Electric chain saw guide plate fault diagnosis system and method based on vibration analysis

Through the fault diagnosis system of electric chain saw guide plate based on vibration analysis, vibration data is collected and analyzed in real time and cutting parameters are optimized. The problems of inaccurate detection of electric chain saw guide plate faults and low cutting efficiency are solved, and more efficient fault detection and maintenance are achieved , reduce maintenance costs.

CN118687794BActive Publication Date: 2024-11-15QIDONG HAISHENG STAMPING PARTS CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411133851.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-15
Estimated Expiration
2044-08-19

AI Technical Summary

Technical Problem

In the prior art, the fault detection of electric chain saw guide plates is inaccurate, the cutting efficiency is low, and the maintenance is not timely, resulting in high equipment failure rate and increased maintenance costs.

Method used

Adopt the fault diagnosis system of electric chain saw guide plate based on vibration analysis, and collect vibration data in real time through data acquisition module, maintenance record reading module, primary configuration module, wood sample determination module, joint optimization cycle module and parameter combination acquisition module to collect vibration data in real time and set up Fault detection indicators, optimize cutting parameters, perform multi-stage fault diagnosis and iteration, obtain the optimal parameter combination, and set a shutdown protection mechanism.

Benefits of technology

Improves the accuracy of fault detection, improves cutting efficiency, reduces maintenance costs, extends equipment service life, and improves safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118687794B_ABST
    Figure CN118687794B_ABST
Patent Text Reader

Abstract

The present invention discloses a fault diagnosis system and method for an electric chain saw guide plate based on vibration analysis, which belongs to the field of mechanical equipment fault diagnosis. The system includes: a data acquisition module for collecting vibration monitoring data of an electric chain saw guide plate; a maintenance record reading module for reading the historical maintenance record of the electric chain saw guide plate and setting fault detection indicators; a primary configuration module for performing primary configuration on M steel cutting teeth on the saw chain; a wood sample determination module for determining a target wood sample, cutting the target wood sample with N turns of the saw chain, and reading a cutting parameter set; a joint optimization cycle module for establishing a joint optimization cycle of cutting parameters corresponding to M steel cutting teeth; a parameter combination acquisition module for acquiring an optimal parameter combination and setting a shutdown protection mechanism. The present application solves the technical problems in the prior art of inaccurate fault detection of electric chain saw guide plates, low cutting efficiency, and untimely maintenance, which lead to high equipment failure rates and increased maintenance costs.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the field of mechanical equipment fault diagnosis, and in particular to an electric chain saw guide plate fault diagnosis system and method based on vibration analysis. Background Art

[0002] With the widespread application of mechanical equipment in the industrial and agricultural fields, equipment fault diagnosis and maintenance have become particularly important. As a commonly used wood cutting tool, electric chain saws are widely used in fields such as forest felling, wood processing and construction. However, during high-intensity and high-frequency use, electric chain saws are prone to various mechanical failures, such as guide bar wear, chain slack and bearing damage. These failures not only affect cutting efficiency and quality, but also cause equipment downtime, increase maintenance costs, and even cause safety accidents.

[0003] Traditional maintenance of electric chain saws mainly relies on regular manual inspections and empirical judgments, which is a method with low efficiency and poor accuracy. In recent years, fault diagnosis technology based on vibration analysis has gradually been applied to the maintenance of mechanical equipment. By monitoring and analyzing the vibration signals during equipment operation, the operating status of the equipment can be detected in real time, and potential faults can be discovered early. However, most vibration analysis technologies are currently applied to large industrial equipment, and there is little research on small portable equipment such as electric chain saws. The vibration monitoring and fault diagnosis system for the guide plate of the electric chain saw is still imperfect, and an efficient and accurate fault diagnosis method is urgently needed to improve the service life and safety of the electric chain saw. Summary of the invention

[0004] The present application provides an electric chain saw guide bar fault system and method based on vibration analysis, aiming to solve the technical problems in the prior art of inaccurate electric chain saw guide bar fault detection, low cutting efficiency and untimely maintenance, which lead to high equipment failure rate and increased maintenance costs.

[0005] In view of the above problems, the present application provides an electric chain saw guide bar fault system and method based on vibration analysis.

[0006] The first aspect disclosed in the present application provides an electric chain saw guide fault system based on vibration analysis, the system comprising a data acquisition module for collecting vibration monitoring data of the electric chain saw guide based on a vibration monitoring device after the electric chain saw is started, the vibration monitoring data comprising vibration amplitude, vibration frequency and vibration phase; a maintenance record reading module for reading the historical maintenance record of the electric chain saw guide and setting fault detection indicators, the fault detection indicators comprising vibration amplitude threshold, vibration frequency range and vibration phase stability; a primary configuration module for performing primary configuration of M steel cutting teeth on the saw chain based on the continuous vibration corresponding to the power engine of the electric chain saw and the connected anti-vibration spring in combination with the vibration monitoring data; a wood sample determination module for determining after completing the primary configuration and before performing the work task A target wood sample corresponding to the same wood type is cut by the saw chain N times, and the first-turn cutting parameter set, the second-turn cutting parameter set, the third-turn cutting parameter set, ..., and the N-th-turn cutting parameter set are read, wherein the first-turn cutting parameter set includes cutting force, saw chain speed, and saw tooth wear; a joint optimization cycle module is used to establish a cutting parameter joint optimization cycle corresponding to the M steel cutting teeth according to the first-turn cutting parameter set, the second-turn cutting parameter set, the third-turn cutting parameter set, ..., and the N-th-turn cutting parameter set; a parameter combination acquisition module is used to perform a joint iteration of multi-stage electric chain saw guide plate fault diagnosis and N-turn cutting based on the cutting parameter joint optimization cycle in combination with the fault detection index, obtain the optimal parameter combination, and set the shutdown protection mechanism corresponding to the work task.

[0007] Another aspect disclosed in the present application provides a method for detecting a fault of an electric chain saw guide plate based on vibration analysis, the method comprising: collecting vibration monitoring data of the electric chain saw guide plate based on a vibration monitoring device after the electric chain saw is started, the vibration monitoring data including vibration amplitude, vibration frequency, and vibration phase; reading the historical maintenance record of the electric chain saw guide plate, setting fault detection indicators, the fault detection indicators including vibration amplitude threshold, vibration frequency range, and vibration phase stability; performing primary configuration of M steel cutting teeth on the saw chain based on the continuous vibration corresponding to the power engine of the electric chain saw and the connected shockproof spring in combination with the vibration monitoring data; after completing the primary configuration, determining the corresponding wood type before performing the work task. A target wood sample, the saw chain cuts the target wood sample for N turns, reads the first turn cutting parameter set, the second turn cutting parameter set, the third turn cutting parameter set, ..., the Nth turn cutting parameter set, wherein the first turn cutting parameter set includes cutting force, saw chain speed, and saw tooth wear; according to the first turn cutting parameter set, the second turn cutting parameter set, the third turn cutting parameter set, ..., the Nth turn cutting parameter set, establish a cutting parameter joint optimization loop corresponding to the M steel cutting teeth; based on the cutting parameter joint optimization loop, combine the fault detection index to perform multi-stage electric chain saw guide plate fault diagnosis and N-turn cutting joint iteration, obtain the optimal parameter combination, and set the shutdown protection mechanism corresponding to the work task.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] Due to the adoption of a technical solution of an electric chain saw guide bar fault diagnosis system based on vibration analysis, vibration monitoring data is collected based on a vibration monitoring device after the electric chain saw is started, historical maintenance records are read to set fault detection indicators, and M steel cutting teeth are initially configured in combination with the continuous vibration of the electric chain saw power engine and the shock-proof spring, the target wood sample is determined for N-turn cutting, a cutting parameter joint optimization cycle is established, and multi-stage fault diagnosis and joint iteration are performed in combination with fault detection indicators, thereby solving the problems of inaccurate electric chain saw guide bar fault detection, low cutting efficiency and untimely maintenance in the prior art, and achieving the technical effect of improving fault detection accuracy, improving cutting efficiency and reducing maintenance costs.

