Intelligent diagnosis and early warning method and system and mini-tiller

Abstract

The invention relates to the technical field of mini-tiller intellectualization, and discloses an intelligent diagnosis early warning method and system and a mini-tiller, and the method comprises the steps: building a mathematical model between soil characteristics and mini-tiller operation parameters, and employing a multi-objective optimization algorithm to carry out the comprehensive optimization of the mini-tiller operation parameters, carrying out fault prediction and diagnosis on the mini-tiller by utilizing a deep learning algorithm, fusing state data acquired by a sensor by adopting a Bayesian reasoning method, and carrying out real-time estimation on a soil state and an equipment state through a Kalman filtering algorithm; the system comprises a sensor module, a processing module, an optimization module, an intelligent diagnosis module, a Kalman filtering module and a control module. The mini-tiller comprises a rack, a power system, an operation cutter, a sensor system and an operation control system. The working state and soil conditions of the mini-tiller are monitored in real time, and an efficient sensor system and an intelligent analysis algorithm are combined, so that the technical effect of accurately monitoring the equipment state and soil characteristics is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent micro-tillers, and specifically to an intelligent diagnosis and warning method, system and micro-tiller. Background Art

[0002] With the development of agricultural modernization, as an important agricultural operation tool, the micro-tiller has been widely used in soil tillage and crop planting. The main function of the micro-tiller is to loosen and cut the soil using its cutter system, improve the soil structure, and enhance the tillage effect of the land. In traditional agricultural production, the efficient operation of the micro-tiller has significantly improved production efficiency and saved labor costs. However, in actual operation, the micro-tiller often faces challenges in different soil conditions, and the operating state of the equipment is also affected by various factors, resulting in a significant reduction in the operation effect and efficiency.

[0003] Existing traditional micro-tillers mostly adopt fixed tillage cutters. During operation, they rely on operators to manually adjust the operation depth and speed. Although they can complete basic soil tillage tasks, they lack intelligent and automatic adjustment functions, and the operation effect is unstable and the efficiency is low.

[0004] However, the operating parameters of existing subsoiling knives are difficult to adjust in real time according to soil conditions and usually rely on manual judgment or fixed settings, which leads to low operating efficiency. Especially in irregular soil environments, it is difficult to maximize the performance of the micro-tiller. Moreover, existing micro-tillers lack an intelligent diagnosis and warning system and cannot monitor the states such as wear and force of the subsoiling knives in real time. They rely on manual inspection and regular maintenance, and it is difficult to detect potential faults in time, resulting in equipment damage and operation interruption. Therefore, the present invention provides an intelligent diagnosis and warning method, system and micro-tiller to solve the deficiencies in the prior art. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the present invention provides an intelligent diagnosis and warning method, system and micro-tiller, which solves the problem that the operating parameters of existing subsoiling knives are difficult to adjust in real time according to soil conditions and usually rely on manual judgment or fixed settings, resulting in low operating efficiency.

[0006] To achieve the above object, the present invention is realized through the following technical solutions: An intelligent diagnosis and warning method for a micro-tiller includes the following steps:

[0007] By establishing a mathematical model between soil characteristics and micro-tiller operating parameters, a non-linear relationship of micro-tiller operating parameters is obtained;

[0008] Based on the mathematical model, a multi-objective optimization algorithm is used to comprehensively optimize the micro-tiller operating parameters, and preliminary operating parameters are calculated;

[0009] Collect the status data of the micro-tiller through sensors, and use deep learning algorithms to predict and diagnose the faults of the micro-tiller;

[0010] Adopt the Bayesian inference method to fuse the status data collected by sensors, calculate the probability of equipment failure and issue early warnings;

[0011] Estimate the soil status and equipment status in real time through the Kalman filtering algorithm, optimize the preliminary operation parameters and adjust the operation parameters of the micro-tiller.

[0012] Preferably, the operation parameters of the micro-tiller include operation depth, rotation speed, tool wear, operation efficiency, soil disturbance degree, and contact force between the tool and the soil.

[0013] Preferably, the non-linear relationship is constructed through tribology theory and material mechanics theory, specifically:

[0014] F c = k1·S a ·H b ·D y ;

[0015] Among them, F c represents the contact force between the soil and the tool, S represents the soil hardness, H represents the soil humidity, D represents a certain measure of the soil particle structure; a, b, y are parameters to be fitted, and k1 is a constant.

[0016] Preferably, the steps of establishing the mathematical model between the soil characteristics and the operation parameters of the micro-tiller include the following:

[0017] Collect the soil characteristic data and the corresponding micro-tiller operation parameter data under different operation conditions, and the soil characteristic data includes soil hardness, humidity and particle structure;

[0018] Based on the regression analysis method or machine learning algorithm, establish a mathematical model for the relationship between the soil characteristic data and the micro-tiller operation parameters;

[0019] Evaluate the error of the established mathematical model and correct the parameters.

