Self-adaptive wear monitoring and diagnosing system for chain blade

Abstract

The invention provides a chain blade self-adaptive wear monitoring and diagnosis system, and relates to the technical field of wear monitoring, and the system comprises an operation data collection module which is used for collecting blade operation data; the operation wear module is used for carrying out wear diagnosis on the blade operation data; the operation optimization module is used for introducing a first operation strategy to carry out operation optimization; the depth wear module is used for carrying out wear diagnosis on the first depth operation data; the depth maintenance module is used for introducing a second operation strategy to carry out depth maintenance on the first depth operation data; and the continuous monitoring module is used for starting the self-adaptive blade operation data and continuously monitoring the self-adaptive blade operation data. The technical problem that in the prior art, due to the fact that corresponding diagnosis and optimization strategies are not provided according to different stages or different positions of abrasion, the maintenance efficiency is low can be solved, the self-adaptive adjustment strategy is adopted according to the abrasion characteristics of the blade through the multi-dimensional sensor, and the maintenance efficiency of the chain blade is improved.

Description

Technical Field

[0001] The present application relates to the technical field of wear monitoring, and in particular to a chain blade adaptive wear monitoring and diagnosis system. Background Art

[0002] A chain blade is a tool used to cut or sever materials. It is usually composed of a series of metal blades and chains. Similar to a chain, the sharp edge of the blade is used to complete the cutting work through the movement of the chain. It is commonly used in wood cutting, tree pruning, and certain industrial applications. During long-term use, chain blades often wear unevenly due to the different cutting loads borne by different parts, resulting in excessive wear on one part of the blade while other parts are relatively lightly worn. Uneven wear not only affects the cutting performance of the blade, but may also cause the blade to be unbalanced, further exacerbating the wear. Existing wear diagnosis is difficult to provide customized solutions for different stages or locations of wear, and the use of the same maintenance strategy may lead to waste of resources or inappropriate maintenance timing.

[0003] In summary, the prior art has technical problems such as uneven wear due to different cutting loads borne by different parts of the chain blade, difficulty in providing corresponding diagnosis and optimization strategies according to different stages or positions of wear, resulting in low maintenance efficiency. Summary of the invention

[0004] The purpose of this application is to provide an adaptive wear monitoring and diagnostic system for chain blades to solve the technical problems in the prior art that different parts of the chain blades bear different cutting loads, resulting in uneven wear, and it is difficult to provide corresponding diagnosis and optimization strategies according to different stages or positions of wear, resulting in low maintenance efficiency.

[0005] In order to achieve the above-mentioned purpose, the present application provides a chain blade adaptive wear monitoring and diagnosis system, wherein the chain blade adaptive wear monitoring and diagnosis system includes: an operation data acquisition module, the operation data acquisition module is used to collect blade operation data in real time through a multi-dimensional sensor to obtain blade operation data; an operation wear module, the operation wear module is used to perform wear diagnosis on the blade operation data based on a pattern recognition model and extract wear characteristic parameters; an operation optimization module, the operation optimization module is used to introduce a first operation strategy to perform operation optimization on the blade operation data based on the wear characteristic parameters to obtain first depth operation data; a depth wear module, the depth wear module is used to perform wear diagnosis on the first depth operation data based on a wear warning model to obtain depth wear characteristic parameters; a depth maintenance module, the depth maintenance module is used to introduce a second operation strategy to perform depth maintenance on the first depth operation data based on the depth wear characteristic parameters to obtain adaptive blade operation data; a continuous monitoring module, the continuous monitoring module is used to start the adaptive blade operation data and continuously monitor the adaptive blade operation data.

[0006] Optionally, the pattern recognition model includes a vibration recognition channel, a temperature recognition channel and a load recognition channel; the blade operation data is input into the pattern recognition model for channel mapping to obtain vibration key parameters, temperature key parameters and load key parameters; based on the vibration recognition channel, temperature recognition channel and load recognition channel, the vibration key parameters, temperature key parameters and load key parameters are subjected to limit over-limit analysis to obtain the wear characteristic parameters.

[0007] Optionally, frequency domain analysis is performed on the key vibration parameters based on the vibration identification channel to obtain frequency domain amplitude and frequency domain frequency; if the frequency domain amplitude meets the amplitude change threshold, a vibration amplitude diagnosis result is obtained, wherein the vibration amplitude diagnosis result includes a decrease in blade sharpness; if the frequency domain frequency meets the frequency offset threshold, a vibration frequency diagnosis result is obtained, wherein the vibration frequency diagnosis result includes uneven blade wear; if any diagnostic result of the vibration amplitude diagnosis result and the vibration frequency diagnosis result is obtained, a vibration wear characteristic parameter is obtained, and the vibration wear characteristic parameter is added to the wear characteristic parameter.

[0008] Optionally, a sample wear map is constructed based on sample wear characteristic parameters and sample wear degree; the wear characteristic parameters are input into the sample wear map for mapping analysis to obtain the wear degree; a time iteration simulation is performed based on the wear degree to obtain the wear change trend; and the first operating strategy is generated based on the wear change trend.

[0009] Optionally, a wear critical value is extracted according to the wear change trend; the blade is adaptively operated with the goal of delaying the wear critical value in the time dimension until the operation process tends to be stable, thereby generating the first operation strategy.

[0010] Optionally, the wear warning model includes a vibration warning channel, a temperature warning channel and a load warning channel; the first depth operation data is input into the wear warning model for channel mapping to obtain vibration depth parameters, temperature depth parameters and load depth parameters; based on the vibration warning channel, temperature warning channel and load warning channel, the vibration depth parameters, temperature depth parameters and load depth parameters are subjected to limit exceeding standard analysis to obtain the depth wear characteristic parameters.

[0011] Optionally, the second operating strategy includes a blade adjustment angle strategy and a blade adjustment position strategy; based on the blade adjustment angle strategy, the chip removal process is monitored to obtain chip removal data, and based on the chip removal data, the entry angle and exit angle in the first depth operation data are adjusted to obtain the blade adjustment angle; based on the blade adjustment position strategy, the cutting force process is monitored to obtain cutting force distribution data, and based on the cutting force distribution data, the front and rear positions and left and right positions in the first depth operation data are adjusted to obtain the blade adjustment position; the blade maintenance position is obtained according to the blade adjustment angle and the blade adjustment position, and the blade maintenance position is added to the adaptive blade operation data.