[0010] 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 in accordance with the contents of the specification. 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 listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A structural schematic diagram of an electric chain saw guide bar fault system based on vibration analysis is provided for an embodiment of the present application.

[0012] Figure 2 A schematic flow chart of a method for detecting a guide bar fault of an electric chain saw based on vibration analysis is provided for an embodiment of the present application.

[0013] Explanation of reference numerals: data collection module 11 , maintenance record reading module 12 , primary configuration module 13 , wood sample determination module 14 , joint optimization cycle module 15 , parameter combination acquisition module 16 . DETAILED DESCRIPTION

[0014] The overall idea of ​​the technical solution provided by this application is as follows:

[0015] The embodiment of the present application provides a system and method for detecting a fault in a guide plate of an electric chain saw based on vibration analysis. Through a technical solution based on vibration analysis, the vibration data of the guide plate of the electric chain saw is collected in real time, and a fault detection index is set in combination with historical maintenance records. The continuous vibration and shockproof spring of the power engine of the electric chain saw are used to preliminarily configure the steel cutting teeth, and a cutting parameter optimization cycle is established through multiple cutting experiments, and finally a multi-stage fault diagnosis and optimization is performed in combination with the fault detection index.

[0016] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0017] Embodiment 1

[0018] like Figure 1 As shown, the embodiment of the present application provides an electric chain saw guide bar fault system based on vibration analysis, the system comprising:

[0019] The data acquisition module 11 is used to collect vibration monitoring data of the guide plate of the electric chain saw based on the vibration monitoring device after the electric chain saw is started, and the vibration monitoring data includes vibration amplitude, vibration frequency, and vibration phase.

[0020] Specifically, first, the electric chain saw needs to be started to enter the working state. Starting the electric chain saw usually involves pressing a power button or pulling a starter rope (for some models) to start the motor and drive the saw chain to move at high speed on the guide bar. Before the electric chain saw works or when it is started, the vibration monitoring device needs to be correctly deployed at an appropriate position of the electric chain saw, usually installed on the guide bar or close to the guide bar, so that the vibration of the guide bar can be accurately monitored. The vibration monitoring device usually includes a sensor (such as an accelerometer or a vibration sensor).

[0021] When the electric chain saw is started and running stably, the vibration monitoring device will begin to collect vibration monitoring data of the guide bar. Including, vibration amplitude: indicates the maximum distance that the guide bar deviates from its equilibrium position during vibration. The magnitude of the vibration amplitude can reflect the intensity of the impact on the guide bar or the degree of imbalance. Vibration frequency: indicates the speed of the guide bar vibration, usually expressed in Hertz (Hz). Vibration frequency can help identify different types of vibration sources, such as the rotation frequency of the motor, the cutting frequency of the saw chain, or the natural frequency of mechanical parts. Vibration phase: indicates the position of a specific point in the vibration waveform relative to a reference point (such as the starting point of the waveform). Vibration phase is very important for analyzing the timing characteristics and phase relationship of vibration. It can provide information about the location of the vibration source, the direction of vibration propagation, and the vibration mode.

[0022] By collecting vibration monitoring data of the electric chain saw guide plate based on the vibration monitoring device, comprehensive monitoring and evaluation of the working status of the electric chain saw can be achieved, providing strong support for subsequent fault diagnosis and performance optimization.

[0023] Maintenance record reading module 12: used to read the historical maintenance record of the electric chain saw guide bar and set fault detection indicators, which include vibration amplitude threshold, vibration frequency range, and vibration phase stability.

[0024] Specifically, it is necessary to clarify whether historical maintenance records are stored in paper documents, electronic databases, or dedicated maintenance management systems. This depends on the company's maintenance management process and the tools used. If maintenance records are stored in an electronic system or database, you need to obtain the appropriate access rights. Depending on how the maintenance records are stored, use the appropriate tools or platforms to access them. For example, if they are stored in a database, you need to use a SQL query tool; if they are stored in a maintenance management system, you need to log in to that system.

[0025] The historical maintenance records usually include the following: Maintenance date: record the date of each maintenance in order to understand the maintenance cycle and frequency. Maintenance content: record in detail the specific work performed for each maintenance, such as replacing worn parts, adjusting mechanical settings, cleaning and lubrication, etc. Fault record: If a fault or problem is found during the maintenance process, the type, cause, impact of the fault and the repair measures taken should be recorded in detail. Vibration monitoring data: If vibration monitoring data is included in the historical maintenance, then this data will be an important basis for setting fault detection indicators.

[0026] After reading the historical maintenance records, they are analyzed in depth to identify common failure modes, signs before failures occur, and maintenance effects. Based on the analysis results of historical maintenance records, a series of fault detection indicators are set, including: Vibration amplitude threshold: Set an upper limit value for the vibration amplitude. When the real-time monitored vibration amplitude exceeds this threshold, it means that the guide plate has problems such as imbalance, looseness or wear. Vibration frequency range: Define a normal vibration frequency range. When the real-time monitored vibration frequency deviates from this range, it indicates that there is an abnormal vibration source or mechanical failure. Vibration phase stability: Evaluate the stability of the vibration phase, that is, whether the vibration waveform remains consistent in continuous measurements. Changes in phase stability indicate looseness, wear or damage to mechanical components.

[0027] Reading the chain saw guide bar maintenance history and setting fault detection indicators is a decision-making process based on data analysis, which helps to provide early warning of potential failures, reduce downtime and improve equipment reliability.

[0028] The primary configuration module 13 is used to perform primary configuration of the M steel cutting teeth on the saw chain based on the continuous vibration corresponding to the power engine of the electric chain saw and the connected anti-vibration spring in combination with the vibration monitoring data.

[0029] Specifically, the power engine of an electric chain saw generates continuous mechanical vibrations during operation. These vibrations include the natural vibration frequency of the engine and additional vibrations generated during operation. This is due to the combined effect of multiple factors such as the imbalance of internal rotating parts, the periodic force of the motor operation, and changes in external loads. These vibrations will be transmitted to the saw chain and steel cutting teeth through the saw chain's transmission system, affecting the stability and cutting efficiency of the saw chain. As a key component connecting the power engine and the saw chain, the anti-vibration spring mainly absorbs and alleviates the vibration generated by the power engine, reducing the direct impact of the vibration on the saw chain and steel cutting teeth. Through appropriate spring stiffness and damping design, the saw chain can be kept relatively stable in a vibrating environment, improving cutting accuracy and safety.

