240 nodes; the activation function of the second hidden layer also uses the ReLU function, with 200 nodes; the output layer is action a, with 1 node. The learning rate of the network is set to 0.001. The Critic network also adopts a four-layer neural network. The input is a set of system state s and action a, so the input layer contains 9 nodes; the number of nodes in the two hidden layers is 200 and 150 respectively. The activation function of the hidden layer uses the ReLU function. The output layer is the value function Q(s,a), with 1 node, and the learning rate of the network is set to 0.002.
[0133] Step S2.3: Set the reward function to evaluate the performance of the electronic suspension system control strategy model trained in step S2.2
[0134] Reward is the feedback signal given by the digital twin system. It shows the performance of the agent in a specific state with a specific strategy. By setting the reward function appropriately, the optimal suspension height can be determined. In order to achieve a control strategy with consistent tillage depth and low energy consumption, the reward variable R is used to evaluate the characteristics of the electronically controlled suspension system and establish the reward function.
[0135] R=[lv] Formula 3
[0136] In Formula 3, R is the reward variable; l is the tillage depth in cm, which is an important constraint in suspension control; v is the vehicle speed in m / s.
[0137] The reward variable R contains the two most important variables in the control of the electronic suspension system: plowing depth and vehicle speed. By solving the optimization problem of multiple control objectives, the coefficient matrix K in the reward function is dynamically adjusted so that different control objectives have certain control effects at the same time. The immediate reward function is expressed as follows:
[0138] r=-(k1|l-l0| 2 +k2|v-v0| 2 ) Formula 4
[0139] In Formula 4, r is the immediate reward; k1 and k2 are the weight coefficients of tillage depth and vehicle speed, respectively; l is the expected tillage depth, in cm; l0 is the target tillage depth, in cm; v is the expected vehicle speed, in m / s; v0 is the target vehicle speed, in m / s.
[0140] The model is trained using the many years of historical weather condition information, soil information, and tillage depth data collected and recorded in step S1. During the training process, the model learns the optimal suspension height control strategy through interaction with the digital twin system to maximize the cumulative reward of the reward function.
[0141] Step S2.4: The suspension height of the electric tractor's electronically controlled suspension system is set to the tillage depth of the electronically controlled suspension system control strategy model obtained after training in step S2.3, so as to realize a control strategy with consistent tillage depth and low energy consumption.
[0142] Step S3: Apply the digital twin system in actual farming to determine the optimal tillage depth based on real-time environmental parameters and historical data; continuously collect actual farming data for iterative improvement of the digital twin system and reinforcement learning model to improve the accuracy of suspension height prediction and work efficiency.
[0143] The iterative improvement steps include: data collection and analysis, model evaluation, model updating and iterative cycles.
[0144] Data collection and analysis: Collect real-time tillage data, including tillage depth, tillage resistance, soil moisture, soil temperature, soil type, and vehicle speed; clean and pre-process the collected data to remove outliers and noise, and perform feature extraction and dimensionality reduction for subsequent analysis;
[0145] Model evaluation: Using tillage depth consistency and energy consumption as indicators to evaluate model performance, the prediction accuracy and control effect of the digital twin system and reinforcement learning model are evaluated;
[0146] Model update: According to the model evaluation results and problem diagnosis, adjust the model parameters of the digital twin system and the reinforcement learning model parameters trained by the DDPG algorithm;
[0147] Iteration loop: Use the updated model to train with the DDPG algorithm, and continuously collect new data for iterative training and optimization; through the data feedback loop, continuously optimize the reinforcement learning model control strategy to improve the model's prediction accuracy and control effect.
[0148] Through the above iterative improvement steps, the digital twin system and the reinforcement learning model trained by the DDPG algorithm are continuously optimized to achieve more efficient suspension height control and operating efficiency.
[0149] Step S4: In actual farming, the optimal suspension height is predicted and determined by real-time monitoring of environmental parameters and farming resistance, combined with the iteratively improved digital twin system in step S3 and the reinforcement learning model trained by the DDPG algorithm.
[0150] This process helps improve farming efficiency, reduce energy consumption, and maintain uniform tillage depth. By continuously collecting actual farming data for model training and optimization, continuous iterative improvements in suspension height are achieved, thereby achieving higher operating efficiency and lower energy consumption in actual farming.
