A real-time monitoring and damage assessment system and method for the magnetic field characteristics on the surface of a rotor

Abstract

The present invention discloses a system and method for real-time monitoring of the magnetic field characteristics on the surface of a rotor and damage assessment, which relates to the technical field of damage assessment. This method collects detailed magnetic field change data information through real-time monitoring of the magnetic field on the surface of the rotor under different rotational speed conditions. This monitoring means can dynamically capture the magnetic field fluctuation situation and analyze its correlation with the rotational speed of the rotor to ensure early detection and classification assessment of the unbalanced condition, providing accurate data support for further damage analysis. The present invention constructs a damage prediction model by using deep learning technology, combines the unbalanced type and the magnetic field change data to achieve precise assessment of the damage on the surface of the rotor. At the same time, the damage assessment index is linearly normalized to eliminate the influence between different data dimensions and make the assessment result more stable and reliable. By comparing and analyzing the damage assessment index with the threshold value, it is timely determined whether the damage state on the surface of the rotor is abnormal.

Description

Technical Field

[0001] The present invention relates to the technical field of damage assessment, and particularly to a system and method for real-time monitoring of the magnetic field characteristics on the surface of a rotor and damage assessment. Background Art

[0002] In large rotating machinery (such as generators, steam turbines, and motors), the rotor, as a key component, the stability of its operating state directly affects the overall performance and safety of the equipment. Therefore, the monitoring of the magnetic field characteristics on the surface of the rotor and damage assessment are crucial for ensuring the stable operation of the equipment. During the operation of the rotor, due to long-term operation and load changes, problems such as imbalance, vibration, and structural damage may occur. Therefore, real-time monitoring of the magnetic field characteristics on the surface of the rotor and obtaining damage situation data are of great significance for achieving efficient maintenance of the rotor and extending its service life.

[0003] In current rotor damage detection technologies, although various methods have been applied to rotor imbalance detection and vibration monitoring, existing monitoring methods often only focus on static imbalance or dynamic performance at a single frequency, and it is difficult to accurately capture the composite changes in multiple states. Especially for phenomena such as minor damage to the rotor and potential dynamic imbalance, the recognition is not accurate enough, resulting in limited early warning capabilities. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present invention provides a system and method for real-time monitoring of the magnetic field characteristics on the surface of a rotor and damage assessment, which solves the problems in the above background art.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: A method for real-time monitoring of the magnetic field characteristics on the surface of a rotor and damage assessment includes the following steps.

[0006] S1. Pre-use the laser displacement measurement method to check the type of rotor imbalance. If the rotor has a static imbalance state, perform a correction operation.

[0007] S2. After the correction operation, real-time monitor the magnetic field characteristics on the surface of the rotor under different rotational speeds to obtain relevant magnetic field change data information. Based on the relevant magnetic field change data information, analyze the correlation between the magnetic field fluctuation and the rotor rotational speed. If there is a correlation, continue to analyze whether the magnetic field fluctuation is caused by the imbalance of the rotor to obtain the imbalance coefficient Shxs. Based on the value of the imbalance coefficient Shxs, judge the type of rotor imbalance.

[0008] S3. Use deep learning technology to construct a damage prediction model, and based on the rotor imbalance type obtained in S2 and the relevant magnetic field change data information, evaluate the damage situation on the surface of the rotor. After linear normalization processing, construct a damage assessment index Spzs.

[0009] S4. Preset an evaluation threshold Y, compare it with the damage evaluation index Spzs for comparative analysis to estimate the damage condition of the current rotor surface, and based on the estimation result, take corresponding adjustment measures.

[0010] Preferably, the specific steps of S1 include:

[0011] S11. Fix a laser displacement sensor on the side of the rotor in advance, align the laser displacement sensor with a point on the rotor surface and mark it as marking point I. Taking marking point I as the reference point, rotate the rotor, and during the rotation process, collect the time-domain signal through the laser displacement sensor, and analyze the change of the position of the time-domain signal relative to marking point I over time. Among them, the time-domain signal includes time information, displacement data, waveform characteristics and signal offset;

[0012] S12. Perform Fourier transform on the time-domain signal collected by the laser displacement sensor to generate a spectrogram, and find the frequency peak corresponding to the rotational speed on the spectrogram. If there is a frequency component on the spectrogram with the same frequency as the rotational speed, it is initially determined that the current rotor is in a static unbalance state;

[0013] S13. When the rotor is in a static unbalance state, at this time, the rotor will be corrected by the method of adding counterweights.

[0014] Preferably, the specific steps of S2 include:

[0015] S21. After the correction operation, monitor the magnetic field characteristics of the rotor surface in real time under different rotational speeds of the rotor to obtain relevant magnetic field change data information. Among them, the relevant magnetic field change data information includes the magnetic field strength Bq, the frequency-domain amplitude corresponding to the frequency f, the maximum amplitude in the frequency domain the phase of the magnetic field fluctuation the phase of the rotational speed signal the vibration amplitude and the leakage magnetic field strength .

