Chassis of a tiller with adjustable chassis and adjustment control method

Abstract

The present invention proposes a chassis and adjustment control method of a tiller with adjustable chassis, including obtaining data of multiple sensors such as terrain sensors, distance sensors, soil resistance sensors, etc. in real time during travel, and inputting these data into an intelligent control strategy model and a height adjustment model to dynamically adjust the chassis height and the working parameters of the tilling components to achieve precise height adjustment. At the same time, the sensor data is analyzed in real time through a fault diagnosis model to diagnose the fault type and location and provide maintenance tutorials, and the model can continuously optimize itself. In addition, the energy model is used to output the optimal power output power of the tilling components according to the sensor data to optimize energy consumption. The device of the present invention includes a collection module, an intelligent control strategy module, a height adjustment module, a fault diagnosis module, an alarm module, and an energy module. The present invention can improve the automation level, work efficiency, and adaptability of the tiller and optimize energy management.

Description

Technical Field

[0001] The invention relates to the technical field of tillage machines, and in particular to a chassis of a tillage machine with an adjustable chassis and an adjustment control method. Background Art

[0002] Tea trees are one of the important economic crops in my country, and they are mostly planted in hills and slopes. Tea planting requires a tiller. In order to solve the problem that the road surface in mountainous areas is uneven, the tiller has low passability in some cases and is easy to get stuck on the chassis, the existing tillers, such as CN117769905A applied by our company, provide a tiller with an adjustable chassis function, including a front travel system, a gearbox body and a rear travel system. Both the front travel system and the rear travel system have a lifting function, and the lifting of the chassis of the whole machine is realized under the unified control of the system. This invention can solve the problem of the passability of the current tea garden tiller in different mountainous environments, and also solve the difficulty of adjusting the tillage depth in different farming environments. The whole machine can achieve height lifting and lowering through one-button operation, which greatly increases the convenience and labor of the whole machine.

[0003] However, the tiller has the following disadvantages when actually used in mountainous environments such as tea gardens:

[0004] 1. Lack of intelligent control: Existing tillage machines do not have an intelligent control system and cannot automatically adjust the chassis height according to the terrain and work requirements. They rely on the machine's own distance sensor to measure the height to obtain height information, and then rely on the operator to operate the buttons on the overall control system, which requires a high level of experience and skills from the operator.

[0005] 2. Inaccurate height adjustment: When adjusting the chassis height, the existing backhoe tiller can only be operated manually, and it is difficult to achieve accurate height adjustment, resulting in poor stability and adaptability of the backhoe tiller during operation.

[0006] 3. Insufficient fault diagnosis capabilities: When a tiller fails, existing tillers often cannot promptly and accurately diagnose the fault type and location, requiring operators to check them one by one, resulting in low maintenance efficiency and affecting work progress.

[0007] In view of the above reasons, it is necessary to design a machine adjustment and control method for a tiller with better applicability and intelligent control function to solve the current problem of the passability of tea garden tillers in different mountainous environments, realize real-time adjustment of tillage depth, and improve the accuracy and timeliness of fault diagnosis. Summary of the invention

[0008] The embodiment of the present invention provides a chassis of a tiller with adjustable chassis and an adjustment control method, which aims to solve the problems existing in the current technology such as lack of intelligent control, inaccurate height adjustment and insufficient fault diagnosis capability.

[0009] The core technology of the present invention is to collect data in real time through multiple sensors, and use algorithms such as intelligent control strategy models, height adjustment models, fault diagnosis models and energy models to achieve intelligent adjustment of chassis height and working parameters of digging and tilling components, fault diagnosis and optimization, and rational allocation of energy, thereby improving the performance and efficiency of the digging and tilling machine.

[0010] In a first aspect, the present invention provides a chassis adjustment control method for a tiller with adjustable chassis, the method comprising the following steps:

[0011] S00, while traveling, obtaining data from terrain sensors, distance sensors, and soil resistance sensors in real time;

[0012] Among them, the terrain sensor scans the terrain around the tiller in real time to obtain terrain data; the distance sensor provides real-time data on the relative height between the chassis and the ground; the soil resistance sensor provides real-time data on the resistance of the soil to the tilling parts of the tiller;

[0013] S10, inputting terrain data, relative height data and resistance data into the intelligent control strategy model, and dynamically adjusting the chassis height and working parameters of the digging and tilling components according to the output of the intelligent control strategy model;

[0014] Among them, the intelligent control strategy model is trained through historical terrain data, relative height data and resistance data;

[0015] S20, when adjusting the height, input the terrain data, the relative height data and the resistance data into the height adjustment model, use the height adjustment model output as the target height, and compare the target height with the actual height after adjustment until the target height is adjusted;

[0016] Among them, the height adjustment model is established based on the influence of terrain data, relative height data and resistance data on chassis height.

[0017] Furthermore, step S00 also includes acquiring data from a speed sensor, a temperature sensor, and a pressure sensor in real time;

[0018] The speed sensor is used to monitor the motor speed; the temperature sensor is used to monitor the oil temperature; and the pressure sensor is used to monitor the oil pressure.

[0019] Furthermore, in steps S00-S20, the data of the speed sensor, the temperature sensor and the pressure sensor are analyzed in real time by the fault diagnosis model to diagnose the type of fault, the corresponding fault location and the corresponding maintenance tutorial, and the operator is prompted by the alarm module;

[0020] Among them, the fault diagnosis model is established based on expert experience and historical data, and fault diagnosis is performed by combining multiple analysis methods, including threshold judgment, trend analysis and spectrum analysis.

[0021] Furthermore, the fault diagnosis model records historical fault data from the time a fault occurs to the time it is resolved, including parameter conditions, fault type, fault location, and maintenance records when the fault occurred, and continuously optimizes itself by analyzing and learning from historical fault data using machine learning algorithms.

[0022] Furthermore, in step S20, the training step of the height adjustment model includes:

[0023] Define the ground flatness index, slope index, and soil hardness index respectively, and assign weights. The sum of the three weights equals one.

