A method, device, storage medium and controller for online abnormality detection of a fan

Abstract

The present invention provides a method, device, storage medium, and controller for online abnormality detection of a fan. The method comprises: collecting a current signal from the fan; performing signal decomposition on the collected current signal to obtain two or more intrinsic mode components; and determining whether the fan's operation is abnormal based on the two or more intrinsic mode components obtained. The solution provided by the present invention can provide timely early warning or alarm of the fan's operating status, avoiding missed maintenance opportunities.

Description

Technical Field

[0001] The present invention relates to the field of control, and in particular to a method, device, storage medium and controller for online abnormality detection of a fan. Background Art

[0002] During operation, relevant operating parameters often change before a fan malfunction occurs. Prompt inspection at this time can detect the problem early and reduce the risk of downtime. However, current motor monitoring methods mostly rely on electrical indicators such as motor current and frequency. These data are compared with corresponding preset monitoring thresholds. If any of these indicators reaches a predetermined warning value, a warning is issued, prompting maintenance. Alternatively, if any of these indicators reaches a predetermined alarm value, an alarm is issued and the motor is shut down. However, by the time these indicators change significantly, it's often too late to take action, missing the optimal time for maintenance. Furthermore, many faults may not occur without significant changes in electrical parameters, forcing maintenance personnel to discover the problem only after the fault has occurred, at which point any action taken may have already impacted the normal operation of the entire equipment. Summary of the Invention

[0003] The main purpose of the present invention is to overcome the defects of the above-mentioned related technologies and provide an online abnormality detection method, device, storage medium and controller for a fan to solve the problem in the related technologies that the subtle differences between the fan current signals under normal and fault conditions cannot be accurately described.

[0004] On the one hand, the present invention provides an online abnormality detection method for a wind turbine, comprising: collecting a current signal of the wind turbine; performing signal decomposition on the collected current signal to obtain two or more intrinsic mode components; and determining whether there is an abnormality in the operation of the wind turbine based on the two or more intrinsic mode components obtained by decomposition.

[0005] Optionally, performing signal decomposition on the collected current signal to obtain more than two eigenmode components includes: performing signal decomposition on the collected current signal using variational mode decomposition to obtain more than two eigenmode components.

[0006] Optionally, based on the two or more eigenmodal components obtained by decomposition, determining whether there is any abnormality in the operation of the fan includes: selecting N eigenmodal components from the two or more eigenmodal components to perform energy entropy value calculation to obtain the energy entropy value of each of the N selected eigenmodal components; comparing the sum of the energy entropy values ​​of the N eigenmodal function components with a preset entropy value warning value and an entropy value alarm value to determine whether there is any abnormality in the operation of the fan.

[0007] Optionally, it also includes: if it is determined that the operation of the fan is abnormal, a corresponding early warning information or alarm information is issued; wherein, if the result of comparing the sum of the energy entropy values ​​of the N intrinsic mode function components with the entropy value early warning value and the entropy value alarm value exceeds the entropy value early warning value but does not exceed the entropy value alarm value, an early warning information is issued; if the result of comparing the sum of the energy entropy values ​​of the N intrinsic mode function components with the entropy value early warning value and the entropy value alarm value exceeds the entropy value alarm value, an alarm information is issued; and / or, the real-time status of the fan and the early warning information or alarm information of abnormal operation of the fan are displayed.

[0008] On the other hand, the present invention provides an online abnormality detection device for a fan, comprising: an acquisition unit for acquiring the current signal of the fan; a processing unit for performing signal decomposition on the current signal acquired by the acquisition unit to obtain two or more intrinsic mode components; and a determination unit for determining whether there is an abnormality in the operation of the fan based on the two or more intrinsic mode components decomposed by the processing unit.

[0009] Optionally, the processing unit performs signal decomposition on the current signal collected by the collection unit to obtain more than two eigenmode components, including: performing signal decomposition on the collected current signal using variational mode decomposition to obtain more than two eigenmode components.