[0012] Optionally, the adaptive blade operation data is continuously monitored to obtain real-time monitoring quality; the blade is reversed according to the real-time monitoring quality, and the reversing time node is recorded; a predetermined reversing period is determined according to the reversing time node, the blade direction is adjusted based on the reversing period, and the blade reversing data is fed back to the adaptive blade operation data.

[0013] The technical solution provided in this application has at least the following technical effects or advantages: Through the operation data acquisition module, the operation data acquisition module is used to collect blade operation data in real time through multi-dimensional sensors to obtain blade operation data; the operation wear module is used to perform wear diagnosis on the blade operation data based on the pattern recognition model and extract wear characteristic parameters; the operation optimization module is used to introduce a first operation strategy to optimize the blade operation data based on the wear characteristic parameters to obtain the first depth operation data; the depth wear module is used to perform wear diagnosis on the first depth operation data based on the wear warning model to obtain the depth wear characteristic parameters; the depth maintenance module is used to introduce a second operation strategy to perform depth maintenance on the first depth operation data based on the depth wear characteristic parameters to obtain the adaptive blade operation data; the continuous monitoring module is used to start the adaptive blade operation data and continuously monitor the adaptive blade operation data. That is to say, by real-time data collection through multi-dimensional sensors, wear diagnosis using pattern recognition models, optimization of blade cutting parameters, and depth maintenance according to cutting depth changes, the continuous monitoring and adaptive adjustment of the chain blade operation status are realized, and the maintenance efficiency of the chain blade is improved.

[0014] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0016] Figure 1 This is a schematic diagram of the structure of the chain blade adaptive wear monitoring and diagnosis system of the present application; Figure 2 A schematic flow chart of obtaining a first operating strategy in the chain blade adaptive wear monitoring and diagnosis system of the present application.

[0017] Explanation of the accompanying drawings: operation data acquisition module 11, operation wear module 12, operation optimization module 13, depth wear module 14, depth maintenance module 15, continuous monitoring module 16. DETAILED DESCRIPTION

[0018] This application solves the technical problem in the prior art that the chain blade wears unevenly due to the different cutting loads borne by different parts of the chain blade, and it is difficult to provide corresponding diagnosis and optimization strategies according to different stages or positions of wear, resulting in low maintenance efficiency by providing a chain blade adaptive wear monitoring and diagnosis system. By collecting data in real time through multi-dimensional sensors, using pattern recognition models for wear diagnosis, optimizing the cutting parameters of the blade, and performing in-depth maintenance according to changes in cutting depth, the continuous monitoring and adaptive adjustment of the chain blade's operating status are achieved, thereby improving the chain blade's maintenance efficiency.

[0019] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0020] For examples, please see the attached Figure 1 The present application provides a chain blade adaptive wear monitoring and diagnosis system, wherein the chain blade adaptive wear monitoring and diagnosis system specifically includes the following steps: The operation data acquisition module 11 is used to acquire blade operation data in real time through a multi-dimensional sensor to obtain blade operation data.

[0021] Specifically, multiple sensors (such as vibration sensors, temperature sensors, force sensors, and acoustic wave sensors) are placed at key locations of the blade (such as teeth, blade contact points, etc.) to collect real-time operating data of the blade, including vibration frequency, surface temperature, cutting load, acoustic waves, etc. Multidimensional sensors refer to sensors that can collect multiple physical quantities at the same time, provide multi-faceted information about the blade during operation, and help monitor the status of the blade in real time. Blade operation data refers to the values ​​of various physical parameters collected in real time by multidimensional sensors during the blade's operation, reflecting the working status of the blade, such as wear, cutting force, tool temperature, etc.

[0022] Install sensor arrays at appropriate locations on the blade (such as the area where the tool contacts the material, where the blade is fixed, etc.) to synchronously acquire information about the chain blade. The collected blade operation data is transmitted to the data processing unit for processing, and the data is converted into a format that can be analyzed. Through real-time data collection by multi-dimensional sensors, the various states of the blade during operation (such as vibration, temperature, load, etc.) are fully and accurately reflected, and the wear condition of the blade is fully monitored.

[0023] The operation wear module 12 is used to perform wear diagnosis on the blade operation data based on a pattern recognition model and extract wear characteristic parameters.

[0024] Specifically, the pattern recognition model includes a vibration recognition channel, a temperature recognition channel, and a load recognition channel. The vibration recognition channel is used to identify vibration frequency characteristics. Changes in vibration frequency can reflect the wear state of the blade, especially the passivation of the teeth, and reflect the balance and sharpness of the blade. The temperature recognition channel is used to identify temperature changes. Abnormal temperature increases usually indicate that the blade is wearing too fast or there is local overheating. The load recognition channel is used to identify load changes. When the blade is worn, the cutting load may fluctuate or change unstably. Based on the initial data collected, the pattern recognition model is used to perform preliminary wear diagnosis to analyze whether the blade is beginning to show signs of wear.

[0025] The blade operation data is input into the pattern recognition model, which will extract key wear characteristic parameters. Vibration amplitude and frequency are extracted through frequency domain analysis as characteristics of blade wear. Changes in blade surface temperature can reflect the degree of friction during the cutting process. Excessive temperature may indicate blade wear or excessive friction. Load fluctuations can reflect the force state of the blade during the cutting process. Uneven load fluctuations may be a sign of wear. Each recognition channel of the pattern recognition model extracts its own wear characteristic parameters. The extracted key parameters such as vibration, temperature, and load will be compared with the preset normal range (threshold) for limit over-limit analysis. If a key parameter exceeds the preset normal range, it is determined that the wear of that part is abnormal. Through limit over-limit analysis, the wear characteristic parameters of the blade are comprehensively obtained from multiple angles such as vibration, temperature, and load. This is a comprehensive reflection of multi-dimensional data and can provide detailed diagnostic results on blade wear.

[0026] The operation optimization module 13 is used to introduce a first operation strategy to perform operation optimization on the blade operation data based on the wear characteristic parameters to obtain first depth operation data.