[0024] A mathematical model is established to calculate the comprehensive index, which is the ground flatness index*the weight of the ground flatness index+the slope index*the weight of the slope index+the soil hardness index*the weight of the soil hardness index;

[0025] Set the initial weight value based on the actual situation and experience data, and dynamically adjust the weight value according to the actual effect and feedback information during use;

[0026] Formulate calculation rules and set thresholds and adjustment coefficients for each indicator:

[0027] The tillage depth requirement is used as input to establish a mapping relationship between the tillage depth requirement and the chassis height adjustment, thereby determining the final chassis height adjustment amount.

[0028] Furthermore, in step S10, the intelligent control strategy model is based on a decision tree algorithm or a neural network.

[0029] Furthermore, step S00 also includes real-time acquisition of data from a current sensor, a power sensor, and a slope sensor; wherein the current sensor and the power sensor are used to detect the current and power of the motor, respectively, and the slope sensor is used to measure the slope of the terrain;

[0030] By inputting data from current sensors, power sensors, slope sensors, and soil resistance sensors into the energy model, the optimal power output of the tillage components is output;

[0031] Among them, the energy model adopts fuzzy logic control algorithm or neural network control algorithm.

[0032] In a second aspect, the present invention provides a chassis of an adjustable tiller, comprising:

[0033] The acquisition module acquires data from terrain sensors, distance sensors, speed sensors, temperature sensors, pressure sensors, current sensors, power sensors, and soil resistance sensors in real time while traveling;

[0034] Among them, the terrain sensor scans the terrain around the tiller in real time to obtain terrain data; the distance sensor provides real-time relative height data between the chassis and the ground; the soil resistance sensor provides real-time resistance data of the soil to the tilling parts of the tiller; the speed sensor is used to monitor the motor speed; the temperature sensor is used to monitor the oil temperature; the pressure sensor is used to monitor the oil pressure;

[0035] The intelligent control strategy module inputs terrain data, relative height data and resistance data into the intelligent control strategy model, and dynamically adjusts the chassis height and working parameters of the digging and tilling components according to the output of the intelligent control strategy model; wherein the intelligent control strategy model is trained through historical terrain data, relative height data and resistance data;

[0036] A height adjustment module, when adjusting the height, inputs the terrain data, relative height data and resistance data into a height adjustment model, uses the height adjustment model output as a target height, and compares the target height with the actual height after adjustment until the target height is adjusted; wherein the height adjustment model is established based on the influence of the terrain data, relative height data and resistance data on the chassis height;

[0037] The fault diagnosis module uses a fault diagnosis model to analyze the data of the speed sensor, temperature sensor, and pressure sensor in real time to diagnose the type of fault, the corresponding fault location, and the corresponding maintenance tutorial, and prompts the operator through the alarm module; the fault diagnosis model is established based on expert experience and historical data, and performs fault diagnosis through a combination of multiple analysis methods, including threshold judgment, trend analysis, and spectrum analysis; the fault diagnosis model records historical fault data from the time a fault occurs to the time the fault is resolved, including the parameters when the fault occurs, the fault type, the fault location, and the maintenance record, and continuously optimizes itself by analyzing and learning the historical fault data using machine learning algorithms;

[0038] An alarm module, used to issue an audible and visual alarm and / or a text prompt;

[0039] The energy module outputs the optimal power output power of the tillage component by inputting the data of the current sensor, power sensor, terrain sensor, and soil resistance sensor into the energy model; wherein the energy model adopts a fuzzy logic control algorithm or a neural network control algorithm.

[0040] In a third aspect, the present invention provides an electronic device including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the above-mentioned chassis adjustment control method of a tilling machine with adjustable chassis.

[0041] In a fourth aspect, the present invention provides a readable storage medium, in which a computer program is stored. The computer program includes a program code for controlling a process to execute the process. The process includes a chassis adjustment control method of a tiller with adjustable chassis according to the above-mentioned method.

[0042] The main contributions and innovations of the present invention are as follows:

[0043] 1. Improved the passability of the tiller: The chassis height is adjusted in real time through the intelligent control system, so that it can better adapt to the terrain of different mountainous environments and reduce the occurrence of chassis jams.

[0044] 2. Real-time adjustment of tillage depth is achieved: the chassis height is accurately adjusted according to terrain data and work requirements, thereby achieving real-time adjustment of tillage depth without the need to replace tools, saving time and effort.

[0045] 3. Enhanced intelligent control function: The introduction of intelligent control strategy model can automatically adjust the chassis height and working parameters of the tillage components according to real-time data, thereby improving the automation level and working efficiency of the tillage machine.

[0046] 4. Optimized the height adjustment algorithm: A height adjustment model is established based on multiple factors to achieve precise adjustment of the chassis height, so that the tiller can maintain a stable working state and appropriate tillage depth under different terrains without manual operation, which greatly reduces the operating threshold.

[0047] 5. Improved fault diagnosis capabilities: By analyzing sensor data in real time through the fault diagnosis model, the fault type and location can be quickly and accurately diagnosed, and corresponding maintenance tutorials can be provided, reducing maintenance costs and downtime.

[0048] 6. Energy management optimization has been achieved: the energy model is used to output the optimal power output of the digging and tillage components according to factors such as operating load and terrain conditions, so as to reasonably allocate energy, extend the working time of the machine and reduce operating costs.

[0049] The details of one or more embodiments of the invention are set forth in the following drawings and description so that other features, objects, and advantages of the invention are more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0051] Figure 1 is a flow chart of a chassis adjustment control method of a tiller with adjustable chassis according to an embodiment of the present invention;

[0052] Figure 2 4 is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0053] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with one or more embodiments of this specification. Instead, they are merely examples of devices and methods consistent with some aspects of one or more embodiments of this specification as detailed in the appended claims.

[0054] It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the steps included in the method may be more or less than those described in this specification. In addition, a single step described in this specification may be decomposed into multiple steps for description in other embodiments; and multiple steps described in this specification may be combined into a single step for description in other embodiments.

[0055] The present invention is an improvement on CN117769905A. Sensors and a central controller are added to the tiller based on the invention, aiming to solve the defects of lack of intelligent control, inaccurate reliance on operator experience for height adjustment and high operating threshold.