[0020] Preferably, the steps of comprehensively optimizing the operation parameters of the micro-tiller by using the multi-objective optimization algorithm include:

[0021] Define multiple optimization objectives, including operation depth, operation efficiency, tool wear degree and soil disturbance degree;

[0022] Select a suitable multi-objective optimization algorithm, adopt the particle swarm optimization algorithm or the multi-objective genetic algorithm, and weight the optimization process according to the weight of each objective;

[0023] Iteratively calculate the optimization algorithm to solve the optimal combination of operation parameters, and adjust the key parameters of the micro-tiller according to the optimization results.

[0024] Preferably, the steps of using the deep learning algorithm for fault prediction and diagnosis of the micro-tiller include:

[0025] Collect and preprocess the sensor data of the micro-tiller, including the status data of pressure, temperature, vibration and rotational speed;

[0026] Construct and train a deep learning model, using a convolutional neural network or a long short-term memory network, and perform supervised learning through historical fault data and normal working data to learn the fault patterns of the micro-tiller;

[0027] Use the trained deep learning model to predict the real-time collected status data of the micro-tiller, diagnose whether there are potential faults in the equipment, and output the probability of the fault and the type of the fault.

[0028] Preferably, the sensor data includes the data of pressure sensors, temperature sensors, vibration sensors and rotational speed sensors, and the data fusion technology is used for fault prediction and adjustment of the operation parameters of the micro-tiller.

[0029] Preferably, the soil conditions include soil hardness, humidity and particle structure, the equipment conditions include the pressure, temperature, vibration and rotational speed of the micro-tiller, and the soil conditions and equipment conditions are used to evaluate the operation environment and mechanical operation status in real time.

[0030] An intelligent diagnostic and warning micro-tiller system is also provided, including the following modules:

[0031] A sensor module, used to collect soil characteristic data and micro-tiller status data;

[0032] A processing module, used to establish a relationship model between soil characteristics and operation parameters;

[0033] An optimization module, used to perform multi-objective optimization calculation and operation parameter adjustment;

[0034] An intelligent diagnostic module, used to perform equipment fault prediction and diagnosis;

[0035] A Kalman filter module, used to estimate the soil and micro-tiller status in real time and adjust the operation parameters;

[0036] A control module, used to transmit the adjusted operation parameters to the micro-tiller control system.

[0037] An intelligent diagnostic and warning micro-tiller is also provided, including:

[0038] A frame, used to support the components of the micro-tiller and ensure its stability during operation;

[0039] A power system, including an engine or a drive motor, is used to provide the power required for the operation of the micro-tiller.

[0040] An operating tool is used for soil tillage and cutting operations.

[0041] A sensor system, including a temperature sensor, a pressure sensor, and a vibration sensor, is used to collect the operating state data of the micro-tiller.

[0042] An operating control system is used to adjust the operating parameters according to the intelligent diagnosis and early warning method.

[0043] The present invention provides an intelligent diagnosis and early warning method, system, and micro-tiller. It has the following

[0044] Beneficial effects:

[0045] 1. The present invention adopts an intelligent diagnosis and early warning system. By real-time monitoring the operating state of the micro-tiller and soil conditions, combined with an efficient sensor system and intelligent analysis algorithms, it achieves the technical effect of accurately monitoring the equipment state and soil characteristics. Compared with the traditional micro-tiller system that relies on manual judgment or regular maintenance in the prior art, the present invention can predict and diagnose equipment failures in real time, avoid the occurrence of sudden equipment failures, and greatly improve the operating reliability and work efficiency of the equipment.

[0046] 2. The present invention realizes the precise adjustment of the operating parameters of the micro-tiller through the combination of a Kalman filter module and an optimized control system. This technical solution effectively solves the problem of lag in adjusting operating parameters in the prior art, ensures that the micro-tiller can adapt to and maintain the best operating state in real time in a dynamic soil environment. Through this intelligent adjustment, the work efficiency of the micro-tiller is significantly improved, and at the same time, unnecessary energy consumption and equipment wear are reduced.

[0047] 3. The present invention introduces a multi-objective optimization algorithm, comprehensively considering various factors such as operating depth, efficiency, and tool wear, and achieves the technical effect of optimizing the operating parameters of the micro-tiller. Compared with the traditional operating scheme that only considers a single factor, the present invention can achieve comprehensive optimization in a complex operating environment, ensuring both the work quality and work efficiency. The optimized operating parameters also reduce the risk of premature equipment damage and extend the service life of the micro-tiller.

