A method and system for monitoring and analyzing the operating condition of a centrifugal fan

Abstract

The application discloses a centrifugal fan operation condition monitoring and analyzing method and system and belongs to the technical field of equipment monitoring. After operation data of a centrifugal fan in a preset time length is acquired, corresponding estimated normal operation data is estimated through motor power data in the operation data, abnormal types existing are analyzed according to the operation data and the estimated normal operation data, and when a centering abnormality occurs, a centering abnormality subtype is analyzed, and a specific abnormal type occurring in the operation process of the centrifugal fan is analyzed, so that the efficiency of centrifugal fan maintenance is improved.

Description

Technical Field

[0001] This invention relates to the field of equipment monitoring technology, and in particular to a method and system for monitoring and analyzing the operating status of centrifugal fans. Background Technology

[0002] Centrifugal fans are mechanical devices that use the principle of centrifugal force to transport or pressurize gas, and are widely used in industries, construction, environmental protection and other fields.

[0003] Real-time monitoring of centrifugal fans is a key means to ensure their safe and efficient operation. However, in the current technology, there is no automatic analysis of abnormal conditions based on the operating data of centrifugal fans to identify the type of abnormality. This greatly increases the maintenance burden and troubleshooting time of maintenance personnel, resulting in insufficient maintenance efficiency and untimely maintenance, which in turn damages the centrifugal fans. Summary of the Invention

[0004] To address the technical problems existing in the prior art, this invention provides a method for monitoring and analyzing the operating status of a centrifugal fan, comprising the following steps:

[0005] The centrifugal fan's operating data is acquired within a preset time period, including noise data, vibration data, and motor power data.

[0006] The corresponding estimated normal operating data is estimated by using motor power data. The estimated normal operating data includes: estimated normal noise data and estimated normal vibration data.

[0007] Based on the analysis of operational data and estimated normal operation data, the types of anomalies are identified, including: impeller anomalies and alignment anomalies;

[0008] When an alignment anomaly occurs, the alignment anomaly subtypes are analyzed, which are divided into: parallel misalignment, angular misalignment, and combined misalignment.

[0009] Furthermore, the noise data includes impeller noise data and coupling noise data;

[0010] The vibration data is collected by vibration sensors from the axial, horizontal and vertical vibration data of the centrifugal fan coupling, and recorded as axial vibration data, horizontal vibration data and vertical vibration data, respectively.

[0011] Furthermore, the estimation of corresponding predicted normal operating data based on motor power data specifically includes:

[0012] The estimated normal noise data includes estimated normal impeller noise data and estimated normal coupling noise data; the estimated normal vibration data includes estimated normal axial vibration data, estimated normal horizontal vibration data and estimated normal vertical vibration data.

[0013] Using a pre-trained first deep learning model, based on each motor power data point in the motor power data, predict the corresponding estimated normal impeller noise data point and the first estimated normal coupling noise data point, and form the estimated normal impeller noise data and the first estimated normal coupling noise data within the preset time period.

[0014] Using a pre-trained second deep learning model, based on each motor power data point in the motor power data, predict the corresponding estimated normal axial vibration data points, estimated normal horizontal vibration data points, and estimated normal vertical vibration data points, respectively, to form the estimated normal axial vibration data, estimated normal horizontal vibration data, and estimated normal vertical vibration data within the preset time period.

[0015] Using a pre-trained third deep learning model, the second estimated normal coupling noise data is predicted based on the estimated normal vibration data.

[0016] The average of the data points at the same time in the first and second estimated normal coupling noise data is calculated to obtain the estimated normal coupling noise data.

[0017] Furthermore, the analysis of anomaly types based on operational data and estimated normal operation data specifically includes:

[0018] The data points in the impeller noise data and the data points in the estimated normal impeller noise data are respectively recorded as the first data point and the second data point; the data points in the coupling noise data and the data points in the estimated normal coupling noise data are respectively recorded as the third data point and the fourth data point;

[0019] The first data point and the second data point are compared simultaneously, and the first data point that is greater than the corresponding second data point and the difference is greater than or equal to the first preset value is selected and recorded as the first abnormal data point; the third data point and the fourth data point are compared simultaneously, and the third data point that is greater than the corresponding fourth data point and the difference is greater than or equal to the second preset value is selected and recorded as the second abnormal data point.