[0056] Embodiment 1

[0057] In order to solve the problems existing in the prior art, the present invention aims to propose a chassis adjustment control method for a tiller with adjustable chassis, specifically, referring to Figure 1 , the method comprising:

[0058] S00, while traveling, real-time acquisition of data from terrain sensors, distance sensors, and soil resistance sensors; wherein the terrain sensor scans the terrain around the tiller in real time to obtain terrain data; the distance sensor provides real-time relative height data between the chassis and the ground; the soil resistance sensor provides real-time resistance data of the soil to the tilling components of the tiller;

[0059] In this embodiment, the sensor configuration is as follows:

[0060] Terrain sensor: It can be installed on the front or top of the tiller. If a lidar is used, it can be installed on the top for 360-degree scanning. If a camera is used, it can be installed in multiple positions on the front to obtain more comprehensive terrain information, such as the height and slope of the terrain.

[0061] Distance sensor: can be installed at the four corners of the chassis of the tiller to ensure accurate measurement of the distance between the chassis and different parts of the ground. Used to measure the distance between the chassis and the ground to determine the height of the chassis.

[0062] Soil resistance sensor: It can be installed on the digging and tilling components, such as near the digging and tilling tools, and can directly detect the resistance of the soil to the digging and tilling components, thereby inferring the hardness of the soil and the difficulty of tillage.

[0063] Preferably, data transmission and processing are as follows:

[0064] Each sensor transmits the collected data to the central controller of the tiller by wired or wireless means. For example, wired connection can use data line or cable to ensure the stability of data transmission; wireless connection can use Bluetooth, Wi-Fi and other technologies to improve the flexibility of installation, and adopt protocols suitable for real-time data transmission to ensure that sensor data can be transmitted to the central controller quickly and accurately. For example, a custom data packet format is used, which contains information such as sensor type, data value, timestamp, etc. The central controller uses advanced algorithms to analyze and process the data (the intelligent control strategy model below, which is mounted on the central controller), such as using decision trees and neural networks in machine learning algorithms to judge terrain conditions, work requirements and machine status.

[0065] S10, inputting terrain data, relative height data and resistance data into an intelligent control strategy model, and dynamically adjusting the chassis height and working parameters of the digging and tilling components according to the output of the intelligent control strategy model; wherein the intelligent control strategy model is trained by historical terrain data, relative height data and resistance data;

[0066] In this embodiment, the central controller determines the slope and obstacle conditions of the current terrain based on the data from the terrain sensor. If a steep slope or obstacle is encountered, the controller automatically adjusts the lifting and lowering of the front and rear travel systems to increase the chassis height to ensure that the tiller can pass safely.

[0067] Based on the data from the distance sensor, the controller monitors the chassis height in real time and automatically adjusts the chassis height according to work requirements to achieve the optimal tillage depth.

[0068] The data from the soil resistance sensor is used to evaluate the soil hardness. The controller adjusts the working parameters of the tillage components, such as rotation speed and force, according to the soil hardness to improve tillage efficiency.

[0069] The implementation code is as follows:

[0070] # Central controller processing logic

[0071] while True:

[0072] # Receive sensor data

[0073] terrain_data = receive_terrain_sensor_data()

[0074] distance_data = receive_distance_sensor_data()

[0075] soil_resistance_data = receive_soil_resistance_sensor_data()

[0076] # Analyze the data

[0077] terrain_condition = analyze_terrain(terrain_data)

[0078] operation_requirement = determine_operation_requirement(distance_data)

[0079] machine_state = check_machine_state(soil_resistance_data)

[0080] # Intelligent control decision

[0081] if terrain_condition.is_steep_slope_or_obstacle():

[0082] adjust_front_and_rear_walking_systems(height_increase=True)

[0083] elif operation_requirement.requires_depth_adjustment():

[0084] adjust_chassis_height(operation_requirement.target_depth)

[0085] elif machine_state.indicates_high_soil_resistance():

[0086] adjust_digging_parameters(machine_state.soil_hardness)

[0087] # Send control instructions

[0088] send_control_commands()

[0089] Here, we assume that we have acquired the height and slope data of the terrain using a terrain sensor. Our goal is to determine whether the terrain is flat, slightly undulating, or steep based on this data. Then we need to do the following steps:

[0090] 1. Data preparation:

[0091] Collect a large number of samples of terrain data, including measurements of height and slope, and label each sample with the type of terrain it corresponds to (flat, slightly undulating, steep).

[0092] 2. Training decision tree:

[0093] Use the collected data to train a decision tree model. The decision tree automatically learns how to make decisions based on the features (height and slope) in the data.

[0094] 3. Terrain judgment:

[0095] When the tiller obtains new terrain data during actual work, the data is input into the trained decision tree, which will make judgments based on the characteristics of the data and output the predicted results of the terrain type.

[0096] For example, a decision tree might learn the following rule:

[0097] If the height difference is less than a certain threshold and the slope is less than a certain angle, it is judged to be flat terrain.

[0098] If the height difference is within a certain range and the slope is within a certain angle range, it is judged as slightly undulating terrain.

[0099] If the height difference is large and the slope is steep, it is judged as steep terrain.

[0100] By using the decision tree algorithm, the central controller can quickly and accurately judge the terrain conditions based on the real-time collected data, and make corresponding control decisions, such as adjusting the chassis height.

[0101] Similarly, neural networks can also be used for similar judgment tasks. Neural networks can automatically extract features and establish complex relationships between input data and output results by learning a large number of data samples. In practical applications, appropriate algorithms and models can be selected according to specific needs. For example, neural networks can be used for similar judgment tasks through the following steps:

[0102] 1) Data collection: Collect a large number of data samples related to terrain judgment, including terrain height, slope, soil hardness and other characteristic information, as well as corresponding terrain type labels (such as flat, slightly undulating, steep, etc.).

[0103] 2) Data preprocessing: Preprocess the collected data, including data cleaning, normalization, feature extraction and other operations, so that the neural network can better process and learn the data.

[0104] Model selection: Select a suitable neural network model according to specific needs, such as multi-layer perceptron (MLP), convolutional neural network (CNN), recurrent neural network (RNN), etc.

[0105] 3) Model training: Use the preprocessed data to train the neural network. During the training process, the neural network learns the complex relationship between input data and output results by automatically adjusting weights and biases. The training process usually uses the back propagation algorithm to optimize the parameters of the model to minimize the loss function.

[0106] 4) Model evaluation: Use the test set data to evaluate the trained neural network and calculate the model's accuracy, recall, F1 value and other indicators to evaluate the model's performance.

