A wind turbine generator state diagnosis and early warning method and system

Abstract

The application provides a wind turbine generator state diagnosis and early warning method and system, relates to the technical field of wind turbine generator equipment, and acquires generator equipment state data in real time, pre-processes the generator equipment state data, stores the generator equipment state data meeting preset conditions in a diagnosis terminal, calculates the generator equipment state data meeting the preset conditions by the diagnosis terminal, intelligently analyzes the calculation results, diagnoses the state of the wind turbine generator equipment, and performs early warning if a fault occurs; the diagnosis terminal sends the diagnosis and analysis of the generator equipment state data and diagnosis result data to a cloud platform and a PLC controller. The system can not only timely transmit the analysis results to the cloud platform or the PLC controller, but also automatically filter the wind turbine generator operation data, upload valuable data, thereby greatly reducing the calculation amount of the cloud platform or the PLC controller, improving the data processing efficiency and the accuracy of data analysis.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wind turbine generator set power generation equipment, and particularly relates to a wind turbine generator set power generation state diagnosis and early warning method and system. BACKGROUND

[0002] New energy power generation methods include biomass power generation, geothermal power generation, wave power generation, wind power generation, photovoltaic power generation, etc. Among them, new energy power generation equipment such as wind power and photovoltaic power generation will be operated outdoors and will be easily affected by external environment, and thus faults will be caused. Moreover, some new energy power generation equipment will be installed in remote and complex terrain areas, and thus will be subjected to variable loads and working conditions during operation, and thus a high fault occurrence rate will be caused. Therefore, it is necessary to effectively monitor the new energy power generation equipment, and timely find and eliminate faults.

[0003] However, the existing new energy power generation equipment monitoring and diagnosis model is mainly deployed in the cloud or the main control system, and through a large amount of historical data and artificial intelligence algorithms, the operation state of the new energy power generation equipment is monitored.

[0004] However, in the prior art, the effective value, peak-to-peak value, mean square value and kurtosis of the new energy power generation equipment cannot be analyzed and judged, and thus the abnormal situation of the power generation equipment during operation cannot be identified, and the new energy power generation equipment cannot be effectively monitored and faults can be timely found. SUMMARY

[0005] The present application provides a wind turbine generator set power generation state diagnosis and early warning method, which calculates the effective value, peak-to-peak value, mean square value and kurtosis of the data, preliminarily analyzes and judges the time domain characteristics of the real-time data, identifies the abnormal situation of the power generation equipment during operation, effectively monitors the power generation equipment, and timely finds faults of the power generation equipment.

[0006] The wind turbine generator set power generation state diagnosis and early warning method comprises the following steps:

[0007] Step 1: Real-time acquisition of power generation equipment state data, and preprocessing of the power generation equipment state data, storage of the power generation equipment state data meeting the preset conditions in the diagnosis terminal, and the like.

[0008] Step 2: The diagnosis terminal calculates the power generation equipment state data meeting the preset conditions, intelligently analyzes the calculation results, diagnoses the state of the power generation equipment, and performs early warning when a fault occurs.

[0009] Step 3: The diagnosis terminal sends the power generation equipment state data and diagnosis result data after diagnosis and analysis to the cloud platform and PLC controller.

[0010] In step 2, the following steps are further included:

[0011] Perform time-domain characteristic statistics, spectrum analysis, and envelope analysis on the status data of power generation equipment;

[0012] Time-domain characteristic statistics include: RMS value, peak-to-peak value, mean square value, and kurtosis;

[0013] Spectral analysis is a comparative analysis of the extreme values ​​of segmented spectral lines;

[0014] Based on the MCKD algorithm, the bearing fault characteristics are initially extracted and separated from the vibration acceleration signal;

[0015] The data processed by MCKD is subjected to anti-interference processing based on the iterative envelope algorithm to enhance the bearing fault characteristic information.

[0016] Envelope spectrum analysis is used for energy ratio analysis of various bearing fault characteristics;

[0017] The effective value is calculated as follows:

[0018] The mean square value is calculated as follows:

[0019] The kurtosis is calculated as follows:

[0020] The fault characteristic energy ratio is calculated as follows:

[0021] In the formula, E1, E2…E n These represent the energies of the signal at 1, 2, and n times the characteristic frequency after feature extraction, respectively.

[0022] E represents the total energy within a given frequency range.

