Capacitor fault detection method, device and wind turbine generator set

Abstract

The present invention is applicable to the field of fault detection technology, and in particular, relates to a capacitor fault detection method, device and wind turbine generator set, the method comprising: collecting the electrical properties of a single capacitor and dividing them into several items, wherein the items at least include equivalent series resistance, resonant frequency and capacitance value, collecting the test value of each item, extracting the characteristic value, and creating a characteristic vector; creating a branch node corresponding to the single capacitor, mounting the same number of leaf nodes as the items to the branch node, synchronizing the characteristic vector to the leaf node, integrating the branch node and the leaf node, generating a capacitor fingerprint, and embedding a timestamp to create a dynamic fingerprint; collecting the real-time electrical data of the capacitor group, and finding the change characteristics. The present invention can predict the fault location by determining the hidden danger point, prevent the fault range from expanding, avoid equipment damage and shutdown accidents, and ensure the safety and stability of the wind power generation system.

Description

Technical Field

[0001] The present invention relates to the technical field of fault detection, and in particular to a capacitor fault detection method, device and wind turbine generator set. Background Art

[0002] In wind turbines, capacitors are mainly used to improve the power factor and stability of the power system. Since the power generation process of wind turbines is often affected by changes in wind speed, their output power often fluctuates, and wind turbines usually generate inductive loads, resulting in a decrease in power factor. Capacitors compensate for inductive loads by providing reactive power, thereby improving the power factor.

[0003] In a wind turbine generator set, capacitors usually exist in a networked form. When a capacitor fails, the power factor of the wind turbine generator set will decrease, causing an increase in harmonics, reducing the quality of power, and affecting the normal operation of the unit equipment. Therefore, "how to locate the capacitor with hidden dangers" is the technical problem that the present invention needs to solve. Summary of the invention

[0004] The object of the present invention is to provide a capacitor fault detection method, device and wind turbine generator set to solve the problem of "how to locate the hidden danger capacitor" raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for detecting a capacitor failure, the method comprising:

[0007] Collecting electrical properties of a single capacitor and dividing them into several items, wherein the items at least include equivalent series resistance, resonant frequency and capacitance value, collecting test values ​​of each item, extracting characteristic values, and creating characteristic vectors;

[0008] Create a branch node corresponding to the single capacitor one by one, mount the same number of leaf nodes as the single item to the branch node, synchronize the feature vector to the leaf node, integrate the branch node and the leaf node, generate a capacitor fingerprint, and embed a timestamp to create a dynamic fingerprint;

[0009] Collect real-time electrical data of the capacitor bank, find out the change characteristics, locate the leaf nodes corresponding to the change characteristics, define them as abnormal indicators, and define the branch nodes where the abnormal indicators are mounted as potential risk points;

[0010] Based on the real-time electrical data, determine whether the capacitor group has failed. If so, integrate all capacitor fingerprints to obtain a fingerprint group, and integrate a verification mechanism into the fingerprint group to trigger the verification mechanism, verify the potential risk point, and determine the verification result.

[0011] Furthermore, the step of collecting the electrical properties of the single capacitor and dividing them into several single items includes:

[0012] configuring the influencing factors of the electrical properties and adjusting the characteristic values;

[0013] Determine the relationship between the items and use the relationship to correct the verification result.

[0014] Furthermore, the steps of collecting the test value of each single item, extracting the characteristic value, and creating the characteristic vector include:

[0015] Reading out the resonant frequency in the electrical property, and establishing a corresponding relationship between the resonant frequency and time via the timestamp;

[0016] With time as the horizontal axis and the resonant frequency as the vertical axis, a response curve is drawn to identify the precursors of faults and generate alarm information.

[0017] Furthermore, the steps of generating a capacitive fingerprint and embedding a timestamp to create a dynamic fingerprint include:

[0018] Setting the update frequency of the capacitive fingerprint and inserting a mark into the timestamp;

[0019] A tag generated by a timestamp is inserted into the dynamic fingerprint.