Claims
1. An electric tractor electronically controlled suspension system, characterized in that: The electric control suspension system comprises a low-voltage servo motor (1), a lower baffle plate (2), a vehicle frame (3), an upper baffle plate (4), a first cylindrical pin (5), an electric push rod (6), an "L"-shaped sliding frame (7), a diagonal tie rod (8), a connecting pin (9), a suspension frame (10), a GPS locator (11), a main controller (12), a tillage depth controller (13), an electric push rod driver (14), a second cylindrical pin (15), a connecting pin (16), a pin shaft force sensor (17) and a speed reduction mechanism (18); The vehicle frame (3) is a rectangular frame structure, comprising a left column and a right column arranged on the left and right sides, and a top plate arranged between the upper ends of the left column and the right column; The "L"-shaped sliding frame (7) comprises a bottom rectangular frame, a left vertical beam and a right vertical beam, wherein the bottom rectangular frame comprises a front beam, a rear beam, a left vertical beam and a right vertical beam; the left vertical beam and the right vertical beam are perpendicular to the bottom rectangular frame and extend upward, and the bottoms of the left vertical beam and the right vertical beam are connected to the rear ends of the left vertical beam and the right vertical beam; the front ends of the left vertical beam and the right vertical beam are connected to the lower end of the suspension frame (10); The upper ends of the two inclined rods (8) are connected to the upper end of the suspension frame (10) via a connecting pin (9), and the lower ends of the two inclined rods (8) are respectively hinged to the rear parts of the left beam and the right beam of the "L"-shaped sliding frame (7) via a connecting pin (16); the pin shaft force sensor (17) is arranged at the connection between the left beam and the right beam of the "L"-shaped sliding frame (7) and the suspension frame (10); The upper end of the electric push rod (6) is hinged to the top plate of the vehicle frame (3) through a first cylindrical pin (5), and the lower end of the electric push rod (6) is hinged to the rear beam of the "L"-shaped sliding frame (7) through a second cylindrical pin (15); The electric push rod (6) has a built-in magnetostrictive displacement sensor (23); The lower baffle plate (2) is located in front of the vehicle frame (3) and is respectively connected to the left column and the right column of the vehicle frame (3); the upper baffle plate (4) is located in front of the vehicle frame (3) and is respectively connected to the left column and the right column of the vehicle frame (3); the upper baffle plate (4) is located above the lower baffle plate (2); The left vertical beam and the right vertical beam of the "L"-shaped sliding frame (7) are located between the left vertical column, the right vertical column and the lower enclosure plate (2) and the upper enclosure plate (4) of the vehicle frame (3); The low-voltage servo motor (1), the speed reduction mechanism (18) and the vehicle frame (3) are connected in sequence; The GPS locator (11) is installed on the vehicle body and connected to the main controller (12) via a cable; The main controller (12) collects data from the GPS locator (11), the magnetostrictive displacement sensor (23) built into the electric push rod (6), and the pin force sensor (17) through a dedicated signal line to obtain the tillage position and current status information of the electric control suspension system; The data transceiver device (24) is connected to the main controller (12); the data transceiver device (24) remotely transmits and receives data collected by the main controller (12); The main controller (12), the tillage depth controller (13), the electric push rod driver (14) and the electric push rod (6) are connected in sequence.
2. The electric tractor electronically controlled suspension system according to claim 1, characterized in that: The electric control suspension system also includes a long nylon pad (19) and a short nylon pad (22); the long nylon pad (19) is fixed to the front surface of the left column and the right column of the frame (3); and the short nylon pad (22) is fixed to the rear surface of the lower enclosure plate (2) and the upper enclosure plate (4).
3. The electric tractor electronically controlled suspension system according to claim 1, characterized in that: The electric control suspension system also includes a bent plate (20) and a rolling bearing (21); the bent plate (20) is fixed on the left column and the right column of the frame (3), and the rolling bearing (21) is installed on the bent plate (20); the bearing (21) contacts the left beam and the right beam of the "L"-shaped sliding frame (7), plays a guiding and limiting role, and ensures that the "L"-shaped sliding frame (7) is smoothly raised and lowered in the vertical direction.