[0107] 5) Model adjustment: According to the results of model evaluation, the model is adjusted and optimized, such as adjusting the network structure, increasing the amount of training data, adjusting training parameters, etc., to improve the performance of the model.

[0108] 6) Practical application: Apply the trained neural network model to the actual terrain judgment task. When the tiller obtains new terrain data, the data is input into the neural network, and the model automatically outputs the judgment result of the terrain type. For example, when using a multi-layer perceptron for terrain judgment, the terrain height, slope, soil hardness and other features can be used as input, and after calculation and transmission by multiple layers of neurons, the prediction result of the terrain type is finally output. During the training process, the neural network will automatically learn the complex relationship between these features and the terrain type, so that it can accurately judge the terrain.

[0109] Of course, we can also conduct comparative analysis of actual results. The decision tree algorithm performs better when processing small-scale data and clear rules, and can quickly come to a conclusion; the neural network algorithm has advantages when processing large-scale data and complex patterns, and can automatically extract features and build a more accurate model. In practical applications, we can choose the appropriate algorithm according to the specific terrain conditions and data characteristics, or use the two algorithms in combination to improve the accuracy of terrain judgment.

[0110] S20. When adjusting the height (the intelligent control strategy model calls the height adjustment model when adjusting the height), the terrain data, relative height data and resistance data are input into the height adjustment model, and the target height is outputted by the height adjustment model, and the target height is compared with the actual height after adjustment until the target height is adjusted; wherein the height adjustment model is established based on the influence of the terrain data, relative height data and resistance data on the chassis height.

[0111] 1) In this embodiment, the height adjustment model considers the following factors:

[0112] Ground flatness: The ground flatness data, including undulations and bumps, is obtained through terrain sensors.

[0113] Slope: Measure the slope angle of the terrain using terrain sensors.

[0114] Soil Hardness: Assess soil hardness based on information fed back from the soil resistance sensor.

[0115] 2) Therefore, a mathematical model can be established based on the above factors:

[0116] Define the ground flatness index F, which can be calculated from the data obtained by the terrain sensor, such as the statistics of the ground undulation. Define the slope index S, which is represented by the slope angle measured by the terrain sensor. Define the soil hardness index H, which is quantified based on the information fed back by the soil resistance sensor. Assign a weight w to each factor F 、w S and w H , satisfying w F +w S +w H =1. Establish a mathematical model to calculate the comprehensive index I: I=w F *F+w S *S+w H *H.

[0117] 3) Next, adjust the weights and set the initial weights based on the actual situation and empirical data. For example, in general, you can set w F =0.3, w S=0.4, w H =0.3, indicating that the slope has a relatively large impact on the chassis height. During the use of the tiller, the weight value is dynamically adjusted according to the actual effect and feedback information. If it is found that a certain factor has a greater or lesser impact on the chassis height than expected, its weight can be increased or decreased accordingly.

[0118] 4) Next, formulate the calculation rules:

[0119] When the flatness F is less than a certain threshold F threshold When the flatness is poor, the chassis height H should be appropriately increased. adjust The increase can be set according to the specific situation, for example, H adjust =k F *(FF threshold ), where k F is the slope adjustment factor.

[0120] When the slope S is greater than a certain threshold S threshold When the slope is considered large, the chassis height H should be appropriately increased. adjust The increase can be set according to the specific situation, for example, H adjust =k S *(SS threshold ), where k S is the slope adjustment factor.

[0121] When the soil hardness H is greater than a certain H threshold When the threshold is reached, the chassis height H should be appropriately lowered. adjust To increase the digging force, such as H adjust =-k H *(HH threshold ), where k H is the soil hardness adjustment factor.

[0122] Considering the influence of various factors comprehensively, calculate the adjustment amount of chassis height: , where H adjust,F , H adjust,S and H adjust,H They are the adjustments calculated based on the ground flatness, slope and soil hardness respectively.

[0123] 5) Finally, the job requirements need to be included:

[0124] Consider different tillage depth requirements required , which is used as the input of the algorithm.

[0125] Adjust the chassis height according to the tillage depth requirements. For example, if the tillage depth required is deeper, the chassis height can be appropriately lowered; conversely, if the tillage depth required is shallower, the chassis height can be appropriately increased.

[0126] A mapping relationship between tillage depth requirements and chassis height adjustment can be established, e.g. , where k D is the tillage depth adjustment coefficient, D default The default tillage depth.

[0127] The final ride height adjustment is:

[0128]

[0129] Through the above algorithm design, factors such as ground flatness, slope, soil hardness and operating requirements can be more accurately considered to achieve optimal adjustment of the chassis height.

[0130] Embodiment 2

[0131] Based on the same concept, the present invention also proposes a chassis of an adjustable tiller, comprising:

[0132] The acquisition module acquires data from terrain sensors, distance sensors, speed sensors, temperature sensors, pressure sensors, current sensors, power sensors, and soil resistance sensors in real time while traveling;

[0133] Among them, the terrain sensor scans the terrain around the tiller in real time to obtain terrain data; the distance sensor provides real-time relative height data between the chassis and the ground; the soil resistance sensor provides real-time resistance data of the soil to the tilling parts of the tiller; the speed sensor is used to monitor the motor speed; the temperature sensor is used to monitor the oil temperature; the pressure sensor is used to monitor the oil pressure;

[0134] The intelligent control strategy module inputs terrain data, relative height data and resistance data into the intelligent control strategy model, and dynamically adjusts the chassis height and working parameters of the digging and tilling components according to the output of the intelligent control strategy model; wherein the intelligent control strategy model is trained through historical terrain data, relative height data and resistance data;

[0135] A height adjustment module, when adjusting the height, inputs the terrain data, relative height data and resistance data into a height adjustment model, uses the height adjustment model output as a target height, and compares the target height with the actual height after adjustment until the target height is adjusted; wherein the height adjustment model is established based on the influence of the terrain data, relative height data and resistance data on the chassis height;

[0136] The fault diagnosis module uses a fault diagnosis model to analyze the data of the speed sensor, temperature sensor, and pressure sensor in real time to diagnose the type of fault, the corresponding fault location, and the corresponding maintenance tutorial, and prompts the operator through the alarm module; the fault diagnosis model is established based on expert experience and historical data, and performs fault diagnosis through a combination of multiple analysis methods, including threshold judgment, trend analysis, and spectrum analysis; the fault diagnosis model records historical fault data from the time a fault occurs to the time the fault is resolved, including the parameters when the fault occurs, the fault type, the fault location, and the maintenance record, and continuously optimizes itself by analyzing and learning the historical fault data using machine learning algorithms;

[0137] An alarm module, used to issue an audible and visual alarm and / or a text prompt;

[0138] The energy module outputs the optimal power output power of the tillage component by inputting the data of the current sensor, power sensor, terrain sensor, and soil resistance sensor into the energy model; wherein the energy model adopts a fuzzy logic control algorithm or a neural network control algorithm.