[0027] Specifically, the wear characteristic parameters are analyzed to determine the current degree of wear. It is usually determined based on the mapping relationship between the actual wear characteristic parameters and the degree of wear. A time iteration simulation is performed according to the degree of wear to obtain the trend of the wear change, and the first operation strategy is generated accordingly. The wear rate is slowed down, the blade performance is optimized, and the blade service life is increased by adjusting the working state of the blade (such as cutting speed, depth, load, etc.). The blade operation data is optimized according to the first operation strategy, that is, the working parameters of the blade are adjusted to control the working state of the blade in real time. After applying the first operation strategy, the operating state of the blade will change, and new operation data will be generated, called the first depth operation data, which shows the performance of the blade under the new working parameters.

[0028] After the blade applies the first operation strategy and obtains the first depth operation data, the new data is monitored in real time to evaluate the operation optimization effect. By comparing the operation data before and after optimization, it is determined whether the first operation strategy has effectively delayed wear and improved the working performance of the blade. The first depth operation data is new data obtained after optimizing the blade operation by introducing the first operation strategy, which reflects the performance of the blade when cutting after optimization, including new cutting depth, load changes, temperature changes, etc. By applying the first operation strategy, the wear rate of the blade is slowed down, the cutting parameters are optimized and lubrication is increased, and the service life of the blade is extended. According to the optimized operation data, the wear rate of the blade is slowed down and it can continue to work longer in the same time. Through the dynamic adjustment of the first operation strategy, the blade can be adaptively optimized according to the actual wear conditions, thereby ensuring that the blade operates in the best working state.

[0029] The depth wear module 14 is used to perform wear diagnosis on the first depth operation data based on a wear warning model to obtain depth wear characteristic parameters.

[0030] Specifically, the first depth operation data refers to the new data set generated during the operation of the blade after the implementation of the first operation strategy. The wear warning model includes multiple channels, namely, a vibration warning channel, a temperature warning channel, and a load warning channel, which are used to process different parameters respectively. The first depth operation data is input into the wear warning model for channel mapping to obtain the parameters corresponding to each channel, namely, the vibration depth parameter, the temperature depth parameter, and the load depth parameter. Each channel compares the parameters with the pre-set safety range. The vibration warning channel compares the vibration amplitude with the set threshold to determine whether the blade has a sharpness drop or uneven wear; the temperature warning channel compares the surface temperature of the blade with the safety range to determine whether the temperature is too high, indicating that the blade is damaged by friction; the load warning channel analyzes the load fluctuation to determine whether there is uneven load or overload, resulting in uneven wear of the blade.

[0031] Through diagnosis and analysis, the wear warning model extracts the depth wear characteristic parameters and further evaluates the wear state of the blade, including vibration wear characteristics, temperature wear characteristics, and load wear characteristics, which are used to describe the wear state of the blade. Through the wear warning model, the operating state of the blade is analyzed in real time to accurately diagnose the wear condition of the blade.

[0032] The depth maintenance module 15 is used to introduce a second operation strategy to perform depth maintenance on the first depth operation data based on the depth wear characteristic parameters to obtain adaptive blade operation data.

[0033] Specifically, the second operating strategy includes a blade adjustment angle strategy and a blade adjustment position strategy. The blade adjustment angle strategy adjusts the blade's entry angle and exit angle in real time according to the chip removal data accumulated by the blade during the working process to optimize the cutting process and reduce wear; the blade adjustment position strategy adjusts the front and rear position and left and right position of the blade by monitoring the cutting force distribution data during the cutting process. The depth wear characteristic parameter refers to the wear characteristic data accumulated by the blade as the cutting depth increases during the cutting process, including the vibration, temperature, load and other data of the blade at different cutting depths, reflecting the degree and distribution of blade wear. Depth maintenance refers to the optimization and adjustment of the blade's working state according to the depth and characteristics of the wear during the blade wear process, paying attention to the cutting depth, the contact state between the blade and the material, and the cutting force distribution, etc., in order to maintain the blade's optimal performance at the new working depth.

[0034] According to the characteristic parameters of deep wear, the second operation strategy is introduced, that is, the operation parameters of the blade are adjusted according to the current wear degree of the blade, that is, the blade adjustment angle and position. By monitoring the data during the chip removal process, it is determined whether the blade's entry angle and exit angle affect the chip flow. According to the chip removal data, the blade's entry angle and exit angle are optimized. For example, if the blade's entry angle is too large, it may cause chip accumulation or excessive friction. Adjusting to a more suitable angle can reduce wear.

[0035] Through the cutting force distribution data, it is determined whether the front and back, left and right positions of the blade are evenly distributed. Adjust the front and back and left and right positions of the blade to ensure that the cutting process of the blade is more uniform and reduce local wear. For example, the left and right position offset of the blade may cause excessive wear on one side. Through adjustment, the cutting pressure is evenly distributed. Depth maintenance refers to the actual adjustment of the blade according to the second operation strategy, and the working parameters of the blade are dynamically adjusted according to the degree of blade wear and changes in cutting depth. After the angle and position are adjusted, the maintenance position of the blade is determined and recorded in the adaptive blade operation data. It is the best working state of the blade in the current wear stage, which can minimize wear and improve cutting efficiency. By adjusting the entry angle, exit angle and blade position, the angle and position of the blade are dynamically adjusted according to the actual cutting conditions and blade performance, thereby optimizing the cutting process, reducing blade wear, and improving cutting efficiency and product quality.

[0036] The continuous monitoring module 16 is used to start the adaptive blade operation data and continuously monitor the adaptive blade operation data.

[0037] Specifically, adaptive blade operation data refers to blade operation data dynamically generated after optimization and adjustment based on blade wear, cutting status and real-time feedback data, including blade vibration, temperature, load, cutting angle, position and other related parameters. Various parameters (such as vibration, temperature, load, etc.) during blade operation are continuously monitored through multi-dimensional sensors to obtain blade operation data, including vibration (reflecting the balance and sharpness of the blade), temperature (indicating wear and friction status), load (reflecting the force of the blade during cutting), etc. Ensure that the blade is always in the best working state during the entire cutting process to avoid uneven cutting or equipment failure caused by excessive wear or imbalance. Continuous monitoring data can not only adjust the working state of the blade in time, but also provide historical data for long-term optimization. Analyze the wear law of the blade based on historical data and optimize subsequent operation strategies. By optimizing the blade operation data in real time, adjust the working state of the blade, avoid excessive wear of the blade, extend the service life of the blade, and keep the blade in the best cutting state at all times, thereby improving the cutting quality.