4. The electric tractor electronically controlled suspension system according to claim 1, characterized in that: The extension and retraction of the electric push rod (6) can drive the "L"-shaped sliding frame (7) to achieve lifting within a range of 37 cm.
5. A suspension height control method for an electric tractor electronically controlled suspension system according to any one of claims 1 to 4, characterized in that: The method comprises the following steps: Step S1: Establish a digital twin system, which includes an electronically controlled suspension system, farmland monitoring equipment, a digital twin, twin data, a digital twin service platform, and connections between various parts of the digital twin system; The electric control suspension system comprises a magnetostrictive displacement sensor (23) built into the electric push rod (6), a GPS locator (11), a pin force sensor (17), the electric push rod (6) as a suspension height actuator, and a data transceiver (24); The GPS locator (11) can measure the position information of the tractor and the tillage position; the pin force sensor (17) can measure the tillage resistance; the electric push rod (6) can perform the lifting action; and the data transceiver device (24) can complete the remote transmission and reception of information; The farmland monitoring equipment collects weather condition information and soil information in real time, and transmits the weather condition information and soil information to the digital twin service platform; The weather condition information includes rain, snow and temperature; The soil information includes soil moisture, soil temperature, soil type and soil hardness; The digital twin is a dynamic simulation model of the plowing process built in the server; Based on the real-time status information of the electric tractor and its suspension system, the collected weather conditions and soil information, the digital twin is driven to run synchronously in the virtual world. The digital twin simulates and generates dynamics and soil model data, and supports data query and status review. The twin data is a collection of historical data and real-time data generated by the electronically controlled suspension system, the digital twin, and the digital twin service: including the tillage depth data measured by the magnetostrictive displacement sensor (23) built into the electric push rod (6), the geographic location information provided by the GPS locator (11), the force data obtained by the pin force sensor (17), and the dynamics and soil model data simulated by the digital twin. These data are fused and stored in the server for subsequent analysis and decision-making. The pin pressure measured by the pin force sensor (17) is converted into the tillage resistance of the electric tractor in real time; the displacement signal of the magnetostrictive displacement sensor (23) built into the electric push rod (6) is converted into the tillage depth in real time; The digital twin service platform runs on the server and can provide real-time monitoring and data collection functions, prediction and simulation functions, and support remote monitoring and management; The connection between the various parts of the digital twin system is completed through TCP / IP and MQTT protocols; Step S2: Suspension height control: Based on the historical weather condition information, soil information, and tillage depth data collected and recorded in step S1, an online control problem model of the electronically controlled suspension system is established, and the optimal tillage depth is obtained by training with a deep deterministic policy gradient algorithm. The suspension height of the electric tractor's electronically controlled suspension system is set to the tillage depth, thereby achieving a control strategy with consistent tillage depth and low energy consumption. Step S2.1: Establishing the control strategy model of the electronically controlled suspension system The online control problem model of the electronically controlled suspension system is established as follows: s t =[xy Fr θ TS lv] 1 a t =[h] Formula 2 In formula 1 and formula 2, s t is the state observation at time t; a t is the action amount at time t; x and y are the horizontal and vertical coordinates of the tillage position at the current moment in the geodetic coordinate system, in m; Fr is the current tillage resistance, in N; θ is the soil moisture, in %mass; T is the soil temperature, in ℃; S is the soil type; l is the current tillage depth, in cm; v is the current vehicle speed, in m / s; h is the current suspension lifting height, in cm; Step S2.2: Use the deep deterministic policy gradient algorithm to train the electronic suspension system control strategy model established in step S2.1 The deep deterministic policy gradient algorithm adopts a dual network mode. Both the Actor network and the Critic network are equipped with a target network with the same structure. Therefore, there are four networks in the deep deterministic policy gradient algorithm. Step S2.3: Set the reward function to evaluate the performance of the electronic suspension system control strategy model trained in step S2.2 Use the reward variable R to evaluate the characteristics of the electronically controlled suspension system and establish the reward function: R=[lv] Formula 3 In formula 3, R is the reward variable; l is the tillage depth in cm; v is the vehicle speed in m / s; The immediate reward function is expressed as follows: r=-(k1|l-l0| 2 +k2|v-v0| 2 ) Formula 4 In formula 4, r is the immediate reward; k1 and k2 are the weight coefficients of tillage depth and vehicle speed respectively; l is the expected tillage depth, in cm; l0 is the target tillage depth, in cm; v is the expected vehicle speed, in m / s; v0 is the target vehicle speed, in m / s; The model is trained using the historical weather condition information, soil information, and tillage depth data collected and recorded in step S1. During the training process, the model learns the optimal suspension height control strategy through interaction with the digital twin system to maximize the cumulative reward of the reward function. Step S2.4: setting the suspension height of the electric tractor's electronically controlled suspension system to the tillage depth of the electronically controlled suspension system control strategy model obtained after training in step S2.3, so as to achieve a control strategy with consistent tillage depth and low energy consumption; Step S3: Apply the digital twin system in actual farming to determine the optimal tillage depth based on real-time environmental parameters and historical data; continuously collect actual farming data for iterative improvement of the digital twin system and reinforcement learning model to improve the accuracy of suspension height prediction and operation efficiency; Step S4: In actual farming, the optimal hanging height is predicted and determined by real-time monitoring of environmental parameters and farming resistance, and combining the iteratively improved digital twin system in step S3 and the reinforcement learning model trained by the deep deterministic policy gradient algorithm.