[0020] Furthermore, the step of collecting the real-time electrical data of the capacitor bank and finding out the variation characteristics includes:

[0021] Obtaining the load of the wind turbine generator set, and dividing the load into several levels;

[0022] Create a fluctuation range for each level and correct the fluctuation characteristics.

[0023] Furthermore, the step of locating the leaf node corresponding to the change feature, defining it as an abnormal indicator, and defining the branch node mounted with the abnormal indicator as a potential risk point includes:

[0024] Extract the characteristic value and configure the weight of each leaf node;

[0025] The priority of each leaf node is determined, and the update frequency is adjusted.

[0026] Further, based on the real-time electrical data, determining whether the capacitor bank is failed, if yes, integrating all capacitor fingerprints to obtain a fingerprint group, integrating a verification mechanism into the fingerprint group, triggering the verification mechanism, verifying the potential risk point, and determining the verification result comprises:

[0027] Build a multi-level verification strategy and count the number of potential risk points;

[0028] The multi-level verification strategy is activated, and the leaf nodes are verified hierarchically using the priorities.

[0029] Furthermore, the device comprises:

[0030] Creating a module for collecting electrical properties of a single capacitor and dividing it into a number of items, wherein the items at least include equivalent series resistance, resonant frequency and capacitance value, collecting test values ​​of each item, extracting characteristic values, and creating characteristic vectors;

[0031] An embedding module is used to create a branch node corresponding to the single capacitor, mount the same number of leaf nodes as the single item to the branch node, synchronize the feature vector to the leaf node, integrate the branch node and the leaf node, generate a capacitor fingerprint, and embed a timestamp to create a dynamic fingerprint;

[0032] A definition module is used to collect real-time electrical data of the capacitor bank, find out the change characteristics, locate the leaf nodes corresponding to the change characteristics, define them as abnormal indicators, and define the branch nodes mounted with the abnormal indicators as potential risk points;

[0033] The determination module is used to determine whether the capacitor group has failed based on the real-time electrical data. If so, all capacitor fingerprints are integrated to obtain a fingerprint group, and a verification mechanism is integrated into the fingerprint group to trigger the verification mechanism, verify the potential risk point, and determine the verification result.

[0034] Furthermore, the creation module includes:

[0035] An adjustment unit, used to configure the influencing factors of the electrical properties and adjust the characteristic values;

[0036] A correction unit, used for a unit, for determining the relationship between the items, and using the relationship to correct the verification result;

[0037] A reading unit, used for reading the resonant frequency in the electrical property, and establishing a corresponding relationship between the resonant frequency and time via the timestamp;

[0038] The identification unit is used to draw a response curve diagram with time as the horizontal axis and the resonant frequency as the vertical axis, identify the precursor of the fault, and generate alarm information.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] By determining the electrical properties of a single capacitor, data support can be provided for capacitor fault detection. By determining a single item, the analysis process of capacitor faults can be refined and the analysis accuracy can be improved. By creating a dynamic fingerprint, the actual state of the capacitor under different operating conditions can be reflected, ensuring the timeliness and accuracy of fault diagnosis, greatly improving the fault prediction capability. By determining the hidden danger point, the fault location can be predicted to prevent the expansion of the fault scope, avoid equipment damage and shutdown accidents, and ensure the safety and stability of the wind power generation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flowchart of a method for detecting capacitor failure provided by an embodiment of the present invention;

[0042] Figure 2 A first sub-flow chart of a method for detecting capacitor failure provided by an embodiment of the present invention;

[0043] Figure 3 A second sub-flow chart of the method for detecting capacitor failure provided by an embodiment of the present invention;

[0044] Figure 4 A third sub-flow chart of the method for detecting capacitor failure provided by an embodiment of the present invention;

[0045] Figure 5 A fourth sub-flow chart of the method for detecting capacitor failure provided by an embodiment of the present invention;

[0046] Figure 6 A block diagram of a capacitor fault detection device provided by an embodiment of the present invention;

[0047] Figure 7 A block diagram of the components of a module in a capacitor fault detection device provided by an embodiment of the present invention;