[0038] Further, the operation wear module 12 in the chain blade adaptive wear monitoring and diagnosis system is also used for: The pattern recognition model includes a vibration recognition channel, a temperature recognition channel and a load recognition channel; the blade operation data is input into the pattern recognition model for channel mapping to obtain vibration key parameters, temperature key parameters and load key parameters; based on the vibration recognition channel, temperature recognition channel and load recognition channel, the vibration key parameters, temperature key parameters and load key parameters are subjected to limit exceeding standard analysis to obtain the wear characteristic parameters.

[0039] Specifically, the pattern recognition model is a data analysis method that is used to identify regularities and patterns in data through learning and training of large amounts of data. In blade wear monitoring, the pattern recognition model is used to analyze the data collected by the sensor to help determine whether the blade is worn. The pattern recognition model includes multiple recognition channels, each of which specializes in processing a type of input data, namely the vibration recognition channel, the temperature recognition channel, and the load recognition channel. The vibration recognition channel is used to analyze the vibration data of the blade. By analyzing the frequency, amplitude, period and other parameters of the vibration signal, it is determined whether the blade is worn or unbalanced. The temperature recognition channel is used to process the blade temperature data. By analyzing the temperature fluctuation, it can determine abnormal conditions such as excessive friction or material jamming. The load recognition channel is used to analyze the blade load data to determine whether the load is balanced during the blade cutting process. If the load fluctuates greatly, it may indicate that the blade is worn or has resistance.

[0040] The blade operation data collected in real time by multi-dimensional sensors is input into the pattern recognition model, and the three main recognition channels recognize the corresponding types of data respectively. Each recognition channel processes the input data through a specific algorithm to extract its own key parameters. For example, the vibration recognition channel extracts the frequency peak, amplitude and other characteristics of the vibration signal; the temperature recognition channel extracts the maximum fluctuation value and temperature rise rate of the temperature change; the load recognition channel extracts the standard deviation, maximum value and other values ​​of the load. Channel mapping refers to inputting different types of sensor data (such as vibration, temperature, and load) into the corresponding recognition channel, and performing data processing and analysis through the model to obtain specific key parameters, namely vibration key parameters, temperature key parameters and load key parameters.

[0041] The extracted key parameters such as vibration, temperature, load, etc. are compared with the preset normal range to perform limit exceedance analysis. If a key parameter exceeds the preset normal range, it is determined that the wear of that part is abnormal. Limit exceedance analysis analyzes and judges the key parameters to determine whether they exceed the normal threshold (exceed the standard). If the key parameters exceed the set threshold, it may indicate that the blade is abnormally worn and requires maintenance or adjustment. Wear characteristic parameters are important data reflecting the wear status of the blade obtained by analyzing key parameters such as vibration, temperature, load, etc., to determine the degree of wear, wear location and type of wear of the blade.

[0042] For example, if the vibration amplitude exceeds the preset normal range, it means that the sharpness of the blade has decreased or there is an imbalance; if the vibration frequency is offset, it means that the blade has uneven wear or damage; if the temperature fluctuation exceeds the normal range, it means that there is local uneven friction on the blade surface, resulting in increased wear; if the load exceeds the preset normal range, it means that the blade has local jamming or damage, resulting in greater cutting resistance. Through the pattern recognition model, it is possible to comprehensively consider data from multiple aspects such as vibration, temperature and load, and fully reflect the wear condition of the blade, avoiding the limitations of a single indicator.

[0043] Further, the operation wear module 12 in the chain blade adaptive wear monitoring and diagnosis system is also used for: Based on the vibration identification channel, the key vibration parameters are subjected to frequency domain analysis to obtain frequency domain amplitude and frequency domain frequency; if the frequency domain amplitude meets the amplitude change threshold, a vibration amplitude diagnosis result is obtained, wherein the vibration amplitude diagnosis result includes a decrease in blade sharpness; if the frequency domain frequency meets the frequency offset threshold, a vibration frequency diagnosis result is obtained, wherein the vibration frequency diagnosis result includes uneven blade wear; if any diagnosis result of the vibration amplitude diagnosis result and the vibration frequency diagnosis result is obtained, a vibration wear characteristic parameter is obtained, and the vibration wear characteristic parameter is added to the wear characteristic parameter.

[0044] Specifically, during the cutting process, the blade will generate vibration signals due to material cutting, tool wear or other factors. The vibration identification channel helps determine the status of the blade (such as whether it is worn or unbalanced) by analyzing these signals. The blade's vibration data will be processed by the vibration identification channel, using Fourier transform to convert the original time domain vibration signal into a frequency domain signal, decomposing the various frequency components in the signal to help identify whether there are abnormal vibration patterns. Fourier transform can convert complex time domain signals into frequency domain signals and see the intensity of vibration at different frequencies.

[0045] Frequency domain analysis is a method of converting signals from the time domain to the frequency domain, and is often used to extract signal features. Frequency domain analysis can reveal the amplitude and frequency of each frequency component in the signal. For vibration signals, frequency domain analysis identifies the dynamic characteristics of the blade during operation, such as whether there are abnormal vibration patterns or signs of wear.

[0046] After frequency domain analysis, the frequency domain amplitude (i.e., the strength of each frequency component) and frequency domain frequency (i.e., the main frequency component in the signal) are extracted. Frequency domain amplitude refers to the strength or amplitude of the signal at a specific frequency. A higher amplitude usually indicates a stronger vibration component at that frequency. Frequency domain frequency refers to the different frequency components contained in the signal. For blade vibration, changes in frequency domain frequency may be related to blade wear, imbalance, or other abnormal conditions.

