CN118171048A - Turbine equipment vibration data correction method and early warning system - Google Patents
Turbine equipment vibration data correction method and early warning system Download PDFInfo
- Publication number
- CN118171048A CN118171048A CN202410584932.9A CN202410584932A CN118171048A CN 118171048 A CN118171048 A CN 118171048A CN 202410584932 A CN202410584932 A CN 202410584932A CN 118171048 A CN118171048 A CN 118171048A
- Authority
- CN
- China
- Prior art keywords
- interference
- data segment
- data
- vibration signal
- usstr
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000010355 oscillation Effects 0.000 claims abstract description 32
- 230000006870 function Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 230000035939 shock Effects 0.000 claims description 6
- 230000007423 decrease Effects 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 abstract description 8
- 238000001914 filtration Methods 0.000 abstract description 4
- 230000009467 reduction Effects 0.000 abstract description 3
- 230000005284 excitation Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention belongs to the technical field of data acquisition, and provides a turbine equipment vibration data correction method and an early warning system, which are used for acquiring vibration signal data of turbine equipment; scanning each interference data segment in the vibration signal data in sequence; and carrying out data correction on each interference data segment in the vibration signal data to obtain vibration signal correction data. The corrected result can eliminate most outliers, and the real abnormal data in the data segment cannot be lost due to the influence of a large amount of interference data, so that the data has higher reduction degree and cannot generate data distortion; the fault intensity distortion caused by local surge or oscillation is counteracted, and the false filtering problem or the data leakage influence caused by non-serious surge or external oscillation is eliminated.
Description
Technical Field
The invention belongs to the technical field of data acquisition, and particularly relates to a turbine equipment vibration data correction method and an early warning system.
Background
When vibration data of turbine equipment is collected by a sensor in continuous operation, fatigue, oxidation corrosion, friction damage, pipeline aging, leakage, air bubble and other conditions generated by turbine blades are caused by wind pressure generated by external high temperature and high speed, the problems of slow speed rise of the turbine equipment in the starting process, deviation of a designed value of a gas compressor working condition, airflow excitation faults and the like are caused, or the problems of gas compressor stall, vibration aggravation, surge and whistle and the like caused by the conditions are further caused, a large amount of wild points and a large amount of interference data caused by surge are generated in the collected vibration data, and the existing data mining method, such as an outlier detection algorithm, only screens out outliers from similar data for data mining, although partial outliers generated by interference can be screened out, the data generated by interference are not outliers, if distortion caused by aliasing is reduced by an existing filter, the real abnormal data in the data segments are filtered out, so that the vibration data is substantially distorted, and the loss is not the signal of the interference data; therefore, the existing filter can make the vibration state data of the turbine equipment difficult to accurately acquire, and generate larger data distortion.
Disclosure of Invention
The invention aims to provide a turbine equipment vibration data correction method and an early warning system, which are used for solving one or more technical problems in the prior art and at least providing a beneficial selection or creation condition.
In order to achieve the above object, according to an aspect of the present invention, there is provided a turbine-apparatus vibration data correction method including the steps of:
S100, acquiring vibration signal data of turbine equipment;
s200, scanning each interference data segment in the vibration signal data in sequence;
s300, data correction is carried out on each interference data segment in the vibration signal data to obtain vibration signal correction data.
Further, the method for acquiring the vibration signal data of the turbine equipment comprises the following steps: and acquiring vibration signals of the gas turbine in real time through a Gager vibration meter, an accelerometer or a laser vibration meter.
Wherein the gas turbine is a dual-rotor gas turbine or a three-rotor gas turbine.
Further, in S200, the method of scanning each interference data segment in the vibration signal data sequentially includes:
Dividing all vibration signal data into N data segments on average; setting a variable q epsilon [1, N ], and taking a q-th data segment as Vib (q), wherein an average vibration signal in the Vib (q) is MVib (q); wherein N is an integer greater than 3;
In the value range of q, sequentially calibrating interference data of each Vib (q), specifically: in each Vib (q), marking the acquisition time of the vibration signal which is larger than the vibration signal in MVib (q) for the first time as right mark time RT according to reverse time sequence, and acquiring the vibration signal as RVib according to RT; sequentially judging each vibration signal in MVib (q) from RT time to reverse time sequence, and marking the acquisition time of the vibration signal with the vibration signal being larger than RVib for the first time as left mark time LT; vibration signals acquired by LT are LVib; taking a data segment formed by all data acquired in a time period between LT and RT in MVib (q) as an interference data segment; and obtaining the interference data segments of each Vib (q) which are the interference data segments in the vibration signal data.
The data segments are defined as vibration signal value data arranged in time sequence.
The interference data segment is a data segment with two endpoints being wavy oscillation amplitude of vibration signals from left to right, LT is generally the limit moment when the gas turbine is in variable speed unsteadiness, and the data segment collected between LT and RT after the moment can cause the gas turbine airflow excitation state or the unbalanced state with high probability, so that the interference data segment can accurately locate the data segment which is generated by the gas turbine unit and has interference in the latest variable speed unsteady state.
