A tower abnormal vibration detection method, device, equipment and medium

Abstract

The present invention belongs to the technical field of abnormal detection of wind turbines, and specifically provides a tower abnormal vibration detection method, device, equipment and medium. The method comprises the following steps: obtaining the unit drive side vibration data, non-drive side vibration data, pitch angle data and power data of each unit collected by SCADA and aligning the acquired data in time sequence; processing the acquired data to generate a data list; detecting the data in the data list in time sequence to determine whether the unit tower has abnormal vibration; determining whether abnormal vibration of the tower caused by pitch abnormality occurs according to the pitch angle and vibration amplitude; determining whether the vibration deviates from the zero axis according to the sum of bins within the tower unit time; and outputting corresponding abnormal warning information based on the determination result. Effectively monitor the tower tilt problem and reduce related operation and maintenance costs.

Description

Technical Field

[0001] The present invention relates to the technical field of abnormality detection of wind turbines, and in particular to a method, device, equipment and medium for detecting abnormal vibration of a tower. Background Art

[0002] Abnormal tower vibration mainly affects the following aspects: 1) Equipment damage. Excessive vibration values ​​may cause accelerated wear of equipment parts, thereby shortening the service life of the equipment; 2) Decreased efficiency. Too much energy is used for vibration instead of power generation; 3) Noise problems. Equipment vibration often brings strong noise problems, affecting the surrounding environment; 4) Accident risks. Excessive vibration may cause accident risks, such as loose bolts, broken structural joints, etc.; 5) Frequent failures. Due to equipment damage and reduced efficiency, equipment may fail frequently, increasing maintenance costs and downtime.

[0003] The SCADA (Supervisory Control And Data Acquisition) system, i.e., data acquisition and monitoring control system, involves configuration software, data transmission links (such as: data transmission radio, GPRS, etc.) and industrial isolation security gateways. How to use the vibration data collected by SCADA to detect abnormal tower vibration is a technical problem to be solved by this application. Summary of the invention

[0004] In view of the various problems caused by abnormal tower vibration, this application performs abnormal tower vibration detection based on vibration data collected by SCADA, solves the problem of no tower angle analysis instrument, and realizes the monitoring of tower vibration and tilt using conventional data.

[0005] In a first aspect, the technical solution of the present invention provides a method for detecting abnormal vibration of a tower, comprising the following steps:

[0006] Obtain the unit drive side vibration data, non-drive side vibration data, pitch angle data and power data of each unit collected through SCADA and align the acquired data in time sequence;

[0007] Process the acquired data to generate a data list;

[0008] Detect the data in the data list in time sequence to determine whether abnormal vibration occurs in the unit tower;

[0009] Determine whether abnormal vibration of the tower caused by abnormal pitch change occurs based on the pitch change angle and vibration amplitude;

[0010] Determine whether the vibration deviates from the zero axis based on the sum of the tower compartments within a unit time;

[0011] Output corresponding abnormal warning information based on the judgment results.

[0012] As a further limitation of the technical solution of the present invention, the steps of acquiring the unit drive side vibration data, non-drive side vibration data, pitch angle data and power data of each unit collected by SCADA and aligning the acquired data in time sequence include:

[0013] Read the unit drive side vibration data, non-drive side vibration data, pitch angle data and power data of each unit within the set time collected by SCADA according to the machine model field;

[0014] The acquired data are aligned and arranged in time sequence to generate the original data set.

[0015] As a further limitation of the technical solution of the present invention, the step of processing the acquired data to generate a data list includes:

[0016] Select the data whose power is greater than the normal power generation value in all fields of the original data set;

[0017] Remove blank data, dead value data, and jump data from the selected data to generate a first data set;

[0018] Taking the first time length as a window, the first data set is acquired to generate a data list.

[0019] As a further limitation of the technical solution of the present invention, the step of detecting the data in the data list in time sequence to determine whether abnormal vibration occurs in the unit tower includes:

[0020] The non-driving side and driving side time series data in the data list are taken as a window with a second time length, and the maximum vibration amplitude data of the non-driving side and the maximum vibration amplitude data of the driving side in the window are obtained to generate a third data set;

[0021] Subtract the driving side time series data in the third data set by staggered operation to obtain the difference. If the difference is continuously increasing and the corresponding amplitude is greater than the first threshold, the driving side determination result flag is set to 1; wherein the staggered operation is to subtract the previous value from the later value;

[0022] The non-driving side time series data in the third data set is calculated by subtracting the previous data from the latter data, and if the difference is continuously increasing and the corresponding amplitude is greater than the second threshold, the non-driving side determination result flag is set to 1;

[0023] If the determination result flag bits of the driving side and the non-driving side are both 1, the unit tower vibration is considered normal; if only one of the determination result flag bits of the driving side and the non-driving side is 1, the unit tower vibration is considered abnormal.