[0010] Optionally, the determination unit determines whether there is any abnormality in the operation of the fan based on the two or more eigenmodal components decomposed by the processing unit, including: a calculation unit, used to select N eigenmodal components from the two or more eigenmodal components to perform energy entropy value calculation to obtain the energy entropy value of each of the N selected eigenmodal components; a comparison unit, used to compare the sum of the energy entropy values ​​of the N eigenmodal function components with a preset entropy value warning value and an entropy value alarm value to determine whether there is any abnormality in the operation of the fan.

[0011] Optionally, it also includes: an alarm unit, which is used to issue corresponding early warning information or alarm information if the determination unit determines that the operation of the fan is abnormal; wherein, if the result of comparing the sum of the energy entropy values ​​of the N intrinsic mode function components with the entropy value early warning value and the entropy value alarm value exceeds the entropy value early warning value but does not exceed the entropy value alarm value, an early warning information is issued; if the result of comparing the sum of the energy entropy values ​​of the N intrinsic mode function components with the entropy value early warning value and the entropy value alarm value exceeds the entropy value alarm value, an alarm information is issued; and / or, a display unit, which is used to display the real-time status of the fan and early warning information or alarm information of abnormal operation of the fan.

[0012] Another aspect of the present invention provides a storage medium having a computer program stored thereon, wherein the program implements the steps of any of the aforementioned methods when executed by a processor.

[0013] In another aspect, the present invention provides a controller comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the aforementioned methods when executing the program.

[0014] In another aspect, the present invention provides an air conditioner comprising any of the above-mentioned online abnormality detection devices for fans.

[0015] According to the technical solution of the present invention, the current signal of the wind turbine is monitored in real time, and the signal of the wind turbine current signal is decomposed to obtain two or more intrinsic mode components. Based on the two or more intrinsic mode components obtained by decomposition, it is determined whether there is any abnormality in the operation of the wind turbine, so that the working condition of the wind turbine can be warned or alarmed in time to avoid missing the opportunity for maintenance.

[0016] The current signal is decomposed using variational mode decomposition (VMD), and the energy entropy of the intrinsic mode function (IMF) is calculated. The calculated entropy value is compared with the corresponding warning value and alarm value set to issue a warning or alarm for the working condition of the fan. This solves the problem of simply judging the fan condition by comparing electrical indicators such as current and frequency with the corresponding preset monitoring thresholds, which cannot accurately describe the subtle differences between the fan current signals under normal and fault conditions, resulting in untimely treatment measures. Real-time intelligent monitoring of the fan can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1 1 is a schematic diagram of an embodiment of a method for online abnormality detection of a wind turbine provided by the present invention;

[0019] Figure 2 A flow chart of a specific embodiment of the step of determining whether the operation of the wind turbine is abnormal based on the two or more eigenmode components obtained by decomposition is shown;

[0020] Figure 3 This is a schematic diagram of a specific embodiment of the online abnormality detection method for a wind turbine provided by the present invention;

[0021] Figure 4 This is a schematic diagram of a specific embodiment of the online abnormality detection method for a wind turbine provided by the present invention;

[0022] Figure 5 Shown is a schematic diagram of the system structure for implementing the present invention;

[0023] Figure 6 This is a structural block diagram of an embodiment of a device for detecting abnormalities in a fan provided by the present invention;

[0024] Figure 7 It is a structural block diagram of another embodiment of the abnormality detection device for a wind turbine provided by the present invention. DETAILED DESCRIPTION

[0025] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments of the present invention and corresponding drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0026] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] The present invention provides an online abnormality detection method for a fan, which can be implemented in a controller of a device where the fan is located.

[0028] Figure 1 It is a method schematic diagram of an embodiment of the online abnormality detection method of a wind turbine provided by the present invention.

[0029] like Figure 1 As shown, according to one embodiment of the present invention, the anomaly detection method at least includes step S110, step S120 and step S130.