[0048] 4. The intelligent diagnosis module of the present invention can perform real-time analysis and fault prediction on various state data of the micro-tiller, achieving the technical effects of early warning and maintenance. This technical solution solves the problem of passive response to equipment failures in the prior art, discovers potential failures in advance and issues warnings, thereby reducing the downtime and maintenance costs. Through this intelligent early warning mechanism, the work safety and stability of the micro-tiller are significantly improved. Brief Description of the Drawings

[0049] Figure 1 is the flowchart of the method steps of the present invention;

[0050] Figure 2 is the system architecture diagram of the present invention;

[0051] Figure 3 is the schematic diagram of the micro-tiller of the present invention. Detailed Embodiments

[0052] Next, in combination with the accompanying drawings of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present invention.

[0053] Please refer to the attached Figure 1 , the embodiment of the present invention provides a method for intelligent diagnosis and early warning of a micro-tiller, including the following steps:

[0054] S1. By establishing a mathematical model between soil characteristics and micro-tiller operation parameters, a non-linear relationship of micro-tiller operation parameters is obtained;

[0055] S2. Based on the mathematical model, a multi-objective optimization algorithm is used to comprehensively optimize the micro-tiller operation parameters, and preliminary operation parameters are calculated;

[0056] S3. The state data of the micro-tiller, including pressure, temperature, vibration, and rotation speed, are collected by sensors, and a deep learning algorithm is used for fault prediction and diagnosis of the micro-tiller;

[0057] S4. A Bayesian inference method is used to fuse the state data collected by sensors, calculate the probability of equipment failure, and give an early warning in advance;

[0058] S5. The soil state and equipment state are estimated in real time by a Kalman filter algorithm, the preliminary operation parameters are optimized, and the micro-tiller operation parameters are adjusted.

[0059] For step S1, in this embodiment, in order to establish a more accurate mathematical model, a regression analysis method or a machine learning algorithm can be used to model the relationship between soil characteristics and micro-tiller operation parameters. The regression analysis method is usually used to process soil characteristic and operation parameter data with significant statistical correlation. Through the least squares method or other regression methods, a set of mathematical formulas can be obtained to describe the relationship between soil characteristics and operation parameters.

[0060] Specifically, in some embodiments, machine learning algorithms such as support vector machine (SVM) or random forest can effectively process more complex and higher-dimensional data and can dynamically adapt to the impact of soil property changes on operation parameters. These methods gradually improve the accuracy of the model in predicting the relationship between soil properties and operation parameters by training the model.

[0061] In certain embodiments, the established mathematical model is further optimized through tribology theory and material mechanics theory. Based on tribology theory, the contact force between the soil and the tool affects the depth and efficiency of the micro-tiller operation, while material mechanics theory can help analyze the correlation between tool wear and factors such as soil hardness and humidity. By combining these two theories, a non-linear mathematical relationship can be constructed to more accurately simulate the interaction between the soil and the micro-tiller operation.

[0062] In one implementation, this non-linear relationship can be described by the following formula:

[0063] F c =k1·S a ·H b ·D y ;

[0064] Wherein, F c represents the contact force between the soil and the tool, S represents the soil hardness, H represents the soil humidity, D represents a certain measure of the soil particle structure; a, b, y are parameters to be fitted, and k1 is a constant. Through regression analysis or machine learning algorithms, the specific values of the above parameters can be determined, so that the model can accurately reflect the impact of different soil properties on the micro-tiller operation parameters.

[0065] Generally, through the establishment of such a mathematical model, changes in different soil types, operation depths, tool wear, etc. can be comprehensively considered, thereby providing an accurate theoretical basis for the optimization of micro-tiller operation parameters. Through continuous optimization of the model, the system can dynamically adjust the working parameters of the micro-tiller according to soil changes and operation requirements, so that it always maintains the best working state.

[0066] As an option, in this embodiment, the established mathematical model can also be subjected to error evaluation and parameter correction. This process can be achieved by comparing the error between the actual operation data and the model prediction results. In the case of a large error, the model parameters are adjusted through a feedback correction algorithm to improve the adaptability and prediction accuracy of the model.

[0067] For step S2, in this embodiment, in order to achieve the comprehensive optimization of operation parameters, it is first necessary to define multiple optimization objectives. These objectives generally include operation depth, operation efficiency, tool wear degree, and soil disturbance degree, etc. The operation depth directly affects the tillage effect of the soil, while the operation efficiency determines the workload of the micro-tiller within a certain period of time. The tool wear degree and soil disturbance degree affect the service life of the equipment and the soil structure. Therefore, optimizing these parameters is the key to ensuring the efficient and durable operation of the micro-tiller during operation.