[0024] As a further limitation of the technical solution of the present invention, the step of determining whether abnormal vibration of the tower caused by abnormal pitch change occurs according to the pitch change angle and the vibration amplitude includes:

[0025] Rearrange the driving side vibration data and the non-driving side vibration data in the data list according to the pitch angle;

[0026] The arranged data is divided into warehouses according to the set threshold window;

[0027] Obtain data of the non-driving side first percentage maximum vibration amplitude value and the driving side first percentage maximum vibration amplitude value of each window, and integrate them into a fourth data set;

[0028] The vibration amplitude in the fourth data set is subtracted by offset. If the offset subtraction value is positive when the number of offset subtraction values ​​exceeds the specified threshold within the specified point, it is considered that abnormal tower vibration caused by pitch change occurs, and the pitch change angle determination result mark position 1 is set.

[0029] As a further limitation of the technical solution of the present invention, the step of determining whether the vibration deviates from the zero axis according to the sum of bins within a unit time of the tower includes:

[0030] The data in the data list are divided into bins according to the set time length window, and the driving side vibration data and the non-driving side vibration data in the window are respectively taken to sum the data and integrated into the fifth data set;

[0031] The number of points in the fifth data set that leave the zero axis threshold is determined. When it is determined that the number of points exceeds the point number threshold, the tower vibration center offset is determined and the center offset determination result flag position is set to 1.

[0032] As a further limitation of the technical solution of the present invention, the step of outputting corresponding abnormal warning information based on the determination result includes:

[0033] When only one of the determination result flags of the driving side and the non-driving side is 1, the abnormal warning information of the driving side / non-driving side of the tower is output;

[0034] When the pitch angle determination result mark is at position 1, the abnormal tower vibration warning information caused by pitch angle change is output;

[0035] When the center deviation judgment result mark is at 1, the warning information of the tower vibration center deviation is output.

[0036] In a second aspect, the technical solution of the present invention further provides a tower abnormal vibration detection device, including an acquisition module, a data processing module, a unit tower abnormality detection module, a pitch abnormality detection module, a deviation from zero axis detection module and an early warning output module;

[0037] An acquisition module is configured to acquire the unit drive side vibration data, non-drive side vibration data, pitch angle data and power data of each unit collected through SCADA and align the acquired data in time sequence;

[0038] A data processing module is configured to process the acquired data to generate a data list;

[0039] The unit tower abnormality detection module is configured to detect the data in the data list in time sequence to determine whether the unit tower has abnormal vibration;

[0040] A pitch abnormality detection module is configured to determine whether abnormal vibration of the tower caused by pitch abnormality occurs according to the pitch angle and the vibration amplitude;

[0041] The deviation from zero axis detection module is configured to determine whether the vibration deviates from the zero axis according to the sum of bins in the tower unit time;

[0042] The warning output module is configured to output corresponding abnormal warning information based on the determination result.

[0043] As a further limitation of the technical solution of the present invention, the acquisition module is specifically configured to read the unit drive side vibration data, non-drive side vibration data, pitch angle data and power data of each unit within a set time collected by SCADA according to the machine model field; and align the acquired data in time sequence to generate the original data set.

[0044] As a further limitation of the technical solution of the present invention, the data processing module is specifically configured to select data in all fields of the original data set whose power is greater than the normal power generation power value; remove blank data, dead value data, and jump data in the selected data to generate a first data set; and take data from the first data set using a first time length as a window to generate a data list.

[0045] As a further limitation of the technical solution of the present invention, the unit tower abnormality detection module is specifically configured to use the second time length as a window for the non-driving side and driving side time series data in the data list, obtain the non-driving side maximum vibration amplitude data and the driving side maximum vibration amplitude data in the window to generate a third data set; the driving side time series data in the third data set are offset and subtracted to obtain the difference, if the difference is continuously increasing and the corresponding amplitude is greater than the first threshold, the driving side judgment result flag position is set to 1; wherein, the offset subtraction is the latter value minus the former value; the non-driving side time series data in the third data set is obtained by subtracting the former data from the latter data, if the difference is continuously increasing and the corresponding amplitude is greater than the second threshold, the non-driving side judgment result flag position is set to 1; if the judgment result flags of the driving side and the non-driving side are both 1, it is considered that the unit tower vibration is normal; if only one of the judgment result flags of the driving side and the non-driving side is 1, it is considered that the unit tower vibration is abnormal.