[0030] Step S110: collecting the current signal of the wind turbine.

[0031] Specifically, a current detection device (e.g., a current sensor) for detecting the fan current can be installed to collect the fan current signal. For example, the motor current value collected in real time during the fan operation is transmitted to a corresponding controller connected to the motor.

[0032] Step S120 , performing signal decomposition on the collected current signal to obtain two or more eigenmode components.

[0033] In a specific embodiment, variational mode decomposition is used to decompose the collected current signal to obtain two or more eigenmode components. Specifically, variational mode decomposition (VMD) can effectively decompose non-stationary and nonlinear signals. By solving the variational problem, the original signal is non-recursively decomposed into several eigenmode components with limited bandwidth. The collected current signal f(t) is decomposed by variational mode decomposition (VMD):

[0034]

[0035] In formula (1), u(t) is the kth component; K is the number of VMD components.

[0036] Step S130 : determining whether there is any abnormality in the operation of the fan according to the two or more eigenmodal components obtained by decomposition.

[0037] Figure 2 The flowchart of a specific embodiment of the step of determining whether the operation of the fan is abnormal based on the two or more eigenmode components obtained by decomposition is shown. Figure 2 As described above, step S130 includes step S131 and step S132.

[0038] Step S131 : Select N eigenmodal components from the two or more eigenmodal components to perform energy entropy calculation to obtain the energy entropy of each of the N selected eigenmodal components.

[0039] Preferably, the first N eigencomponents of the two or more eigenmode components obtained by decomposition are selected. Specifically, based on comprehensive consideration of computational complexity and performance, the first several eigencomponents after decomposition are selected, for example, the first 3 eigencomponents are selected.

[0040] The energy entropy values ​​of the intrinsic mode function (IMF) components of the fan are different under different working conditions. The current signal of the fan working process is extracted by extracting the entropy value. The energy proportion of each component P k :

[0041]

[0042] Where: Ek is the energy of the eigenmode component: Then the energy entropy of the eigenmode component is:

[0043] H k =-P k lg P k (3)

[0044] Step S132 : comparing the sum of the energy entropy values ​​of the N intrinsic mode function components with a preset entropy value warning value and an entropy value alarm value to determine whether there is any abnormality in the operation of the wind turbine.

[0045] Specifically, if the sum of the energy entropy values ​​of the N intrinsic mode function components exceeds a preset entropy value warning value or an entropy value alarm value, it is determined that the operation of the fan is abnormal.

[0046] The entropy warning value and the entropy alarm value can be tested multiple times when the fan is in a normal state, and the maximum value among the obtained values ​​is used as a reference value to set the entropy warning value and the entropy alarm value.

[0047] Figure 3 It is a method schematic diagram of a specific embodiment of the online abnormality detection method for a wind turbine provided by the present invention.

[0048] like Figure 3 As shown, based on the above embodiment, according to another embodiment of the present invention, the abnormality detection method further includes step S140.

[0049] Step S140: If it is determined that the operation of the fan is abnormal, a corresponding early warning message or alarm message is issued.

[0050] Specifically, if the result of comparing the sum of the energy entropy values ​​of the N intrinsic mode function components with the entropy value warning value and the entropy value alarm value is that it exceeds the entropy value warning value but does not exceed the entropy value alarm value, a warning message is issued; if the result of comparing the sum of the energy entropy values ​​of the N intrinsic mode function components with the entropy value warning value and the entropy value alarm value is that it exceeds the entropy value alarm value, an alarm message is issued. More specifically, if the sum of the energy entropy values ​​of the N intrinsic mode function components exceeds the entropy value alarm value, an alarm signal is issued; otherwise, it is determined whether the entropy value warning value is exceeded. If it exceeds the entropy value warning value, a warning signal is issued. If it does not exceed the entropy value alarm value or the entropy value warning value, it is displayed as normal. Optionally, an alarm signal or a warning signal can be issued by an alarm.