6. The suspension height control method of the electric tractor electronically controlled suspension system according to claim 5, characterized in that: in, In step S1, the digital twin is constructed as follows: Step S1.1: Use MATLAB to construct a dynamic model of the electric suspension actuator, including a motor model, a transmission system model, and a load model of the electric push rod 6; Step S1.2: Using the soil information data measured by the farmland monitoring equipment, a soil mechanical property model is established in MATLAB, including the shear stress-strain relationship of the soil; Step S1.3: Use Unity3D to build a visualization model to present the real-time status and operation of the electric tractor and its suspension system. The visualization model is synchronized with the plowing process and updated in real time to ensure that the model's prediction is consistent with the actual operation.
7. The suspension height control method of the electric tractor electronically controlled suspension system according to claim 5, characterized in that: In step S2.2, the Actor network uses a six-layer neural network; the input is the system state s, and the input layer has 8 nodes; the activation function of the first hidden layer uses the ReLU function, and the number of nodes is 240; the activation function of the second hidden layer also uses the ReLU function, and the number of nodes is 200; the output layer is action a, and has 1 node; The learning rate of the network is set to 0.001; the Critic network also uses a four-layer neural network; the input is a set of system states s and actions a, so the input layer contains 9 nodes; the number of nodes in the two hidden layers is 200 and 150 respectively; the activation function of the hidden layer uses the ReLU function; the output layer is the value function Q(s,a), with 1 node, and the learning rate of the network is set to 0.
002.
8. The suspension height control method of the electric tractor electronically controlled suspension system according to claim 5, characterized in that: in, In step S3, the iterative improvement steps include: data collection and analysis, model evaluation, model update and iterative cycle; Data collection and analysis: Collect real-time tillage data, including tillage depth, tillage resistance, soil moisture, soil temperature, soil type, and vehicle speed; clean and pre-process the collected data to remove outliers and noise, and perform feature extraction and dimensionality reduction for subsequent analysis; Model evaluation: Using tillage depth consistency and energy consumption as indicators to evaluate model performance, the prediction accuracy and control effect of the digital twin system and reinforcement learning model are evaluated; Model update: Adjust the model parameters of the digital twin system and the reinforcement learning model parameters trained by the deep deterministic policy gradient algorithm based on the model evaluation results and problem diagnosis; Iteration loop: Use the updated model to train with the deep deterministic policy gradient algorithm, and continuously collect new data for iterative training and optimization; through the data feedback loop, continuously optimize the reinforcement learning model control strategy to improve the model's prediction accuracy and control effect; Through the above iterative improvement steps, the digital twin system and the reinforcement learning model trained by the deep deterministic policy gradient algorithm are continuously optimized to achieve more efficient suspension height control and operational efficiency.
Citation Information
Patent Citations
Electric suspension control device of tractor
CN103713535A
Intelligent thinning and weeding machine tool with machine vision servo
CN106258028A
Obstacle avoidance track and cutting inclination angle control device and method for suspension type mower
CN113170663A
Robot chassis for multifunctional operation in paddy field and agricultural robot
CN114223339A
V-shaped traction frame of small square bundle bundling machine
CN203801232U