[0068] Generally, the particle swarm optimization algorithm (PSO) or multi-objective genetic algorithm (MOGA) is used as the optimization algorithm because it can find the global optimal solution in multi-dimensional space and can handle the trade-off between multiple objectives. In these embodiments, it is first necessary to assign different weights to each optimization objective according to actual needs to reflect the importance between different objectives. For example, operation efficiency may occupy a higher weight in some specific application scenarios, while in some occasions that require fine tillage, the weights of tool wear degree and soil disturbance degree may be higher.

[0069] As an option, during the optimization process, the optimization algorithm will perform multiple iterative calculations. In each iteration, by evaluating the performance of each set of operation parameters, it gradually converges to the optimal operation parameter combination. These operation parameters can include key indicators such as the operation depth, rotation speed, tool wear, and soil disturbance of the micro-tiller. Through these iterative calculations, a set of optimal operation parameters is finally obtained to ensure that the micro-tiller can achieve the best operation effect in the actual working environment.

[0070] Specifically, in some embodiments, the optimization of the micro-tiller operation parameters can be achieved through a weighted total objective function. Assuming that a certain objective function is f1 and its corresponding weight is w1, the total objective function can be expressed as:

[0071] F total =w1·f1 + w2·f2 + … + w n ·f n ;

[0072] Among them, F total represents the weighted sum of all optimization objectives, f1, f2, …, f n respectively represent each optimization F total represents the weighted sum of all optimization objectives, f1, f2, … (such as soil disturbance degree), and w1, w2, …, w n are the corresponding objective weights. During the optimization process, the algorithm adjusts the parameters of each objective to minimize or maximize the total objective function, thereby solving a set of optimal operation parameters.

[0073] In a possible implementation, through the Particle Swarm Optimization (PSO) algorithm, each member of the particle swarm (i.e., a solution) represents a potential combination of operation parameters. During the optimization process, each particle adjusts its position towards a better direction based on its own experience and the experience of the entire swarm. After multiple iterations, the particle swarm will eventually converge to the global optimal solution, thereby determining the best operation parameters.

[0074] As a further implementation, constraint conditions can also be introduced to limit the optimization process. For example, when the soil hardness is high, the operation depth may not be too deep to avoid damage to the cutting tools due to excessive friction; or under soil conditions with high humidity, the operation depth should be appropriately adjusted to avoid excessive disturbance of the soil structure. Therefore, appropriate constraint conditions need to be set in the optimization algorithm according to these actual situations to ensure that the optimization results can meet the working requirements of the equipment in practical applications.

[0075] Generally, this multi-objective optimization algorithm can handle multiple objectives simultaneously. By weighing the relationships between the objectives, it generates a combination of operation parameters that meets the actual requirements. In practical applications, these parameter combinations can ensure that the micro-tiller maintains the optimal operation effect under different soil conditions and maximally extends the service life of the equipment.

[0076] In some embodiments, to further improve the accuracy and reliability of the optimization results, the optimization algorithm can also perform real-time feedback with actual operation data. By real-time monitoring the operation effect of the micro-tiller, comparing the calculation results of the optimization algorithm with the on-site data, and dynamically adjusting the objective weights in the optimization process according to the comparison results, the optimization scheme can better meet the actual working requirements.

[0077] For step S3, in this embodiment, to achieve real-time adjustment of operation parameters, a series of sensors need to be deployed on the micro-tiller first. These sensors include soil humidity sensors, soil hardness sensors, operation depth sensors, tool wear sensors, etc. The role of these sensors is to collect data on soil conditions and the operation status of the micro-tiller in real time and transmit the data to the central control system. The control system matches the real-time data provided by the sensors with the established mathematical model to obtain the operation parameters that need to be adjusted during the actual operation process.

[0078] Under normal circumstances, for the data collected by sensors, the control system will compare it with the operation parameters obtained through preliminary optimization to determine whether the operation parameters need to be adjusted. For example, when the soil humidity is high, the system may need to adjust the operation depth to avoid excessive disturbance to the soil structure; while when the soil hardness is high, it may be necessary to increase the operation depth to improve the operation effect and work efficiency. At this time, by adjusting operation parameters such as the operation depth and cutter speed in real time, it is possible to ensure that the micro-tiller operation can maintain the best operation performance under various soil conditions.

[0079] Specifically, in this embodiment, the feedback correction algorithm used can be designed based on control theory or fuzzy logic. The PID control (Proportional-Integral-Derivative control) algorithm in control theory is often used in real-time feedback systems. This algorithm generates an adjustment signal based on the deviation between the data feedback by the sensor and the preliminary operation parameters, and controls the operation parameters of the micro-tiller to make it as close as possible to the ideal state.