[0046] As a further limitation of the technical solution of the present invention, the pitch abnormality detection module is specifically configured to rearrange the driving side vibration data and the non-driving side vibration data in the data list according to the pitch angle; divide the arranged data into bins according to the set threshold window; obtain the data of the first percentage maximum vibration amplitude value of the non-driving side and the first percentage maximum vibration amplitude value of the driving side in each window, and integrate them into a fourth data set; perform offset subtraction on the vibration amplitudes in the fourth data set, and if the offset subtraction value that exceeds the specified threshold within the specified point position is positive, it is considered that abnormal tower vibration caused by pitch change occurs, and the pitch angle determination result mark position 1 is set.

[0047] As a further limitation of the technical solution of the present invention, the deviation from the zero axis detection module is specifically configured to divide the data in the data list into bins according to a set time length window, and respectively take the driving side vibration data and the non-driving side vibration data in the window to sum the data, and integrate them into a fifth data set; judge the number of points in the fifth data set that leave the zero axis threshold, and when it is judged that the number of points exceeds the point number threshold, it is determined that the tower vibration center is offset and the center offset determination result mark position is 1.

[0048] As a further limitation of the technical solution of the present invention, the early warning output module is specifically configured to output abnormal early warning information of the tower driving side / non-driving side when only one of the determination result flags of the driving side and the non-driving side is 1; output abnormal early warning information of the tower vibration caused by the pitch change when the pitch angle determination result flag is in the 1 position; output early warning information of the tower vibration center offset when the center offset determination result flag is in the 1 position.

[0049] In a third aspect, the technical solution of the present invention also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores computer program instructions executable by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute the tower abnormal vibration detection method as described in the first aspect.

[0050] In a fourth aspect, the technical solution of the present invention also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the tower abnormal vibration detection method as described in the first aspect.

[0051] It can be seen from the above technical solutions that the present invention has the following advantages: 1) Based on the existing SCADA data, the tower vibration can be monitored without the need for additional sensors; 2) The vibration change amplitude is analyzed from the perspective of pitch change, providing an effective reference for wind turbine design; 3) The tower inclination can be monitored without the need for additional instruments.

[0052] Through SCADA transient data, the vibration of the drive side and non-drive side is monitored in real time, and abnormal vibration of the tower is discovered in time to prevent abnormal tower vibration from affecting the operation of the wind turbine and threatening the safety of personnel; the pitch angle is used as the vibration change benchmark, and the vibration change amplitude is used as the analysis benchmark for monitoring, which effectively provides a reference for the design of the wind turbine. According to the offset of the tower vibration center, the degree of vibration swing of the wind turbine can be understood, so as to understand whether the wind turbine will deviate after being stressed, effectively monitor the tilt of the tower, and reduce related operation and maintenance costs. By using the vibration relationship between the drive side and the non-drive side, the pitch angle and the vibration relationship between the drive side and the non-drive side, and the offset of the vibration center, the abnormal vibration of the tower can be effectively monitored to ensure the safety of the wind turbine, and it can also serve as a reference for the design of the wind turbine.

[0053] In addition, the invention has a reliable design principle, a simple structure and a very broad application prospect. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0055] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention.

[0056] Figure 2 is a schematic flow chart of a method according to another embodiment of the present invention.

[0057] Figure 3 (a) is the non-driving side acceleration characteristic diagram of the time series warning.

[0058] Figure 3 (b) is the acceleration characteristic diagram of the driving side of the time series warning.

[0059] Figure 3 (c) is the center shift feature map of the time series warning.

[0060] Figure 4 (a) is the acceleration characteristic diagram of the non-driving side of the pitch angle-vibration warning.

[0061] Figure 4 (b) is the acceleration characteristic diagram of the driving side of the pitch angle-vibration warning. DETAILED DESCRIPTION

[0062] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0063] like Figure 1 As shown, an embodiment of the present invention provides a tower abnormal vibration detection method, comprising the following steps:

[0064] S1: Acquire the unit drive side vibration data, non-drive side vibration data, pitch angle data and power data of each unit collected through SCADA and align the acquired data in time sequence;

[0065] This step specifically includes: reading the unit drive side vibration data, non-drive side vibration data, pitch angle data and power data of each unit within the set time collected by SCADA according to the machine model field; aligning the acquired data in time sequence to generate the original data set.

[0066] S2: Process the acquired data to generate a data list;

[0067] It should be further explained that data with power greater than the normal power generation value in all fields of the original data set are selected; blank data, dead value data, and jump data in the selected data are removed to generate a first data set; and data of the first data set are taken using the first time length as a window to generate a data list.