[0023] It should be further noted that the iterative envelope calculation method includes the following steps:

[0024] 1) For the input signal Perform DC removal processing to obtain the output signal. ,Right now ;

[0025] 2) For signals Envelope signal is obtained by performing envelope calculation. ;

[0026] 3) Calculate the envelope signal and input signal The characteristic energy ratio of P is obtained. and ;

[0027] 4) If The output result is as follows. and calculate its envelope spectrum; otherwise let And return to step 1).

[0028] It should be further explained that in step one, the acquired power generation equipment state data includes power, rotating speed and bearing model corresponding to the power generation equipment;

[0029] A fault feature frequency database of each component of the power generation equipment is established, and threshold ranges of various data are set.

[0030] It should be further explained that step two further comprises: frequency band segmentation and peak value calculation of the frequency spectrum and the envelope, and setting of an abnormal threshold;

[0031] The frequency band segmentation is to divide the calculated frequency spectrum into rotating frequency display area and non-rotating frequency area with the rated rotating frequency and its multiple frequencies as the segmentation points.

[0032] The envelope frequency band segmentation is set up for identifying whether the bearing fault feature frequency is obvious and calculating the feature energy ratio of the bearing fault feature frequency and its multiple frequencies.

[0033] It should be further explained that the diagnosis of the state of the power generation equipment comprises: statistical diagnosis result data of each data parameter, and evaluation of the health state of the power generation equipment;

[0034] The diagnosis result data comprises effective value, peak-to-peak value, mean square value, kurtosis, analysis result data of the frequency spectrum and the envelope, and comprehensive comparison and analysis, and determination of the running state of the power generation equipment.

[0035] It should be further explained that in step two, the fault feature energy ratio of the bearing fault feature frequency and its multiple frequencies in the envelope spectrum is calculated to identify whether the bearing fault occurs and locate the fault grade.

[0036] It should be further explained that in step two, the real-time running data of the power generation equipment is subjected to FFT calculation, the peak value of the rotating spectrum line in the frequency spectrum is extracted, and it is used as the basis for analyzing whether the power generation equipment has a looseness fault and defining the fault grade.

[0037] The application also provides a wind turbine generator state diagnosis and early warning system, which comprises: a data acquisition module, a data preprocessing module, a diagnosis terminal cloud platform and a PLC controller.

[0038] The data acquisition module is used for acquiring the state data of the power generation equipment in real time, and the data preprocessing module is used for preprocessing the state data of the power generation equipment and storing the power generation equipment state data meeting the preset conditions in the diagnosis terminal.

[0039] The diagnosis terminal is used for calculating the power generation equipment state data meeting the preset conditions, intelligently analyzing the calculation results, diagnosing the state of the power generation equipment, and performing early warning when a fault occurs.

[0040] Also used for time domain feature statistics, spectral analysis and envelope analysis on power generation equipment state data;

[0041] The time domain feature statistics include: effective value, peak-to-peak value, mean square value and kurtosis;

[0042] The spectral analysis is a segmented spectrum maximum value comparison analysis;

[0043] The bearing fault features are preliminarily extracted and separated based on the MCKD algorithm on the vibration acceleration signal;

[0044] The anti-interference processing is carried out on the data processed by the MCKD based on the iterative envelope algorithm, and the bearing fault feature information is enhanced;

[0045] The envelope spectrum analysis is a bearing each fault feature energy ratio analysis;

[0046] The effective value calculation method is:

[0047] The mean square value calculation method is:

[0048] The kurtosis calculation method is:

[0049] The fault feature energy ratio calculation method is:

[0050] In the formula, E1, E2…E n Respectively, the energy of the signal after feature extraction at 1, 2 and n times the characteristic frequency;

[0051] E is the total energy in the selected frequency range.

[0052] The diagnostic terminal is also used for sending the power generation equipment state data and the diagnostic result data after diagnostic analysis to the cloud platform and the PLC controller.

[0053] It should be further explained that the diagnostic terminal is also used for real-time tracking and collecting the power generation equipment state, realizing the power generation equipment state data sharing, forming the comparison trend chart of the same type of power generation equipment state data in different time periods; and the power generation equipment state data is displayed in trend with hours, days and weeks.

[0054] From the above technical solutions, the present application has the following advantages:

[0055] The wind turbine generator state diagnosis and early warning method and system can intelligently analyze real-time operation data of the power generation equipment.