[0030] The vibration monitoring device is used to collect the vibration data of the electric chain saw guide in real time, including key parameters such as vibration amplitude, vibration frequency and vibration phase. The collected vibration data is deeply analyzed to identify the periodic components, abnormal fluctuations and fault signs in the vibration. According to the analysis results of the vibration data, the M steel cutting teeth on the saw chain are initially configured. This includes determining the spacing, arrangement and angle adjustment of the steel cutting teeth to minimize the cutting instability and wear caused by vibration. By adjusting the configuration of the steel cutting teeth, the relative balance of the saw chain in dynamic conditions is achieved, reducing the additional vibration and noise caused by imbalance.

[0031] Specifically, first conduct vibration monitoring to evaluate the impact of the current saw chain and steel cutter configuration on vibration. Based on the monitoring results, design a new steel cutter configuration scheme, including adjusting the spacing, angle, and arrangement. Use simulation software or experimental platforms to simulate and verify the new configuration scheme to evaluate its shock absorption effect and cutting performance. Apply the verified configuration scheme to the actual electric chain saw, and conduct on-site testing and adjustments to further optimize performance. Record key data and observations during the configuration process to provide a reference for subsequent maintenance and optimization.

[0032] Through the above steps, combined with the continuous vibration of the electric chain saw power engine and the shock-absorbing effect of the shock-absorbing spring, the steel cutting teeth on the saw chain are initially configured using vibration monitoring data to ensure the balance and cutting efficiency of the saw chain.

[0033] The wood sample determination module 14 is used to determine the target wood sample corresponding to the same wood type after completing the primary configuration and before executing the work task, cut the target wood sample with the saw chain N turns, and read the first turn cutting parameter set, the second turn cutting parameter set, the third turn cutting parameter set, ..., the Nth turn cutting parameter set, wherein the first turn cutting parameter set includes cutting force, saw chain speed, and saw tooth wear.

[0034] Specifically, it is necessary to select a representative target wood sample that is the same or similar to the wood type encountered in the upcoming work task to ensure the accuracy and repeatability of the test results.

[0035] Use an electric chain saw that has completed primary configuration to continuously cut the target wood sample for N turns. The selection of N should be based on the needs and purpose of the test. It should be enough to collect sufficient data, but also avoid excessive cutting that may damage the wood sample or saw chain. During the cutting process, read and record the cutting parameter set of each turn in real time or regularly. These parameter sets are essential for evaluating saw chain performance, optimizing cutting conditions, and predicting saw chain life. Specifically, each cutting parameter set should include the following: First turn cutting parameter set: Cutting force: refers to the resistance of the saw chain during the cutting process, which is an important indicator for evaluating cutting difficulty and saw chain load. Saw chain speed: refers to the linear speed of the saw chain during the cutting process, which affects cutting efficiency and saw chain wear. Saw tooth wear: By comparing the changes in saw tooth shape or size before and after cutting, the degree of saw tooth wear can be estimated. Second turn to Nth turn cutting parameter set: For the second turn to Nth turn cutting, the above three parameters also need to be recorded, and their changing trends with the increase in the number of cutting times need to be paid attention to. This helps to reveal the law of changes in saw chain performance over time, as well as the signs of performance degradation or failure.

[0036] By comparing the parameter changes between different cutting revolutions, the stability, durability and cutting efficiency of the saw chain can be evaluated. If some parameters are found to fluctuate abnormally or exceed the normal range, it is necessary to further check the saw chain configuration, adjust the cutting conditions or perform necessary maintenance.

[0037] This module can comprehensively evaluate the performance of the electric chain saw under actual working conditions and improve the working efficiency and stability of the equipment by continuously optimizing cutting parameters.

[0038] The joint optimization loop module 15 is used to establish a cutting parameter joint optimization loop corresponding to the M steel cutting teeth according to the first cutting parameter set, the second cutting parameter set, the third cutting parameter set, ..., the Nth cutting parameter set.

[0039] Specifically, ensure that all cutting parameter sets (including cutting force, chain speed, saw tooth wear, etc.) have been accurately recorded and organized. Next, perform correlation analysis between parameters. This includes analyzing the changing trends of parameters such as cutting force, chain speed, saw tooth wear between different cutting revolutions, as well as their mutual influence. For example, it is found that as the chain speed increases, the cutting force will also increase accordingly, but at the same time, the saw tooth wear will also accelerate. For M steel cutting teeth, evaluate their performance during the cutting process separately. This is achieved by analyzing the changes in cutting parameters corresponding to each steel cutting tooth. For example, you can observe which steel cutting teeth wear the fastest during the cutting process and which ones can maintain better cutting efficiency.

[0040] Use regression analysis or machine learning methods (such as linear regression, support vector machine, neural network, etc.) to establish a cutting parameter model for steel cutting teeth. It will take into account all relevant cutting parameters (cutting force, saw chain speed, saw tooth wear, etc.) and their mutual influence, aiming to find an optimal combination of cutting parameters to maximize cutting efficiency, minimize saw tooth wear and reduce energy consumption. Secondly, in the optimization model, the optimization objectives and constraints are clearly set. The optimization objectives include minimizing cutting time, maximizing cutting quality, minimizing saw tooth wear, etc. The constraints include the maximum speed limit of the saw chain, the safe range of cutting force, the allowable limit of saw tooth wear, etc. The optimization variables include, cutting force: optimize the cutting force by adjusting the power output of the electric chain saw and the tension of the saw chain. Saw chain speed: adjust the speed of the saw chain to find the best cutting speed. Saw tooth configuration: according to the cutting parameter model, optimize the configuration of M steel cutting teeth to balance wear and improve cutting performance.

[0041] Use joint optimization algorithms (such as genetic algorithm, particle swarm optimization, simulated annealing, etc.) to jointly optimize the cutting parameters. Generate the initial optimization population based on the results of multiple sets of cutting parameters. Define the fitness function, including comprehensive evaluation indicators of cutting efficiency and sawtooth life. Through multiple iterations, selection, crossover and mutation operations, gradually optimize the cutting parameters and find the optimal solution.

[0042] Adjust the cutting force, chain speed and tooth configuration of the electric chain saw according to the optimization results. During the actual cutting process, monitor the cutting force, chain speed and tooth wear in real time to ensure the effectiveness of the optimized parameters. According to the actual cutting results, make feedback adjustments and continuously optimize the cutting parameters.

[0043] This module can establish a joint optimization cycle of cutting parameters for M steel cutting teeth based on multiple cutting parameter sets, improve the cutting efficiency and tooth life of the electric chain saw, and ensure that the equipment can maintain optimal performance under different working conditions.

[0044] Parameter combination acquisition module 16: used to perform joint iteration of multi-stage electric chain saw guide bar fault diagnosis and N-turn cutting based on the cutting parameter joint optimization cycle and in combination with the fault detection index, obtain the optimal parameter combination, and set the shutdown protection mechanism corresponding to the work task.