[0048] Figure 8 A block diagram of the components of an embedded module in a capacitor fault detection device provided by an embodiment of the present invention;

[0049] Fig. 9 A block diagram of the components of the definition module in the capacitor fault detection device provided by the embodiment of the present invention;

[0050] Fig.10 A block diagram of the composition of a determination module in a capacitor fault detection device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0052] In Example 1, Figure 1 The implementation process of the capacitor fault detection method provided by the embodiment of the present invention is shown and described in detail below:

[0053] S100: Collecting electrical properties of a single capacitor and dividing them into a number of items, wherein the items at least include equivalent series resistance, resonant frequency and capacitance value, collecting test values ​​of each item, extracting characteristic values, and creating characteristic vectors.

[0054] The collected electrical properties are divided into several items, including equivalent series resistance, resonant frequency and capacitance value. The electrical properties reflect the core performance of the single capacitor during operation. The single item is a refinement of the core performance. Each item is accurately tested to obtain the test value, and the characteristic value is extracted through data processing technology. The characteristic value can be the changing trend of the equivalent series resistance, the offset amplitude of the resonant frequency and the stability of the capacitance value. The characteristic value is quantified in numerical form and integrated into a multi-dimensional characteristic vector, where the multi-dimensional characteristic vector is mainly used to characterize the overall operating status of the single capacitor.

[0055] S200: Create branch nodes corresponding to the single capacitors one by one, mount the same number of leaf nodes as the single item to the branch nodes, synchronize the feature vectors to the leaf nodes, integrate the branch nodes and leaf nodes, generate capacitor fingerprints, embed timestamps, and create dynamic fingerprints.

[0056] A branch node corresponding to each single capacitor is created, and leaf nodes with the same number as the electrical attribute items are mounted under each branch node, including equivalent series resistance leaf nodes, resonant frequency leaf nodes, and capacitance value leaf nodes. The multi-dimensional feature vector is synchronized to the corresponding leaf node, and the branch nodes and leaf nodes are integrated to generate a capacitor fingerprint, where the capacitor fingerprint is used to diagnose the capacitor status.

[0057] S300: Collect real-time electrical data of the capacitor bank, find out the change characteristics, locate the leaf nodes corresponding to the change characteristics, define them as abnormal indicators, and define the branch nodes mounted with the abnormal indicators as potential risk points.

[0058] Collect real-time electrical data of the capacitor group, which includes key attributes such as equivalent series resistance, resonant frequency, capacitance value, as well as environmental data such as temperature and wind speed; continuously monitor and analyze these data, and when a significant deviation or abnormal change is detected in a certain real-time electrical data, define the change as a change feature, where the change feature is the specific single item that caused the change; compare the change feature with the pre-established dynamic fingerprint, quickly locate the leaf node corresponding to the change feature, and identify the branch node to which it belongs as a hidden danger point. The hidden danger point represents the potential fault location or performance degradation area in the capacitor group, and the hidden danger point should be the key target of fault diagnosis and maintenance.

[0059] S400: Based on the real-time electrical data, determine whether the capacitor group has failed. If so, integrate all capacitor fingerprints to obtain a fingerprint group, integrate a verification mechanism into the fingerprint group, trigger the verification mechanism, verify the potential risk point, and determine the verification result.

[0060] Real-time electrical data or actual measurement values ​​are used to determine whether the capacitor group has failed. When failure is confirmed, the capacitance fingerprints of all individual capacitors in the capacitor group are integrated to generate a comprehensive fingerprint group, and a verification mechanism is integrated into the fingerprint group. The verification mechanism is mainly used to verify the potential danger points by analyzing and comparing the deviation between the potential danger points and the normal operating characteristics, combined with the actual measurement values.

[0061] In Example 2, Figure 2 The implementation process of the capacitor fault detection method provided by the embodiment of the present invention is shown. The steps of collecting the electrical properties of the single capacitor and dividing them into several individual items are described in detail as follows:

[0062] S101: configuring the influencing factors of the electrical properties and adjusting the characteristic values.