[0020] If the ratio of the number of first abnormal data points to the number of first data points is greater than or equal to the first preset ratio, then an impeller abnormality is determined to exist; if the ratio of the number of second abnormal data points to the number of third data points is greater than or equal to the second preset ratio, then an alignment abnormality is determined to exist.

[0021] Furthermore, when a midpoint anomaly occurs, the midpoint anomaly subtype is analyzed, specifically as follows:

[0022] Based on the axial vibration data, horizontal vibration data, and vertical vibration data, the mean values ​​of axial vibration V1, horizontal vibration V2, and vertical vibration V3 are calculated respectively; based on the estimated normal axial vibration data, estimated normal horizontal vibration data, and estimated normal vertical vibration data, the mean values ​​of estimated normal axial vibration N1, estimated normal horizontal vibration N2, and estimated normal vertical vibration N3 are calculated respectively.

[0023] Fast Fourier transform was performed on the axial vibration data, horizontal vibration data, and vertical vibration data to obtain the axial vibration spectrum, horizontal vibration spectrum, and vertical vibration spectrum, respectively.

[0024] If V2-N2≥Y2 and / or V3-N3≥Y3, and V1-N1<Y1, and in the horizontal vibration spectrum and / or vertical vibration spectrum, the second harmonic amplitude is greater than the first harmonic amplitude in the corresponding spectrum, then it is determined to be parallel misalignment;

[0025] If V2-N2 < Y2 and V3-N3 < Y3, and V1-N1 ≥ Y1, and in the axial vibration spectrum, the second harmonic amplitude is greater than the first harmonic amplitude, then it is determined that the angle is misaligned.

[0026] If V2-N2≥Y2 and / or V3-N3≥Y3, and V1-N1≥Y1, and in the horizontal vibration spectrum and / or vertical vibration spectrum, the second harmonic amplitude is greater than the first harmonic amplitude in the corresponding spectrum, and in the axial vibration spectrum, the second harmonic amplitude is greater than the first harmonic amplitude, then it is determined to be a comprehensive misalignment.

[0027] The present invention also provides a centrifugal fan operation status monitoring and analysis system, comprising:

[0028] The data acquisition module is used to acquire the operating data of the centrifugal fan within a preset time period. The operating data includes noise data, vibration data, and motor power data.

[0029] The normal operation data estimation module is used to estimate the corresponding estimated normal operation data based on the motor power data. The estimated normal operation data includes: estimated normal noise data and estimated normal vibration data.

[0030] The first anomaly type analysis module is used to analyze the anomaly types based on the operating data and the estimated normal operating data. The anomaly types include: impeller anomaly and alignment anomaly.

[0031] The second anomaly type analysis module is used to analyze the anomaly subtypes when an alignment anomaly occurs. The alignment anomaly subtypes are divided into: parallel misalignment, angular misalignment, and comprehensive misalignment.

[0032] The noise data includes impeller noise data and coupling noise data;

[0033] The vibration data is collected by vibration sensors from the axial, horizontal and vertical vibration data of the centrifugal fan coupling, and recorded as axial vibration data, horizontal vibration data and vertical vibration data, respectively.

[0034] Furthermore, the estimation of corresponding predicted normal operating data based on motor power data specifically includes:

[0035] The estimated normal noise data includes estimated normal impeller noise data and estimated normal coupling noise data; the estimated normal vibration data includes estimated normal axial vibration data, estimated normal horizontal vibration data and estimated normal vertical vibration data.

[0036] Using a pre-trained first deep learning model, based on each motor power data point in the motor power data, predict the corresponding estimated normal impeller noise data point and the first estimated normal coupling noise data point, and form the estimated normal impeller noise data and the first estimated normal coupling noise data within the preset time period.

[0037] Using a pre-trained second deep learning model, based on each motor power data point in the motor power data, predict the corresponding estimated normal axial vibration data points, estimated normal horizontal vibration data points, and estimated normal vertical vibration data points, respectively, to form the estimated normal axial vibration data, estimated normal horizontal vibration data, and estimated normal vertical vibration data within the preset time period.

[0038] Using a pre-trained third deep learning model, the second estimated normal coupling noise data is predicted based on the estimated normal vibration data.