[0056] When the fault feature in the signal is not obvious and is submerged by noise or other interference signals and is difficult to be found, the real-time data is calculated by the MCKD, the bearing fault feature information is preliminarily extracted, then the iteration envelope operation is performed, the feature energy ratio of the output result is calculated, and the calculation result is used as the basis for stopping iteration, so as to further enhance the bearing fault feature information and locate the bearing fault type.

[0057] The real-time operation data is calculated by the FFT, the peak value of the frequency spectrum is extracted, and the peak value is used as the main basis for analyzing whether the power generation equipment has a loosening fault and defining the fault level. Thus, the partial fault of the power generation equipment can be processed and recognized on the edge side. For the fault analysis of the power generation equipment group, the data accuracy directly affects the analysis accuracy of the fault reason, so that the data obtained on the power generation equipment side is used for fault analysis, the analysis accuracy and efficiency are improved, and the timeliness of processing the fault is improved, thereby protecting the normal operation of the power generation equipment.

[0058] The system can not only transmit the analysis result to the cloud platform or the PLC controller in time, but also automatically filter the operation data of the power generation equipment and upload the valuable data, so that the calculation amount of the cloud platform or the PLC controller is greatly reduced, and the data processing efficiency and the data analysis accuracy are improved. BRIEF DESCRIPTION OF DRAWINGS

[0059] In order to more clearly illustrate the technical solutions of the present application, the drawings needed in the description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0060] Figure 1 The wind turbine generator state diagnosis and early warning method flow chart;

[0061] Figure 2 The wind turbine generator state diagnosis and early warning method flow chart;

[0062] Figure 3 The iteration method embodiment flow chart;

[0063] Figure 4 is a result graph based on the effective value calculation of a certain wind farm;

[0064] Figure 5 is a result graph based on the peak-to-peak value calculation of a certain wind farm;

[0065] Figure 6 is a result graph based on the kurtosis calculation of a certain wind farm;

[0066] Figure 7 is a result graph based on the mean square value calculation of a certain wind farm;

[0067] Figure 8 is a result graph of FFT calculation.

[0068] Figure 9 is a result graph of bearing fault diagnosis characteristic energy ratio of each unit.

[0069] Figure 10 is a schematic diagram of the characteristic energy ratio diagnosed for each unit;

[0070] Figure 11 is a result graph based on the characteristic energy ratio of multiple units;

[0071] Figure 12 is a curve graph of the characteristic energy ratio of bearing fault diagnosis of each unit. DETAILED DESCRIPTION

[0072] As shown in Figure 1 , the present application provides a diagram provided in a wind turbine generator state diagnosis and early warning method, which only illustrates the basic concept of the present application in a schematic manner, and the wind turbine generator state diagnosis and early warning method of the present application can acquire and process associated data based on artificial intelligence technology. The diagnosis and early warning method uses a digital computer or a machine simulated, extended and expanded by a digital computer controlled machine to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0073] The hardware of the diagnosis and early warning method can use sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. The software technology of the diagnosis and early warning method mainly includes computer vision technology, speech processing technology, natural language processing technology and machine learning / deep learning, etc. Among them, the diagnosis and early warning method can also simulate or realize human learning behavior to acquire new knowledge or skills, reorganize the existing knowledge structure to continuously improve its own performance.

[0074] As shown in Figure 1A flow chart of a preferred embodiment of the wind turbine generator state diagnosis and early warning method of the present application is shown. The wind turbine generator state diagnosis and early warning method is applied in one or more diagnosis terminals, which is a device capable of automatically performing numerical calculation and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessor, Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), Digital Signal Processor (DSP), embedded device, etc.

[0075] The diagnosis terminal can be any kind of electronic product that can interact with users, such as personal computer, tablet computer, smart phone, Personal Digital Assistant (PDA), Internet Protocol Television (IPTV), smart wearable device, etc.

[0076] The diagnosis terminal can also include network device and / or user device. The network device includes but is not limited to single network server, server group composed of multiple network servers or cloud composed of a large number of hosts or network servers based on Cloud Computing.

[0077] The network in which the diagnosis terminal is located includes but is not limited to Internet, wide area network, metropolitan area network, local area network, Virtual Private Network (VPN), etc.