[0139] In this embodiment, the specific implementation scheme of the fault diagnosis module is as follows:

[0140] 1. Sensor monitoring:

[0141] Various sensors are installed in various key systems of the tiller, including but not limited to speed sensors for monitoring motor speed, temperature sensors for monitoring oil temperature, and pressure sensors for monitoring oil pressure. For example, various sensors such as speed sensors, temperature sensors, pressure sensors, and current sensors are installed in key parts of the tiller, such as the engine, gearbox, and hydraulic system, to monitor the motor speed, oil temperature, oil pressure, current, and other working parameters in real time. These sensors collect the working parameters of key components in real time and transmit the data to the central controller.

[0142] The motor here is mainly the engine of the tiller or the power source of the tiller, while the oil temperature and oil pressure are mainly the hydraulic system powered by the two cylinders of the tiller and the oil tank of the engine.

[0143] Specifically, it can be:

[0144] Motor speed: Determine the normal operating speed range according to the motor model and specifications. For example, the normal speed range of a certain motor model is 1000-2000 rpm, and the fluctuation range within this range can be further set, such as ±50 rpm as the normal fluctuation range.

[0145] Oil temperature: Consider the working environment of the tiller and the requirements of the hydraulic system to determine the normal range of oil temperature. Generally speaking, the oil temperature is between 40-60 degrees Celsius, but under different working conditions, there may be some changes.

[0146] Oil pressure: According to the design parameters of the hydraulic system, the normal range of oil pressure is set. For example, the pressure of the main hydraulic system may be between 15-25MPa, while the pressure range of the auxiliary hydraulic system may be different.

[0147] Current: According to the rated current and load of the motor, set the normal current range. At the same time, consider the starting current and peak current of the motor and determine the corresponding allowable range.

[0148] Other parameters: such as vibration amplitude, noise level, etc., should also be set within normal ranges based on the characteristics of the equipment and working requirements.

[0149] 2. Fault diagnosis algorithm design:

[0150] Set a detailed normal range for each operating parameter. For example, the motor speed may fluctuate normally within a specific speed range, the oil temperature should be within a certain temperature range, and the oil pressure also has a corresponding reasonable pressure range.

[0151] Fault diagnosis is performed by combining multiple analysis methods. In addition to threshold judgment, trend analysis, spectrum analysis and other technologies can also be used. For example, by monitoring the trend of parameter changes, it can be determined whether there is a gradual deterioration; through spectrum analysis, it can be detected whether there are abnormal vibration or noise signals.

[0152] Among them, threshold judgment: as a basic fault detection method, when the parameter exceeds the set normal range, the fault alarm is immediately triggered.

[0153] Trend analysis: Monitor parameters in real time and record their changing trends. By analyzing the trends, determine whether there is a gradual deterioration. For example, if the oil temperature continues to rise over a period of time, it may indicate a potential failure even if it has not yet reached the set high temperature threshold.

[0154] Spectrum analysis: Use sensors to collect vibration and noise signals and perform spectrum analysis. By detecting abnormal frequency components in the spectrum, it is determined whether there are abnormal vibration or noise signals, and the possible cause of the failure can be inferred. For example, abnormal increase in vibration at a certain frequency may be related to the failure of a specific component.

[0155] Multi-parameter correlation analysis: Comprehensively consider the relationship between multiple parameters. For example, when the motor speed decreases, the current increases, and the oil temperature rises, it may indicate that the motor is overloaded and the heat dissipation is poor, and there is a possibility of multiple faults.

[0156] Establish a fault diagnosis model based on expert experience and historical data. The model should include various possible fault types, corresponding parameter abnormal patterns, and possible fault locations. For example, when the motor speed suddenly drops and the current increases, it may be that the motor load is too large or the transmission system is faulty; when the oil temperature continues to rise and the oil pressure drops, it may be that there is a leak in the hydraulic system or a cooling system failure.

[0157] The basic steps to establish a fault diagnosis model based on expert experience and historical data are as follows:

[0158] Collect expert experience: Work with experienced maintenance engineers and technicians to collect their experience knowledge on various fault types encountered in actual work, corresponding parameter abnormality patterns, and possible fault locations.

[0159] Organize historical data: Analyze the historical fault records of the tiller, including parameter data, fault description, maintenance measures and other information when the fault occurred, and find out the patterns and connections.

[0160] Construct a fault diagnosis model: Based on expert experience and historical data, a fault diagnosis model is constructed. The model should include various possible fault types, such as motor fault, hydraulic system fault, transmission system fault, etc., and list the corresponding parameter abnormality patterns for each fault type. For example, a motor fault may manifest as abnormal motor speed, abnormal current, temperature increase, etc.; a hydraulic system fault may manifest as abnormal oil pressure, abnormal oil temperature, leakage, etc. At the same time, the model should also point out the possible fault location to guide maintenance personnel to quickly locate and repair it.

[0161] Model verification and optimization: In actual applications, the accuracy and reliability of the fault diagnosis model are continuously verified, and it is optimized and improved based on new fault data and experience. For example, by analyzing actual fault cases, deficiencies in the model are discovered and timely adjustments and improvements are made.

[0162] 3. Real-time analysis and judgment:

[0163] The fault diagnosis algorithm receives parameter data from sensors in real time and performs rapid analysis.

[0164] Each parameter is monitored in real time. Once a parameter is found to be out of the normal range or showing an abnormal trend, the fault diagnosis process is immediately initiated. According to the fault diagnosis model, the abnormal conditions of multiple parameters are comprehensively analyzed to accurately determine the possible fault type and location.