[0045] Specifically, according to the specifications of the electric chain saw, the type of wood and preliminary experience, the initial values ​​of the cutting parameters, such as chain speed, cutting depth, feed speed, etc., are set. The current parameter combination is used to perform N-turn cutting, while the cutting parameter set (including cutting force, chain speed, saw tooth wear, etc.) and fault detection data are collected in real time. Based on the collected cutting parameter set, the cutting parameter joint optimization cycle is used to analyze the mutual influence between the parameters and adjust the parameters to optimize the cutting efficiency, reduce wear and reduce energy consumption. Combined with the fault detection index, the collected vibration, temperature, current and other data are analyzed in real time to identify whether there are abnormalities or potential faults. According to the results of the fault diagnosis program, the fault type, location and cause are determined. If an abnormality is detected, the cutting parameters (such as cutting force, chain speed and saw tooth configuration) are dynamically adjusted according to the feedback of the fault diagnosis model to optimize the cutting process and reduce the occurrence of faults. If the fault is not related to the parameters, the parameters are kept unchanged or fine-tuned to adapt to the new working environment. The N-turn cutting is performed again using the adjusted parameter combination, and the above cutting parameter optimization and fault diagnosis process are repeated. Through multiple iterations, the optimal parameter combination is gradually approached.

[0046] According to the results of fault detection indicators and cutting parameter optimization, a series of shutdown protection conditions are preset. These conditions may include vibration amplitude exceeding the threshold, temperature being too high, abnormal current fluctuations, etc. When the real-time monitoring data reaches the preset shutdown conditions, the system automatically triggers the shutdown protection mechanism, cuts off the power supply and issues an alarm. At the same time, the relevant parameters and status information at the time of shutdown are recorded for subsequent analysis and processing.

[0047] Through a multi-stage joint iteration process, this module can not only obtain the optimal cutting parameter combination for a given work task and improve cutting efficiency and quality; it can also prevent potential failures by setting a shutdown protection mechanism to ensure the safety of operators and the continuous operation of the production line.

[0048] Furthermore, the system provided in the embodiment of the application is also used to perform the following steps, including:

[0049] Based on the historical maintenance record of the electric chain saw guide bar, the historical vibration monitoring data is used as the original signal for wavelet transformation to extract vibration characteristics at different frequencies;

[0050] Using a machine learning model, combined with vibration characteristics at different frequencies, to train an electric chain saw guide fault diagnosis model to identify a class of potential failure modes of the electric chain saw guide, wherein the class of potential failure modes includes bearing wear and chain slack;

[0051] Based on the type of potential failure mode and failure probability, the vibration amplitude threshold and the vibration frequency range in the failure detection index are dynamically adjusted.

[0052] Specifically, relevant information is extracted from the maintenance record database of the electric chain saw. The acquired maintenance records are sorted and cleaned to ensure the integrity and accuracy of the data. Vibration-related data are extracted from the maintenance records, including information such as vibration amplitude, vibration frequency, and vibration phase. The historical vibration data is preprocessed, such as denoising and normalization, to ensure data quality.

[0053] Wavelet transform is a signal processing technique that decomposes a signal into different frequency components while maintaining time information. It is suitable for analyzing non-stationary signals (such as vibration signals). The historical vibration monitoring data is used as the original signal and wavelet transform is performed. The appropriate wavelet basis function (such as Daubechies wavelet) and the number of decomposition levels are selected. Through wavelet transform, vibration characteristics at different frequencies are extracted, such as detailed information of high-frequency components and trend information of low-frequency components. These characteristics reflect the changes of vibration signals on different time scales.

[0054] The extracted vibration features are organized into feature vectors as input to the machine learning model. Each feature vector includes vibration amplitude, frequency, and phase information at different frequencies. Different fault types are marked based on the fault description in the maintenance record, such as bearing wear, chain slack, etc. These labels serve as the output of the model. Select a suitable machine learning model, such as support vector machine (SVM), random forest, or neural network. Use the labeled feature data to train the model so that it can identify different fault modes. During the training process, adjust the model parameters for optimal performance. The trained model can input real-time vibration feature data to predict the fault type and probability of the electric chain saw guide. The identified fault modes include bearing wear, chain slack, etc., which are further analyzed based on the probability of the fault mode.

[0055] Based on the failure probability output by the model, analyze the probability of occurrence of each potential failure mode. Identify the failure development trend by analyzing the time series changes of the failure probability. Dynamically adjust the threshold of the vibration amplitude based on the failure probability and historical vibration data. For example, when the probability of bearing wear increases, the vibration amplitude threshold can be lowered to improve the sensitivity of detection. Adjust the vibration frequency range according to the frequency characteristics of different failure modes. For example, chain slack is usually accompanied by vibrations of specific frequencies, and the frequency range in the fault detection index should include these specific frequencies. Adjust the detection standard of phase stability by analyzing the vibration phase. When phase instability is detected, further diagnosis is performed in combination with the failure mode.

[0056] Through the above steps, the electric chain saw guide bar fault diagnosis system based on vibration analysis can effectively utilize historical maintenance records and vibration characteristics, establish and dynamically adjust fault detection indicators, and improve the accuracy and real-time performance of fault detection.

[0057] Furthermore, the system provided in the embodiment of the application is also used to perform the following steps, including:

[0058] Extracting phase information of historical vibration monitoring data, and performing time series analysis to identify phase anomaly points, wherein the phase anomaly points include phase deviation segments and phase discontinuity segments;

[0059] The phase locking value algorithm is used to quantify the vibration phase stability within the historical timing cycle and obtain the vibration phase stability index;

[0060] The second type of potential fault mode is added by the vibration phase stability index, and the electric chain saw guide plate fault diagnosis model is updated in combination with the electric chain saw operating conditions.

[0061] Specifically, the historical vibration monitoring data of the electric chain saw guide is extracted from the maintenance record database to ensure the integrity and accuracy of the data. The historical vibration signal is processed to extract the vibration phase information. The phase change of the vibration signal over time is obtained using Fourier transform or other signal processing techniques. The phase angle at each time point is calculated to form a phase time series.

[0062] Smooth the phase time series data to reduce the impact of noise and highlight the true phase change trend. Analyze the trend changes in the phase time series and identify the long-term and short-term change characteristics of the phase. Identify the segments in the phase time series where the phase angle deviates from the normal range. These segments reflect the unstable or abnormal state of the vibration system. Identify the segments in the phase time series where the phase changes or jumps suddenly. These discontinuous segments usually indicate that the vibration system has a large impact or fault.

[0063] The phase lock value algorithm is used to quantify the degree of phase change of the vibration signal within a cycle. The phase lock value reflects the phase stability of the vibration signal. For each time window, the standard deviation or mean square error of the phase time series is calculated to quantify the amplitude of the phase change. According to the phase lock value, the vibration phase stability index is calculated. The higher the stability index, the more stable the phase of the vibration signal. The vibration phase stability index is calibrated to define the critical value of stability and instability for fault detection.

[0064] Based on the vibration phase stability index, two types of potential fault modes are defined. For example, phase deviation segments and phase discontinuity segments can correspond to different fault modes, such as chain slack and bearing wear. The identified phase anomalies and corresponding fault modes are input into the fault diagnosis model for pattern recognition and classification. Vibration data of electric chain saws under different operating conditions are collected, including data under different loads, speeds and environmental conditions. The vibration phase stability index is combined with the operating condition data to analyze the phase changes and fault modes under different conditions. For example, phase instability under high load can better reflect the problem of chain slack. Based on the new vibration phase stability index and operating condition data, the fault diagnosis model is retrained to enable it to more accurately identify and predict faults. The accuracy and stability of the updated fault diagnosis model are verified through cross-validation and test data sets. The fault diagnosis model and fault detection indicators are continuously optimized based on feedback and data from actual operation.