[0047] The amplitude change threshold is set based on experimental or historical data to determine whether the vibration amplitude has changed abnormally. If the frequency domain amplitude exceeds the amplitude change threshold, a vibration amplitude diagnosis result is obtained, indicating that the blade's sharpness has decreased or there is an imbalance. The frequency offset threshold is set based on the blade's operating frequency and actual working conditions to determine whether the vibration frequency has significantly shifted. If the vibration frequency shifts, a vibration frequency diagnosis result is obtained, indicating that the blade has uneven wear or damage.

[0048] If the vibration amplitude changes beyond the threshold, and / or the frequency offset exceeds the threshold, any diagnostic result is triggered, and the corresponding diagnostic result is converted into a vibration wear characteristic parameter and added to the wear characteristic parameter. Through the frequency domain analysis of vibration, the wear type of the blade, such as sharpness reduction and uneven wear, is accurately identified, and an early warning is issued at the early stage of blade wear to avoid severe degradation of blade performance or reduced cutting efficiency due to excessive wear.

[0049] Further, as attached Figure 2 As shown, the operation optimization module 13 in the chain blade adaptive wear monitoring and diagnosis system is also used for: Construct a sample wear map based on sample wear characteristic parameters and sample wear degree; input the wear characteristic parameters into the sample wear map for mapping analysis to obtain the wear degree; perform time iteration simulation based on the wear degree to obtain the wear change trend; generate the first operation strategy based on the wear change trend.

[0050] Specifically, key parameters and specific degrees used to characterize the wear state are extracted from the actual operation data as sample wear characteristic parameters and sample wear degree. Sample wear characteristic parameters include vibration amplitude, temperature, load, cutting depth, etc., and sample wear degree includes light wear, moderate wear, heavy wear, etc. A sample wear mapping is established based on the relationship between sample wear characteristic parameters and wear degree, and the wear characteristic parameters are mapped to the corresponding wear degree.

[0051] The wear characteristic parameters (such as vibration, temperature, load, etc.) obtained from the real-time operation data of the blade are input into the sample wear mapping, and the input wear characteristic parameters are mapped and analyzed to convert them into corresponding wear degrees. Time iteration simulation refers to the simulation and prediction of the wear changes of the blade in different time steps, taking into account the changing wear conditions of the blade during use, and continuously updating the wear degree through time steps to predict future wear trends.

[0052] Perform time-iterative simulation on the degree of wear to predict the trend of wear changes in the future. The future degree of wear is predicted by simulating the changes in the current wear state. For example, if the current degree of wear of the blade is moderate, based on the wear growth trend in historical data, it is predicted that the degree of wear may increase to severe wear in the future. During the simulation, the wear state is continuously adjusted according to the time step to update the wear prediction results. Through time-iterative simulation, the trend of wear change is obtained, that is, the speed and direction of blade wear change in the future, which is usually manifested as an increase, decrease, or stabilization of the degree of wear.

[0053] According to the degree of wear and the trend of wear variation, a corresponding first operation strategy is formulated, aiming to slow down the wear rate and extend the service life of the blade by adjusting the working parameters, optimizing the cutting process or performing preventive maintenance. By analyzing the trend of wear variation, the wear critical value of the blade is determined, that is, the maximum degree of wear that the blade can withstand during operation. With the goal of delaying the wear critical value in the time dimension, the operating parameters of the blade are adjusted. In other words, by adjusting the operating parameters or maintenance strategies, the time for the blade to reach the wear critical value is delayed as much as possible. Through adaptive operation adjustment, the wear rate of the blade is stabilized within an acceptable range. Based on the wear critical value and the results of the adaptive operation, the specific operation strategy formulated includes but is not limited to adjusting the speed, load, cutting depth, and lubrication level of the blade to optimize the performance of the blade and extend its service life.

[0054] Further, the operation optimization module 13 in the chain blade adaptive wear monitoring and diagnosis system is also used for: A wear critical value is extracted according to the wear variation trend; and the blade is adaptively operated with the goal of delaying the wear critical value in the time dimension until the operation process tends to be stable, thereby generating the first operation strategy.

[0055] Specifically, by analyzing the trend of wear variation, the wear critical value of the blade is determined, that is, the maximum degree of wear that the blade can withstand during operation. After exceeding the wear critical value, the blade may experience serious performance degradation or even cause equipment failure. According to the extracted wear critical value, a goal of delaying this critical value is set. By monitoring the operating status of the blade in real time, the working parameters of the blade are adjusted in time to delay the arrival of the wear critical value. Time dimension delay refers to delaying the arrival point of the wear critical value relative to time, that is, by optimizing the blade's operating strategy, the time for the blade to reach the wear critical value is delayed. This is achieved by adjusting cutting parameters, maintenance frequency, etc., so that the blade can maintain an efficient working state for a longer time and avoid reaching the wear critical value too early. For example, if the current wear level of the blade is close to the critical value, the wear can be slowed down by reducing the cutting speed, reducing the cutting depth or increasing lubrication.

[0056] According to the current wear state and predicted wear trend, the working state of the blade is adjusted in real time through adaptive operation strategy to ensure that the blade is in the best operating state. After adaptive adjustment, the wear state of the blade should tend to be stable, that is, the wear rate no longer increases significantly. Eventually, a complete first operation strategy will be generated, which not only includes how to delay the arrival of the wear critical value, but also how to optimize and maintain the blade during wear. For example, the first operation strategy includes reducing the cutting depth, reducing the cutting speed, increasing the lubricating oil supply, and regularly checking and replacing the blade. By delaying the arrival of the wear critical value, the service life of the blade can be extended, and the working parameters of the blade can be adjusted in real time to ensure that the blade is always in a stable working state during the wear process, avoiding production interruptions caused by premature wear of the blade.

[0057] Furthermore, the depth wear module 14 in the chain blade adaptive wear monitoring and diagnosis system is also used for: The wear warning model includes a vibration warning channel, a temperature warning channel and a load warning channel; the first depth operation data is input into the wear warning model for channel mapping to obtain vibration depth parameters, temperature depth parameters and load depth parameters; based on the vibration warning channel, temperature warning channel and load warning channel, the vibration depth parameters, temperature depth parameters and load depth parameters are subjected to limit exceeding standard analysis to obtain the depth wear characteristic parameters.