[0063] Determine the influencing factors of the electrical properties of the single capacitor, where the influencing factors include the dielectric material, electrical parameters and temperature of the single capacitor, and offset the characteristic value to improve the accuracy of the characteristic value.

[0064] S102: Determine the relationship between the items, and use the relationship to correct the verification result.

[0065] There is often an intrinsic connection between single items (such as voltage, current, phase difference and capacitance value); for example, the phase difference between voltage and current reflects the dielectric properties of the capacitor, and the harmonic component is related to the internal equivalent series resistance of the capacitor; by cross-validating the test values, the accuracy of the feature vector can be greatly improved.

[0066] In Example 3, Figure 2The implementation process of the capacitor fault detection method provided by the embodiment of the present invention is shown. The steps of collecting the test value of each single item, extracting the characteristic value, and creating the characteristic vector are described in detail as follows:

[0067] S103: reading out the resonant frequency in the electrical property, and establishing a corresponding relationship between the resonant frequency and time via the timestamp.

[0068] By reading the resonant frequency in the electrical properties and establishing its corresponding relationship with time; the resonant frequency refers to the frequency when the capacitor resonates under the joint action of other components; when the capacitor fails, its resonant frequency will also change, because changes in parameters such as the capacitor's capacitance value and internal resistance will directly affect the resonance characteristics of the circuit.

[0069] S104: Draw a response curve diagram with time as the horizontal axis and the resonant frequency as the vertical axis, identify the precursor of the fault, and generate alarm information.

[0070] During the monitoring process of the capacitor group, a response curve of the capacitor group is drawn with time as the horizontal axis and the resonant frequency as the vertical axis, wherein the response curve is used to intuitively display the changing trend of the resonant frequency over time; the frequency threshold is used to determine the precursor of the fault, and an alarm message is generated and sent to a preset terminal, wherein the preset terminal can be a terminal for maintenance personnel of the wind turbine generator set.

[0071] In Example 4, Figure 3 The implementation process of the capacitor fault detection method provided by the embodiment of the present invention is shown. The steps of generating a capacitor fingerprint, embedding a timestamp, and creating a dynamic fingerprint are described in detail as follows:

[0072] S201: Setting the updating frequency of the capacitive fingerprint and inserting a mark into the timestamp.

[0073] The updating frequency of the capacitive fingerprint is determined, and if the current time is the same as the mark, the capacitive fingerprint is updated.

[0074] S202: Insert a tag generated by a timestamp into the dynamic fingerprint.

[0075] After the capacitor fingerprint is updated, the label generated by the timestamp is inserted into it, and all the capacitor fingerprints are integrated; in other words, the change feature can reflect the working status of the capacitor group in real time and capture the changes of each single item in time.

[0076] In Example 5, Figure 4 The implementation process of the capacitor fault detection method provided by the embodiment of the present invention is shown. The steps of collecting the real-time electrical data of the capacitor group and finding the change characteristics are described in detail as follows:

[0077] S301: Obtain the load of the wind turbine generator set, and divide the load into several levels.

[0078] Obtain real-time load data of wind turbines and divide the load into several levels according to environmental requirements; for example, the load can be divided into low load, medium load and high load levels.

[0079] S302: Create a fluctuation range for each level and correct the variation characteristics.

[0080] A fluctuation range is configured for each level of load, wherein the fluctuation range includes the starting point and end point of the real-time electrical data, and the fluctuation range is used to correct the variation characteristics.

[0081] In Example 6, Figure 4 The implementation process of the capacitor fault detection method provided by the embodiment of the present invention is shown. The following steps of locating the leaf node corresponding to the change feature, defining it as an abnormal indicator, and defining the branch node mounted by the abnormal indicator as a potential risk point are described in detail as follows:

[0082] S303: extract the characteristic value and configure the weight of each leaf node.

[0083] Determine the importance of each eigenvalue and the degree of influence of the eigenvalue on the performance of the capacitor bank, configure a weight for each eigenvalue, and synchronize the weight to the corresponding leaf node. The configuration of the weight also needs to consider the sensitivity of the eigenvalue and the degree of contribution to fault prediction.