[0016] Preferably, the specific steps of S2 also include:

[0017] S22. Based on the relevant magnetic field change data information, analyze the correlation between the magnetic field fluctuation and the rotor rotational speed to obtain the influence factor Yxyz. The influence factor Yxyz is obtained through the following formula:

[0018] ;

[0019] In the formula, represents the i-th rotational speed value, is denoted as the first magnetic field fluctuation factor under the i-th rotational speed condition, is denoted as the standard deviation of the rotational speed value, is denoted as the standard deviation of the first magnetic field fluctuation factor, is denoted as and the covariance of, where i is the number of different rotational speed values Zs;

[0020] S23, the first magnetic field fluctuation factor under the i-th rotational speed condition is obtained through the following formula:

[0021] ;

[0022] In the formula, denotes the average magnetic field intensity under the i-th rotational speed condition, n denotes the number of different rotational speed conditions, i = 1, 2, 3,..., n, denotes the average magnetic field intensity under all rotational speed conditions;

[0023] If the influence factor Yxyz falls within a pre-set threshold, then it will be determined at this time that there is no correlation between the current magnetic field fluctuation and the rotor rotational speed;

[0024] If the influence factor Yxyz does not fall within the pre-set threshold, then it will be determined at this time that there is a correlation between the current magnetic field fluctuation and the rotor rotational speed, and an analysis instruction for dynamic unbalance type will be sent out at this time.

[0025] Preferably, the specific steps of S2 further include:

[0026] S24. After receiving the analysis instruction for dynamic unbalance type obtained in S23, analyze whether the magnetic field fluctuation is caused by the unbalance of the rotor to obtain an imbalance coefficient Shxs, and the imbalance coefficient Shxs is obtained through the following formula:

[0027] ;

[0028] In the formula, is denoted as the influence factor, is denoted as the frequency domain amplitude corresponding to the frequency f, is denoted as the maximum amplitude in the frequency domain, is denoted as the absolute value of the phase difference, , and are all weight values, where, , and The specific values are set by the user according to the situation.

[0029] Preferably, the specific steps of S2 further include:

[0030] S25. Preset an imbalance threshold K, and compare the imbalance coefficient Shxs with the imbalance threshold K to determine whether the current magnetic field fluctuation is caused by the imbalance of the rotor. The specific content is as follows:

[0031] If the imbalance coefficient Shxs exceeds the imbalance threshold K, it will be determined that the current magnetic field fluctuation is caused by the imbalance of the rotor, and at this time, it will be determined again that the current rotor is of the dynamic imbalance type;

[0032] If the imbalance coefficient Shxs does not exceed the imbalance threshold K, it will be determined that the current magnetic field fluctuation is not caused by the imbalance of the rotor.

[0033] Preferably, the specific steps of S3 include:

[0034] S31. When the rotor is of the dynamic imbalance type, analyze the characteristics of the magnetic field on the rotor surface, analyze the damage condition on the rotor surface, and use deep learning technology to construct an initial model. Input the relevant magnetic field change data information into the initial model for training and testing, and then use the trained initial model as the state recognition model. Respectively obtain the characteristic information in the state recognition model, and use the obtained characteristic information to train and test the state recognition model. Combining the fact that the current rotor is of the dynamic imbalance type, use the trained state recognition model as the damage prediction model, and according to the damage prediction model, fit and output the damage assessment index Spzs under the corresponding rotational speed condition.

[0035] Preferably, the specific steps of S3 also include:

[0036] S32. The damage assessment index Spzs under the corresponding rotational speed condition is obtained through the following formula:

[0037] ;

[0038] In the formula, represents the second magnetic field fluctuation factor, represents the vibration amplitude, represents the magnetic leakage field intensity, and are both weight values, represents the correction constant, and The specific values are set by the user according to the situation, and ln is the symbol of the natural logarithm.

[0039] Preferably, the specific steps of S4 include:

[0040] S41. By comparing and analyzing the damage assessment index Spzs with the assessment threshold Y, to estimate and judge the damage condition on the current rotor surface. The specific content is as follows:

[0041] When the damage assessment index Spzs exceeds the assessment threshold Y, it is estimated that the damage condition on the current rotor surface is in an abnormal state at this time. When the device is started, it needs to be quickly accelerated above the resonance frequency;

[0042] When the damage assessment index Spzs does not exceed the assessment threshold Y, it is estimated that the damage condition on the current rotor surface is not in an abnormal state at this time, and the real-time monitoring operation continues.

[0043] A real-time monitoring and damage assessment system for the magnetic field characteristics of a rotor surface includes an initial type judgment module, a secondary type judgment module, a damage evaluation module, and a feedback module;

[0044] The initial type judgment module is used to pre-detect the rotor imbalance type by using the laser displacement measurement method. If the rotor has a static imbalance state, a correction operation is performed;

[0045] The secondary type judgment module is used to, after the correction operation, monitor the magnetic field characteristics of the rotor surface in real time under different rotational speeds of the rotor to obtain relevant magnetic field change data information. Based on the relevant magnetic field change data information, analyze the correlation between the magnetic field fluctuation and the rotor rotational speed. If there is a correlation, continue to analyze whether the magnetic field fluctuation is caused by the imbalance of the rotor to obtain the imbalance coefficient Shxs, and judge the rotor imbalance type based on the value of the imbalance coefficient Shxs;

[0046] The damage evaluation module is used to construct a damage prediction model by using deep learning technology, and evaluate the damage condition of the rotor surface based on the obtained rotor imbalance type and the relevant magnetic field change data information to construct a damage assessment index Spzs;

[0047] The feedback module is used to preset an assessment threshold Y, and compare and analyze it with the damage assessment index Spzs to estimate the damage condition on the current rotor surface, and take corresponding adjustment measures based on the estimation result.