[0051] Optionally, the method may further include displaying the real-time status of the fan and early warning or alarm information indicating abnormal fan operation. Specifically, changes in the fan and real-time monitoring status may be transmitted to the controller system via a communication interface for display on a display screen, and early warning or alarm information may be displayed in real time on the display screen to prompt maintenance personnel to take urgent action, thereby improving safety and utilization.

[0052] To clearly illustrate the technical solution of the present invention, the execution process of the online abnormality detection method for a wind turbine provided by the present invention is described below with reference to a specific embodiment.

[0053] Figure 4 FIG. 1 is a schematic diagram of a specific embodiment of the online abnormality detection method for a fan provided by the present invention. Figure 4 As shown,

[0054] S1: The fan current is detected by the current sensor, and the motor current value collected in real time during the operation of the fan is transmitted to the corresponding controller connected to the motor.

[0055] S2: Decompose the current signal into several intrinsic mode functions (IMFs) using variational mode decomposition (VMD) in the processor.

[0056] S3: Select the intrinsic mode function (IMF) components (select the first N eigencomponents after decomposition, N ≥ 3) and calculate the energy entropy value.

[0057] S4: Set corresponding warning values ​​and alarm values, and compare the calculated energy entropy value with the warning values ​​and alarm values; if it exceeds the alarm value, execute step S5, otherwise, execute step S6.

[0058] S5: If the alarm value is exceeded, an alarm signal is sent to the alarm device for alarm, and then step S8 is executed.

[0059] S6: If the alarm value is not exceeded, determine whether the warning value is exceeded. If the warning value is exceeded, execute step S7; otherwise, execute step S8.

[0060] S7: If the warning value is exceeded, a signal is sent to the alarm to issue a warning signal. If it is not exceeded, it will be displayed as normal.

[0061] S8: The real-time status of the fan (such as current) is transmitted to the controller system through the communication interface, and the alarm is displayed in real time to prompt maintenance personnel to deal with it urgently and improve safety utilization.

[0062] Figure 5 Shown is a schematic diagram of the system structure of the present invention. Figure 5As shown, the abnormality detection system includes a fan, a processor, a current detection device, an alarm, and a display screen. The current detection device is used to collect the fan's current signal. The processor is used to decompose the collected current signal to obtain two or more intrinsic mode components. Based on the two or more intrinsic mode components obtained by decomposition, it is determined whether the fan's operation is abnormal. The alarm is used to provide an abnormality warning or alarm. The display screen is used to display the fan's real-time status and warning information or alarm information of abnormal fan operation.

[0063] The present invention also provides an online abnormality detection device for a fan, which can be implemented in a controller of a device where the fan is located.

[0064] Figure 6 FIG. 1 is a structural block diagram of an embodiment of a device for detecting abnormalities in a fan provided by the present invention. Figure 6 As shown, the abnormality detection device 100 includes a collection unit 110 , a processing unit 120 and a determination unit 130 .

[0065] The acquisition unit 110 is used to acquire the current signal of the wind turbine.

[0066] Specifically, a current detection device (e.g., a current sensor) for detecting the fan current can be installed to collect the fan current signal. For example, the motor current value collected in real time during the fan operation is transmitted to a corresponding controller connected to the motor.

[0067] The processing unit 120 is configured to perform signal decomposition on the current signal collected by the collection unit 110 to obtain two or more eigenmode components.

[0068] In a specific embodiment, variational mode decomposition is used to decompose the collected current signal to obtain two or more eigenmode components. Specifically, variational mode decomposition (VMD) can effectively decompose non-stationary and nonlinear signals. By solving the variational problem, the original signal is non-recursively decomposed into several eigenmode components with limited bandwidth. The collected current signal f(t) is decomposed by variational mode decomposition (VMD):

[0069]

[0070] In formula (1), u(t) is the kth component; K is the number of VMD components.

[0071] The determination unit 130 is configured to determine whether there is any abnormality in the operation of the wind turbine according to the two or more eigenmodal components decomposed by the processing unit 120 .