[0084] S304: Determine the priority of each leaf node and adjust the update frequency.

[0085] The leaf nodes are divided into several priorities, each of which corresponds to an update frequency, and the capacitive fingerprint is updated according to the update frequency.

[0086] In Example 7, Figure 5 The implementation process of the capacitor fault detection method provided by the embodiment of the present invention is shown. The following is a detailed description of the steps of judging whether the capacitor bank is failed based on the real-time electrical data, and if so, integrating all capacitor fingerprints to obtain a fingerprint group, integrating a verification mechanism into the fingerprint group, triggering the verification mechanism, verifying the potential danger point, and determining the verification result, as follows:

[0087] S401: Construct a multi-level verification strategy and count the number of potential risk points.

[0088] A multi-level authentication strategy is a collection of authentication methods.

[0089] S402: Activate a multi-level verification strategy, and perform hierarchical verification on the leaf nodes using the priorities.

[0090] The leaf nodes are sorted in descending order of priority, and the potential danger points therein are verified in turn.

[0091] Figure 6 The structure block diagram of the capacitor fault detection device provided by the embodiment of the present invention is shown. The capacitor fault detection device 1 includes:

[0092] Creating module 11, for collecting electrical properties of a single capacitor and dividing it into several single items, wherein the single items at least include equivalent series resistance, resonant frequency and capacitance value, collecting test values ​​of each single item, extracting characteristic values, and creating characteristic vectors;

[0093] The embedding module 12 is used to create a branch node corresponding to the single capacitor, mount the same number of leaf nodes as the single item to the branch node, synchronize the feature vector to the leaf node, integrate the branch node and the leaf node, generate a capacitor fingerprint, and embed a timestamp to create a dynamic fingerprint;

[0094] A definition module 13 is used to collect real-time electrical data of the capacitor bank, find out the change characteristics, locate the leaf nodes corresponding to the change characteristics, define them as abnormal indicators, and define the branch nodes mounted with the abnormal indicators as potential risk points;

[0095] The determination module 14 is used to determine whether the capacitor group has failed based on the real-time electrical data. If so, all capacitor fingerprints are integrated to obtain a fingerprint group, and a verification mechanism is integrated into the fingerprint group to trigger the verification mechanism, verify the potential risk point, and determine the verification result.

[0096] Figure 7 The structure block diagram of the capacitor fault detection device provided by the embodiment of the present invention is shown, and the creation module 11 includes:

[0097] An adjustment unit 111, configured to configure the influencing factors of the electrical properties and adjust the characteristic values;

[0098] A correction unit 112, used for determining the relationship between the items and correcting the verification result by using the relationship;

[0099] A reading unit 113, used to read the resonant frequency in the electrical property, and establish a corresponding relationship between the resonant characteristic and time via the timestamp;

[0100] The identification unit 114 is used to draw a response curve diagram with time as the horizontal axis and the resonant frequency as the vertical axis, identify the precursor of the fault, and generate alarm information.

[0101] Figure 8 The structure block diagram of the capacitor fault detection device provided by the embodiment of the present invention is shown, and the embedded module 12 includes:

[0102] A marking unit 121, used to set the updating frequency of the capacitive fingerprint and insert a mark into the timestamp;

[0103] The inserting unit 122 is used to insert a tag generated by a timestamp into the dynamic fingerprint.

[0104] Fig. 9 The structure block diagram of the capacitor fault detection device provided by the embodiment of the present invention is shown, and the definition module 13 includes:

[0105] A division unit 131 is used to obtain the load of the wind turbine generator set and divide the load into several levels;

[0106] A correction unit 132, used to create a fluctuation range for each level and correct the variation characteristics;

[0107] A configuration unit 133, configured to extract the characteristic value and configure the weight of each leaf node;

[0108] The determination unit 134 is used to determine the priority of each leaf node and adjust the update frequency.