[0048] The present invention provides a real-time monitoring and damage assessment system and method for the magnetic field characteristics of a rotor surface, having the following beneficial effects:

[0049] (1) First, the rotor unbalance type is investigated by the laser displacement measurement method, which can accurately detect the static unbalance of the rotor. After confirming the existence of the static unbalance state, the correction operation is immediately carried out. This method ensures accurate correction in the initial stage and provides a stable basis for subsequent damage monitoring and evaluation. After the correction operation is completed, the method monitors the magnetic field on the rotor surface in real time under different rotational speed conditions, collects detailed magnetic field change data information. This monitoring means can dynamically capture the magnetic field fluctuations and analyze their correlation with the rotor speed, ensuring early detection and classification evaluation of the unbalance condition, and providing accurate data support for further damage analysis. The present invention constructs a damage prediction model by using deep learning technology, combines the unbalance type and the magnetic field change data to achieve precise evaluation of the damage on the rotor surface. At the same time, the damage evaluation index is linearly normalized to eliminate the influence between different data dimensions, making the evaluation result more stable and reliable. By comparing and analyzing the damage evaluation index with a preset evaluation threshold, it can be timely judged whether the damage state on the rotor surface is abnormal. When the damage index exceeds the threshold, the system can quickly take corresponding adjustment measures to effectively avoid damage expansion and ensure the safety and operation stability of the equipment. In summary, this method realizes the intelligent management of rotor damage based on multi-level monitoring and evaluation, thereby improving the accuracy and real-time performance of damage detection, further enhancing the safe operation level of the equipment, and extending the service life of the rotor.

[0050] (2) This method analyzes the correlation between the magnetic field fluctuation and the rotor speed by calculating the value of the influence factor. The calculation formula of the influence factor can quantify the influence degree between the magnetic field fluctuation and the rotor through statistical methods such as the covariance and standard deviation of the rotational speed and the magnetic field fluctuation factor. This correlation analysis method not only improves the accuracy of dynamic unbalance identification but also reduces the possibility of misjudgment.

[0051] (3)After detecting the dynamic unbalance state of the rotor, the method constructs an initial model through deep learning technology, and trains and tests the model in combination with the magnetic field change data to ensure that the model can accurately identify the changes in the magnetic field characteristics on the rotor surface. After multiple trainings, the initial model is upgraded to a state recognition model, and key feature information is further extracted and intensively trained. Finally, the model is upgraded to a damage prediction model, and a damage assessment index under different rotational speeds is fitted. This deep learning-based modeling process can capture complex non-linear features, thereby effectively improving the accuracy of damage assessment and enabling the system to adapt to the changing working conditions of the rotor. After the damage prediction model generates the damage assessment index, by comparing and analyzing it with a preset assessment threshold, the state of the damage on the rotor surface can be automatically judged. When it exceeds the threshold, the system automatically identifies it as an abnormal state and triggers a preset response strategy. During the startup or shutdown process, a strategy of quickly passing through the resonance region is adopted to ensure that the equipment quickly passes through the dangerous area and avoids staying near the resonance frequency for too long, thereby reducing the damage risk caused by vibration. This intelligent recognition and response mechanism ensures that the equipment takes corresponding measures quickly in the abnormal state and effectively improves the ability of fault prevention. Description of the Drawings

[0052] Figure 1 Schematic flow chart of a method for real-time monitoring and damage assessment of the magnetic field characteristics on the surface of a rotor according to the present invention;

[0053] Figure 2 Block diagram of a system for real-time monitoring and damage assessment of the magnetic field characteristics on the surface of a rotor according to the present invention. Detailed Embodiments

[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0055] Embodiment 1

[0056] Please refer to Figure 1 , the present invention provides a method for real-time monitoring and damage assessment of the magnetic field characteristics on the surface of a rotor, including the following steps.

[0057] S1. Use the laser displacement measurement method in advance to check the type of rotor imbalance. If the rotor has a static imbalance state, perform a correction operation.

[0058] S2. After the calibration operation, the magnetic field characteristics on the rotor surface are monitored in real time under different rotational speeds of the rotor to obtain relevant magnetic field change data information. Based on the relevant magnetic field change data information, the correlation between the magnetic field fluctuation and the rotational speed of the rotor is analyzed. If there is a correlation, it is further analyzed whether the magnetic field fluctuation is caused by the imbalance of the rotor to obtain the imbalance coefficient Shxs. Based on the value of the imbalance coefficient Shxs, the imbalance type of the rotor is judged.

[0059] S3. A damage prediction model is constructed using deep learning technology, and based on the rotor imbalance type obtained in S2 and the relevant magnetic field change data information, the damage condition on the rotor surface is evaluated. After linear normalization processing, a damage assessment index Spzs is constructed.

[0060] S4. An evaluation threshold Y is preset in advance and compared with the damage assessment index Spzs for analysis to estimate and judge the damage condition on the current rotor surface. Based on the estimation and judgment results, corresponding adjustment measures are taken.