[0078] The method of the present application will be described in detail below in combination with Figures 1 to 3 The method can be applied in wind turbine generator state diagnosis and analysis, analyzes the trend of the state data of the power generation equipment, evaluates whether the operation data of the wind turbine generator meets the requirements, whether the risk is abnormal, and has a positive effect on reducing the hidden danger of the wind turbine generator. The system and method of the present application can also release the computing capacity of the cloud or PLC controller, reduce energy consumption, and improve the efficiency of normal operation and operation.

[0079] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0080] The following examples take wind power generation as an example, and the power generation equipment of the application is a wind turbine generator.

[0081] Please refer to Figures 1 to 3 The flow chart of the generator state diagnosis and early warning method of the wind turbine generator in an embodiment is shown, and the method comprises the following steps:

[0082] S101, real-time acquisition of power generation equipment state data, and preprocessing of the power generation equipment state data, and storage of the power generation equipment state data meeting the preset conditions in the diagnosis terminal;

[0083] Specifically, the power generation equipment state data is preprocessed, and the data meeting the conditions of power, speed and sampling duration is stored in the diagnosis terminal on the wind turbine generator side, the diagnosis terminal stores the working state and real-time running data collected, the working state collected by the processor includes start, stop, power limit, yaw, etc., and the real-time running data includes power, speed and sampling duration.

[0084] In combination with the current working state of the wind turbine generator, the real-time running data is screened, and the start-stop and normal running states are autonomously identified. The parameters of each bearing of the power generation equipment are set, the fault characteristic frequency database of each component of the bearing is established, and the threshold range of each type is set.

[0085] The fault characteristic frequency database of each component of the bearing can be calculated from the speed and bearing parameters. The threshold range can be obtained from the experience value and set near each fault characteristic frequency and its multiple frequency. In this system, the preprocessing method is used to realize the screening of the real-time running data, so as to directly perform the operation and analysis of the subsequent steps.

[0086] S102, the diagnosis terminal calculates the power generation equipment state data meeting the preset conditions, intelligently analyzes the calculation results, and diagnoses the state of the wind turbine generator, and if a fault occurs, an early warning is performed:

[0087] In the embodiment of the application, the power generation equipment state data is subjected to time domain characteristic statistics, frequency spectrum analysis and envelope analysis.

[0088] The time domain characteristic statistics include effective value, peak-to-peak value, mean square value and kurtosis, etc., wherein the mean square value represents the energy of the signal, and the kurtosis can describe the change degree of the waveform of the data signal, which is beneficial to detect the impact component in the signal.

[0089] The spectrum analysis is a comparison analysis of the maximum and minimum of segmented spectrum lines; and the envelope spectrum analysis is a bearing fault characteristic energy ratio analysis.

[0090] The corresponding calculation formula is as follows:

[0091] The effective value calculation mode is:

[0092] The mean square value calculation mode is:

[0093] The kurtosis calculation mode is:

[0094] The fault characteristic energy ratio calculation mode is:

[0095] In the formula, E1, E2…E n are the energy of the signal after characteristic extraction at 1, 2 and n times the characteristic frequency respectively; E is the total energy in the fixed frequency range. The greater P is, the greater the ratio of the total characteristic energy at the characteristic frequency to the total energy in the fixed frequency range, and the more characteristic information and the more obvious characteristics.

[0096] The iterative envelope calculation mode of the application is:

[0097] 1. The input signal is subjected to DC removal to obtain the output signal , i.e. ; ;

[0098] 2. The envelope signal is calculated from the signal ;

[0099] 3. The characteristic energy ratio P of the envelope signal and the input signal is calculated to obtain and ;

[0100] 4. If , the output result is obtained, and the envelope spectrum is calculated; otherwise, let , and return to step 1.

[0101] In the present application, the time domain feature statistics is intelligently analyzed, and the abnormal threshold is set; the thresholds of the effective value, the peak-to-peak value, the mean square value and the kurtosis are set according to the experience value in combination with the characteristics of the wind turbine generator. The thresholds corresponding to each parameter are set according to the experience, and the wind turbine generator with abnormal operation data is preliminarily screened out through the effective value, the peak-to-peak value and the kurtosis.

[0102] In the embodiment of the present application, the frequency band segmentation and peak value calculation are performed on the spectrum and envelope, and the abnormal threshold is set.

[0103] The frequency band segmentation is to divide the calculated spectrum into the rotation frequency display region and the non-rotation frequency region by taking the rated rotation frequency and its multiple frequencies (generally set as 10 times the frequency) as the segmentation points.