[0058] Specifically, a wear warning model is constructed based on historical data to determine how wear parameters (such as vibration, temperature, load, etc.) change under different wear conditions. Historical wear data should include cutting data at multiple stages, such as blade vibration (frequency domain and time domain), blade surface temperature, cutting load (cutting depth, feed speed, power, etc.), cutting speed, blade life (amount of material cut or working time), etc., and recorded and classified according to different wear conditions (such as light wear, moderate wear, and heavy wear). Light wear refers to small changes in vibration, no obvious temperature increase, and relatively stable load; moderate wear refers to a significant increase in vibration, gradual temperature increase, load fluctuations, and may be accompanied by small noise or irregular vibration; heavy wear refers to severe vibration, significant temperature increase, drastic load changes, large gaps or deformations on the blade surface, and even overheating.

[0059] The acquired historical data is preprocessed and feature extracted, including denoising, normalization and data cleaning. The characteristic parameters related to wear are extracted from the processed data, including the key parameters of vibration, the fluctuation range of blade temperature, and the fluctuation amplitude of load. The wear warning model needs to establish a separate warning channel for each monitoring indicator (vibration, temperature, load). Each warning channel analyzes according to the corresponding characteristic parameters and provides corresponding warning signals. Each warning channel sets a set of thresholds and issues a warning signal when the measured characteristic parameters exceed these thresholds. Label each set of historical data according to the actual wear conditions, such as light wear, moderate wear, and heavy wear. Select a suitable machine learning model according to the data characteristics, such as decision tree, support vector machine (SVM), random forest, neural network, etc., and predict the wear state of new data by learning the patterns in the sample data. Use sample data and labels to train the warning model. By adjusting the parameters of the model, the model can accurately predict the degree of wear of the blade. Evaluate the performance of the model through indicators such as cross-validation, accuracy, and recall. If the warning accuracy of the model is not high, the model can be tuned, such as adjusting the threshold, using more characteristic parameters, or choosing a more complex model.

[0060] If the random forest algorithm is used for training, a more accurate and stable prediction result is obtained by creating multiple decision trees (usually hundreds to thousands of trees) and combining the prediction results. A random forest classification model is trained to accurately predict the degree of blade wear based on the input feature data (vibration, temperature, and load). During the training process, the random forest builds multiple decision trees. Each tree is built on randomly selected training samples and features. Each time a tree is built, a subset is randomly selected from the original data set (with replacement sampling), and then the decision tree is trained with this subset. When each node is split, a specific number of features are randomly selected instead of using all features for division, thereby increasing the diversity of the tree.

[0061] During the training process, the random forest continuously builds multiple trees through multiple iterations and votes on the prediction results of each tree (majority voting method). Finally, the voting results of all decision trees are combined to form the final prediction. After training, the model is evaluated using the test data set, including accuracy, precision, recall, etc. By adjusting hyperparameters such as the number of trees, maximum depth, and minimum number of sample splits, the model can be further optimized to improve its prediction effect on new data.

[0062] According to different degrees of wear, key characteristic parameters are extracted from the first depth operation data, including vibration characteristic parameters, temperature change parameters, and load change parameters, and these data are mapped to different warning channels for analysis. The wear warning model includes a vibration warning channel, a temperature warning channel, and a load warning channel, which process different data respectively. The vibration warning channel is used to monitor the vibration data of the blade during operation and evaluate the stability and balance of the blade. Abnormal vibration amplitude may indicate that the blade is worn or unevenly worn; the temperature warning channel is used to monitor the temperature changes during the operation of the blade. Excessive temperature usually indicates that the friction is large and the blade may wear faster; the load warning channel is used to monitor the load on the blade during the cutting process. Abnormal load fluctuations may indicate that the blade is stuck or unevenly loaded in certain areas, which in turn affects the cutting effect and the wear rate of the blade.

[0063] In each early warning channel, the depth parameters of vibration, temperature and load are analyzed for limit exceeding standards, that is, based on the thresholds set by historical data and theoretical models, it is determined whether each parameter exceeds the normal range. For example, if the vibration amplitude exceeds the set threshold (such as 2.5mm / s), it is considered that the blade may be at risk of wear or uneven wear; if the temperature exceeds the set threshold (such as 90°C), it indicates that the blade is aggravated and friction increases; if the load fluctuates greatly or continuously exceeds the set threshold (such as above 18N), there may be blade jamming or uneven load.

[0064] Through the analysis of vibration, temperature and load exceeding the limit, a series of depth wear characteristic parameters are obtained. The depth wear characteristic parameters represent the wear characteristics of the blade under different depth conditions, and usually reflect whether the blade needs to be replaced, repaired or adjusted. Through the analysis of the wear warning model, the wear state of the blade can be discovered in time. Before the blade wear reaches the critical level, the wear characteristic parameters are monitored and analyzed in real time, and warnings are issued in time to avoid equipment failures caused by excessive wear.

[0065] Furthermore, the depth maintenance module 15 in the chain blade adaptive wear monitoring and diagnosis system is also used for: The second operation strategy includes a blade adjustment angle strategy and a blade adjustment position strategy; based on the blade adjustment angle strategy, the chip removal process is monitored to obtain chip removal data, and based on the chip removal data, the entry angle and exit angle in the first depth operation data are adjusted to obtain the blade adjustment angle; based on the blade adjustment position strategy, the cutting force process is monitored to obtain cutting force distribution data, and based on the cutting force distribution data, the front and rear positions and left and right positions in the first depth operation data are adjusted to obtain the blade adjustment position; the blade maintenance position is obtained according to the blade adjustment angle and the blade adjustment position, and the blade maintenance position is added to the adaptive blade operation data.

[0066] Specifically, the second operation strategy is to adjust the blade based on the wear characteristic parameters during the blade wear process to optimize the blade's operating state and extend its service life, including adjusting the blade's angle and position to improve cutting efficiency and stability and reduce wear. The blade adjustment angle strategy refers to adjusting the blade's entry angle and exit angle in real time based on the chip removal data accumulated during the blade's operation to optimize the cutting process and reduce wear.