[0061] In this embodiment, in step S1, the imbalance type of the rotor is checked by the laser displacement measurement method, and the calibration operation is performed when the static imbalance state is found. This process can effectively reduce the vibration and mechanical stress caused by the imbalance, ensure the stability of the rotor operation, and extend the service life of the equipment. At the same time, through precise displacement measurement, the imbalance sign can be detected at an early stage to prevent its further expansion. In step S2, by monitoring the magnetic field characteristics on the rotor surface under different rotational speeds in real time, detailed magnetic field change data information is obtained, and the correlation between the magnetic field fluctuation and the rotational speed of the rotor is analyzed. If there is a correlation between the magnetic field fluctuation and the rotational speed, it is further judged whether it is caused by different types of imbalances of the rotor (such as static imbalance or dynamic imbalance). This method can accurately identify the source and influence of the imbalance, making the rotor imbalance diagnosis more comprehensive and targeted, and avoiding the limitation of single vibration signal analysis. In step S3, a damage prediction model is constructed using deep learning technology, and the damage condition is evaluated based on the rotor imbalance type and the relevant magnetic field change data information. The deep learning model can extract potential features from complex magnetic field and imbalance data for accurate damage prediction. The damage assessment index is generated through linear normalization processing, and this index can reflect the damage degree of the rotor, improving the accuracy and reliability of the diagnosis, and providing technical support for the intelligent monitoring of the equipment operation state. In step S4, an evaluation threshold is set and compared with the damage assessment index for analysis, so as to realize automatic damage assessment. When the damage assessment index exceeds the threshold, the system automatically prompts the abnormal state, and reduces the risk of damage expansion through corresponding adjustment measures (such as the strategy of quickly passing through the resonance region). This method not only improves the real-time performance of damage detection, but also can actively give an early warning before the abnormality occurs to ensure the safety and stability of the equipment.

[0062] Example 2

[0063] Please refer to Figure 1 , specifically: The specific steps of S1 include:

[0064] S11. Fix a laser displacement sensor on the side of the rotor in advance, align the laser displacement sensor with a point on the rotor surface, and mark it as marking point I. Taking marking point I as the reference point, rotate the rotor, and during the rotation process, collect the time-domain signal through the laser displacement sensor, and analyze the change of the position of the time-domain signal relative to marking point I over time. Among them, the time-domain signal includes time information, displacement data, waveform characteristics, and signal offset;

[0065] Among them, the time information includes: Time axis: The horizontal axis of the time-domain signal is time, indicating the specific time point during the acquisition process. The time information can be absolute time (such as seconds, milliseconds, etc.) or relative time (such as the time point relative to the start time of the measurement); Sampling frequency: The sampling frequency (or sampling rate) refers to the number of signal samples collected per second, usually expressed in Hertz (Hz). For example, a sampling frequency of 1 kHz means collecting 1000 data points per second. The sampling frequency affects the resolution and accuracy of the signal.

[0066] The displacement data includes: Displacement amount: The core data measured by the laser displacement sensor is the displacement amount of the object at a certain moment, that is, the offset of the object relative to the reference position. Displacement is usually in millimeters, micrometers, or nanometers; Instantaneous displacement value: The vertical axis of the time-domain signal shows the displacement value at each time point, that is, the instantaneous displacement value. Each instantaneous displacement value represents the relative position of the object at a specific moment.

[0067] The waveform characteristics include: Signal waveform: The curve formed by the displacement data recorded by the laser displacement sensor changing over time is the time-domain waveform. Through the waveform, the change trend of displacement over time can be observed; Waveform amplitude: The amplitude of the waveform represents the maximum and minimum values of the displacement signal, representing the offset range of the object relative to the initial position. Waveform period (if any): If the displacement of the object shows periodic changes (such as rotor imbalance), then repeated periodic fluctuations can be observed in the waveform.

[0068] Signal offset means that in some cases, the displacement signal may contain an offset value, which represents the initial position or reference position of the object. The offset of the signal can be removed through data processing to more clearly analyze the actual displacement fluctuations.

[0069] S12. By performing Fourier transform (FFT) on the time-domain signal collected by the laser displacement sensor, a spectrogram is generated, and the frequency peak identical to the rotational speed is searched for on the spectrogram. If there is a frequency component on the spectrogram that is identical to the rotational speed frequency (i.e., the fundamental frequency), it is preliminarily determined that the current rotor is in a static unbalance state, indicating that the offset of the rotor's center of gravity causes periodic displacement fluctuations, indicating the existence of static unbalance.

[0070] S13. When the rotor is in a static unbalance state, the rotor will be corrected by adding counterweights at this time.

[0071] In this embodiment, through the precise detection of the unbalance type of the rotor by the laser displacement sensor, the static unbalance state can be effectively identified in the early stage. By using the marked point as a reference point, the system can accurately capture the displacement fluctuation information of the rotor relative to the reference during the rotation process. In this way, the static unbalance state can be judged and corrected in a timely manner before the unbalance significantly affects the operation of the equipment, effectively reducing the mechanical stress and vibration amplitude of the equipment and extending the service life of the equipment. By performing Fourier transform (FFT) on the time-domain signal collected by the laser displacement sensor to generate a spectrogram, the frequency characteristics of the rotor unbalance can be efficiently identified. Especially the detection of the fundamental frequency (i.e., the frequency component with the same frequency as the rotational speed) helps to confirm whether there is static unbalance in the rotor. This spectrogram analysis method can clearly display the vibration frequency distribution of the rotor, making the diagnosis more intuitive and accurate, and ensuring a quick judgment of the unbalance state. After confirming the static unbalance state, the method of adding counterweights is automatically triggered for correction. By adding counterweights to the light side of the rotor to balance the center of gravity, the offset and vibration caused by the unbalance are reduced. This method does not require manual intervention and can automatically complete the correction after the system detects the unbalance, greatly improving the operation stability of the equipment and reducing the operation hazards caused by the unbalance. To sum up, the present invention realizes the efficient identification and correction of the static unbalance of the rotor through steps such as laser displacement measurement, Fourier spectrogram analysis, and automatic counterweight correction, thereby greatly improving the safety and operation stability of the equipment and significantly reducing the losses and maintenance costs caused by the unbalance.