[0165] 4. Alerts and information provision:

[0166] When a fault is detected, the central controller will immediately send out obvious alarm signals, such as sound and light alarms, to alert the operator. At the same time, it will provide the operator with detailed fault diagnosis information, including a description of the fault type, possible fault location, and recommended repair measures. This information can be displayed on the operation panel or sent to the operator via a mobile terminal.

[0167] In order to facilitate operators to quickly locate the fault, a location diagram of the faulty component or indicator light prompts can also be provided.

[0168] 5. Learning and Optimization:

[0169] The fault diagnosis algorithm should have learning capabilities and be able to record historical fault data, including the parameters when the fault occurred, fault type, fault location, and maintenance records.

[0170] By analyzing and learning from historical fault data, the parameters and rules of the fault diagnosis model are continuously optimized to improve the accuracy and timeliness of fault diagnosis. Machine learning algorithms, such as neural networks and decision trees, can be used to train historical data to automatically discover potential fault modes and patterns.

[0171] The code is as follows:

[0172] # Fault diagnosis algorithm function

[0173] def fault_diagnosis_algorithm(parameter_data):

[0174] # Set the normal range of parameters

[0175] normal_range = {

[0176] 'motor_speed': (min_speed, max_speed),

[0177] 'oil_temperature': (min_temp, max_temp),

[0178] 'oil_pressure': (min_pressure, max_pressure),

[0179] 'motor_current': (min_current, max_current)

[0180] # Add normal ranges for other parameters

[0181] }

[0182] # Check if the parameters are abnormal

[0183] for parameter, value in parameter_data.items():

[0184] if not normal_range[parameter][0]<= value<= normal_range[parameter][1]:

[0185] # Determine the fault type and location based on abnormal parameters

[0186] if parameter =='motor_speed' and value <normal_range[parameter][0]:

[0187] if parameter_data['motor_current']>normal_range['motor_current'][1]:

[0188] fault_type = 'motor overload'

[0189] fault_location ='motor or transmission system'

[0190] else:

[0191] fault_type = 'motor failure'

[0192] fault_location = 'motor'

[0193] elif parameter == 'oil_temperature' and value>normal_range[parameter][1]:

[0194] if parameter_data['oil_pressure'] <normal_range['oil_pressure'][0]:

[0195] fault_type = 'hydraulic system leakage'

[0196] fault_location = 'hydraulic system'

[0197] else:

[0198] fault_type = 'overheating'

[0199] fault_location = 'cooling system or excessive workload'

[0200] # Add other fault judgment logic

[0201] # Issue alerts and provide troubleshooting information

[0202] send_alarm(fault_type, fault_location)

[0203] return

[0204] # No failure detected

[0205] return 'no fault detected'

[0206] # Central controller monitoring logic

[0207] while True:

[0208] # Receive sensor parameter data

[0209] parameter_data = receive_sensor_data()

[0210] # Perform troubleshooting

[0211] fault_result = fault_diagnosis_algorithm(parameter_data)

[0212] # Take appropriate measures based on the diagnosis results

[0213] if fault_result!= 'no fault detected':

[0214] # Handling failure situations

[0215] handle_fault(fault_result)

[0216] # Record fault information

[0217] record_fault(fault_result, parameter_data)

[0218] In this embodiment, the following are specific steps to implement the energy management algorithm:

[0219] 1) Data collection:

[0220] Install a variety of sensors to fully monitor the operating load and terrain conditions. For example, soil resistance sensors are used to measure the resistance of the digging and tilling components, current sensors and power sensors monitor the working status of the motor, slope sensors measure the slope of the terrain, and height sensors obtain information such as the flatness of the ground. These sensors should have high precision and real-time performance, be able to accurately collect relevant data, and transmit the data to the control system in real time.

[0221] 2) Establish energy model:

[0222] A detailed energy consumption model is established based on the mechanical structure of the tiller, the characteristics of the power system and the collected data. The model should consider the complex relationship between power output, operating load, terrain conditions and other related factors and energy consumption.

[0223] Through the analysis and fitting of a large amount of experimental data, the specific parameters of the model can be determined. At the same time, theoretical analysis and simulation technology can also be used to verify and optimize the accuracy of the model. For example, experiments are conducted in different working scenarios, and the following data are recorded:

[0224] Power output: The speed and torque of the engine.

[0225] Working load: The soil resistance applied to the tilling components is measured using a soil resistance sensor.

[0226] Terrain conditions: Use a slope sensor to measure the slope of the terrain.

[0227] Running speed: The machine's running speed is recorded by a speed measuring device.

[0228] Soil Type: Record the soil type at the job site.

[0229] Energy consumption: Measures the fuel or electrical energy consumed by an engine.

[0230] Analyzing the collected data, it is hypothesized that the following relationship exists between energy consumption and power output, workload, terrain conditions, and operating speed:

[0231] Energy consumption = a × power output + b × workload + c × terrain conditions + d × operating speed + e

[0232] Among them, a, b, c, d are parameters to be determined, and e is a constant term. The values ​​of these parameters are determined by fitting the data using mathematical software. According to the law of conservation of energy, part of the energy output by the engine is used to overcome the workload, part is used to overcome the terrain resistance, and part is lost in the transmission system. Therefore, the various parameters in the model should correspond to these physical processes. Use simulation software to establish a virtual model of the tiller, input various parameters in the experimental data, and simulate the working process of the tiller.

[0233] 3) Algorithm design:

[0234] Based on the established energy model, an intelligent energy management algorithm is designed, which should be able to accurately control power output according to the real-time collected data on operating load and terrain conditions.

[0235] For example, when the workload is light or the terrain is flat, the power output is reduced to reduce energy waste; when the workload is heavy or the terrain is steep, the power output is appropriately increased to ensure the normal operation of the tiller. Intelligent control algorithms, such as fuzzy logic control and neural network control, can be used to achieve precise control of power output.

[0236] For example, by using a fuzzy logic control algorithm and setting multiple fuzzy rules, the corresponding power output strategy is determined according to different combinations of workload and terrain conditions. When the workload is light and the terrain is flat, the fuzzy logic control algorithm will output a lower power output command to reduce energy waste; when encountering a larger workload or steep terrain, the algorithm will automatically adjust to a higher power output to ensure that the tiller has enough power to complete the work.