[0067] During the cutting process, chips are generated when the blade contacts the material. Through the blade adjustment angle strategy, the chip removal process is monitored in real time to obtain chip removal data, including the shape, flow direction, size, etc. of the chips. By analyzing the chip removal data, it is determined whether the chip flow of the blade is smooth. If the chip flow is not smooth or chip jamming occurs, it may be that the blade's entry angle or exit angle is inappropriate. According to the analysis results in the chip removal data, adjust the entry angle and exit angle to make the blade's cutting process smoother and reduce wear. If the chip flow is difficult, the entry angle can be reduced, the exit angle can be increased, and the fluidity of the chips can be improved. If the chips are too large or too small, adjust the angle according to the material type and blade design.

[0068] The blade's entry and exit angles affect the stability of the cut and the rate of wear. Adjusting the angle allows the blade to maintain a more even cutting force on the material, reducing localized excessive wear. If the blade's entry angle is too large or too small, it will cause uneven cutting forces during cutting, which will cause one side or part of the blade to wear prematurely. Adjusting the entry angle can keep the cutting force evenly distributed and reduce wear. Similarly, the blade's exit angle affects the chip removal process. Unsmooth chip removal will increase friction between the blade and the material, causing increased wear. Properly adjusting the exit angle can help improve chip removal efficiency and reduce the blade's wear rate.

[0069] Cutting force is the interaction force between the blade and the material during cutting, which is usually divided into tangential force, transverse force and axial force. According to the blade adjustment position strategy, the force sensor monitors the force of the blade in contact with the material during the cutting process in real time, reflecting the size and distribution of the cutting force borne by the blade at different positions. According to the cutting force distribution data, adjust the front and back position and left and right position in the first depth operation data. The blade adjustment position strategy refers to adjusting the front and back position and left and right position of the blade by monitoring the cutting force distribution data during the cutting process. By accurately controlling the blade position, the cutting force distribution is maintained uniformly, thereby reducing excessive local wear of the blade.

[0070] The purpose of blade position adjustment is to ensure that the blade is always in the optimal cutting position to reduce uneven wear. As the blade wears, the contact angle may change, resulting in uneven cutting or unbalanced loads. By fine-tuning the blade position, you can optimize the contact between the blade and the material and avoid irregular wear. If the cutting force on the front or back of the blade is too high, you can adjust the front and back position of the blade to make it more evenly loaded; if the cutting force on one side of the blade is too high, you can adjust the left and right position of the blade to ensure that the blade is evenly loaded throughout the cutting process.

[0071] During long-term use, the blade may shift position due to machine vibration, external force or other factors. By adjusting the installation position of the blade to maintain the best contact between the blade and the workpiece, you can ensure cutting stability. The front and back position of the blade affects the distribution of cutting force. Fine-tuning the blade position can avoid excessive local wear or unstable cutting. Left and right position adjustment helps optimize the force distribution of the blade and avoid excessive wear on one side.

[0072] After comprehensively adjusting the blade's angle (entry angle and exit angle) and position (front-back position and left-right position), determine the blade's maintenance position, which is the best working state for the blade at the current wear stage, and can minimize wear and improve cutting efficiency. The maintenance position will be recorded and added to the adaptive blade operation data as a reference for subsequent cutting operations. Monitor the blade's wear status in real time and adjust the operation strategy based on the maintenance position. By adjusting the blade's angle and position, ensure that the blade's cutting process is smoother, avoid problems such as chip jamming and excessive wear, and thus improve cutting efficiency and quality.

[0073] Furthermore, the continuous monitoring module 16 in the chain blade adaptive wear monitoring and diagnosis system is also used for: The adaptive blade operation data is continuously monitored to obtain real-time monitoring quality; the blade is commutated according to the real-time monitoring quality, and the commutation time node is recorded; a predetermined commutation period is determined according to the commutation time node, the blade direction is adjusted based on the commutation period, and the blade commutation data is fed back to the adaptive blade operation data.

[0074] Specifically, once the blade starts running, various operating data of the blade are continuously collected through real-time monitoring tools (such as vibration sensors, temperature sensors, load sensors, etc.) to obtain real-time monitoring quality, including parameters such as vibration, temperature, and load. Real-time monitoring quality can reflect the current working status of the blade, help determine whether the blade is in an ideal working state, and whether maintenance, adjustment, or reversing is required.

[0075] When it is detected that a part of the blade is excessively worn or abnormal (such as the vibration amplitude and temperature of the blade exceed the threshold), the blade reversing operation is performed. The purpose of reversing is to make different parts of the blade wear evenly and avoid excessive local wear, thereby extending the service life of the blade. For example, suppose that during the cutting process, the front end of the blade is severely worn, resulting in an increase in the vibration amplitude. Based on the real-time monitoring data, it is decided to adjust the working direction of the blade so that the cutting force is transferred to the unworn part of the blade, ensuring that the other part is utilized, effectively reducing the local excessive wear of the blade, maintaining even wear of the blade during the cutting process, improving cutting efficiency, and extending the life of the blade.

[0076] Each reversing operation records a reversing time node, which is a key operating data point used to track the blade's reversing history. The reversing time node is the time point when the reversing is determined. Based on the reversing time node, the scheduled reversing cycle is determined, which determines the time when the blade is regularly reversing. For example, if the blade needs to be reversed after each 10 hours of operation, the scheduled reversing cycle is set to 10 hours. This cycle may be adjusted with different stages of blade wear to maintain the best cutting effect.

[0077] The blade direction is adjusted according to the reversing cycle, and the reversing is performed, and the specific data of the blade reversing operation is recorded, including the time node of the reversing, the reversing cycle, the blade status before and after the reversing, and other information. The reversing operation data (such as the time node of the reversing, the wear status before and after, etc.) is fed back to the adaptive blade operation data to update the blade operation strategy, and perform more accurate blade maintenance based on historical data in future operations. For example, if the operating efficiency of the blade is improved after reversing, this feedback is recorded and inferred whether more frequent reversing or adjustment of the reversing cycle is required in the future. Through the blade reversing operation, local excessive wear of the blade can be avoided, and the wear can be evenly distributed, thereby extending the service life of the blade. Regular blade reversing operations can prevent the blade from being scrapped prematurely due to excessive wear, reduce the frequency of blade replacement, and reduce overall maintenance costs.