[0068] S3: Detect the data in the data list in time sequence to determine whether the unit tower has abnormal vibration; this step specifically includes:

[0069] The non-driving side and driving side time series data in the data list are taken as a window with a second time length, and the maximum vibration amplitude data of the non-driving side and the maximum vibration amplitude data of the driving side in the window are obtained to generate a third data set;

[0070] Subtract the driving side time series data in the third data set by staggered operation to obtain the difference. If the difference is continuously increasing and the corresponding amplitude is greater than the first threshold, the driving side determination result flag is set to 1; wherein the staggered operation is to subtract the previous value from the later value;

[0071] The non-driving side time series data in the third data set is calculated by subtracting the previous data from the latter data, and if the difference is continuously increasing and the corresponding amplitude is greater than the second threshold, the non-driving side determination result flag is set to 1;

[0072] If the determination result flag bits of the driving side and the non-driving side are both 1, the unit tower vibration is considered normal; if only one of the determination result flag bits of the driving side and the non-driving side is 1, the unit tower vibration is considered abnormal.

[0073] S4: Determine whether abnormal vibration of the tower caused by abnormal pitch change occurs according to the pitch change angle and the vibration amplitude; specifically, rearrange the driving side vibration data and the non-driving side vibration data in the data list according to the pitch change angle;

[0074] The arranged data is divided into warehouses according to the set threshold window;

[0075] Obtain data of the non-driving side first percentage maximum vibration amplitude value and the driving side first percentage maximum vibration amplitude value of each window, and integrate them into a fourth data set;

[0076] The vibration amplitude in the fourth data set is subtracted by offset. If the offset subtraction value is positive when the number of offset subtraction values ​​exceeds the specified threshold within the specified point, it is considered that abnormal tower vibration caused by pitch change occurs, and the pitch change angle determination result mark position 1 is set.

[0077] S5: judging whether the vibration deviates from the zero axis according to the bin summation results within the tower unit time; specifically comprising: binning the data in the data list according to the set time length window, taking the driving side vibration data and the non-driving side vibration data in the window respectively, summing the data, and integrating them into the fifth data set;

[0078] The number of points in the fifth data set that leave the zero axis threshold is determined. When it is determined that the number of points exceeds the point number threshold, the tower vibration center offset is determined and the center offset determination result flag position is set to 1.

[0079] S6: Outputting corresponding abnormal warning information based on the determination result; this step specifically includes:

[0080] When only one of the determination result flags of the driving side and the non-driving side is 1, the abnormal warning information of the driving side / non-driving side of the tower is output;

[0081] When the pitch angle determination result mark is at position 1, the abnormal tower vibration warning information caused by pitch angle change is output;

[0082] When the center deviation judgment result mark is at 1, the warning information of the tower vibration center deviation is output.

[0083] The vibration of the drive side and non-drive side of the wind turbine should be stable and fluctuate within a certain range. Under normal timing conditions, the vibration of the drive side and non-drive side should be proportional. Under abnormal conditions, this ratio will change. This is the premise for timing prediction of abnormalities on the drive side and non-drive side. At the same time, for normal units, the vibration of the drive side or non-drive side should not suddenly increase after the pitch is changed. However, some units will have this feature, which is a manifestation of aerodynamic imbalance. At the same time, the vibration of the drive side and non-drive side should fluctuate around the vibration center (zero axis). If the vibration center is not on the zero axis, it can be considered that the vibration center has shifted, which can be regarded as a manifestation of tower tilt.

[0084] Based on the existing measuring points, this application collects the vibration and pitch signals of the driving side and non-driving side, analyzes the data characteristics of the vibration signals, adjusts the threshold according to historical experience, and completes the monitoring of abnormal tower vibration and tilt. The focus is on analyzing the vibration amplitude changes and vibration center changes of the cleaned data, as well as the changes of vibration with pitch change, based on the SCADA second-level data. Specifically: 1) Monitor the abnormal vibration from a timing perspective, tending to the sudden change of vibration over a period of time; 2) Consider the changes of vibration with pitch change from the perspective of pitch change, and the startup imbalance that occurs with pitch change; 3) Consider the correlation between the change of vibration center and the tilt of the tower from the perspective of the change of the vibration center of the unit. The use of vibration data solves the problem of no tower angle analysis instrument, and realizes the monitoring of tower vibration and tilt using conventional data. First, the vibration of the driving side and the non-driving side is timed to clean up abnormal data, and at the same time, it is ensured that the unit is in operation. Then the driving side and the non-driving side are observed. Under normal circumstances, the vibrations of the driving side and the non-driving side are in a certain ratio, and the vibration amplitude will not exceed a certain value. If the vibration amplitude exceeds the threshold at the same time, it can be considered that it is a normal vibration caused by factors such as strong wind. If only one side vibrates beyond the threshold and the ratio changes significantly, it is considered that the unilateral vibration is too strong and there is a certain risk, and an early warning is issued.