[0039] The average of the data points at the same time in the first and second estimated normal coupling noise data is calculated to obtain the estimated normal coupling noise data.

[0040] Furthermore, the analysis of anomaly types based on operational data and estimated normal operation data specifically includes:

[0041] The data points in the impeller noise data and the data points in the estimated normal impeller noise data are respectively recorded as the first data point and the second data point; the data points in the coupling noise data and the data points in the estimated normal coupling noise data are respectively recorded as the third data point and the fourth data point;

[0042] The first data point and the second data point are compared simultaneously, and the first data point that is greater than the corresponding second data point and the difference is greater than or equal to the first preset value is selected and recorded as the first abnormal data point; the third data point and the fourth data point are compared simultaneously, and the third data point that is greater than the corresponding fourth data point and the difference is greater than or equal to the second preset value is selected and recorded as the second abnormal data point.

[0043] If the ratio of the number of first abnormal data points to the number of first data points is greater than or equal to the first preset ratio, then an impeller abnormality is determined to exist; if the ratio of the number of second abnormal data points to the number of third data points is greater than or equal to the second preset ratio, then an alignment abnormality is determined to exist.

[0044] The present invention also provides an electronic device, including a processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, and when the processor executes the computer instructions, the electronic device executes any of the centrifugal fan operation status monitoring and analysis methods described above.

[0045] The present invention also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a processor of an electronic device, cause the processor to perform any of the centrifugal fan operation status monitoring and analysis methods described above.

[0046] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0047] This invention obtains the operating data of a centrifugal fan within a preset time period, estimates the corresponding expected normal operating data based on the motor power data in the operating data, analyzes the types of anomalies based on the operating data and the expected normal operating data, and analyzes the subtypes of the anomalies when centering anomalies occur, thereby improving the efficiency of centrifugal fan maintenance.

[0048] By estimating the first estimated normal coupling noise data based on motor power, and predicting the second estimated normal coupling noise data based on estimated normal vibration data, the average of the data points at the same time in the first and second estimated normal coupling noise data is calculated to obtain the estimated normal coupling noise data. This avoids the problem of only reflecting the motor power data and ignoring the dynamic characteristics of the mechanical structure. The estimated normal coupling noise data obtained by combining vibration data that can characterize the physical movement of mechanical components covers both the energy input and mechanical response dimensions of coupling noise, avoiding the one-sidedness of a single data source. Attached Figure Description

[0049] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is a flowchart of a centrifugal fan operation status monitoring and analysis method according to the present invention;

[0052] Figure 2 This is a flowchart of step S2 in a centrifugal fan operation status monitoring and analysis method of the present invention. Detailed Implementation

[0053] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0054] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0055] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" and "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0056] Example 1

[0057] See Figures 1 to 2 As shown, the present invention provides a method for monitoring and analyzing the operating status of a centrifugal fan, which specifically includes the following steps:

[0058] S1. Obtain the operating data of the centrifugal fan within a preset time period;

[0059] The operational data includes: noise data, vibration data, and motor power data;

[0060] S2. Estimate the corresponding expected normal operating data based on motor power data;

[0061] The estimated normal operating data includes: estimated normal noise data and estimated normal vibration data;

[0062] S3. Analyze the types of anomalies based on the operating data and the estimated normal operating data;

[0063] The anomaly types include: impeller anomalies and alignment anomalies;

[0064] S4. When a midpoint anomaly occurs, analyze the midpoint anomaly subtype;

[0065] The centering anomaly subtypes are divided into: parallel misalignment, angular misalignment, and combined misalignment.

[0066] S1. Obtain the operating data of the centrifugal fan within a preset time period:

[0067] In some embodiments, noise data are collected at the impeller and coupling positions of the centrifugal fan using high-sensitivity microphones, and recorded as impeller noise data and coupling noise data, respectively.

[0068] In some embodiments, vibration data of the coupling of the centrifugal fan in the axial, horizontal and vertical directions are collected by vibration sensors and recorded as axial vibration data, horizontal vibration data and vertical vibration data, respectively.

[0069] Axial vibration data is collected by installing the vibration sensor axis parallel to the coupling shaft centerline on the outer flange surface of the coupling cover; a vibration sensor is installed on each of the bearing seats on both sides of the coupling, with the horizontal direction parallel to the ground and the vertical direction perpendicular to the ground, to collect horizontal vibration data and vertical vibration data respectively.