[0237] Neural network control algorithms can also be used to train neural networks to learn the optimal power output mode under different operating conditions, thereby achieving smarter energy management.

[0238] 4) Real-time monitoring and adjustment:

[0239] During the operation of the tiller, sensors continuously monitor changes in load and terrain conditions in real time. The control system receives this data at a high frequency and performs real-time analysis.

[0240] The energy management algorithm makes quick decisions based on real-time data to adjust power output. For example, if it detects a sudden increase in workload or a steepening of the terrain, the algorithm will immediately increase power output to ensure the performance of the tiller; and when the workload decreases or the terrain becomes flat, the algorithm will reduce power output accordingly to achieve efficient use of energy.

[0241] At the same time, a feedback mechanism is set up to optimize and adjust the algorithm online according to the actual energy consumption. For example, by comparing the actual energy consumption with the expected consumption, the algorithm can automatically adjust the parameters to improve the accuracy and efficiency of energy management.

[0242] 5) System Integration:

[0243] Integrate the energy management algorithm into the central controller of the tiller to ensure that the algorithm and other systems (such as the travel system, tillage system, etc.) can work closely together. Achieve seamless connection between the algorithm and sensors, controllers and power systems to ensure real-time data transmission and accurate execution of instructions. For example, sensor data is transmitted to the controller via a high-speed communication bus, and the controller accurately controls the output power of the power system based on the decision results of the energy management algorithm.

[0244] In addition, a user interface can be developed to allow operators to intuitively understand the working status of the energy management system and make necessary manual interventions or settings.

[0245] Through the above steps, an energy management algorithm can be implemented to optimize the energy consumption of the tiller and extend the working time of the machine. Such an algorithm can improve the energy utilization efficiency of the tiller and reduce operating costs, while also helping to reduce the impact on the environment.

[0246] Embodiment 3

[0247] This embodiment also provides an electronic device, referring to Figure 2 , comprises a memory 404 and a processor 402, wherein the memory 404 stores a computer program, and the processor 402 is configured to run the computer program to execute the steps in any of the above method embodiments.

[0248] This electronic device may be the central controller mentioned in the above two embodiments, and the processing logic code of the central controller is as follows:

[0249] # Receive sensor data

[0250] terrain_data = receive_terrain_sensor_data()

[0251] distance_data = receive_distance_sensor_data()

[0252] soil_resistance_data = receive_soil_resistance_sensor_data()

[0253] # Analyze the data

[0254] terrain_condition = analyze_terrain(terrain_data)

[0255] operation_requirement= determine_operation_requirement(distance_data)

[0256] machine_state = check_machine_state(soil_resistance_data)

[0257] # Intelligent control decision

[0258] if terrain_condition.is_steep_slope_or_obstacle():

[0259] adjust_front_and_rear_walking_systems(height_increase=True)

[0260] elif operation_requirement.requires_depth_adjustment():

[0261] adjust_chassis_height(operation_requirement.target_depth)

[0262] elif machine_state.indicates_high_soil_resistance():

[0263] adjust_digging_parameters(machine_state.soil_hardness)

[0264] # Send control instructions

[0265] send_control_commands()

[0266] Specifically, the processor 402 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiment of the present invention.

[0267] Among them, the memory 404 may include a large capacity memory 404 for data or instructions. For example, but not limitation, the memory 404 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In appropriate cases, the memory 404 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 404 may be inside or outside the data processing device. In a specific embodiment, the memory 404 is a non-volatile memory. In a specific embodiment, the memory 404 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (Erasable Programmable Read-Only Memory, EPROM for short), an electrically erasable PROM (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), an electrically alterable ROM (Electrically Alterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. In appropriate circumstances, the RAM may be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM may be a fast page mode dynamic random access memory 404 (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0268] The memory 404 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 402 .

[0269] The processor 402 reads and executes the computer program instructions stored in the memory 404 to implement any one of the chassis adjustment control methods for the tilling machine with adjustable chassis in the above embodiments.

[0270] Optionally, the electronic device may further include a transmission device 406 and an input / output device 408 , wherein the transmission device 406 is connected to the processor 402 , and the input / output device 408 is connected to the processor 402 .

[0271] The transmission device 406 can be used to receive or send data via a network. Specific examples of the above-mentioned network may include a wired or wireless network provided by a communication provider of the electronic device. In one example, the transmission device includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 406 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0272] Input / output devices 408 are used to input or output information.

[0273] Embodiment 4

[0274] This embodiment also provides a readable storage medium, in which a computer program is stored. The computer program includes a program code for controlling a process to execute the process. The process includes a chassis adjustment control method for a tilling machine with adjustable chassis according to the first embodiment.

[0275] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0276] In general, various embodiments may be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects of the invention may be implemented in hardware, while other aspects may be implemented in firmware or software executed by a controller, microprocessor, or other computing device, but the invention is not limited thereto. Although various aspects of the invention may be shown and described as block diagrams, flow charts, or using some other graphical representation, it should be understood that, as non-limiting examples, the boxes, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0277] Embodiments of the present invention may be implemented by computer software that is executable by a data processor of a mobile device, such as in a processor entity, or by hardware, or by a combination of software and hardware. Computer software or programs (also referred to as program products) including software routines, applets and / or macros may be stored in any device-readable data storage medium, and they include program instructions for performing specific tasks. A computer program product may include one or more computer executable components configured to perform an embodiment when the program is run. One or more computer executable components may be at least one software code or a portion thereof. In addition, at this point, it should be noted that, for example, Figure 1 Any block of the logic flow in the program may represent program steps, or interconnected logic circuits, blocks and functions, or a combination of program steps and logic circuits, blocks and functions. The software may be stored on physical media such as memory chips or storage blocks implemented within the processor, magnetic media such as hard disk or floppy disks, and optical media such as, for example, DVDs and their data variants, CDs, etc. Physical media are non-transitory media.

[0278] Those skilled in the art should understand that the technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0279] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.