[0065] Through the above steps, the vibration phase information can be effectively extracted and analyzed, the phase locking value algorithm and the vibration phase stability index can be used to identify potential fault modes, and the fault diagnosis model can be updated and optimized in combination with the operating conditions of the electric chain saw to improve the accuracy and real-time performance of fault detection.

[0066] Furthermore, the system provided in the embodiment of the application is also used to perform the following steps, including:

[0067] Introducing a cutting thickness detection sensor, which is used to measure the cutting thickness of the electric chain saw in real time;

[0068] Based on the cutting thickness of the electric chain saw, the PID algorithm is used to dynamically adjust the cutting force of the M steel cutting teeth controlled by the power engine of the electric chain saw, synchronously capture the cutting thickness changes of the target wood sample, and perform wire cutting step uniformity control of N-turn cutting.

[0069] Specifically, install a cutting thickness detection sensor at an appropriate position of the electric chain saw to ensure that it can measure the thickness change of the wood in real time during the cutting process. Select a high-precision laser sensor or contact sensor to ensure the accuracy of the measurement results. After the installation is completed, perform an initial calibration on the cutting thickness detection sensor to ensure that its measurement results are accurate and set a baseline value. During the cutting process of the electric chain saw, the cutting thickness detection sensor collects cutting thickness data in real time. De-noise and filter the collected cutting thickness data to extract effective thickness change information. Analyze the changing trend of the cutting thickness and identify abnormal thickness points that occur during the cutting process.

[0070] Introduce PID (proportional-integral-differential) control algorithm in the control system to dynamically adjust the cutting force. Set the initial parameters of the PID controller (proportional coefficient Kp, integral coefficient Ki, differential coefficient Kd) and adjust according to the actual situation. Calculate the error between the cutting thickness and the set value in real time. According to the error, use the PID algorithm to calculate the adjustment amount and dynamically adjust the output power of the electric chain saw power engine to control the cutting force of M steel cutting teeth. According to the adjusted cutting force, provide real-time feedback and make further adjustments to ensure the thickness uniformity during the cutting process.

[0071] During the N-time cutting process, the data of the cutting thickness detection sensor and the vibration monitoring data are recorded synchronously. The changing trend of the cutting thickness is analyzed in real time, abnormal cutting conditions are identified, and cutting parameters are adjusted in time. The cutting process is step-by-step uniformity controlled to ensure uniform thickness of each cut and avoid vibration and wear caused by uneven thickness. According to the real-time measured data, the cutting parameters are optimized, and the cutting force and speed are adjusted to ensure the stability and efficiency of the cutting process.

[0072] The cutting process is divided into multiple stages, and fault diagnosis and parameter optimization are performed in each stage. At each stage, potential faults are identified based on vibration monitoring data and cutting thickness data combined with fault detection indicators. For detected faults, timely processing and adjustments are made to ensure the continuity and stability of the cutting process. After each cutting stage, iterative optimization is performed based on the fault diagnosis results and cutting parameters. Cutting force, saw chain speed and steel cutting tooth configuration are adjusted to optimize cutting parameters to ensure the best state for each cut. During the entire cutting process, data is continuously monitored and recorded, and dynamic adjustments and optimizations are performed to ensure the optimal parameter combination is finally obtained.

[0073] Through the above steps, the system can combine the cutting thickness detection sensor and PID algorithm to measure and adjust the cutting force in real time, realize the coordinated iteration of multi-stage electric chain saw guide bar fault diagnosis and N-turn cutting, improve cutting efficiency and accuracy, and ensure the stability and safety of the cutting process.

[0074] Furthermore, the system provided in the embodiment of the application is also used to perform the following steps, including:

[0075] generating a first combined cycle corresponding to the type of potential failure mode based on the cut thickness variation of the target wood sample;

[0076] generating a second combined cycle corresponding to the second type of potential failure mode based on the cutting thickness variation of the target wood sample;

[0077] The cutting parameter joint optimization loop is used as the outer loop, and the first joint loop corresponding to the first type of potential fault mode and the second joint loop corresponding to the second type of potential fault mode are used as the inner loop to establish a nested loop. The nested loop is used to perform joint iteration of multi-stage electric chain saw guide bar fault diagnosis and N-turn cutting to obtain the optimal parameter combination.

[0078] Specifically, based on the cutting thickness data, the thickness variation characteristics associated with a class of potential failure modes (such as chain slack) are identified. These thickness variation characteristics are matched with the historical failure data to confirm the specific manifestations of a class of potential failure modes. Based on the matching results, the first combined cycle is generated to define the cutting parameter adjustment strategy and optimization scheme associated with a class of potential failure modes.

[0079] Similarly, based on the cutting thickness data, the thickness variation characteristics related to the second type of potential failure mode (such as bearing wear) are identified. These thickness variation characteristics are matched with the historical failure data to confirm the specific manifestations of the second type of potential failure mode. Based on the matching results, the second combined cycle is generated to define the cutting parameter adjustment strategy and optimization scheme related to the second type of potential failure mode.

[0080] Based on the cutting parameter joint optimization loop, set the initial cutting parameters, including cutting force, saw chain speed and steel cutting tooth configuration. Set optimization goals, such as maximizing cutting efficiency and minimizing saw tooth wear. Nest the first joint loop corresponding to the first type of potential failure mode in the outer loop, and dynamically adjust the cutting parameters to deal with problems such as chain slack. Nest the second joint loop corresponding to the second type of potential failure mode in the outer loop, and dynamically adjust the cutting parameters to deal with problems such as bearing wear. In each cutting task, perform parameter optimization of the outer loop first, and then trigger the failure mode adjustment of the inner loop based on real-time monitoring data. Continuously monitor cutting thickness and vibration data, and adjust cutting parameters based on monitoring results to ensure uniformity and stability of the cutting process. Through multiple iterations and feedback, gradually optimize cutting parameters and fault detection strategies to improve cutting efficiency and equipment stability.

[0081] The cutting process is divided into multiple stages, and fault diagnosis and parameter optimization are performed independently in each stage. At each stage, fault diagnosis is performed based on real-time monitoring data, potential failure modes are identified and corresponding adjustments are made. After each stage, iterative optimization is performed based on the fault diagnosis results and cutting parameters. Cutting force, chain speed and steel cutting tooth configuration are adjusted to optimize cutting parameters to ensure the best state for each cut. During the entire cutting process, data is continuously monitored and recorded, and dynamic adjustments and optimizations are performed to ensure the optimal parameter combination is finally obtained.

[0082] Summarize and analyze the monitoring data and optimization results of each stage to identify the optimal parameter combination. Evaluate the performance of the optimal parameter combination, including cutting efficiency, quality, and equipment stability. Solidify the optimal parameter combination into the control system of the electric chain saw as the default configuration for subsequent cutting tasks. Apply the optimal parameter combination in actual work to ensure that the electric chain saw can maintain efficient and stable operation under different working conditions.