[0070] It should be noted that in this scheme, the sampling frequency of all data acquisition devices is synchronized.

[0071] S2. Estimate the corresponding expected normal operating data based on motor power data:

[0072] The estimation of corresponding estimated normal operating data based on motor power data is specifically as follows:

[0073] S21. The estimated normal noise data includes estimated normal impeller noise data and estimated normal coupling noise data, and the estimated normal vibration data includes estimated normal axial vibration data, estimated normal horizontal vibration data and estimated normal vertical vibration data.

[0074] S22. Using the pre-trained first deep learning model, predict the corresponding estimated normal impeller noise data points and the first estimated normal coupling noise data points according to each motor power data point in the motor power data, and form the estimated normal impeller noise data and the first estimated normal coupling noise data within the preset time period.

[0075] S23. Using the pre-trained second deep learning model, based on each motor power data point in the motor power data, predict the corresponding estimated normal axial vibration data points, estimated normal horizontal vibration data points, and estimated normal vertical vibration data points respectively, and form the estimated normal axial vibration data, estimated normal horizontal vibration data, and estimated normal vertical vibration data within the preset time period.

[0076] S24. Using a pre-trained third deep learning model, predict the second estimated normal coupling noise data based on the estimated normal vibration data.

[0077] S25. Calculate the average of the data points at the same time in the first estimated normal coupling noise data and the second estimated normal coupling noise data to obtain the estimated normal coupling noise data.

[0078] The first deep learning model is trained using a large number of motor power data points, as well as corresponding normal impeller noise data points and normal coupling noise data points as training samples. It takes the motor power value at a certain moment as input and outputs the estimated normal impeller noise data value and the first estimated normal coupling noise data value at that moment.

[0079] The second deep learning model is trained using a large number of motor power data points and corresponding normal axial vibration data points, normal horizontal vibration data points and normal vertical vibration data points as training samples. It takes the motor power value at a certain moment as input and outputs the estimated normal axial vibration data value, estimated normal horizontal vibration data value and estimated normal vertical vibration data value at that moment.

[0080] The third deep learning model is trained using a large number of normal axial vibration data values, normal horizontal vibration data values, normal vertical vibration data values, and corresponding normal coupling noise data values ​​as training samples. It is input with normal axial vibration data values, normal horizontal vibration data values, and normal vertical vibration data values ​​at a certain moment, and outputs the second estimated normal coupling noise data value at that moment.

[0081] The average value of the data points at the same time in the first estimated normal coupling noise data and the second estimated normal coupling noise data is calculated. For example, the average value of the first estimated normal coupling noise data point at time a and the average value of the second estimated normal coupling noise data point at time a are calculated to obtain the data value of the estimated normal coupling noise data point at time a. In this way, the average value of the first estimated normal coupling noise data point and the second estimated normal coupling noise data point obtained within the preset time period are calculated to obtain the estimated normal coupling noise data within the preset time period.

[0082] S3. Analyze the types of anomalies based on operational data and estimated normal operation data:

[0083] The types of anomalies analyzed based on operational data and estimated normal operation data are specifically as follows:

[0084] S31. Record the data points in the impeller noise data and the data points in the estimated normal impeller noise data as the first data point and the second data point, respectively; record the data points in the coupling noise data and the data points in the estimated normal coupling noise data as the third data point and the fourth data point, respectively;

[0085] S32. Simultaneously compare the first data point and the second data point, and filter out the first data point that is greater than the corresponding second data point and whose difference is greater than or equal to the first preset value, and record it as the first abnormal data point; simultaneously compare the third data point and the fourth data point, and filter out the third data point that is greater than the corresponding fourth data point and whose difference is greater than or equal to the second preset value, and record it as the second abnormal data point.

[0086] S33. If the ratio of the number of first abnormal data points to the number of first data points is greater than or equal to the first preset ratio, then it is determined that there is an impeller abnormality; if the ratio of the number of second abnormal data points to the number of third data points is greater than or equal to the second preset ratio, then it is determined that there is an alignment abnormality.