[0072] The calculation unit 131 is configured to select N eigenmode components from the two or more eigenmode components to perform energy entropy calculations to obtain an energy entropy value of each of the selected N eigenmode components.

[0073] Preferably, the first N eigencomponents of the two or more IMF components obtained by decomposition are selected. Specifically, based on comprehensive consideration of computational complexity and performance, the first several eigencomponents after decomposition are selected, for example, the first 3 eigencomponents are selected.

[0074] The energy entropy values ​​of the intrinsic mode function (IMF) components of the fan are different under different working conditions. The current signal of the fan working process is extracted by extracting the entropy value. The energy proportion of each component P k :

[0075]

[0076] In formula (2): E k is the energy of the eigenmode component: Then the energy entropy of the eigenmode component is:

[0077] H k =-P k lg P k (3)

[0078] The comparison unit 132 is used to compare the sum of the energy entropy values ​​of the N intrinsic mode function components with a preset entropy value warning value and an entropy value alarm value to determine whether there is any abnormality in the operation of the wind turbine.

[0079] Specifically, if the sum of the energy entropy values ​​of the N intrinsic mode function components exceeds a preset entropy value warning value or an entropy value alarm value, it is determined that the operation of the fan is abnormal.

[0080] The entropy warning value and the entropy alarm value can be tested multiple times when the fan is in a normal state, and the maximum value among the obtained values ​​is used as a reference value to set the entropy warning value and the entropy alarm value.

[0081] Figure 7 FIG. 1 is a structural block diagram of another embodiment of the abnormality detection device for a fan provided by the present invention. Figure 7 As shown, based on the above embodiment, according to another embodiment of the present invention, the abnormality detection device 100 further includes an alarm unit 140.

[0082] The alarm unit 140 is configured to issue a corresponding early warning message or alarm message if the determination unit 130 determines that the operation of the fan is abnormal.

[0083] Specifically, if the result of comparing the sum of the energy entropy values ​​of the N intrinsic mode function components with the entropy value warning value and the entropy value alarm value is that it exceeds the entropy value warning value but does not exceed the entropy value alarm value, a warning message is issued; if the result of comparing the sum of the energy entropy values ​​of the N intrinsic mode function components with the entropy value warning value and the entropy value alarm value is that it exceeds the entropy value alarm value, an alarm message is issued; more specifically, if the sum of the energy entropy values ​​of the N intrinsic mode function components exceeds the entropy value alarm value, an alarm signal is issued; otherwise, it is determined whether the entropy value warning value is exceeded. If it exceeds the entropy value warning value, a warning signal is issued. If it does not exceed the entropy value alarm value or the entropy value warning value, it is displayed as normal.

[0084] Optionally, the device 100 further includes a display unit (not shown) for displaying the real-time status of the fan and warning or alarm information regarding abnormal fan operation. Specifically, changes in the fan and real-time monitoring status can be transmitted to the controller system via a communication interface for display on the display screen. Warning or alarm information can also be displayed in real time on the display screen, prompting maintenance personnel to take urgent action and improving safety utilization.

[0085] The present invention also provides a storage medium corresponding to the online abnormality detection method for the wind turbine, on which a computer program is stored, and when the program is executed by a processor, the steps of any of the above methods are implemented.

[0086] The present invention also provides a controller corresponding to the online abnormality detection method of the wind turbine, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the aforementioned methods when executing the program.

[0087] The present invention also provides a controller corresponding to the online abnormality detection device of the wind turbine, comprising any of the aforementioned online abnormality detection devices of the wind turbine.

[0088] Based on this, the solution provided by the present invention monitors the current signal of the wind turbine in real time, decomposes the current signal of the wind turbine to obtain two or more intrinsic mode components, and determines whether there is any abnormality in the operation of the wind turbine based on the two or more intrinsic mode components obtained by decomposition, so as to be able to issue early warning or alarm in time to avoid missing the maintenance opportunity.