[0078] In summary, the chain blade adaptive wear monitoring and diagnosis system provided by the present application has the following technical effects: Through the operation data acquisition module, the operation data acquisition module is used to collect blade operation data in real time through multi-dimensional sensors to obtain blade operation data; the operation wear module is used to perform wear diagnosis on the blade operation data based on the pattern recognition model and extract wear characteristic parameters; the operation optimization module is used to introduce a first operation strategy to optimize the blade operation data based on the wear characteristic parameters to obtain the first depth operation data; the depth wear module is used to perform wear diagnosis on the first depth operation data based on the wear warning model to obtain the depth wear characteristic parameters; the depth maintenance module is used to introduce a second operation strategy to perform depth maintenance on the first depth operation data based on the depth wear characteristic parameters to obtain the adaptive blade operation data; the continuous monitoring module is used to start the adaptive blade operation data and continuously monitor the adaptive blade operation data. That is to say, by real-time data collection through multi-dimensional sensors, wear diagnosis using pattern recognition models, optimization of blade cutting parameters, and depth maintenance according to cutting depth changes, the continuous monitoring and adaptive adjustment of the chain blade operation status are realized, and the maintenance efficiency of the chain blade is improved.

[0079] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0080] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. Chain blade adaptive wear monitoring and diagnostic system, characterized in that: include: An operation data acquisition module, wherein the operation data acquisition module is used to acquire blade operation data in real time through a multi-dimensional sensor to obtain blade operation data; An operation wear module, the operation wear module is used to perform wear diagnosis on the blade operation data based on a pattern recognition model and extract wear characteristic parameters; An operation optimization module, the operation optimization module is used to introduce a first operation strategy to perform operation optimization on the blade operation data based on the wear characteristic parameters to obtain first depth operation data; A depth wear module, the depth wear module is used to perform wear diagnosis on the first depth operation data based on a wear warning model to obtain depth wear characteristic parameters; A depth maintenance module, the depth maintenance module is used to introduce a second operation strategy to perform depth maintenance on the first depth operation data based on the depth wear characteristic parameter to obtain adaptive blade operation data; A continuous monitoring module is used to start the adaptive blade operation data and continuously monitor the adaptive blade operation data.

2. The chain blade adaptive wear monitoring and diagnostic system according to claim 1, characterized in that: The method of performing wear diagnosis on the blade operation data based on the pattern recognition model and extracting wear characteristic parameters includes: The pattern recognition model includes a vibration recognition channel, a temperature recognition channel and a load recognition channel; Inputting the blade operation data into the pattern recognition model for channel mapping to obtain vibration key parameters, temperature key parameters and load key parameters; Based on the vibration identification channel, the temperature identification channel and the load identification channel, the limit exceeding standard analysis is performed on the vibration key parameter, the temperature key parameter and the load key parameter to obtain the wear characteristic parameter.

3. The chain blade adaptive wear monitoring and diagnostic system according to claim 2, characterized in that: The obtaining of the wear characteristic parameter comprises: Performing frequency domain analysis on the key vibration parameters based on the vibration identification channel to obtain frequency domain amplitude and frequency domain frequency; If the frequency domain amplitude satisfies the amplitude change threshold, a vibration amplitude diagnosis result is obtained, wherein the vibration amplitude diagnosis result includes a decrease in blade sharpness; If the frequency domain frequency satisfies the frequency offset threshold, a vibration frequency diagnosis result is obtained, wherein the vibration frequency diagnosis result includes uneven wear of the blade; If any of the vibration amplitude diagnosis result and the vibration frequency diagnosis result is obtained, a vibration wear characteristic parameter is obtained, and the vibration wear characteristic parameter is added to the wear characteristic parameter.

4. The chain blade adaptive wear monitoring and diagnostic system according to claim 1, characterized in that: Get the first run strategy, including: Constructing a sample wear map according to the sample wear characteristic parameters and the sample wear degree; Inputting the wear characteristic parameters into the sample wear map for mapping analysis to obtain the wear degree; Performing time iteration simulation based on the wear degree to obtain a wear variation trend; The first operation strategy is generated according to the wear change trend.

5. The chain blade adaptive wear monitoring and diagnostic system according to claim 4, characterized in that: Generating the first operation strategy according to the wear variation trend includes: Extracting a wear critical value according to the wear variation trend; The blade is adaptively operated with the goal of delaying the wear critical value in the time dimension until the operation process tends to be stable, and the first operation strategy is generated.

6. The chain blade adaptive wear monitoring and diagnostic system according to claim 1, characterized in that: The performing wear diagnosis on the first depth operation data based on the wear warning model to obtain depth wear characteristic parameters includes: The wear warning model includes a vibration warning channel, a temperature warning channel and a load warning channel; Inputting the first depth operation data into the wear warning model for channel mapping to obtain vibration depth parameters, temperature depth parameters and load depth parameters; Based on the vibration warning channel, the temperature warning channel and the load warning channel, the vibration depth parameter, the temperature depth parameter and the load depth parameter are subjected to limit exceeding standard analysis to obtain the depth wear characteristic parameter.

7. The chain blade adaptive wear monitoring and diagnostic system according to claim 1, characterized in that: The introducing the second operation strategy to perform in-depth maintenance on the first in-depth operation data to obtain adaptive blade operation data includes: The second operation strategy includes a blade adjustment angle strategy and a blade adjustment position strategy; Based on the blade adjustment angle strategy, the chip removal process is monitored to obtain chip removal data, and based on the chip removal data, the entry angle and the exit angle in the first depth operation data are adjusted to obtain a blade adjustment angle; Based on the blade adjustment position strategy, the cutting force process is monitored to obtain cutting force distribution data, and the front-to-back position and the left-to-right position in the first depth operation data are adjusted based on the cutting force distribution data to obtain the blade adjustment position; A blade maintenance position is obtained according to the blade adjustment angle and the blade adjustment position, and the blade maintenance position is added to the adaptive blade operation data.

8. The chain blade adaptive wear monitoring and diagnostic system according to claim 1, characterized in that: The continuously monitoring the adaptive blade operation data includes: Continuously monitoring the operating data of the adaptive blade to obtain real-time monitoring quality; Perform blade reversal according to the real-time monitoring quality and record the reversal time node; A predetermined commutation period is determined according to the commutation time node, a blade direction is adjusted based on the commutation period, and blade commutation data is fed back to the adaptive blade operation data.

Images