[0087] S4. When a midpoint anomaly occurs, analyze the midpoint anomaly subtype:

[0088] When a midpoint anomaly occurs, the midpoint anomaly subtype is analyzed, specifically as follows:

[0089] Based on the axial vibration data, horizontal vibration data, and vertical vibration data, the mean values ​​of axial vibration V1, horizontal vibration V2, and vertical vibration V3 are calculated respectively; based on the estimated normal axial vibration data, estimated normal horizontal vibration data, and estimated normal vertical vibration data, the mean values ​​of estimated normal axial vibration N1, estimated normal horizontal vibration N2, and estimated normal vertical vibration N3 are calculated respectively.

[0090] Fast Fourier transform was performed on the axial vibration data, horizontal vibration data, and vertical vibration data to obtain the axial vibration spectrum, horizontal vibration spectrum, and vertical vibration spectrum, respectively.

[0091] If V2-N2≥Y2 and / or V3-N3≥Y3, and V1-N1<Y1, and in the horizontal vibration spectrum and / or vertical vibration spectrum, the second harmonic amplitude is greater than the first harmonic amplitude in the corresponding spectrum, then it is determined to be parallel misalignment;

[0092] If V2-N2 < Y2 and V3-N3 < Y3, and V1-N1 ≥ Y1, and in the axial vibration spectrum, the second harmonic amplitude is greater than the first harmonic amplitude, then it is determined that the angle is misaligned.

[0093] If V2-N2≥Y2 and / or V3-N3≥Y3, and V1-N1≥Y1, and in the horizontal vibration spectrum and / or vertical vibration spectrum, the second harmonic amplitude is greater than the first harmonic amplitude in the corresponding spectrum, and in the axial vibration spectrum, the second harmonic amplitude is greater than the first harmonic amplitude, then it is determined to be a comprehensive misalignment.

[0094] In centrifugal fans, the octave amplitude refers to the vibration amplitude in the vibration spectrum that is an integer multiple of the fundamental frequency (1st octave) of the equipment's rotational speed. The fundamental frequency (1st octave) corresponds to the actual rotational speed frequency of the centrifugal fan. Octaves (2nd octave, 3rd octave, etc.) are integer multiples of the fundamental frequency.

[0095] When the two shafts are not parallel, it means that the axes of the two shafts are parallel but there is a radial offset, which causes the coupling to be subjected to periodic radial shear force during rotation. When the shafts rotate, the parallel offset of the coupling will cause the axes of the two shafts to periodically deviate from the ideal position in the radial direction. Every half revolution, the direction of the radial shear force of the coupling reverses once, and every one revolution, the direction of the shear force changes twice. The vibration frequency is twice the rotational frequency.

[0096] When the angles are misaligned, that is, when there is an angular deviation between the two shafts (the axes intersect at a certain angle), the coupling will generate periodic alternating axial tensile or compressive forces during rotation due to the tilt of the angle. When the shaft rotates to a certain position (e.g., 0°), one side of the coupling is under tension and the other side is under compression. After rotating 180°, the positions of tension and compression are completely reversed. For each rotation, the direction of the axial force changes twice, resulting in a vibration frequency that is twice the rotational frequency. This dynamic change of periodic reverse force will generate strong 2 times the frequency vibration in the axial direction.

[0097] Example 2

[0098] This invention also provides a centrifugal fan operation status monitoring and analysis system, specifically comprising:

[0099] The data acquisition module is used to acquire the operating data of the centrifugal fan within a preset time period. The operating data includes noise data, vibration data, and motor power data.

[0100] The normal operation data estimation module is used to estimate the corresponding estimated normal operation data based on the motor power data. The estimated normal operation data includes: estimated normal noise data and estimated normal vibration data.

[0101] The first anomaly type analysis module is used to analyze the anomaly types based on the operating data and the estimated normal operating data. The anomaly types include: impeller anomaly and alignment anomaly.

[0102] The second anomaly type analysis module is used to analyze the anomaly subtypes when an alignment anomaly occurs. The alignment anomaly subtypes are divided into: parallel misalignment, angular misalignment, and comprehensive misalignment.

[0103] The noise data includes impeller noise data and coupling noise data;

[0104] The vibration data is collected by vibration sensors from the axial, horizontal and vertical vibration data of the centrifugal fan coupling, and recorded as axial vibration data, horizontal vibration data and vertical vibration data, respectively.