[0080] For example, when the soil humidity and hardness change, through the feedback mechanism of the PID controller, the operation depth and cutter speed can be dynamically adjusted:

[0081]

[0082] Among them, u(t) represents the control output signal of the system, e(t) represents the error between the sensor feedback data and the target parameter, K p , K i , K d are the proportional, integral, and derivative coefficients respectively, represents the error accumulation (integration) from 0 to the current moment t, t is the time variable, τ is the virtual time variable of integration, is the differential part of the error. Through this control algorithm, the system can correct the operation parameters in real time, thus ensuring the accuracy and efficiency of the operation.

[0083] As an option, a fuzzy logic control algorithm can also be adopted. In fuzzy logic control, the system processes the data feedback by the sensor according to a preset fuzzy rule base to generate a control signal. For example, when the soil humidity is too high, the fuzzy rule may be defined as "if the humidity is high, then reduce the operation depth"; while when the soil hardness is too large, it is "if the hardness is large, then increase the operation depth". This control method can provide more flexible parameter adjustment in more complex situations.

[0084] In a possible implementation, the feedback correction process is not limited to adjusting the operation depth and the tool rotation speed, but can also involve optimizing other parameters. For example, the influence of tool wear on the operation effect can also be monitored in real time by sensors. When the tool wears to a certain extent, the system will trigger a mechanism for repairing or replacing the tool to ensure that the rotary tiller is always in the best operating state.

[0085] In some embodiments, the adjustment process can also be combined with a fault diagnosis module. When an abnormal situation occurs during the operation (such as tool failure, sudden change in soil conditions, etc.), the system can immediately issue a warning and make corresponding adjustments. For example, if the soil hardness changes beyond a predetermined threshold, the system can automatically adjust the operation parameters to avoid excessive tool wear or reduced operation efficiency, and at the same time feedback the fault information to the operator.

[0086] Generally, through dynamic feedback and adjustment, it is possible to ensure that the rotary tiller is always in the optimal working state during the operation. This process can not only improve the operation efficiency, reduce unnecessary energy consumption, but also extend the service life of the equipment, reduce the frequency of failures, thereby greatly improving the economic efficiency and stability of the entire rotary tiller system.

[0087] For step S4, in this embodiment, the operation state of the rotary tiller is further optimized through real-time data collection and an intelligent decision-making mechanism. Specifically, in this step, the rotary tiller continuously collects information on changes in the soil environment through sensors and inputs this data into the central control system. Based on the pre-established model and real-time feedback information, the system makes further corrections to the operation parameters. This correction not only involves basic operation parameters such as operation depth and rotation speed, but can also adjust the tool wear condition, soil disturbance condition, etc.

[0088] Generally, real-time correction is based on an intelligent algorithm built into the system (for example, an optimization algorithm based on machine learning or deep learning). By analyzing historical data and current operation data, it predicts possible changes during the operation. According to these prediction results, the system can automatically generate adjustment signals and send adjustment instructions to the rotary tiller for corresponding parameter optimization.

[0089] As an option, an adaptive control algorithm can be introduced. Such algorithms continuously adjust control parameters according to the real-time data input into the system to maximize the system performance. By making real-time adjustments to each step of the operation process, the system can adaptively adjust the operation depth, tool rotation speed, etc. under different soil conditions to ensure that the operation effect is not affected by the external environment.

[0090] Specifically, the monitoring of the operating state of the micro-tiller is optimized through the following key indicators: soil humidity, soil hardness, tillage depth, tool wear, and soil disturbance, etc. Based on these monitoring data, the system uses mathematical models (such as statistical analysis methods based on regression analysis, least squares method, etc.) to establish an accurate relationship between the input and output, and adjusts the operating parameters in real time according to these relationships. For example, assume the function for controlling the depth is:

[0091] D(t) = f(H, M, S);

[0092] where D(t) is the tillage depth, H is the soil hardness, M is the soil humidity, S is the tool wear state, and the function f(·) is the relationship between the tillage depth and other parameters deduced according to the real-time data and the model. By tracking the real-time changes of these input parameters, the system can adjust the tillage depth according to the set rules, so that the micro-tiller always maintains the optimal operating state.

[0093] In a possible implementation, a fuzzy control system can be introduced to handle the uncertainties in the operation process. The fuzzy control system can generate different operating parameter adjustment strategies according to various input conditions in different soil environments. For example, when the soil humidity is too low, the system will adjust the tillage depth according to the preset fuzzy rules to reduce soil damage; while in the case of higher humidity, it will adjust the tool rotation speed and tillage depth according to another set of fuzzy rules to ensure the operation effect. Fuzzy control can effectively handle the uncertainties of the system input and avoid the performance limitations caused by fixed rules in traditional control systems.

[0094] As a further implementation, a real-time fault diagnosis module can be considered. By analyzing the operating state of the equipment, such as abnormal fluctuations in operating parameters, abnormal changes in tool wear, etc., this module can detect potential faults in time and perform self-correction or send out warning signals. For example, when the tool wear reaches the set threshold, the system will automatically lower the tillage depth or send a reminder to replace the tool; when there is an abnormal deviation in the tillage depth, the system will automatically correct the depth, thus avoiding the decline of the operation effect.