[0085] Secondly, the vibration abnormalities on the non-driving side and the driving side are monitored by the pitch angle. The principle is that when the pitch is changed, due to design or installation reasons, the unit will have aerodynamic imbalance during the pitch change, resulting in abnormal vibration of the unit. The specific calculation method is to divide the vibration of the driving side and the non-driving side into bins according to the pitch angle. After the bins are divided, the 80% maximum value is calculated as the amplitude, and the latter value is subtracted from the former value. If the number of values ​​exceeding the threshold within the specified length is greater than the specified value, it is considered that the vibration after the pitch change is too large, and there may be unreasonable design or installation.

[0086] Finally, when the unit vibrates, it should monitor the fluctuations around the vibration center. The main basis is that when the unit vibrates, it should fluctuate around the zero axis. If there is a deviation, it means that the vibration center has shifted. Based on this, the deviation of the vibration from the zero axis threshold on the drive side and the non-drive side is monitored. If the average vibration value is far away from the zero axis, the alarm vibration center is shifted, and the operation and maintenance engineer needs to check the relevant fans.

[0087] like Figure 2 As shown, the specific process is as follows:

[0088] Data reading: Get the real-time 1-second data of the entire field for a certain period of time (at least 1 day, to ensure a certain amount of data) according to the model field.

[0089] Step 1: Read data: Read data according to fields, which is Data;

[0090] Step 2: Filter the data to ensure that the unit is in operation: select all fields with power > p1 when the data is Data1;

[0091] Step 3: Clean the data: remove blank data, dead value data, and jump data from Data1 and save it as Data1;

[0092] Step 4: Data partitioning: Take the data of Data1 in a one-hour window and take it as Data2_series;

[0093] Abnormal tower vibration detection process:

[0094] Step 5: Extract features of the driving side and non-driving side: Take the driving side and non-driving side time series of Data2_series as a window of 10 seconds and obtain the maximum vibration amplitude f in 10 seconds vibx and f viby , organized into characteristic value data Data3; data characteristic diagrams are shown in Figure 3 (a), Figure 3 (b) and Figure 3 (c);

[0095] Step 6: Timing determination on the drive side: Calculate the difference of Data3 misalignment (subtract the previous from the latter), and determine the change of the difference: if it shows a continuous increase, and the corresponding amplitude is greater than the threshold F1 requirement, the result is collected as result_1=1 on the drive side;

[0096] Step 7: Non-driving side timing determination: repeat step 6, the corresponding amplitude is greater than the threshold F2 requirement, and the result is non-driving side result_2=1;

[0097] Step 8: Result output: If both result_1 on the driving side and result_2 on the non-driving side are 1, it is considered normal. If only one is 1, it is considered abnormal and the tower driving side / non-driving side abnormality is reported.

[0098] Abnormal tower vibration detection process caused by pitch change:

[0099] Step 9: Take bin data for calculation: Take bin data Data2_series, and rearrange the driving side vibration data and non-driving side vibration data according to the pitch angle;

[0100] Step 10: Feature extraction: Divide the data into bins according to the 0.1 degree pitch value and obtain the 80% maximum vibration amplitude f of each window vibx-pitch and f viby-pitch , integrated into Data4; the data feature graphs are shown in Figure 4 (a) and Figure 4 (b);

[0101] Step 11: Abnormal feature identification: Data4 performs offset subtraction on the vibration amplitude. If the subtraction value is mainly increasing (more than D2 offset subtraction values ​​are positive within D1 points), it is considered that abnormal tower vibration caused by pitch change occurs.

[0102] Tower vibration center deviation monitoring process:

[0103] Step 12: Take the sub-bin data for calculation: Take the sub-bin data Data2_series, divide it into 1-minute bins, take the Vibx and Viby data of one minute respectively, and organize them into Data5;

[0104] Step 13: Feature extraction: Based on the summation result, determine the number of points y1 that leave the zero-axis threshold Y1. If it exceeds the threshold Y2, an early warning of tower vibration center deviation is issued.

[0105] The main variables are described as follows:

[0106] Data: data read by the fan;

[0107] Data1: data on the unit’s operating status after removing abnormal values;

[0108] Data2_series: a series of data blocks divided into hourly bins;

[0109] : Maximum vibration amplitude of non-driving side acceleration for 10 seconds;

[0110] : Maximum vibration amplitude of the driving side acceleration for 10 seconds;

[0111] Data3: and The integrated value of

[0112] f vibx-pitch : 80% maximum vibration amplitude value of the non-driving side sorted by pitch;

[0113] f viby-pitch : 80% maximum vibration amplitude value of the driving side sorted by pitch;

[0114] Data4:f vibx-pitch and f viby-pitch The integrated value of

[0115] Vibx: non-driving side acceleration;

[0116] Viby: driving side acceleration;

[0117] Main parameter description:

[0118] p1: power during normal power generation, generally set to 100;

[0119] F1: Non-drive side vibration amplitude requirements, which vary from model to model;

[0120] F2: The vibration amplitude requirement on the drive side varies for different models;

[0121] D1: specified point;

[0122] D2: specified threshold;

[0123] Y1: threshold value for leaving the zero axis;

[0124] Y2: The threshold value of the number of points leaving the zero axis.