[0072] Embodiment 3

[0073] Please refer to Figure 1 , specifically: The specific steps of S2 include:

[0074] S21. After the correction operation, the magnetic field characteristics on the surface of the rotor are monitored in real time under different rotational speeds of the rotor to obtain relevant magnetic field change data information. Among them, the relevant magnetic field change data information includes the magnetic field intensity Bq, the frequency-domain amplitude corresponding to the frequency f, the maximum amplitude in the frequency domain, the phase of the magnetic field fluctuation , the phase of the rotational speed signal , the vibration amplitude and the leakage magnetic field intensity .

[0075] The specific steps of S2 also include:

[0076] S22. Based on the relevant magnetic field change data information, analyze the correlation between the magnetic field fluctuation and the rotor speed to obtain the influence factor Yxyz, and the influence factor Yxyz is obtained through the following formula:

[0077] ;

[0078] In the formula, represents the i-th rotational speed value, represents the first magnetic field fluctuation factor under the i-th rotational speed condition, represents the standard deviation of the rotational speed value, represents the standard deviation of the first magnetic field fluctuation factor, represents and the covariance of, and i represents the number of different rotational speed values Zs;

[0079] S23. The first magnetic field fluctuation factor under the i-th rotational speed condition is obtained through the following formula:

[0080] ;

[0081] In the formula in total, represents the average magnetic field intensity under the i-th rotational speed condition, n represents the number of different rotational speed conditions, i = 1, 2, 3,..., n, represents the average magnetic field intensity under all rotational speed conditions;

[0082] The above magnetic field intensity Bq can be monitored and obtained through a fluxgate sensor;

[0083] If the influence factor Yxyz falls within the preset threshold, it will be determined at this time that there is no correlation between the current magnetic field fluctuation and the rotor speed;

[0084] If the influence factor Yxyz does not fall within the preset threshold, it will be determined at this time that there is a correlation between the current magnetic field fluctuation and the rotor speed, and an analysis instruction for the dynamic unbalance type will be sent out at this time.

[0085] In this embodiment, after the calibration operation, by monitoring the magnetic field characteristics of the rotor in real time at different rotational speeds, multi-dimensional data information such as the magnetic field strength at each position on the rotor surface, the frequency-domain amplitude corresponding to the frequency, the maximum frequency-domain amplitude, the phase of the magnetic field fluctuation, the phase of the rotational speed signal, the vibration amplitude, and the leakage magnetic field strength can be accurately obtained. This data information provides rich basic data for subsequent magnetic field fluctuation analysis, making the rotor state assessment more comprehensive and effectively improving the monitoring accuracy. Through the analysis of relevant magnetic field change data, the influencing factor is calculated and it is detected whether it falls within the preset threshold to determine whether there is a correlation between the magnetic field fluctuation and the rotor rotational speed. This data-based correlation analysis can effectively distinguish the normal fluctuation of the rotor from the unbalanced fluctuation, avoid misjudgment, and further improve the accuracy of unbalanced state recognition. In addition, this process adaptively judges the relationship between the fluctuation and the rotational speed, making the system have a higher level of intelligence. When it is detected that the influencing factor exceeds the threshold, indicating a significant correlation between the magnetic field fluctuation and the rotational speed, the system can automatically issue an analysis instruction for the type of dynamic unbalance. This automatic identification and feedback mechanism enables the device to quickly respond to possible dynamic unbalance situations without manual intervention, realizing timely early warning and handling of potential faults, and effectively improving the fault response efficiency. In summary, through the combination of multi-parameter monitoring, correlation analysis, and automatic identification and feedback, the present invention realizes the efficient and accurate monitoring of the magnetic field characteristics and unbalanced state of the rotor, significantly improves the operation reliability and safety of the device, and provides strong support for equipment maintenance and fault prevention.

[0086] Embodiment 4

[0087] Please refer to Figure 1 , specifically: The specific steps of S2 further include:

[0088] S24. After receiving the analysis instruction for the type of dynamic unbalance obtained in S23, analyze whether the magnetic field fluctuation is caused by the unbalance of the rotor to obtain the imbalance coefficient Shxs, and the imbalance coefficient Shxs is obtained through the following formula:

[0089] ;

[0090] In the formula, represents the influencing factor, represents the frequency-domain amplitude corresponding to the frequency f, represents the maximum amplitude in the frequency domain, represents the absolute value of the phase difference, , and are all weight values. Among them, , and The specific values are set by the user according to the situation; It reflects the proportion of the vibration amplitude at frequency f to the maximum vibration amplitude. The closer the ratio is to 1, the closer the frequency component is to the maximum vibration component; the smaller the ratio, the relatively weaker the vibration component at that frequency. This ratio is used to analyze the relative contribution of the vibration intensity at a specific frequency in the overall vibration, helping to judge the significance of a certain frequency component.

[0091] The frequency-domain amplitude corresponding to the above-mentioned frequency f and the maximum amplitude in the frequency domain can be monitored and obtained through an acceleration sensor or a laser vibrometer;

[0092] The absolute value of the phase difference can be obtained through the following formula:

[0093] ;

[0094] The specific steps of S2 also include:

[0095] S25. Preset an imbalance threshold K, and compare the imbalance coefficient Shxs with the imbalance threshold K to determine whether the current magnetic field fluctuation is caused by the imbalance of the rotor. The specific content is as follows:

[0096] If the imbalance coefficient Shxs exceeds the imbalance threshold K, it will be determined that the current magnetic field fluctuation is caused by the imbalance of the rotor, and at this time, it will be determined again that the current rotor is of the dynamic imbalance type;

[0097] If the imbalance coefficient Shxs does not exceed the imbalance threshold K, it will be determined that the current magnetic field fluctuation is not caused by the imbalance of the rotor.