[0095] Generally, it is not just a single parameter correction process, but also involves multi-dimensional optimization in the whole operation process. Through real-time monitoring and dynamic adjustment, the micro-tiller can always maintain the optimal operating state, thereby improving the operation efficiency, reducing soil disturbance, reducing tool wear, and at the same time improving the reliability and economic benefits of the whole system.

[0096] For step S5, in this embodiment, by recording and analyzing the operation data of the entire operation process, the operation strategy of the micro-tiller is further optimized. In this step, the sensors of the micro-tiller not only collect environmental data in real time, but also can feedback various status information during the operation process, such as operation depth, tool wear, operation efficiency, etc. Through the analysis of the central control system, these data are compared with the previously optimized operation parameters, so as to provide feedback for subsequent operations and self-adjust the system.

[0097] Generally, by reviewing the data of the entire operation process and combining historical data with real-time feedback, the operation effect of the micro-tiller is comprehensively evaluated. This process includes analyzing the relationship between operation parameters and operation effects, so as to find potential improvement spaces and further optimize the operation process and parameter settings.

[0098] As an option, various evaluation methods can be introduced to evaluate the operation effect. For example, the system can evaluate the impact of the micro-tiller on the soil according to the relationship between the operation depth and the degree of soil disturbance. The operation efficiency can be evaluated by comparing the workload per unit time under different operation modes, and the tool wear condition can be estimated by analyzing the sensor data to obtain its actual service life and maintenance cycle.

[0099] Specifically, in this embodiment, the execution also involves the statistics and processing of operation data. For example, assume that the system continuously monitors indicators such as soil humidity, operation depth, and tool wear during the entire operation process, and obtains a set of data sets {D1, D2, …, D n}, where D i represents the data collected in the i-th time. Through statistical analysis of these data, the system obtains key indicators such as the average depth, average efficiency, and tool wear rate of the operation, and compares them with the preset optimal parameters. The evaluation is carried out through the following mathematical formula:

[0100]

[0101] Among them, E i represents the efficiency during the i-th operation process, E avg is the average value of the operation efficiency, and n is the number of operations. Based on these data, the system can judge the deviation between the current operation state and the expected target, and correct it by adjusting the operation parameters.

[0102] In a possible implementation, the operation process can be further optimized through data mining techniques. By performing in-depth learning analysis on historical operation data, the system can discover potential patterns in the operation process and predict possible problems that may occur in future operation processes. For example, through training on a large amount of soil type and operation data, the system can predict the best match between operation depth and efficiency under a specific soil condition, thereby providing optimization suggestions for subsequent operations.

[0103] As a further implementation, the analysis and evaluation results can be used not only for the immediate adjustment of the micro-tiller but also for long-term operation strategy planning. Through long-term accumulation and analysis of operation data, the system can form an optimized operation model and adjust the operation strategy of the micro-tiller according to factors such as different seasons, climates, and soil conditions. For example, in the case of low soil moisture, it may be necessary to increase the operation depth; while in a high-humidity environment, it may be necessary to reduce the operation depth to avoid excessive disturbance of the soil structure. Through these real-time adjustments and long-term strategy planning, the micro-tiller can achieve more efficient, economical, and environmentally friendly operations.

[0104] A micro-tiller intelligent diagnosis and early warning system described below can be correspondingly referred to with a micro-tiller intelligent diagnosis and early warning method described above.

[0105] Please refer to the attached Figure 2 , the present invention also provides a micro-tiller intelligent diagnosis and early warning system, including:

[0106] A sensor module for collecting soil characteristic data and micro-tiller status data; the sensor module includes a soil moisture sensor, a soil hardness sensor, an operation depth sensor, a tool wear sensor, a rotation speed sensor, etc., to obtain parameters related to soil conditions and the operating state of the micro-tiller in real time. These data provide basic support for subsequent data processing and decision-making.

[0107] A processing module for establishing a relationship model between soil characteristics and operation parameters; by establishing a relationship model between soil characteristics and operation parameters, analyzing the influence of soil characteristics such as moisture, hardness, and temperature on the operation of the micro-tiller, and constructing an accurate mathematical model. This module builds an optimized model based on historical data and real-time collected data through technologies such as machine learning, thereby providing a basis for the intelligent adjustment of the micro-tiller

[0108] An optimization module for performing multi-objective optimization calculations and adjusting operation parameters; by combining soil data with operation requirements, using multi-objective optimization algorithms (such as particle swarm optimization algorithm, genetic algorithm, etc.) to intelligently optimize and adjust parameters such as the operation depth and rotation speed of the micro-tiller to improve operation efficiency, reduce equipment wear, and ensure operation quality. The output of this module will be the basis for subsequent decision-making and control module adjustments.