[0089] Variational mode decomposition (VMD) is used to decompose the current signal and calculate the intrinsic mode function (IMF) energy entropy. The calculated entropy value is compared with the corresponding warning value and alarm value set to issue a warning or alarm for the wind turbine's operating condition. The corresponding warning value and alarm value are set, and the calculated entropy value is compared. When the real-time monitored entropy value reaches the warning value, a warning signal is issued, and the corresponding information will be prompted on the touch screen or display, prompting timely inspection of the equipment status. When the monitoring value reaches the alarm value, an alarm signal is issued, indicating that the equipment has a serious problem and cannot continue to operate, otherwise serious losses will be caused. At this time, the control program will stop the corresponding equipment and display the alarm in real time, prompting maintenance personnel to take urgent action.

[0090] This application solves the problem that the fan condition was previously judged simply by comparing electrical indicators such as current and frequency with the corresponding preset monitoring thresholds, and was unable to accurately describe the subtle differences between the fan current signals under normal and fault conditions, resulting in untimely treatment measures. This application can realize real-time intelligent monitoring of the fan.

[0091] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and implementations are within the scope and spirit of the present invention and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwiring, or a combination of any of these. Furthermore, each functional unit may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit.

[0092] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0093] The units described as separate components may or may not be physically separate, and the components of the control device may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0094] If the integrated unit is implemented in the form of 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 the present invention, or the part that contributes to the relevant technology, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0095] The foregoing description is merely an embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of the claims.

Claims

1. A method for online abnormality detection of a fan, characterized in that: include: collecting a current signal of the fan; Performing signal decomposition on the collected current signal to obtain two or more eigenmode components, including: performing signal decomposition on the collected current signal using variational mode decomposition to obtain two or more eigenmode components; Determining whether the operation of the fan is abnormal based on the two or more eigenmodal components obtained by decomposition includes: Selecting N eigenmodal components from the two or more eigenmodal components to perform energy entropy calculations to obtain an energy entropy value of each of the N selected eigenmodal components; The sum of the energy entropy values ​​of the N eigenmodal components is compared with a preset entropy value early warning value and an entropy value alarm value to determine whether there is any abnormality in the operation of the fan.

2. The method according to claim 1, characterized in that Also includes: If it is determined that the operation of the fan is abnormal, a corresponding early warning message or alarm message is issued; and / or, Display the real-time status of the fan and early warning information or alarm information of abnormal operation of the fan.

3. An online abnormality detection device for a fan, characterized in that: include: A collection unit, used for collecting the current signal of the fan; A processing unit, configured to perform signal decomposition on the current signal collected by the collection unit to obtain two or more intrinsic mode components, comprising: Decomposing the collected current signal by using variational mode decomposition to obtain two or more eigenmode components; A determination unit, configured to determine whether the operation of the fan is abnormal based on the two or more eigenmodal components decomposed by the processing unit, comprising: a calculation unit, configured to select N eigenmodal components from the two or more eigenmodal components, perform energy entropy calculations, and obtain an energy entropy value of each of the N selected eigenmodal components; The comparison unit is used to compare the sum of the energy entropy values ​​of the N eigenmodal components with a preset entropy value warning value and an entropy value alarm value to determine whether there is any abnormality in the operation of the fan.

4. The device according to claim 3, characterized in that Also includes: an alarm unit, configured to issue a corresponding early warning message or alarm message if the determination unit determines that the operation of the fan is abnormal; and / or, The display unit is used to display the real-time status of the fan and early warning information or alarm information of abnormal operation of the fan.

5. A storage medium, characterized in that A computer program is stored thereon, and when the program is executed by a processor, the steps of the method according to claim 1 or 2 are implemented.

6. A controller, characterized in that: The controller includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the method according to claim 1 or 2 are implemented.

7. A controller, characterized in that: The controller includes the online abnormality detection device for the wind turbine as claimed in claim 3 or 4.

Images