[0083] Through the above steps, the system can perform joint iteration of multi-stage fault diagnosis and N-turn cutting based on cutting thickness changes and fault detection indicators, and finally obtain the optimal cutting parameter combination to ensure the efficiency and stability of the electric chain saw in actual work.

[0084] Furthermore, the system provided in the embodiment of the application is also used to perform the following steps, including:

[0085] Based on the type of potential failure mode, generating a type of failure spectrum diagram corresponding to the target wood sample;

[0086] Based on a type of fault spectrum diagram corresponding to the target wood sample, the first-turn cutting parameter set, the second-turn cutting parameter set, the third-turn cutting parameter set, ..., the Nth-turn cutting parameter set corresponding to N-turn cutting, a first cutting parameter space is established;

[0087] Based on the first cutting parameter space, a search is performed to maximize the quality of the wood sawn surface and the energy consumption utilization rate, and the first combined cycle is established.

[0088] Specifically, a class of potential failure modes includes chain slack and uneven saw tooth wear. Based on the cutting thickness variation data of the target wood sample, the vibration and cutting characteristics related to a class of potential failure modes are extracted. The extracted cutting thickness variation signal is subjected to spectral analysis, and the vibration characteristics of different frequency components are obtained using fast Fourier transform (FFT) or wavelet transform. Based on the spectral analysis results, a class of fault spectrum diagrams are generated. The spectrum diagram shows the distribution of vibration amplitudes at different frequencies during the cutting process of the target wood sample.

[0089] Summarize the first-turn cutting parameter set, the second-turn cutting parameter set, the third-turn cutting parameter set, and so on, the Nth-turn cutting parameter set collected during the N-times cutting process. These parameter sets include key indicators such as cutting force, saw chain speed, and saw tooth wear. Match these cutting parameters with a class of fault spectrum diagrams to identify the cutting parameter features associated with a class of potential fault modes. Based on the matching results, construct a multidimensional cutting parameter space. Each dimension corresponds to a cutting parameter, such as cutting force, saw chain speed, vibration frequency, and vibration amplitude. Define the boundary conditions of the parameter space, such as the upper and lower limits of the cutting force, the range of the saw chain speed, etc., to ensure the rationality of the parameter space.

[0090] Set optimization goals, including maximizing the quality of the sawn surface of the wood and the utilization rate of energy consumption. These goals help improve cutting efficiency and quality while reducing energy consumption. Define evaluation indicators, such as sawn surface smoothness, cutting accuracy, energy consumption, etc., to measure the quality of the optimization results. Use optimization algorithms (such as genetic algorithms, particle swarm optimization, or simulated annealing, etc.) to search in the first cutting parameter space to find the best parameter combination that meets the optimization goals. According to the evaluation indicators, construct a fitness function to evaluate the performance of each parameter combination. The higher the value of the fitness function, the better the optimization effect of the parameter combination. Based on the optimization search results, generate a first combined cycle corresponding to a class of potential failure modes. This cycle includes the optimized cutting parameter combination and the corresponding adjustment strategy. In the actual cutting process, the optimized parameter combination and adjustment strategy in the first combined cycle are applied to monitor the cutting process in real time to ensure the uniformity of the cutting thickness and the stability of the quality.

[0091] Through this step, the system can generate the first combined cycle corresponding to a class of potential failure modes based on the cutting thickness variation of the target wood sample, ensuring the uniformity and quality of the cutting process while improving energy consumption utilization. This optimization method can continuously improve the performance and reliability of electric chain saws in actual work.

[0092] Furthermore, the system provided in the embodiment of the application is also used to perform the following steps, including:

[0093] Based on the first cutting parameter space, establishing a multi-layer branch architecture;

[0094] In the multi-layer branch architecture, in each layer of branches, the vibration amplitude threshold and the vibration frequency range in the fault detection index are used as constraints, and single-layer branch pruning is performed with the goal of accelerating cutting efficiency;

[0095] After completing the single-layer branch pruning, traverse the multi-layer branches and perform depth-first search and breadth-first exploration in sequence to perform multi-layer branch pruning on the nested loop;

[0096] The multi-layer branch pruning is associated one-to-one with the nested loop jump logic.

[0097] Specifically, in the first cutting parameter space, each dimension represents a key cutting parameter, such as cutting force, saw chain speed, vibration frequency and vibration amplitude, etc. A reasonable range is set for each parameter to ensure that the parameter space covers all optimization combinations.

[0098] The first cutting parameter space is divided into multiple levels, each level represents a subdivision of a parameter or a group of related parameters. In each level, a number of branch nodes are divided according to different values ​​or ranges of the parameters, and each node represents a specific parameter combination or configuration.

[0099] Single-layer branch pruning includes setting fault detection constraints, vibration amplitude threshold: setting the maximum allowable value of the vibration amplitude as a constraint. Vibration frequency range: setting a reasonable range of vibration frequency as a constraint. Phase stability: ensuring the stability of the vibration phase to avoid excessive deviation. The pruning condition is to prune the branches that do not meet the conditions in each layer of branches according to the set fault detection constraints. Only valid branches that meet the conditions are retained to reduce the search space and speed up the optimization.

[0100] In a multi-layer branch architecture, a depth-first search is performed from top to bottom, traversing each branch node layer by layer. The parameter combination and corresponding performance indicators of each path are recorded to identify the optimal path. In each level, all branch nodes are traversed horizontally to evaluate the performance of each node. The performance of all branch nodes in each layer is compared, and the nodes with the best performance are retained and optimized layer by layer. Based on the depth-first search and breadth-first exploration, multi-layer branches are comprehensively pruned to further narrow the search scope. The pruned branch architecture is associated with the nested loop jump logic, and multi-stage fault diagnosis and cutting parameter optimization are performed through the optimized branch architecture.

[0101] Nested loops and jump logic,The nested loop structure includes,Outer loop: Joint optimization loop according to cutting parameters, overall optimization. Inner loop: At each stage, dynamically adjust cutting parameters according to fault detection results and cutting thickness changes to achieve real-time optimization. Jump conditions are to set conditional jump logic based on fault detection indicators and optimization results. At each branch node, decide whether to jump to the next node or fall back to the previous node based on the detection results. Adjust the jump logic based on real-time monitoring data to ensure the effectiveness and stability of the optimization path.

[0102] Through the above steps, the system can generate a joint cycle corresponding to the potential fault mode based on the cutting thickness variation of the target wood sample, establish a multi-layer branch architecture and multi-layer branch cutting, realize the joint iteration of multi-stage fault diagnosis and N-turn cutting, and finally obtain the optimal cutting parameter combination to improve the working efficiency and reliability of the electric chain saw.

[0103] In summary, the electric chain saw guide plate fault diagnosis system based on vibration analysis provided by the embodiment of the present application has the following technical effects:

[0104] 1. Through the data acquisition module, maintenance record reading module, primary configuration module, wood sample determination module, joint optimization cycle module and parameter combination acquisition module, the system can collect vibration data in real time, set fault detection indicators, optimize cutting parameters and perform multi-stage fault diagnosis and iteration, thereby improving fault detection accuracy and cutting efficiency, and setting up a shutdown protection mechanism to reduce equipment failures and maintenance costs.