[0105] In some embodiments, estimating the corresponding estimated normal operating data using motor power data specifically involves:

[0106] The estimated normal noise data includes estimated normal impeller noise data and estimated normal coupling noise data; the estimated normal vibration data includes estimated normal axial vibration data, estimated normal horizontal vibration data and estimated normal vertical vibration data.

[0107] Using a pre-trained first deep learning model, based on each motor power data point in the motor power data, predict the corresponding estimated normal impeller noise data point and the first estimated normal coupling noise data point, and form the estimated normal impeller noise data and the first estimated normal coupling noise data within the preset time period.

[0108] Using a pre-trained second deep learning model, based on each motor power data point in the motor power data, predict the corresponding estimated normal axial vibration data points, estimated normal horizontal vibration data points, and estimated normal vertical vibration data points, respectively, to form the estimated normal axial vibration data, estimated normal horizontal vibration data, and estimated normal vertical vibration data within the preset time period.

[0109] Using a pre-trained third deep learning model, the second estimated normal coupling noise data is predicted based on the estimated normal vibration data.

[0110] The average of the data points at the same time in the first and second estimated normal coupling noise data is calculated to obtain the estimated normal coupling noise data.

[0111] In some embodiments, the analysis of anomaly types based on operational data and estimated normal operation data specifically includes:

[0112] The data points in the impeller noise data and the data points in the estimated normal impeller noise data are respectively recorded as the first data point and the second data point; the data points in the coupling noise data and the data points in the estimated normal coupling noise data are respectively recorded as the third data point and the fourth data point;

[0113] The first data point and the second data point are compared simultaneously, and the first data point that is greater than the corresponding second data point and the difference is greater than or equal to the first preset value is selected and recorded as the first abnormal data point; the third data point and the fourth data point are compared simultaneously, and the third data point that is greater than the corresponding fourth data point and the difference is greater than or equal to the second preset value is selected and recorded as the second abnormal data point.

[0114] If the ratio of the number of first abnormal data points to the number of first data points is greater than or equal to the first preset ratio, then an impeller abnormality is determined to exist; if the ratio of the number of second abnormal data points to the number of third data points is greater than or equal to the second preset ratio, then an alignment abnormality is determined to exist.

[0115] In some embodiments, the step of analyzing the midpoint anomaly subtype when a midpoint anomaly occurs specifically involves:

[0116] Based on the axial vibration data, horizontal vibration data, and vertical vibration data, the mean values ​​of axial vibration V1, horizontal vibration V2, and vertical vibration V3 are calculated respectively; based on the estimated normal axial vibration data, estimated normal horizontal vibration data, and estimated normal vertical vibration data, the mean values ​​of estimated normal axial vibration N1, estimated normal horizontal vibration N2, and estimated normal vertical vibration N3 are calculated respectively.

[0117] Fast Fourier transform was performed on the axial vibration data, horizontal vibration data, and vertical vibration data to obtain the axial vibration spectrum, horizontal vibration spectrum, and vertical vibration spectrum, respectively.

[0118] If V2-N2≥Y2 and / or V3-N3≥Y3, and V1-N1<Y1, and in the horizontal vibration spectrum and / or vertical vibration spectrum, the second harmonic amplitude is greater than the first harmonic amplitude in the corresponding spectrum, then it is determined to be parallel misalignment;

[0119] If V2-N2 < Y2 and V3-N3 < Y3, and V1-N1 ≥ Y1, and in the axial vibration spectrum, the second harmonic amplitude is greater than the first harmonic amplitude, then it is determined that the angle is misaligned.

[0120] If V2-N2≥Y2 and / or V3-N3≥Y3, and V1-N1≥Y1, and in the horizontal vibration spectrum and / or vertical vibration spectrum, the second harmonic amplitude is greater than the first harmonic amplitude in the corresponding spectrum, and in the axial vibration spectrum, the second harmonic amplitude is greater than the first harmonic amplitude, then it is determined to be a comprehensive misalignment.

[0121] Example 3

[0122] The present invention also provides an electronic device, including: a processor, a transmitting device, an input device, an output device, and a memory. The processor may be implemented using a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit, or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory may be implemented using a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), and is used to store computer program code. The computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes a method as described in any of the above possible implementation methods.

[0123] Example 4

[0124] The present invention also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a processor of an electronic device, cause the processor to perform a method as described in any of the above possible implementations.