Claims

1. A chassis adjustment control method for a tiller with adjustable chassis, characterized in that: The following steps are involved: S00, while traveling, obtaining data from terrain sensors, distance sensors, and soil resistance sensors in real time; The terrain sensor scans the terrain around the tiller in real time to obtain terrain data; the distance sensor provides real-time relative height data between the chassis and the ground; the soil resistance sensor provides real-time resistance data of the soil to the tilling parts of the tiller; S10, inputting the terrain data, the relative height data and the resistance data into an intelligent control strategy model, and dynamically adjusting the chassis height and the working parameters of the digging and tilling components according to the output of the intelligent control strategy model; Wherein, the intelligent control strategy model is obtained by training with historical terrain data, relative height data and resistance data, and the intelligent control strategy model is based on a decision tree algorithm or a neural network; S20, when adjusting the height, inputting the terrain data, the relative height data and the resistance data into a height adjustment model, outputting the height adjustment model as a target height, and comparing the target height with the actual height after adjustment until the target height is adjusted; The height adjustment model is established based on the influence of terrain data, relative height data and resistance data on chassis height, and the training steps of the height adjustment model include: Define the ground flatness index, slope index, and soil hardness index respectively, and assign weights. The sum of the three weights equals one. A mathematical model is established to calculate the comprehensive index, which is the ground flatness index*the weight of the ground flatness index+the slope index*the weight of the slope index+the soil hardness index*the weight of the soil hardness index; Set the initial weight value based on the actual situation and experience data, and dynamically adjust the weight value according to the actual effect and feedback information during use; Formulate calculation rules and set thresholds and adjustment coefficients for each indicator: The tillage depth requirement is used as input to establish a mapping relationship between the tillage depth requirement and the chassis height adjustment, thereby determining the final chassis height adjustment amount.

2. The chassis adjustment control method of a tiller with adjustable chassis according to claim 1, characterized in that: Step S00 also includes acquiring data from a speed sensor, a temperature sensor, and a pressure sensor in real time; The speed sensor is used to monitor the motor speed; the temperature sensor is used to monitor the oil temperature; and the pressure sensor is used to monitor the oil pressure.

3. The chassis adjustment control method of a tiller with adjustable chassis as claimed in claim 2, characterized in that: In steps S00-S20, the data of the speed sensor, temperature sensor and pressure sensor are analyzed in real time by the fault diagnosis model to diagnose the type of fault, the corresponding fault location and the corresponding maintenance tutorial, and the operator is prompted by the alarm module; The fault diagnosis model is established based on expert experience and historical data, and fault diagnosis is performed by combining multiple analysis methods, including threshold judgment, trend analysis, and spectrum analysis.

4. The chassis adjustment control method of a tiller with adjustable chassis as claimed in claim 3, characterized in that: The fault diagnosis model records historical fault data from the time a fault occurs to the time it is resolved, including parameter conditions, fault type, fault location, and maintenance records when the fault occurs, and continuously optimizes itself by analyzing and learning the historical fault data using a machine learning algorithm.

5. The chassis adjustment control method of a tiller with adjustable chassis according to any one of claims 1 to 4, characterized in that: Step S00 also includes acquiring data of a current sensor, a power sensor, and a slope sensor in real time; wherein the current sensor and the power sensor are used to detect the current and power of the motor respectively, and the slope sensor is used to measure the slope of the terrain; By inputting data from current sensors, power sensors, slope sensors, and soil resistance sensors into the energy model, the optimal power output of the tillage components is output; Wherein, the energy model adopts a fuzzy logic control algorithm or a neural network control algorithm.

6. An adjustable tiller chassis, characterized in that: include: The acquisition module acquires data from terrain sensors, distance sensors, speed sensors, temperature sensors, pressure sensors, current sensors, power sensors, and soil resistance sensors in real time while traveling; Among them, the terrain sensor scans the terrain around the tiller in real time to obtain terrain data; the distance sensor provides real-time relative height data between the chassis and the ground; the soil resistance sensor provides real-time resistance data of the soil to the tilling parts of the tiller; the speed sensor is used to monitor the motor speed; the temperature sensor is used to monitor the oil temperature; the pressure sensor is used to monitor the oil pressure; An intelligent control strategy module inputs terrain data, relative height data and resistance data into an intelligent control strategy model, and dynamically adjusts the chassis height and working parameters of the digging and tilling components according to the output of the intelligent control strategy model; wherein the intelligent control strategy model is obtained by training with historical terrain data, relative height data and resistance data, and the intelligent control strategy model is based on a decision tree algorithm or a neural network; The height adjustment module inputs the terrain data, relative height data and resistance data into the height adjustment model during height adjustment, uses the height adjustment model output as the target height, and compares the target height with the actual height after adjustment until the target height is adjusted; wherein the height adjustment model is established based on the influence of the terrain data, relative height data and resistance data on the chassis height, and the training steps of the height adjustment model include: Define the ground flatness index, slope index, and soil hardness index respectively, and assign weights. The sum of the three weights equals one. A mathematical model is established to calculate the comprehensive index, which is the ground flatness index*the weight of the ground flatness index+the slope index*the weight of the slope index+the soil hardness index*the weight of the soil hardness index; Set the initial weight value based on the actual situation and experience data, and dynamically adjust the weight value according to the actual effect and feedback information during use; Formulate calculation rules and set thresholds and adjustment coefficients for each indicator: Taking the tillage depth requirement as input, a mapping relationship between the tillage depth requirement and the chassis height adjustment is established to determine the final chassis height adjustment amount; The fault diagnosis module uses a fault diagnosis model to analyze the data of the speed sensor, temperature sensor, and pressure sensor in real time to diagnose the type of fault, the corresponding fault location, and the corresponding maintenance tutorial, and prompts the operator through the alarm module; the fault diagnosis model is established based on expert experience and historical data, and performs fault diagnosis through a combination of multiple analysis methods, including threshold judgment, trend analysis, and spectrum analysis; the fault diagnosis model records historical fault data from the time a fault occurs to the time the fault is resolved, including the parameters when the fault occurs, the fault type, the fault location, and the maintenance record, and continuously optimizes itself by analyzing and learning the historical fault data using machine learning algorithms; An alarm module, used to issue an audible and visual alarm and / or a text prompt; The energy module outputs the optimal power output power of the tillage component by inputting the data of the current sensor, power sensor, terrain sensor, and soil resistance sensor into the energy model; wherein the energy model adopts a fuzzy logic control algorithm or a neural network control algorithm.

Images