[0109] An intelligent diagnosis module, which is used for equipment fault prediction and diagnosis; based on sensor data and historical fault data, using artificial intelligence and data mining algorithms (such as deep learning, support vector machine, etc.), it evaluates the equipment status in real time and predicts potential fault risks. For example, when the system detects tool wear, abnormal transmission system or other equipment performance degradation, it can issue early warning signals in advance and trigger corresponding maintenance strategies to avoid adverse effects on operations caused by equipment failures.

[0110] A Kalman filter module, which is used for real-time estimation of the soil and the micro-tiller status and adjustment of operation parameters; adopting the Kalman filter algorithm, by fusing measurement data from multiple sensors, it estimates the optimal estimated value of the soil conditions and the micro-tiller status in real time. This estimated value can be used to adjust the operation parameters of the micro-tiller in real time, so as to achieve more precise operation control, especially to maintain the stability of the system when the environment changes greatly.

[0111] A control module, which is used for transmitting the adjusted operation parameters to the micro-tiller control system; through real-time communication with the control system of the micro-tiller, it precisely controls key parameters such as operation depth and rotation speed to ensure that the micro-tiller can operate efficiently and stably under different soil conditions. The control module can also automatically adjust the operation strategy or stop the operation when receiving the warning information from the intelligent diagnosis module to ensure the safe operation of the equipment.

[0112] The system of this embodiment can be used to execute the above method embodiment, and its principle and technical effects are similar, so they will not be elaborated here.

[0113] An intelligent diagnosis and warning micro-tiller described below can be correspondingly referred to with a micro-tiller intelligent diagnosis and warning method described above.

[0114] Please refer to the appendix Figure 3 , the present invention also provides an intelligent diagnosis and warning micro-tiller, including:

[0115] A frame, which is used for supporting the components of the micro-tiller and ensuring its stability during operation; the frame is made of high-strength materials and has good compressive and vibration resistance performance, and can maintain the stability and durability of the micro-tiller in a complex soil environment. The design of the frame takes into account the operation requirements of the micro-tiller and is easy for later maintenance and replacement of accessories, ensuring the long-term use reliability of the micro-tiller.

[0116] A power system, including an engine or a drive motor, which is used for providing the power required to drive the micro-tiller to work; it is optimized according to the working environment and operation intensity requirements of the micro-tiller to ensure that the micro-tiller can operate continuously and stably under high-load conditions. At the same time, the power system has energy-saving features and can adjust the power output according to different operation modes to improve the fuel use efficiency or the electric energy utilization rate and reduce energy waste during operation.

[0117] Working tool, used for soil tillage and cutting operations; the working tool is made of highly wear-resistant materials and precisely designed, capable of efficiently handling various soil types, including soft soil, clayey soil, etc. The shape and cutting depth of the tool can be automatically adjusted according to real-time soil feedback to ensure the optimization of the operation effect. In the implementation of the present invention, the tool is also integrated with a wear sensor, which can monitor the wear status of the tool in real time and send a warning signal through the intelligent diagnosis module when the set wear threshold is reached.

[0118] Sensor system, including a temperature sensor, a pressure sensor, and a vibration sensor, used to collect the working state data of the micro-tiller; the temperature sensor monitors the temperature of the engine or drive motor to avoid overheating; the pressure sensor detects the cutting pressure of the working tool to ensure the normal operation of the tool and avoid overload; the vibration sensor can detect possible mechanical failures (such as bearing damage, tool imbalance, etc.) by monitoring the vibration frequency of the micro-tiller. The data collected by the sensor system will be transmitted to the control system of the micro-tiller in real time for the intelligent diagnosis module to perform real-time analysis and fault prediction.

[0119] Operation control system, used to adjust the operation parameters according to the intelligent diagnosis and warning method; receive the data from the sensor system in real time, and combine the relationship model between the preset soil characteristics and operation parameters to automatically optimize key parameters such as operation depth and tool rotation speed to ensure the efficiency and stability of the operation. In addition, the operation control system is also linked with the intelligent diagnosis module. When the system detects a device failure or abnormality, it can automatically adjust the operation parameters to reduce damage to the device and even trigger an emergency shutdown procedure to prevent the expansion of the fault.

[0120] The micro-tiller of this embodiment can be used to implement the above method embodiment, and its principle and technical effects are similar, so they will not be elaborated here.