[0125] The beneficial effects of this invention are as follows:

[0126] This invention obtains the operating data of a centrifugal fan within a preset time period, estimates the corresponding expected normal operating data based on the motor power data in the operating data, analyzes the types of anomalies based on the operating data and the expected normal operating data, and analyzes the subtypes of the anomalies when centering anomalies occur, thereby improving the efficiency of centrifugal fan maintenance.

[0127] By estimating the first estimated normal coupling noise data based on motor power, and predicting the second estimated normal coupling noise data based on estimated normal vibration data, the average of the data points at the same time in the first and second estimated normal coupling noise data is calculated to obtain the estimated normal coupling noise data. This avoids the problem of only reflecting the motor power data and ignoring the dynamic characteristics of the mechanical structure. The estimated normal coupling noise data obtained by combining vibration data that can characterize the physical movement of mechanical components covers both the energy input and mechanical response dimensions of coupling noise, avoiding the one-sidedness of a single data source.

[0128] In the description of this specification, the references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0129] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0130] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for monitoring and analyzing the operating status of a centrifugal fan, characterized in that, Includes the following steps: The centrifugal fan's operating data is acquired within a preset time period, including noise data, vibration data, and motor power data. The corresponding estimated normal operating data is estimated by using motor power data. The estimated normal operating data includes: estimated normal noise data and estimated normal vibration data. Based on the analysis of operational data and estimated normal operation data, the types of anomalies are identified, including: impeller anomalies and alignment anomalies; When an alignment anomaly occurs, the alignment anomaly subtypes are analyzed, which are divided into: parallel misalignment, angular misalignment, and combined misalignment. The noise data includes impeller noise data and coupling noise data; The vibration data is collected by vibration sensors in the axial, horizontal and vertical directions of the centrifugal fan coupling, and recorded as axial vibration data, horizontal vibration data and vertical vibration data, respectively. Specifically, the estimation of corresponding estimated normal operating data based on motor power data includes: The estimated normal noise data includes estimated normal impeller noise data and estimated normal coupling noise data; the estimated normal vibration data includes estimated normal axial vibration data, estimated normal horizontal vibration data and estimated normal vertical vibration data. Using a pre-trained first deep learning model, based on each motor power data point in the motor power data, predict the corresponding estimated normal impeller noise data point and the first estimated normal coupling noise data point, and form the estimated normal impeller noise data and the first estimated normal coupling noise data within the preset time period. Using a pre-trained second deep learning model, based on each motor power data point in the motor power data, predict the corresponding estimated normal axial vibration data points, estimated normal horizontal vibration data points, and estimated normal vertical vibration data points, respectively, to form the estimated normal axial vibration data, estimated normal horizontal vibration data, and estimated normal vertical vibration data within the preset time period. Using a pre-trained third deep learning model, the second estimated normal coupling noise data is predicted based on the estimated normal vibration data. The average of the data points at the same time in the first and second estimated normal coupling noise data is calculated to obtain the estimated normal coupling noise data.

2. The centrifugal fan operation status monitoring and analysis method according to claim 1, characterized in that, The estimation of corresponding estimated normal operating data based on motor power data is specifically as follows: Using a pre-trained first deep learning model, the corresponding estimated normal impeller noise data points are predicted based on each motor power data point in the motor power data, forming the estimated normal impeller noise data within the preset time period. Using a pre-trained second deep learning model, based on each motor power data point in the motor power data, the corresponding estimated normal axial vibration data points, estimated normal horizontal vibration data points, and estimated normal vertical vibration data points are predicted respectively, forming the estimated normal axial vibration data, estimated normal horizontal vibration data, and estimated normal vertical vibration data within the preset time period.

3. The centrifugal fan operation status monitoring and analysis method according to claim 1, characterized in that, The types of anomalies analyzed based on operational data and estimated normal operation data are specifically as follows: The data points in the impeller noise data and the data points in the estimated normal impeller noise data are respectively recorded as the first data point and the second data point; the data points in the coupling noise data and the data points in the estimated normal coupling noise data are respectively recorded as the third data point and the fourth data point; The first data point and the second data point are compared simultaneously, and the first data point that is greater than the corresponding second data point and whose difference is greater than or equal to the first preset value is selected and recorded as the first abnormal data point. The third data point and the fourth data point are compared simultaneously, and the third data point that is greater than the corresponding fourth data point and whose difference is greater than or equal to the second preset value is selected and recorded as the second abnormal data point. If the ratio of the number of first abnormal data points to the number of first data points is greater than or equal to the first preset ratio, then it is determined that there is an impeller abnormality. If the ratio of the number of second abnormal data points to the number of third data points is greater than or equal to the second preset ratio, then an alignment anomaly is determined to exist.