[0109] Fig.10 The structure block diagram of the capacitor fault detection device provided by the embodiment of the present invention is shown, and the determination module 14 includes:

[0110] A statistical unit 141 is used to construct a multi-level verification strategy and count the number of potential risk points;

[0111] The activation unit 142 is used to activate the multi-level verification strategy and perform hierarchical verification on the leaf nodes using the priority.

[0112] The creation module 11 is mainly used to complete step S100, the embedding module 12 is mainly used to complete step S200, the definition module 13 is mainly used to complete step S300, and the determination module 14 is mainly used to complete step S400;

[0113] The adjustment unit 111 is mainly used to complete step S101, the correction unit 112 is mainly used to complete step S102, the reading unit 113 is mainly used to complete step S103, and the identification unit 114 is mainly used to complete step S104;

[0114] The marking unit 121 is mainly used to complete step S201, and the inserting unit 122 is mainly used to complete step S202;

[0115] The dividing unit 131 is mainly used to complete step S301, the correcting unit 132 is mainly used to complete step S302, the configuring unit 133 is mainly used to complete step S303, and the determining unit 134 is mainly used to complete step S304;

[0116] The statistical unit 141 is mainly used to complete step S401, and the activation unit 142 is mainly used to complete step S402.

[0117] The functions that can be achieved by the above-mentioned capacitor fault detection method are all completed by a computer device, and the computer device includes one or more processors and one or more memories, and at least one program code is stored in the one or more memories. The program code is loaded and executed by the one or more processors to achieve the functions of the capacitor fault detection method.

[0118] The processor takes out instructions from the memory one by one, analyzes the instructions, and then completes the corresponding operations according to the instruction requirements, generating a series of control commands, so that the various parts of the computer can automatically, continuously and coordinately move to become an organic whole, realize the input of programs, the input of data, and the calculation and output of results. The arithmetic operations or logical operations generated in this process are all completed by the operator; the memory includes a read-only memory, which is used to store computer programs, and a protection device is provided outside the memory.

[0119] Exemplarily, the computer program may be divided into one or more modules, one or more modules are stored in a memory and executed by a processor to implement the present invention. One or more modules may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in a terminal device.

[0120] Those skilled in the art will understand that the description of the above service equipment is merely an example and does not constitute a limitation on the terminal equipment. It may include more or fewer components than described above, or a combination of certain components, or different components, for example, it may include input and output devices, network access equipment, buses, etc.

[0121] The processor may be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire user terminal.

[0122] The above-mentioned memory can be used to store computer programs and / or modules. The above-mentioned processor realizes various functions of the above-mentioned terminal device by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. The memory mainly includes a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as an information collection template display function, a product information release function, etc.), etc.; the data storage area can store data created according to the use of the capacitor fault detection device (such as product information collection templates corresponding to different product types, product information that needs to be released by different product providers, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card, a secure digital card, a flash memory card, at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0123] If the module / unit integrated in the terminal device 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 present invention implements all or part of the modules / units in the above-mentioned embodiment device, and can also be completed by instructing the relevant hardware through a computer program. The above-mentioned computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can realize the functions of the above-mentioned various device embodiments. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device that can carry computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0124] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0125] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for detecting capacitor failure, characterized in that: The method comprises: Collecting electrical properties of a single capacitor and dividing them into several items, wherein the items at least include equivalent series resistance, resonant frequency and capacitance value, collecting test values ​​of each item, extracting characteristic values, and creating characteristic vectors; Create a branch node corresponding to the single capacitor one by one, mount the same number of leaf nodes as the single item to the branch node, synchronize the feature vector to the leaf node, integrate the branch node and the leaf node, generate a capacitor fingerprint, and embed a timestamp to create a dynamic fingerprint; Collect real-time electrical data of the capacitor bank, find out the change characteristics, locate the leaf nodes corresponding to the change characteristics, define them as abnormal indicators, and define the branch nodes where the abnormal indicators are mounted as potential risk points; Based on the real-time electrical data, determine whether the capacitor group has failed. If so, integrate all capacitor fingerprints to obtain a fingerprint group, and integrate a verification mechanism into the fingerprint group to trigger the verification mechanism, verify the potential risk point, and determine the verification result.