[0098] In this embodiment, after receiving the dynamic imbalance type analysis instruction, the method analyzes the imbalance coefficient using the magnetic field fluctuation data, which can quantify the cause of imbalance. The calculation formula of the imbalance coefficient is based on the influence factor, frequency-domain amplitude, phase difference and their weight parameters, comprehensively considering the vibration characteristics of the rotor at different frequencies, especially the ratio of the amplitude corresponding to the frequency to the maximum amplitude, helping to identify the contribution degree of a specific frequency to the overall vibration, so as to accurately judge whether the source of the magnetic field fluctuation is an imbalance problem. This method further improves the accuracy of identifying dynamic imbalance and avoids misjudging fluctuations caused by other factors. By presetting the imbalance threshold and comparing it with the imbalance coefficient, the method of the present invention can judge in real time whether the magnetic field fluctuation is caused by the rotor imbalance. When the imbalance coefficient exceeds the threshold, the system automatically determines that the magnetic field fluctuation is caused by dynamic imbalance and quickly prompts the type of dynamic imbalance. This threshold comparison mechanism reduces the dependence on complex data analysis, realizes automatic fault identification, can quickly respond in the early stage of the fault, and effectively prevents the aggravation of the imbalance problem.

[0099] Embodiment 5

[0100] Please refer to Figure 1 , specifically: The specific steps of S3 include:

[0101] S31. When the rotor is of the dynamic unbalance type, analyze the characteristics of the magnetic field on the rotor surface, analyze the damage condition on the rotor surface, and use deep learning technology to construct an initial model. Input the relevant magnetic field change data information into the initial model for training and testing, and then use the trained initial model as the state recognition model. Respectively obtain the feature information in the state recognition model, and use the obtained feature information to train and test the state recognition model. Considering that the current rotor is of the dynamic unbalance type, use the trained state recognition model as the damage prediction model. According to the damage prediction model, fit and output the damage assessment index Spzs under the corresponding rotational speed condition.

[0102] The specific steps of S3 also include:

[0103] S32. The damage assessment index Spzs under the corresponding rotational speed condition is obtained through the following formula:

[0104] ;

[0105] In the formula, represents the second magnetic field fluctuation factor, represents the vibration amplitude, represents the leakage magnetic field intensity, and are both weight values, represents the correction constant, and The specific values are set by the user according to the situation. ln is the symbol of the natural logarithm.

[0106] The second magnetic field fluctuation factor can be obtained through the following formula:

[0107] ;

[0108] Among them, represents the average magnetic field intensity under the corresponding rotational speed condition, represents the magnetic field intensity at the jth monitoring point, m represents the number of monitoring points on the rotor surface, j = 1, 2, 3,..., m; the second magnetic field fluctuation factor represents the magnetic field fluctuation situation between each monitoring point of the rotor under the corresponding rotational speed condition;

[0109] The vibration amplitude can be monitored and obtained through an acceleration sensor;

[0110] The leakage magnetic field intensity It can be monitored and obtained through a Hall effect sensor or a magnetoresistive sensor.

[0111] The specific steps of S4 include:

[0112] S41. By comparing and analyzing the damage assessment index Spzs with the assessment threshold Y, to estimate and judge the damage situation on the current rotor surface, the specific content is as follows:

[0113] If the damage assessment index Spzs exceeds the assessment threshold Y, at this time, it will be estimated and judged that the damage situation on the current rotor surface is in an abnormal state. When the device starts, it needs to be quickly accelerated above the resonance frequency to reduce the time in the resonance zone, and quickly decelerate when stopping to avoid staying in the resonance zone for a long time;

[0114] If the damage assessment index Spzs does not exceed the assessment threshold Y, at this time, it will be estimated and judged that the damage situation on the current rotor surface is not in an abnormal state, and continue with the real-time monitoring operation.

[0115] During the startup or shutdown process, the rotor will inevitably pass through the resonance frequency range. To avoid staying in the resonance frequency for a long time, a strategy of quickly passing through the resonance zone can be adopted.

[0116] In this embodiment, the method constructs an initial model through deep learning technology, inputs various rotor magnetic field change data into the model for training and testing, gradually optimizes to obtain a state recognition model, and further forms a final damage prediction model. The deep learning model can extract potential feature information from a large amount of complex data, and then accurately identify the damage situation on the rotor surface. This damage assessment method based on intelligent algorithms can significantly improve the accuracy and reliability of identification, and avoid the uncertainty of human judgment in traditional methods. Through the damage prediction model, the damage assessment index of the rotor under specific speed conditions is fitted and output, and combined with key parameters such as the second magnetic field fluctuation factor, vibration amplitude, and leakage magnetic field intensity, a quantitative description of the damage state is realized. This quantitative assessment method is convenient for real-time monitoring of the rotor health state, ensuring that abnormal signals can be captured in the early stage of damage. After obtaining the damage assessment index, by comparing and analyzing it with the preset assessment threshold, the severity of the rotor damage can be accurately judged. When it exceeds the threshold, the system will immediately judge that the rotor damage is in an abnormal state and take corresponding countermeasures, such as quickly accelerating through the resonance zone when starting and quickly decelerating when stopping, avoiding staying in the resonance zone for too long, reducing the risk of further damage. This intelligent early warning and rapid response mechanism can effectively prevent the vibration amplification problem caused by resonance and ensure the safe operation of the equipment.