[0105] 2. By performing wavelet transform on historical vibration monitoring data to extract vibration characteristics at different frequencies, and combining it with a machine learning model to identify potential fault modes, the fault detection indicators are dynamically adjusted, so that the system can accurately identify potential faults such as bearing wear and chain looseness, thereby improving the accuracy and timeliness of fault diagnosis.

[0106] 3. Introduce a cutting thickness detection sensor to measure the cutting thickness of the electric chain saw in real time, and use the PID algorithm to dynamically adjust the cutting force to ensure the thickness uniformity and stability during the cutting process. Through the collaborative iteration of multi-stage electric chain saw guide bar fault diagnosis and N-turn cutting, the cutting quality and efficiency are improved.

[0107] Embodiment 2

[0108] Based on the same inventive concept as the electric chain saw guide bar fault diagnosis system based on vibration analysis in the aforementioned embodiment, Figure 2 As shown, the embodiment of the present application provides a method for diagnosing a fault of a guide bar of an electric chain saw based on vibration analysis, the method comprising:

[0109] Step S100: After the electric chain saw is started, based on the vibration monitoring device, collecting vibration monitoring data of the guide plate of the electric chain saw, wherein the vibration monitoring data includes vibration amplitude, vibration frequency, and vibration phase;

[0110] Step S200: reading the historical maintenance record of the electric chain saw guide bar and setting a fault detection index, wherein the fault detection index includes a vibration amplitude threshold, a vibration frequency range, and a vibration phase stability;

[0111] Step S300: Based on the continuous vibration corresponding to the power engine of the electric chain saw and the connected anti-vibration spring, combined with the vibration monitoring data, the M steel cutting teeth on the saw chain are preliminarily configured;

[0112] Step S400: After completing the primary configuration, before executing the work task, determine the target wood sample corresponding to the same wood type, cut the target wood sample with the saw chain for N turns, and read the first turn cutting parameter set, the second turn cutting parameter set, the third turn cutting parameter set, ..., the Nth turn cutting parameter set, wherein the first turn cutting parameter set includes cutting force, saw chain speed, and saw tooth wear;

[0113] Step S500: establishing a cutting parameter joint optimization cycle corresponding to the M steel cutting teeth according to the first cutting parameter set, the second cutting parameter set, the third cutting parameter set, ..., the Nth cutting parameter set;

[0114] Step S600: Based on the cutting parameter joint optimization cycle, the multi-stage electric chain saw guide bar fault diagnosis and N-turn cutting are jointly iterated in combination with the fault detection index to obtain the optimal parameter combination, and set the shutdown protection mechanism corresponding to the work task.

[0115] Furthermore, the historical maintenance records of the electric chain saw guide bar are read and the fault detection indicators are set, including:

[0116] Based on the historical maintenance record of the electric chain saw guide bar, the historical vibration monitoring data is used as the original signal for wavelet transformation to extract vibration characteristics at different frequencies;

[0117] Using a machine learning model, combined with vibration characteristics at different frequencies, to train an electric chain saw guide fault diagnosis model to identify a class of potential failure modes of the electric chain saw guide, wherein the class of potential failure modes includes bearing wear and chain slack;

[0118] Based on the type of potential failure mode and failure probability, the vibration amplitude threshold and the vibration frequency range in the failure detection index are dynamically adjusted.

[0119] Furthermore, the method further comprises:

[0120] Extracting phase information of historical vibration monitoring data, and performing time series analysis to identify phase anomaly points, wherein the phase anomaly points include phase deviation segments and phase discontinuity segments;

[0121] The phase locking value algorithm is used to quantify the vibration phase stability within the historical timing cycle and obtain the vibration phase stability index;

[0122] The second type of potential fault mode is added by the vibration phase stability index, and the electric chain saw guide plate fault diagnosis model is updated in combination with the electric chain saw operating conditions.

[0123] Furthermore, the fault detection index is combined to perform a coordinated iteration of multi-stage electric chain saw guide bar fault diagnosis and N-turn cutting, including:

[0124] Introducing a cutting thickness detection sensor, which is used to measure the cutting thickness of the electric chain saw in real time;

[0125] Based on the cutting thickness of the electric chain saw, the PID algorithm is used to dynamically adjust the cutting force of the M steel cutting teeth controlled by the power engine of the electric chain saw, synchronously capture the cutting thickness changes of the target wood sample, and perform wire cutting step uniformity control of N-turn cutting.

[0126] Furthermore, the cutting thickness variation of the target wood sample is captured synchronously, and the cutting step uniformity control of N-turn cutting is performed, including:

[0127] generating a first combined cycle corresponding to the type of potential failure mode based on the cut thickness variation of the target wood sample;

[0128] generating a second combined cycle corresponding to the second type of potential failure mode based on the cutting thickness variation of the target wood sample;

[0129] The cutting parameter joint optimization loop is used as the outer loop, and the first joint loop corresponding to the first type of potential fault mode and the second joint loop corresponding to the second type of potential fault mode are used as the inner loop to establish a nested loop. The nested loop is used to perform joint iteration of multi-stage electric chain saw guide bar fault diagnosis and N-turn cutting to obtain the optimal parameter combination.

[0130] Further, based on the cutting thickness variation of the target wood sample, a first combined cycle corresponding to the type of potential failure mode is generated, including:

[0131] Based on the type of potential failure mode, generating a type of failure spectrum diagram corresponding to the target wood sample;

[0132] Based on a type of fault spectrum diagram corresponding to the target wood sample, the first-turn cutting parameter set, the second-turn cutting parameter set, the third-turn cutting parameter set, ..., the Nth-turn cutting parameter set corresponding to N-turn cutting, a first cutting parameter space is established;

[0133] Based on the first cutting parameter space, a search is performed to maximize the quality of the wood sawn surface and the energy consumption utilization rate, and the first combined cycle is established.

[0134] Further, based on the first cutting parameter space, searching is performed to maximize the sawn surface quality and energy utilization rate of the wood, and the first combined cycle is established, which also includes:

[0135] Based on the first cutting parameter space, establishing a multi-layer branch architecture;

[0136] In the multi-layer branch architecture, in each layer of branches, the vibration amplitude threshold and the vibration frequency range in the fault detection index are used as constraints, and single-layer branch pruning is performed with the goal of accelerating cutting efficiency;

[0137] After completing the single-layer branch pruning, traverse the multi-layer branches and perform depth-first search and breadth-first exploration in sequence to perform multi-layer branch pruning on the nested loop;

[0138] The multi-layer branch pruning is associated one-to-one with the nested loop jump logic.