2. The method for detecting capacitor failure according to claim 1, characterized in that: The step of collecting the electrical properties of a single capacitor and dividing it into a plurality of individual items includes: configuring the influencing factors of the electrical properties and adjusting the characteristic values; Determine the relationship between the items and use the relationship to correct the verification result.

3. The method for detecting capacitor failure according to claim 2, characterized in that: The steps of collecting the test value of each single item, extracting the characteristic value, and creating the characteristic vector include: Reading out the resonant frequency in the electrical property, and establishing a corresponding relationship between the resonant frequency and time via the timestamp; With time as the horizontal axis and the resonant frequency as the vertical axis, a response curve is drawn to identify the precursors of faults and generate alarm information.

4. The method for detecting capacitor failure according to claim 3, characterized in that: The steps of generating a capacitive fingerprint, embedding a timestamp, and creating a dynamic fingerprint include: Setting the update frequency of the capacitive fingerprint and inserting a mark into the timestamp; A tag generated by a timestamp is inserted into the dynamic fingerprint.

5. The method for detecting capacitor failure according to claim 1, characterized in that: The step of collecting the real-time electrical data of the capacitor bank and finding out the variation characteristics comprises: Obtaining the load of the wind turbine generator set, and dividing the load into several levels; Create a fluctuation range for each level and correct the fluctuation characteristics.

6. The method for detecting capacitor failure according to claim 4, characterized in that: The steps of locating the leaf node corresponding to the change feature, defining it as an abnormal indicator, and defining the branch node mounted with the abnormal indicator as a potential risk point include: Extract the characteristic value and configure the weight of each leaf node; The priority of each leaf node is determined, and the update frequency is adjusted.

7. The method for detecting capacitor failure according to claim 6, characterized in that: The step of judging whether the capacitor bank is failed based on the real-time electrical data, and if so, integrating all capacitor fingerprints to obtain a fingerprint group, integrating a verification mechanism into the fingerprint group, triggering the verification mechanism, and verifying the potential risk point, and determining the verification result comprises: Build a multi-level verification strategy and count the number of potential risk points; The multi-level verification strategy is activated, and the leaf nodes are verified hierarchically using the priorities.

8. A device for detecting capacitor failure, characterized in that: The device comprises: Creating a module for collecting electrical properties of a single capacitor and dividing it into a number of items, wherein the items at least include equivalent series resistance, resonant frequency and capacitance value, collecting test values ​​of each item, extracting characteristic values, and creating characteristic vectors; An embedding module is used to create a branch node corresponding to the single capacitor, mount the same number of leaf nodes as the single item to the branch node, synchronize the feature vector to the leaf node, integrate the branch node and the leaf node, generate a capacitor fingerprint, and embed a timestamp to create a dynamic fingerprint; A definition module is used to collect real-time electrical data of the capacitor bank, find out the change characteristics, locate the leaf nodes corresponding to the change characteristics, define them as abnormal indicators, and define the branch nodes mounted with the abnormal indicators as potential risk points; The determination module is used to determine whether the capacitor group has failed based on the real-time electrical data. If so, all capacitor fingerprints are integrated to obtain a fingerprint group, and a verification mechanism is integrated into the fingerprint group to trigger the verification mechanism, verify the potential risk point, and determine the verification result.

9. The capacitor failure detection device according to claim 8, characterized in that: The creation module includes: An adjustment unit, used to configure the influencing factors of the electrical properties and adjust the characteristic values; A correction unit, used for a unit, for determining the relationship between the items, and using the relationship to correct the verification result; A reading unit, used to read the resonant frequency in the electrical property, and establish a corresponding relationship between the resonant frequency and time via the timestamp; The identification unit is used to draw a response curve diagram with time as the horizontal axis and the resonant frequency as the vertical axis, identify the precursor of the fault, and generate alarm information.

10. A wind turbine generator set, characterized in that: include: A capacitor fault detection device as claimed in any one of claims 8 and 9.

Images