[0104] The system of the present application has the interference signal identification function, discriminates whether there is a large interference near the fault characteristic frequency on the spectrum, and if so, performs the MCKD and the iterative envelope, calculates the characteristic energy ratio, judges whether the bearing fault exists in combination with the time domain feature statistics, and if not, performs the fault diagnosis through the time domain feature statistics and the characteristic energy ratio.

[0105] The envelope frequency band segmentation is set up for discriminating whether the bearing fault characteristic frequency is obvious and calculating the characteristic energy ratio of the bearing fault characteristic frequency and its multiple frequencies. The energy characteristic ratio of the fault characteristic frequency of each component of the bearing is calculated to determine whether the bearing has obvious damage and locate the fault type.

[0106] In the embodiment of the present application, the data parameters in the statistical calculation result are calculated, and the health status of the wind turbine generator is evaluated. The collected data is preliminarily processed and diagnosed. The data parameters include the analysis results of the effective value, the peak-to-peak value, the mean square value, the kurtosis, the spectrum and the envelope, and the comprehensive comparative analysis is performed to determine the operation state of the wind turbine generator.

[0107] S103, the diagnosis terminal sends the power generation equipment state data and the diagnosis result data after diagnosis and analysis to the cloud platform and the PLC controller.

[0108] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0109] The cloud platform of the present application is a general term of network technology, information technology, integration technology, management platform technology, application technology and the like based on the cloud computing commercial mode application, can form a resource pool, and is used on demand, flexible and convenient. The cloud platform technology changes the diagnosis of the abnormal state of the wind turbine generator into an important support to provide background service needs a large amount of computing and storage resources, such as video websites, picture websites and more portal websites.

[0110] In the wind turbine generator state diagnosis and early warning method provided by the application, the cloud platform and the PLC controller receive the power generation equipment state data and the diagnosis result data, and according to the received IP address, the power generation equipment state data and the diagnosis result data are archived and stored.

[0111] The application also constructs a power generation equipment data state diagram, and updates the power generation equipment data state diagram in real time. The application also configures a power generation equipment state data operation interface, so that the operator can add, delete, modify and query data on the power generation equipment state data operation interface.

[0112] The application also sends control information instructions to the diagnosis terminal in real time based on a local area network or a wide area network, acquires the power generation equipment state data and the diagnosis result data, compares the acquired power generation equipment state data and the diagnosis result data with a preset threshold, and obtains the current state information.

[0113] The application predicts the current power generation equipment state data trend, forms a power generation equipment state bar chart or a power generation equipment state curve chart for the operator to refer to, collects each power generation equipment state data, realizes data sharing, collects the wind turbine generator state in real time, realizes power generation equipment state data sharing, forms a comparison trend chart of the same type of power generation equipment state data in different time periods, and displays the power generation equipment state data trend by hour, day or week.

[0114] Further, as a refinement and expansion of the specific implementation of the above embodiment, in order to completely describe the specific implementation process in this embodiment, taking the actual measurement data of a certain wind farm in a week as an example, the algorithm system verification is performed, Figures 4 to 8 The calculation results of the time domain feature statistics effective value, peak-to-peak value, kurtosis and mean square value are shown in the figure. As can be seen from the figure, except for the wind turbine generator equipment with an abnormal amplitude, the operation characteristics of each wind turbine generator equipment have certain aggregation and difference. The time domain statistics of the generator equipment all exceed the set threshold, indicating that the operation condition of the generator equipment has certain abnormal conditions and needs to be analyzed and focused on. The generator whose value is less than the threshold represents stable and good operation condition. The FFT and envelope spectrum calculation are performed on the generator data exceeding the threshold. On the one hand, the frequency spectrum is used to identify whether there is a power generation equipment loosening condition, including but not limited to the amplitude of the rotating frequency being higher than the amplitude of the non-rotating frequency region, or the rotating frequency amplitude being greater than the set threshold and having multiple frequency conditions of the rotating frequency.

[0115] The bearing fault characteristic frequency is distinguished by envelope spectrum in another aspect. If the fault characteristic frequency has a high amplitude, it indicates that the fault characteristic is obvious, and the characteristic energy ratio is directly calculated and has high reliability. If the fault characteristic frequency is submerged or interfered by other spectral lines, the time domain signal is analyzed by the MCKD algorithm, and then the iterative envelope calculation is performed. The characteristic energy ratio is used as the criterion for exiting iteration, and the analysis results of the iterative envelope and the characteristic energy ratio are output. By comparing the characteristic energy ratio and the interval of the calculated characteristic frequency, it is determined whether the bearing has a fault and the fault location is positioned.