[0139] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0140] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. Electric chain saw guide bar fault diagnosis system based on vibration analysis, It is characterized in that include: A data acquisition module, used for collecting vibration monitoring data of the guide plate of the electric chain saw based on the vibration monitoring device after the electric chain saw is started, wherein the vibration monitoring data includes vibration amplitude, vibration frequency and vibration phase; A maintenance record reading module, used to read the historical maintenance record of the electric chain saw guide plate and set fault detection indicators, wherein the fault detection indicators include a vibration amplitude threshold, a vibration frequency range, and a vibration phase stability; A primary configuration module, for performing primary configuration of M steel cutting teeth on the saw chain based on the continuous vibration corresponding to the power engine of the electric chain saw and the connected anti-vibration spring, in combination with the vibration monitoring data, wherein the primary configuration includes determining the spacing, arrangement and angle adjustment of the steel cutting teeth; A wood sample determination module is used to determine a target wood sample corresponding to the same wood type after completing the primary configuration and before executing the work task, and to cut the target wood sample with the saw chain for N turns, and to read a first turn cutting parameter set, a second turn cutting parameter set, a third turn cutting parameter set, ..., an Nth turn cutting parameter set, wherein the first turn cutting parameter set includes a cutting force, a saw chain speed, and a saw tooth wear amount; A joint optimization cycle module is used to establish a cutting parameter joint optimization cycle corresponding to the M steel cutting teeth according to the first cutting parameter set, the second cutting parameter set, the third cutting parameter set, ..., the Nth cutting parameter set; A parameter combination acquisition module is used to perform a joint iteration of multi-stage electric chain saw guide bar fault diagnosis and N-turn cutting based on the cutting parameter joint optimization cycle and in combination with the fault detection index to obtain the optimal parameter combination and set a shutdown protection mechanism corresponding to the work task.

2. The electric chain saw guide bar fault diagnosis system based on vibration analysis as claimed in claim 1, It is characterized in that Read the chain saw guide bar maintenance history and set fault detection indicators, including: Based on the historical maintenance record of the electric chain saw guide bar, the historical vibration monitoring data is used as the original signal for wavelet transformation to extract vibration characteristics at different frequencies; Using a machine learning model, combined with vibration characteristics at different frequencies, to train an electric chain saw guide fault diagnosis model to identify a class of potential failure modes of the electric chain saw guide, wherein the class of potential failure modes includes bearing wear and chain slack; Based on the type of potential failure mode and failure probability, the vibration amplitude threshold and the vibration frequency range in the failure detection index are dynamically adjusted.

3. The electric chain saw guide bar fault diagnosis system based on vibration analysis as claimed in claim 2, It is characterized in that include: Extracting phase information of historical vibration monitoring data, and performing time series analysis to identify phase anomaly points, wherein the phase anomaly points include phase deviation segments and phase discontinuity segments; The phase locking value algorithm is used to quantify the vibration phase stability within the historical timing cycle and obtain the vibration phase stability index; The second type of potential fault mode is added by the vibration phase stability index, and the electric chain saw guide plate fault diagnosis model is updated in combination with the electric chain saw operating conditions.

4. The electric chain saw guide bar fault diagnosis system based on vibration analysis as claimed in claim 3, It is characterized in that Combined with the fault detection index, a multi-stage electric chain saw guide bar fault diagnosis and N-turn cutting collaborative iteration are performed, including: Introducing a cutting thickness detection sensor, which is used to measure the cutting thickness of the electric chain saw in real time; Based on the cutting thickness of the electric chain saw, the PID algorithm is used to dynamically adjust the cutting force of the M steel cutting teeth controlled by the power engine of the electric chain saw, synchronously capture the cutting thickness changes of the target wood sample, and perform wire cutting step uniformity control of N-turn cutting.

5. The electric chain saw guide bar fault diagnosis system based on vibration analysis as claimed in claim 4, It is characterized in that Synchronously capture the cutting thickness variation of the target wood sample and perform cutting step uniformity control for N-turn cutting, including: generating a first combined cycle corresponding to the type of potential failure mode based on the cut thickness variation of the target wood sample; generating a second combined cycle corresponding to the second type of potential failure mode based on the cutting thickness variation of the target wood sample; The cutting parameter joint optimization loop is used as the outer loop, and the first joint loop corresponding to the first type of potential fault mode and the second joint loop corresponding to the second type of potential fault mode are used as the inner loop to establish a nested loop. The nested loop is used to perform joint iteration of multi-stage electric chain saw guide bar fault diagnosis and N-turn cutting to obtain the optimal parameter combination.

6. The electric chain saw guide bar fault diagnosis system based on vibration analysis as claimed in claim 5, It is characterized in that Based on the cutting thickness variation of the target wood sample, a first combined cycle corresponding to the type of potential failure mode is generated, comprising: Based on the type of potential failure mode, generating a type of failure spectrum diagram corresponding to the target wood sample; Based on a type of fault spectrum diagram corresponding to the target wood sample, the first-turn cutting parameter set, the second-turn cutting parameter set, the third-turn cutting parameter set, ..., the Nth-turn cutting parameter set corresponding to N-turn cutting, a first cutting parameter space is established; Based on the first cutting parameter space, a search is performed to maximize the quality of the wood sawn surface and the energy consumption utilization rate, and the first combined cycle is established.

7. The electric chain saw guide bar fault diagnosis system based on vibration analysis as claimed in claim 6, It is characterized in that Based on the first cutting parameter space, searching is performed to maximize the sawn surface quality and energy utilization rate of the wood, and the first combined cycle is established, further comprising: Based on the first cutting parameter space, establishing a multi-layer branch architecture; In the multi-layer branch architecture, in each layer of branches, the vibration amplitude threshold and the vibration frequency range in the fault detection index are used as constraints, and single-layer branch pruning is performed with the goal of accelerating cutting efficiency; After completing the single-layer branch pruning, traverse the multi-layer branches and perform depth-first search and breadth-first exploration in sequence to perform multi-layer branch pruning on the nested loop; The multi-layer branch pruning is associated one-to-one with the nested loop jump logic.

8. Electric chain saw guide bar fault diagnosis method based on vibration analysis, It is characterized in that The method is applied to the electric chain saw guide plate fault diagnosis system based on vibration analysis according to any one of claims 1 to 7, and the method comprises: After the electric chain saw is started, based on the vibration monitoring device, vibration monitoring data of the guide plate of the electric chain saw is collected, wherein the vibration monitoring data includes vibration amplitude, vibration frequency, and vibration phase; Read the historical maintenance record of the electric chain saw guide bar and set fault detection indicators, wherein the fault detection indicators include a vibration amplitude threshold, a vibration frequency range, and a vibration phase stability; Based on the continuous vibration corresponding to the power engine of the electric chain saw and the connected anti-vibration spring, combined with the vibration monitoring data, the M steel cutting teeth on the saw chain are preliminarily configured, wherein the preliminarily configured includes determining the spacing, arrangement and angle adjustment of the steel cutting teeth; After completing the primary configuration, before executing the work task, determine the target wood sample corresponding to the same wood type, cut the target wood sample with the saw chain for N turns, and read the first turn cutting parameter set, the second turn cutting parameter set, the third turn cutting parameter set, ..., the Nth turn cutting parameter set, wherein the first turn cutting parameter set includes cutting force, saw chain speed, and saw tooth wear; According to the first-turn cutting parameter set, the second-turn cutting parameter set, the third-turn cutting parameter set, ..., the N-th-turn cutting parameter set, a cutting parameter joint optimization cycle corresponding to the M steel cutting teeth is established; Based on the cutting parameter joint optimization cycle, the multi-stage electric chain saw guide bar fault diagnosis and N-turn cutting are jointly iterated in combination with the fault detection index to obtain the optimal parameter combination, and the shutdown protection mechanism corresponding to the work task is set.