4. A centrifugal fan operation status monitoring and analysis system, employing the centrifugal fan operation status monitoring and analysis method as described in any one of claims 1 to 3, characterized in that, include: The data acquisition module is used to acquire the operating data of the centrifugal fan within a preset time period. The operating data includes noise data, vibration data, and motor power data. The noise data includes impeller noise data and coupling noise data. The vibration data is acquired by a vibration sensor to collect the axial, horizontal, and vertical vibration data of the centrifugal fan coupling, which are recorded as axial vibration data, horizontal vibration data, and vertical vibration data, respectively. The normal operation data estimation module is used to estimate the corresponding predicted normal operation data based on motor power data. The predicted normal operation data includes: predicted normal noise data and predicted normal vibration data; wherein, the predicted normal noise data includes predicted normal impeller noise data and predicted normal coupling noise data, and the predicted normal vibration data includes predicted normal axial vibration data, predicted normal horizontal vibration data, and predicted normal vertical vibration data. The normal operation data estimation module is specifically used for: using a pre-trained first deep learning model to predict the corresponding first estimated normal coupling noise data points based on each motor power data point in the motor power data, forming the first estimated normal coupling noise data within the preset time period; using a pre-trained third deep learning model to predict the second estimated normal coupling noise data based on the estimated normal vibration data; and calculating the average of the data points at the same time in the first estimated normal coupling noise data and the second estimated normal coupling noise data to obtain the estimated normal coupling noise data. The first anomaly type analysis module is used to analyze the anomaly types based on the operating data and the estimated normal operating data. The anomaly types include: impeller anomaly and alignment anomaly. The second anomaly type analysis module is used to analyze the anomaly subtypes when an alignment anomaly occurs. The alignment anomaly subtypes are divided into: parallel misalignment, angular misalignment, and comprehensive misalignment.

5. The centrifugal fan operation status monitoring and analysis system according to claim 4, characterized in that, The normal operation data estimation module is also used for: Using a pre-trained first deep learning model, the corresponding estimated normal impeller noise data points are predicted based on each motor power data point in the motor power data, thus forming the estimated normal impeller noise data within the preset time period. Using a pre-trained second deep learning model, based on each motor power data point in the motor power data, the corresponding estimated normal axial vibration data points, estimated normal horizontal vibration data points, and estimated normal vertical vibration data points are predicted, forming the estimated normal axial vibration data, estimated normal horizontal vibration data, and estimated normal vertical vibration data within the preset time period.

6. The centrifugal fan operation status monitoring and analysis system according to claim 4, characterized in that, The first anomaly type analysis module is specifically used for: The data points in the impeller noise data and the data points in the estimated normal impeller noise data are respectively recorded as the first data point and the second data point; the data points in the coupling noise data and the data points in the estimated normal coupling noise data are respectively recorded as the third data point and the fourth data point; The first data point and the second data point are compared simultaneously, and the first data point that is greater than the corresponding second data point and whose difference is greater than or equal to the first preset value is selected and recorded as the first abnormal data point. The third data point and the fourth data point are compared simultaneously, and the third data point that is greater than the corresponding fourth data point and whose difference is greater than or equal to the second preset value is selected and recorded as the second abnormal data point. If the ratio of the number of first abnormal data points to the number of first data points is greater than or equal to the first preset ratio, then it is determined that there is an impeller abnormality. If the ratio of the number of second abnormal data points to the number of third data points is greater than or equal to the second preset ratio, then an alignment anomaly is determined to exist.

7. An electronic device, characterized in that, The device includes a processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, and when the processor executes the computer instructions, the electronic device performs the centrifugal fan operation status monitoring and analysis method as described in any one of claims 1 to 3.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which includes program instructions that, when executed by a processor of an electronic device, cause the processor to perform the centrifugal fan operation status monitoring and analysis method as described in any one of claims 1 to 3.

Images