[0125] The embodiment of the present invention further provides a tower abnormal vibration detection device, the abnormality detection device comprising:

[0126] 1) an acquisition unit, configured to acquire operation data of each wind turbine in a plurality of wind turbines in a wind farm, wherein the operation data includes power data in the wind turbine, vibration data of a driving side and a non-driving side, and blade pitch data;

[0127] 2) a determination unit configured to determine a staggered subtraction value of bin maximum values ​​of the driving side vibration and the non-driving side vibration of each wind turbine set;

[0128] 3) a statistical value determination unit, configured to determine a first statistical value of the offset subtraction value, wherein the first statistical value represents a statistical value greater than 0 of the offset subtraction within a specified continuous data range;

[0129] 4) An abnormality detection unit, configured to determine whether the vibration installed in the unit to be detected is abnormal by comparing the first statistical value.

[0130] The embodiment of the present invention further provides a tower abnormal vibration detection device, comprising an acquisition module, a data processing module, a unit tower abnormality detection module, a pitch abnormality detection module, a deviation from zero axis detection module and an early warning output module;

[0131] An acquisition module is configured to acquire the unit drive side vibration data, non-drive side vibration data, pitch angle data and power data of each unit collected through SCADA and align the acquired data in time sequence;

[0132] A data processing module is configured to process the acquired data to generate a data list;

[0133] The unit tower abnormality detection module is configured to detect the data in the data list in time sequence to determine whether the unit tower has abnormal vibration;

[0134] A pitch abnormality detection module is configured to determine whether abnormal vibration of the tower caused by pitch abnormality occurs according to the pitch angle and the vibration amplitude;

[0135] The deviation from zero axis detection module is configured to determine whether the vibration deviates from the zero axis according to the sum of bins in the tower unit time;

[0136] The warning output module is configured to output corresponding abnormal warning information based on the determination result.

[0137] In some embodiments, the acquisition module is specifically configured to read the unit drive side vibration data, non-drive side vibration data, pitch angle data and power data of each unit within a set time collected through SCADA according to the machine model field; and align the acquired data in time sequence to generate the original data set.

[0138] In some embodiments, the data processing module is specifically configured to select data in all fields of the original data set whose power is greater than the normal power generation value; remove blank data, dead value data, and jump data in the selected data to generate a first data set; and take data from the first data set using a first time length as a window to generate a data list.

[0139] In some embodiments, the unit tower abnormality detection module is specifically configured to use the second time length as a window for the non-driving side and driving side time series data in the data list, obtain the non-driving side maximum vibration amplitude data and the driving side maximum vibration amplitude data in the window to generate a third data set; the driving side time series data in the third data set are offset and subtracted to obtain the difference, if the difference is continuously increasing and the corresponding amplitude is greater than the first threshold, the driving side judgment result flag is set to 1; wherein, the offset subtraction is the subtraction of the latter value from the former value; the non-driving side time series data in the third data set is subtracted from the former data to obtain the difference, if the difference is continuously increasing and the corresponding amplitude is greater than the second threshold, the non-driving side judgment result flag is set to 1; if the judgment result flags of the driving side and the non-driving side are both 1, it is considered that the unit tower vibration is normal; if only one of the judgment result flags of the driving side and the non-driving side is 1, it is considered that the unit tower vibration is abnormal.

[0140] In some embodiments, the pitch abnormality detection module is specifically configured to rearrange the driving side vibration data and the non-driving side vibration data in the data list according to the pitch angle; divide the arranged data into bins according to the set threshold window; obtain the data of the first percentage maximum vibration amplitude value of the non-driving side and the first percentage maximum vibration amplitude value of the driving side in each window, and integrate them into a fourth data set; perform offset subtraction on the vibration amplitudes in the fourth data set, and if the offset subtraction value is positive and exceeds the specified threshold within the specified point position, it is considered that abnormal tower vibration caused by pitch change occurs, and the pitch angle determination result mark position 1 is set.

[0141] In some embodiments, the deviation from zero axis detection module is specifically configured to bin the data in the data list according to a set time length window, and respectively take the driving side vibration data and the non-driving side vibration data in the window to sum the data, and integrate them into a fifth data set; determine the number of points in the fifth data set that leave the zero axis threshold, and when it is determined that the number of points exceeds the point number threshold, it is determined that the tower vibration center is offset and the center offset determination result mark position is 1.