[0121] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent diagnosis and early warning method for a micro-tiller, characterized in that, It includes the following steps: By establishing a mathematical model between soil properties and microtiller operation parameters, a non-linear relationship of microtiller operation parameters is obtained; Based on the mathematical model, a multi-objective optimization algorithm is used to comprehensively optimize the microtiller operation parameters, and preliminary operation parameters are calculated; The state data of the microtiller is collected through sensors, and a deep learning algorithm is used for fault prediction and diagnosis of the microtiller; The Bayesian inference method is used to fuse the state data collected by sensors, calculate the probability of equipment failure and issue an early warning; The real-time estimation of soil state and equipment state is carried out through the Kalman filtering algorithm, the preliminary operation parameters are optimized, and the microtiller operation parameters are adjusted.

2. The intelligent diagnosis and early warning method for a micro-tiller according to claim 1, wherein, The microtiller operation parameters include operation depth, rotation speed, tool wear, operation efficiency, soil disturbance degree, and contact force between the tool and the soil.

3. The intelligent diagnosis and early warning method for a micro-tiller according to claim 1, wherein The non-linear relationship is constructed through tribology theory and material mechanics theory, specifically: F c = k1·S a ·H b ·D y ; Among them, F c represents the contact force between the soil and the tool, S represents the soil hardness, H represents the soil humidity, and D represents a certain measure of the soil particle structure; a, b, and y are parameters to be fitted, and k1 is a constant.

4. The intelligent diagnosis and early warning method for a micro-tiller according to claim 1, wherein The establishment of the mathematical model between soil properties and microtiller operation parameters includes the following steps: Collect soil property data and corresponding microtiller operation parameter data under different operation conditions. The soil property data includes soil hardness, humidity, and particle structure; Based on the regression analysis method or machine learning algorithm, establish a mathematical model for the relationship between soil property data and microtiller operation parameters; Carry out error evaluation and parameter correction for the established mathematical model.

5. The intelligent diagnosis and early warning method for a micro-tiller according to claim 1, characterized in that, The steps of comprehensively optimizing the microtiller operation parameters by using the multi-objective optimization algorithm include: Define multiple optimization objectives, including operation depth, operation efficiency, tool wear degree, and soil disturbance degree; Select a suitable multi-objective optimization algorithm, adopt the particle swarm optimization algorithm or multi-objective genetic algorithm, and weight the optimization process according to the weight of each objective; Carry out iterative calculation on the optimization algorithm, solve the optimal operation parameter combination, and adjust the key parameters of the microtiller according to the optimization results.

6. The intelligent diagnosis and early warning method for a micro-tiller according to claim 1, characterized in that, The steps of using the deep learning algorithm for fault prediction and diagnosis of the microtiller include: Collect and preprocess the sensor data of the microtiller, including the state data of pressure, temperature, vibration, and rotation speed; Construct and train a deep learning model, adopt a convolutional neural network or long short-term memory network, and carry out supervised learning through historical fault data and normal working data to learn the fault patterns of the microtiller; Use the trained deep learning model to predict the real-time collected microtiller state data, diagnose whether there are potential faults in the equipment, and output the probability of the fault and the fault type.

7. The intelligent diagnosis and early warning method for a micro-tiller according to claim 6, wherein The sensor data includes the data of pressure sensors, temperature sensors, vibration sensors, and rotation speed sensors, and data fusion technology is used for fault prediction and microtiller operation parameter adjustment.

8. The intelligent diagnosis and early warning method for a micro-tiller according to claim 1, wherein The soil state includes soil hardness, humidity, and particle structure, and the equipment state includes the pressure, temperature, vibration, and rotation speed of the microtiller. The soil state and equipment state are used to evaluate the operation environment and mechanical operation status in real time.

9. An intelligent diagnosis and early warning system for a micro-tiller, which is applied to the intelligent diagnosis and early warning method for a micro-tiller according to any one of claims 1-8, and is characterized in that, It includes the following modules: Sensor module, used to collect soil property data and microtiller state data; Processing module, used to establish a relationship model between soil properties and operation parameters; Optimization module, used to carry out multi-objective optimization calculation and operation parameter adjustment; An intelligent diagnosis module for equipment fault prediction and diagnosis; A Kalman filter module for real-time estimation of the soil and micro-tiller states and adjustment of operating parameters; A control module for transmitting the adjusted operating parameters to the micro-tiller control system.

10. An intelligent diagnostic and warning micro-tiller, applied to the intelligent diagnostic and warning method for a micro-tiller according to any one of claims 1-8, characterized in that, It includes: A frame for supporting the components of the micro-tiller and ensuring its stability during operation; A power system including an engine or a drive motor for providing the power required to drive the micro-tiller; Working tools for soil tillage and cutting operations; A sensor system including a temperature sensor, a pressure sensor, and a vibration sensor for collecting the working state data of the micro-tiller; An operation control system for adjusting operating parameters according to the intelligent diagnosis and early warning method.

Images