[0116] Typically, the bearing has four basic faults of inner and outer rings, rolling elements and retainers. Each fault has different fault characteristic frequencies. The diagnosis process can calculate four characteristic energy ratios by the obtained data, take the maximum value, and compare it with the set threshold characteristic energy. According to the comparison result, the fault type is defined. The various thresholds involved in the present application can be set according to the actual application, and the specific values are not limited in the present application.

[0117] Figures 9 to 12 is the result of the characteristic energy ratio of each unit for bearing fault diagnosis. It is the calculation result of the bearing retainer, rolling element, outer ring and inner ring. It can be seen that the characteristic energy ratio of each unit corresponding to different fault types has obvious differences, which verifies the effectiveness of the wind turbine generator bearing fault diagnosis and early warning method mentioned in the present application.

[0118] The following is an embodiment of the wind turbine generator state diagnosis and early warning system provided by the present disclosure. The wind turbine generator state diagnosis and early warning system and the wind turbine generator state diagnosis and early warning method of each embodiment described above belong to the same inventive concept. The details not described in the embodiment of the wind turbine generator state diagnosis and early warning system can be referred to the embodiment of the wind turbine generator state diagnosis and early warning method described above.

[0119] The power generation equipment new energy power generation equipment state anomaly diagnosis and early warning system includes a data acquisition module, a data preprocessing module, a diagnosis terminal cloud platform and a PLC controller.

[0120] The data acquisition module is used to acquire the power generation equipment state data in real time. The data preprocessing module preprocesses the power generation equipment state data, and stores the power generation equipment state data meeting the preset condition in the diagnosis terminal.

[0121] The diagnosis terminal is used to calculate the power generation equipment state data meeting the preset condition, and intelligently analyze the calculation results to diagnose the state of the wind turbine generator. If a fault occurs, a warning is given.

[0122] The diagnostic terminal is also used for sending the power generation equipment state data and the diagnosis result data after diagnosis analysis to the cloud platform and the PLC controller.

[0123] The system can not only transmit the analysis result to the cloud platform or the PLC controller in time, but also automatically filter the wind turbine generator operation data, and upload the valuable data, so that the calculation amount of the cloud platform or the PLC controller is greatly reduced, and the data processing efficiency and the data analysis accuracy are improved.

[0124] The units and algorithm steps of each example described in the embodiments disclosed in the wind turbine generator state diagnosis and early warning method and system provided by the application can be realized by electronic hardware, computer software or combination of both. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the application.

[0125] In the wind turbine generator state diagnosis and early warning method and system provided by the application, it should be understood that the disclosed system, device and method can be realized by other ways. For example, the device examples described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can be in another way, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can also be electrical, mechanical or other forms of connection.

[0126] The computer program code for carrying out operations of the present disclosure can be written in one or more programming languages or combinations of languages including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0127] The above description of disclosed embodiments provides enabling concepts for making or using the application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for generator condition diagnosis and early warning in wind turbine units, characterized in that, The methods include: Step 1: Acquire real-time status data of power generation equipment, preprocess the status data, and store the status data of power generation equipment that meets the preset conditions in the diagnostic terminal. Step 2: The diagnostic terminal calculates the status data of the power generation equipment that meets the preset conditions, and performs intelligent analysis on the calculation results to diagnose the status of the power generation equipment. If a fault occurs, an early warning is issued. Among them, time-domain characteristic statistics, spectrum analysis and envelope analysis are performed on the status data of power generation equipment; Time-domain characteristic statistics include: RMS value, peak-to-peak value, mean square value, and kurtosis; Spectral analysis is a comparative analysis of the extreme values ​​of segmented spectral lines; Based on the MCKD algorithm, the bearing fault characteristics are initially extracted and separated from the vibration acceleration signal; The data processed by MCKD is subjected to anti-interference processing based on the iterative envelope algorithm to enhance the bearing fault characteristic information. The calculation method of the iterative envelope algorithm includes the following steps: 1) For the input signal Perform DC removal processing to obtain the output signal. ,Right now ; 2) For signals Envelope signal is obtained by performing envelope calculation. ; 3) Calculate the envelope signal and input signal The characteristic energy ratio of P is obtained. and ; 4) If The output result is as follows. And calculate its envelope spectrum; otherwise let (and return to step 1); Envelope spectrum analysis is used for energy ratio analysis of various bearing fault characteristics; The effective value is calculated as follows: The mean square value is calculated as follows: The kurtosis is calculated as follows: The fault characteristic energy ratio is calculated as follows: In the formula, E1, E2…E n These represent the energies of the signal at 1, 2, and n times the characteristic frequency after feature extraction, respectively. E represents the total energy within a given frequency range; This includes frequency band segmentation and peak value calculation for the spectrum and envelope, and setting anomaly thresholds; The frequency band segmentation uses the rated frequency and its multiple harmonics as the dividing points to divide the calculated spectrum into a frequency-reversed display area and a non-frequency-reversed area; Envelope band segmentation is established to identify whether the characteristic frequencies of bearing faults are obvious and to calculate the characteristic energy ratio of the characteristic frequencies of bearing faults and their harmonics; Step 3: The diagnostic terminal sends the analyzed power generation equipment status data and diagnostic results data to the cloud platform and PLC controller.