[0117] Embodiment 6

[0118] Please refer to Figure 2, specifically: A real-time monitoring and damage assessment system for the magnetic field characteristics of a rotor surface, including an initial type judgment module, a secondary type judgment module, a damage evaluation module, and a feedback module;

[0119] The initial type judgment module is used to pre-detect the rotor imbalance type by using the laser displacement measurement method. If the rotor has a static imbalance state, a correction operation is performed;

[0120] The secondary type judgment module is used to, after the correction operation, monitor in real time the magnetic field characteristics of the rotor surface under different rotational speeds of the rotor to obtain relevant magnetic field change data information. Based on the relevant magnetic field change data information, analyze the correlation between the magnetic field fluctuation and the rotor rotational speed. If there is a correlation, continue to analyze whether the magnetic field fluctuation is caused by the imbalance of the rotor to obtain an imbalance coefficient Shxs. Based on the value of the imbalance coefficient Shxs, judge the rotor imbalance type;

[0121] The damage evaluation module is used to construct a damage prediction model by using deep learning technology and, based on the obtained rotor imbalance type and the relevant magnetic field change data information, evaluate the damage condition of the rotor surface to construct a damage evaluation index Spzs;

[0122] The feedback module is used to pre-set an evaluation threshold Y and compare and analyze it with the damage evaluation index Spzs to estimate and judge the current damage condition of the rotor surface and, based on the estimation and judgment results, take corresponding adjustment measures.

[0123] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A real-time monitoring and damage assessment method for the magnetic field characteristics on the surface of a rotor, characterized in that: Including the following steps, S1. Pre - use the laser displacement measurement method to check the rotor imbalance type. If the rotor has a static imbalance state, perform a correction operation; S2. After the correction operation, monitor the magnetic field characteristics on the rotor surface in real - time under different rotational speeds of the rotor to obtain relevant magnetic field change data information. Based on the relevant magnetic field change data information, analyze the correlation between the magnetic field fluctuation and the rotor speed. If there is a correlation, continue to analyze whether the magnetic field fluctuation is caused by the rotor imbalance to obtain the imbalance coefficient Shxs. Based on the value of the imbalance coefficient Shxs, judge the rotor imbalance type; S3. Use deep - learning technology to build a damage prediction model, and based on the rotor imbalance type obtained in S2 and the relevant magnetic field change data information, evaluate the damage condition on the rotor surface. After linear normalization processing, build a damage assessment index Spzs; S4. Preset an evaluation threshold Y, and compare and analyze it with the damage assessment index Spzs to estimate and judge the current damage condition on the rotor surface. Based on the estimation and judgment results, take corresponding adjustment measures.

2. A method for real-time monitoring and damage assessment of the magnetic field characteristics on the surface of a rotor according to claim 1, characterized in that: The specific steps of S1 include: S11. Fix a laser displacement sensor on the side of the rotor in advance, align the laser displacement sensor with a point on the rotor surface, and mark it as mark point I. Taking mark point I as the reference point, rotate the rotor and collect the time - domain signal through the laser displacement sensor during the rotation process. Analyze the change of the position of the time - domain signal relative to mark point I over time. The time - domain signal includes time information, displacement data, waveform characteristics, and signal offset; S12. Perform a Fourier transform on the time - domain signal collected by the laser displacement sensor to generate a spectrogram, and find the frequency peak corresponding to the rotational speed on the spectrogram. If there is a frequency component on the spectrogram with the same frequency as the rotational speed, initially judge that the current rotor is in a static imbalance state; S13. When the rotor is in a static imbalance state, perform a correction operation on the rotor by adding counterweights.

3. A real-time monitoring and damage assessment method for the magnetic field characteristics on the surface of a rotor according to claim 2, characterized in that: The specific steps of S2 include: S21. After the calibration operation, the magnetic field characteristics on the rotor surface are monitored in real time under different rotational speeds of the rotor to obtain relevant magnetic field change data information, where the relevant magnetic field change data information includes the magnetic field intensity Bq at each position on the rotor surface, the frequency-domain amplitude corresponding to the frequency f, the maximum amplitude in the frequency domain, the phase of the magnetic field fluctuation, the phase of the rotational speed signal, the vibration amplitude, and the leakage magnetic field intensity under different rotational speeds of the rotor. , the maximum amplitude in the frequency domain , the phase of the magnetic field fluctuation , the phase of the rotational speed signal , the vibration amplitude and the leakage magnetic field intensity .

4. A method for real-time monitoring and damage assessment of the magnetic field characteristics on the surface of a rotor according to claim 3, characterized in that: The specific steps of S2 also include: S22. Based on the relevant magnetic field change data information, analyze the correlation between the magnetic field fluctuation and the rotor speed to obtain the influence factor Yxyz. The influence factor Yxyz is obtained through the following formula: ； In the formula, is expressed as the i-th rotational speed value, is expressed as the first magnetic field fluctuation factor under the i-th rotational speed condition, is expressed as the standard deviation of the rotational speed value, is expressed as the standard deviation of the first magnetic field fluctuation factor, is expressed as and the covariance of, where i represents the number of different rotational speed values Zs; S23, the first magnetic field fluctuation factor under the i-th rotational speed condition Obtained through the following formula: ； wherein, represents the average magnetic field intensity under the i-th rotational speed condition, n represents the number of different rotational speed conditions, and i = 1, 2, 3,..., n, represents the average magnetic field intensity under all rotational speed conditions; If the influence factor Yxyz falls within the preset threshold, then judge that there is no correlation between the current magnetic field fluctuation and the rotor speed at this time; If the influence factor Yxyz does not fall within the preset threshold, then judge that there is a correlation between the current magnetic field fluctuation and the rotor speed at this time, and send out a dynamic imbalance type analysis instruction outward.