[0142] In some embodiments, the early warning output module is specifically configured to output abnormal early warning information of the tower driving side / non-driving side when only one of the determination result flags of the driving side and the non-driving side is 1; to output abnormal early warning information of the tower vibration caused by the pitch change when the pitch angle determination result flag is 1; and to output early warning information of the tower vibration center offset when the center offset determination result flag is 1.

[0143] The embodiment of the present invention also provides an electronic device, which includes: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus. The communication bus can be used for information transmission between the electronic device and the sensor. The processor can call the logic instructions in the memory to execute the following method: S1: obtain the unit drive side vibration data, non-drive side vibration data, pitch angle data and power data of each unit collected by SCADA and align the acquired data in time sequence; S2: process the acquired data to generate a data list; S3: detect the data in the data list in time sequence to determine whether the unit tower has abnormal vibration; S4: determine whether the abnormal vibration of the tower caused by the pitch abnormality occurs according to the pitch angle and the vibration amplitude; S5: determine whether the vibration deviates from the zero axis according to the sum of the bins in the tower unit time; S6: output the corresponding abnormal warning information based on the determination result.

[0144] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0145] An embodiment of the present invention provides a non-transitory computer-readable storage medium, which stores computer instructions. The computer instructions enable a computer to execute the method provided by the above method embodiment, for example, including: S1: acquiring the unit drive side vibration data, non-drive side vibration data, pitch angle data and power data of each unit collected by SCADA and aligning the acquired data in time sequence; S2: processing the acquired data to generate a data list; S3: detecting the data in the data list in time sequence to determine whether abnormal vibration occurs in the unit tower; S4: determining whether abnormal vibration of the tower caused by pitch abnormality occurs according to the pitch angle and vibration amplitude; S5: determining whether the vibration deviates from the zero axis according to the sum of the bins within unit time of the tower; S6: outputting corresponding abnormal warning information based on the determination result.

[0146] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0147] An embodiment of a tower abnormal vibration detection device provided in an embodiment of the present invention discloses that the device and the tower abnormal vibration detection methods of the above-mentioned embodiments belong to the same inventive concept. For details not fully described in the embodiment of the tower abnormal vibration detection device, reference can be made to the embodiment of the above-mentioned tower abnormal vibration detection method.

[0148] The abnormal vibration detection device of the tower is a unit and algorithm step of each example described in combination with the embodiments disclosed in this article, which can be implemented by electronic hardware, computer software or a combination of the two. 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 according to the function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0149] Although the present invention has been described in detail with reference to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person of ordinary skill in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and these shall be within the scope of protection of the present invention.

Claims

1. A tower abnormal vibration detection method based on SCADA vibration data, characterized in that: The steps include: Obtain the unit drive side vibration data, non-drive side vibration data, pitch angle data and power data of each unit collected through SCADA and align the acquired data in time sequence; Process the acquired data to generate a data list; Detect the data in the data list in time sequence to determine whether abnormal vibration occurs in the unit tower; Determine whether abnormal vibration of the tower caused by abnormal pitch change occurs based on the pitch change angle and vibration amplitude; Determine whether the vibration deviates from the zero axis based on the sum of the tower compartments within a unit time; Output corresponding abnormal warning information based on the judgment results; The steps of detecting the data in the data list in time sequence to determine whether abnormal vibration occurs in the tower of the unit include: The non-driving side and driving side time series data in the data list are taken as a window with a second time length, and the maximum vibration amplitude data of the non-driving side and the maximum vibration amplitude data of the driving side in the window are obtained to generate a third data set; Subtract the driving side time series data in the third data set by staggered operation to obtain the difference. If the difference is continuously increasing and the corresponding amplitude is greater than the first threshold, the driving side determination result flag is set to 1; wherein the staggered operation is to subtract the previous value from the later value; The non-driving side time series data in the third data set is calculated by subtracting the previous data from the latter data, and if the difference is continuously increasing and the corresponding amplitude is greater than the second threshold, the non-driving side determination result flag is set to 1; If the determination result flags of the driving side and the non-driving side are both 1, the unit tower vibration is considered normal; if only one of the determination result flags of the driving side and the non-driving side is 1, the unit tower vibration is considered abnormal; The steps of determining whether abnormal vibration of the tower caused by abnormal pitch change occurs according to the pitch change angle and vibration amplitude include: Rearrange the driving side vibration data and the non-driving side vibration data in the data list according to the pitch angle; The arranged data is divided into warehouses according to the set threshold window; Obtain data of the non-driving side first percentage maximum vibration amplitude value and the driving side first percentage maximum vibration amplitude value of each window, and integrate them into a fourth data set; The vibration amplitude in the fourth data set is subtracted by offset. If the offset subtraction value exceeds the specified threshold within the specified point and is positive, it is considered that abnormal tower vibration caused by pitch change occurs, and the pitch change angle determination result mark position 1 is set.