2. The method for wind turbine generator condition diagnosis and early warning according to claim 1, characterized in that, In step one, the acquired power generation equipment status data includes power, speed, and the bearing model corresponding to the power generation equipment; Establish a database of fault characteristic frequencies for each component of the power generation equipment and set threshold ranges for various types of data.

3. The method for wind turbine generator condition diagnosis and early warning according to claim 1, characterized in that, Diagnosing the status of power generation equipment includes: statistically analyzing various data parameters in the diagnostic results and assessing the health status of the power generation equipment; The diagnostic results data include the analysis results of RMS values, peak-to-peak values, mean square values, kurtosis, spectrum, and envelope, and are comprehensively compared and analyzed to determine the operating status of the power generation equipment.

4. The method for wind turbine generator condition diagnosis and early warning according to claim 1, characterized in that, In step two, the fault characteristic energy ratio of the bearing fault characteristic frequency and its harmonic in the envelope spectrum is calculated to automatically identify whether a bearing fault has occurred and to determine the fault level.

5. The method for wind turbine generator condition diagnosis and early warning according to claim 1, characterized in that, In step two, Furthermore, FFT calculations are performed on the real-time operating data of the power generation equipment to extract the peak values ​​of the relay spectrum lines in the spectrum, which are used as the basis for analyzing whether the power generation equipment has experienced loosening faults and defining the fault level.

6. A wind turbine generator condition diagnosis and early warning system, characterized in that, The system adopts the wind turbine generator status diagnosis and early warning method as described in any one of claims 1 to 5; The system includes: a data acquisition module, a data preprocessing module, a diagnostic terminal cloud platform, and a PLC controller; The data acquisition module is used to acquire the status data of the power generation equipment in real time, and the data preprocessing module preprocesses the status data of the power generation equipment and stores the status data of the power generation equipment that meets the preset conditions in the diagnostic terminal. The diagnostic terminal is used to calculate the status data of power generation equipment that meets preset conditions, and to intelligently analyze the calculation results to diagnose the status of the power generation equipment. If a fault occurs, an early warning will be issued. It is also used to perform time-domain characteristic statistics, spectrum analysis, and envelope analysis on the status data of power generation equipment; Time-domain characteristic statistics include: RMS value, peak-to-peak value, mean square value, and kurtosis; Spectral analysis is a comparative analysis of the extreme values ​​of segmented spectral lines; Based on the MCKD algorithm, the bearing fault characteristics are initially extracted and separated from the vibration acceleration signal; The data processed by MCKD is subjected to anti-interference processing based on the iterative envelope algorithm to enhance the bearing fault characteristic information. Envelope spectrum analysis is used for energy ratio analysis of various bearing fault characteristics; The effective value is calculated as follows: The mean square value is calculated as follows: The kurtosis is calculated as follows: The fault characteristic energy ratio is calculated as follows: In the formula, E1, E2…E n These represent the energies of the signal at 1, 2, and n times the characteristic frequency after feature extraction, respectively. E represents the total energy within a given frequency range; The diagnostic terminal is also used to send the analyzed power generation equipment status data and diagnostic results data to the cloud platform and PLC controller.

Images