5. A real-time monitoring and damage assessment method for the surface magnetic field characteristics of a rotor according to claim 4, characterized in that: The specific steps of S2 also include: S24. After receiving the dynamic imbalance type analysis instruction obtained in S23, analyze whether the magnetic field fluctuation is caused by the rotor imbalance to obtain the imbalance coefficient Shxs. The imbalance coefficient Shxs is obtained through the following formula: ； Wherein, is expressed as the influence factor, is expressed as the frequency domain amplitude corresponding to the frequency f, is expressed as the maximum amplitude in the frequency domain, is expressed as the absolute value of the phase difference, , and are all weight values, wherein, , and The specific values are set by the user according to the situation.

6. The real-time monitoring and damage assessment method for the magnetic field characteristics on the surface of a rotor according to claim 5, characterized in that: The specific steps of S2 also include: S25. Preset an imbalance threshold K, and compare the imbalance coefficient Shxs with the imbalance threshold K to determine whether the current magnetic field fluctuation is caused by the imbalance of the rotor. The specific content is as follows: If the imbalance coefficient Shxs exceeds the imbalance threshold K, it will be determined that the current magnetic field fluctuation is caused by the imbalance of the rotor, and at this time, it will be determined again that the current rotor is of the dynamic imbalance type; If the imbalance coefficient Shxs does not exceed the imbalance threshold K, it will be determined that the current magnetic field fluctuation is not caused by the imbalance of the rotor.

7. A real-time monitoring and damage assessment method for the surface magnetic field characteristics of a rotor according to claim 6, characterized in that: The specific steps of S3 include: S31. When the rotor is of the dynamic imbalance type, analyze the characteristics of the magnetic field on the rotor surface, analyze the damage condition on the rotor surface, and use deep learning technology to construct an initial model. Input relevant magnetic field change data information into the initial model for training and testing, and then use the trained initial model as the state recognition model. Respectively obtain the characteristic information in the state recognition model, and use the obtained characteristic information to train and test the state recognition model. Considering that the current rotor is of the dynamic imbalance type, use the trained state recognition model as the damage prediction model, and according to the damage prediction model, fit and output the damage assessment index Spzs under the corresponding rotational speed condition.

8. A real-time monitoring and damage assessment method for the magnetic field characteristics on the surface of a rotor according to claim 7, characterized in that: The specific steps of S3 also include: S32. The damage assessment index Spzs under the corresponding rotational speed condition is obtained through the following formula: ； Wherein, is represented as the second magnetic field fluctuation factor, is represented as the vibration amplitude, is represented as the leakage magnetic field intensity, and are both weight values, is represented as the correction constant, and The specific values are set by the user according to the situation, and ln is the symbol of the natural logarithm.

9. A real-time monitoring and damage assessment method for the magnetic field characteristics on the surface of a rotor according to claim 1, characterized in that: The specific steps of S4 include: S41. By comparing and analyzing the damage assessment index Spzs with the assessment threshold Y, estimate and judge the damage condition on the current rotor surface. The specific content is as follows: If the damage assessment index Spzs exceeds the assessment threshold Y, it will be estimated and judged that the damage condition on the current rotor surface is in an abnormal state, and it is necessary to quickly accelerate to above the resonance frequency when the device is started; If the damage assessment index Spzs does not exceed the assessment threshold Y, it will be estimated and judged that the damage condition on the current rotor surface is not in an abnormal state, and continue with the real-time monitoring operation.

10. A real-time monitoring and damage assessment system for the rotor surface magnetic field characteristics, which is used to implement the real-time monitoring and damage assessment method for the rotor surface magnetic field characteristics described in any one of the above claims 1 to 9, and is characterized in that: It includes an initial type judgment module, a secondary type judgment module, a damage evaluation module and a feedback module; The initial type judgment module is used to pre-check the rotor imbalance type by using the laser displacement measurement method. If the rotor has a static imbalance state, correction operations will be carried out; The secondary type judgment module is used to, after the correction operation, monitor in real time the magnetic field characteristics on the rotor surface under different rotational speeds of the rotor to obtain relevant magnetic field change data information. Based on the relevant magnetic field change data information, analyze the correlation between the magnetic field fluctuation and the rotor rotational speed. If there is a correlation, continue to analyze whether the magnetic field fluctuation is caused by the imbalance of the rotor to obtain the imbalance coefficient Shxs, and judge the imbalance type of the rotor based on the value of the imbalance coefficient Shxs; The damage evaluation module is used to use deep learning technology to construct a damage prediction model, and based on the obtained rotor imbalance type and the relevant magnetic field change data information, evaluate the damage condition on the rotor surface to construct the damage assessment index Spzs; The feedback module is used to preset an evaluation threshold Y, compare and analyze it with the damage evaluation index Spzs to estimate the damage condition of the current rotor surface, and take corresponding adjustment measures based on the estimation result.

Images