2. The tower abnormal vibration detection method based on SCADA vibration data according to claim 1 is characterized in that: The steps of acquiring the unit drive side vibration data, non-drive side vibration data, pitch angle data and power data of each unit collected through SCADA and aligning the acquired data in time sequence include: Read the unit drive side vibration data, non-drive side vibration data, pitch angle data and power data of each unit within the set time collected by SCADA according to the machine model field; The acquired data are aligned and arranged in time sequence to generate the original data set.

3. The tower abnormal vibration detection method based on SCADA vibration data according to claim 2 is characterized in that: The steps of processing the acquired data to generate a data list include: Select the data whose power is greater than the normal power generation value in all fields of the original data set; Remove blank data, dead value data, and jump data from the selected data to generate a first data set; Taking the first time length as a window, the first data set is acquired to generate a data list.

4. The tower abnormal vibration detection method based on SCADA vibration data according to claim 3 is characterized in that: The steps of determining whether the vibration deviates from the zero axis according to the sum of the tower compartments per unit time include: The data in the data list are divided into bins according to the set time length window, and the driving side vibration data and the non-driving side vibration data in the window are respectively taken to sum the data and integrated into the fifth data set; The number of points in the fifth data set that leave the zero axis threshold is determined. When it is determined that the number of points exceeds the point number threshold, the tower vibration center offset is determined and the center offset determination result flag position is set to 1.

5. The tower abnormal vibration detection method based on SCADA vibration data according to claim 4 is characterized in that: The steps of outputting corresponding abnormal warning information based on the determination result include: When only one of the determination result flags of the driving side and the non-driving side is 1, the abnormal warning information of the driving side / non-driving side of the tower is output; When the pitch angle determination result mark is at position 1, the abnormal tower vibration warning information caused by pitch angle change is output; When the center deviation judgment result mark is at 1, the warning information of the tower vibration center deviation is output.

6. A tower abnormal vibration detection device based on SCADA vibration data, characterized in that: It includes an acquisition module, a data processing module, a unit tower abnormality detection module, a pitch abnormality detection module, a deviation from zero axis detection module and an early warning output module; An acquisition module is configured to acquire the unit drive side vibration data, non-drive side vibration data, pitch angle data and power data of each unit collected through SCADA and align the acquired data in time sequence; A data processing module, configured to process the acquired data to generate a data list; The unit tower abnormality detection module is configured to detect the data in the data list in time sequence to determine whether the unit tower has abnormal vibration; A pitch abnormality detection module is configured to determine whether abnormal vibration of the tower caused by pitch abnormality occurs according to the pitch angle and the vibration amplitude; The deviation from zero axis detection module is configured to determine whether the vibration deviates from the zero axis according to the sum of bins in the tower unit time; An early warning output module is configured to output corresponding abnormal early warning information based on the determination result; The unit tower abnormality detection module is specifically configured to use the second time length as a window for the non-driving side and driving side time series data in the data list, obtain the non-driving side maximum vibration amplitude data and the driving side maximum vibration amplitude data in the window to generate a third data set; The driving side time series data in the third data set are offset and subtracted to obtain the difference. If the difference is continuously increasing and the corresponding amplitude is greater than the first threshold, the driving side judgment result flag is set to 1; wherein the offset subtraction is the subtraction of the latter value from the former value; the non-driving side time series data in the third data set are subtracted from the former data to obtain the difference. If the difference is continuously increasing and the corresponding amplitude is greater than the second threshold, the non-driving side judgment result flag is set to 1; if the judgment result flags of the driving side and the non-driving side are both 1, it is considered that the vibration of the unit tower is normal; if only one of the judgment result flags of the driving side and the non-driving side is 1, it is considered that the vibration of the unit tower is abnormal; The pitch abnormality detection module is specifically configured to rearrange the driving side vibration data and the non-driving side vibration data in the data list according to the pitch angle; divide the arranged data into bins according to the set threshold window; obtain the data of the first percentage maximum vibration amplitude value of the non-driving side and the first percentage maximum vibration amplitude value of the driving side in each window, and integrate them into a fourth data set; perform offset subtraction on the vibration amplitudes in the fourth data set, and if the offset subtraction value that exceeds the specified threshold within the specified point position is positive, it is considered that abnormal tower vibration caused by pitch change occurs, and the pitch angle determination result mark position 1 is set.

7. An electronic device, characterized in that: The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores computer program instructions executable by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute the tower abnormal vibration detection method based on SCADA vibration data as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the tower abnormal vibration detection method based on SCADA vibration data according to any one of claims 1 to 5.

Images