Because the gas turbine unit is often in a variable speed non-steady state, the time interval between different acquisition moments of the effective vibration signals acquired by the sensor is longer, and particularly, the vibration signals are segmented at equal intervals by a common peak hold down sampling method, and the equal interval segmentation leads to the fact that the signals are missed or the false acquisition happens between the equal interval segmentation; in a variable speed non-steady state, vibration data generated by a gas turbine unit in an airflow excitation state and an unbalance state can cause state interference signals or wild value points for generating vibration signals, the wild value points can be confused with real abnormal data, and the abnormal data can be filtered by using the existing filter, so that the problems of omission and distortion of the abnormal data occur.
Further, in S300, the method for obtaining the vibration signal correction data by performing data correction on each interference data segment in the vibration signal data includes:
the method for calculating the interference intensity of each interference data segment comprises the following steps of:
The total number of increases between every two adjacent vibration signal values in each vibration signal value recorded in the data segment is UsAdd, and the total number of decreases between every two adjacent vibration signal values is UsSub; then calculate the interference intensity UsStr = UsAdd ++ (UsAdd + UsSub) ×100 for the data segment;
Respectively obtaining stable offset sequences corresponding to the interference data segments according to the interference intensity of the interference data segments, wherein the stable offset sequences are specifically as follows:
taking the acquisition time of the median of each interference data segment as the median time; taking the median time of the current interference data segment as MBT;
Acquiring the median time MAT of the nearest interference data segment before the distance T1; marking an interference data segment corresponding to the MAT as a prepositive interference data segment;
taking a data segment from MAT to MBT in vibration signal data, and calculating the interference intensity of the data segment as the continuous interference intensity of the current interference data segment, wherein the method for calculating the interference intensity of the data segment comprises the following steps:
The total number of increases between every two adjacent vibration signal values in each vibration signal value recorded in the data segment is UsAdd, and the total number of decreases between every two adjacent vibration signal values is UsSub; then calculate the interference intensity UsStr = UsAdd ++ (UsAdd + UsSub) ×100 for the data segment;
If the interference intensity of the current interference data segment is larger than the continuous interference intensity, taking the interference intensity of the current interference data segment as trend intensity, otherwise, taking the average value of the interference intensity of the pre-interference data segment and the interference intensity of the current interference data segment as trend intensity;
Sequencing all vibration signal values in the current interference data segment and the pre-interference data segment according to the acquired time sequence;
Subtracting the vibration signal values with the same serial numbers in the current interference data segment and the pre-interference data segment to obtain difference values, marking the result of multiplying each difference value by the trend intensity value as a stable offset, and sequentially forming each stable offset into a stable offset sequence;
And respectively carrying out data correction on each interference data segment according to the corresponding stable offset sequence to obtain vibration signal correction data.
The specific method for respectively carrying out data correction on each interference data segment according to the corresponding stable offset sequence to obtain vibration signal correction data comprises the following steps: and sequentially adding the stable offset sequence and the numerical value with the same serial number in the corresponding interference data segment to obtain vibration signal correction data.
The larger the value of the interference intensity of the data section is, the larger the external interference intensity is, the smaller the value is, the external interference intensity is small, and the interference intensity is the interference of any one of anomalies such as abnormal speed increase of the gas turbine in the starting process, deviation of the working condition of the gas compressor from the designed value, airflow excitation faults and the like on the data section; if the interference intensity of the current interference data segment is larger than the continuous interference intensity, the interference caused by the abnormality on the data segment is represented to have stronger continuity between the current interference data segment and the pre-interference data segment, otherwise, the interference is not continuous; if the gas turbine has continuity, calculating a stable offset sequence according to the interference intensity of the current interference data segment which can most represent the current state of the gas turbine, otherwise, expanding the stable offset sequence to a preposed interference data segment for comprehensive calculation; the calculated stable offset sequence can carry out offset correction according to the change of each value in the previous approximate period, and because the method does not carry out data filtering, but carries out the correction of eliminating the interference influence on each vibration data correspondingly, the corrected result can eliminate most outlier points, and the true abnormal data in the data segment can not be lost due to the influence of a large amount of interference data, so the data has higher reduction degree and can not generate data distortion.
Although the above technical solution can accurately restore the vibration data of the gas turbine in a normal state, if a surging phenomenon of the gas turbine compressor or an external vibration phenomenon (such as external impact, water flow or air flow aggravation and other external influences) occurs between the front interference data segment and the current interference data segment, even if surging or external vibration is not serious, the data generated by the above data correction method are seriously distorted, and the principle is that surging causes the air flow inside the gas turbine to generate an air flow oscillation phenomenon along the axis direction of the compressor, so that the strong mechanical vibration of the compressor component is caused, thereby generating strong interference on the acquired vibration signal, and consequently, unavoidable data distortion is generated, and in order to eliminate the problem, the application proposes the following method to eliminate the influence caused by surging:
Preferably, in S300, the method for obtaining vibration signal correction data by performing data correction on each interference data segment in the vibration signal data includes:
respectively calculating the interference intensity of each interference data segment;
The average value of the interference intensity of all the interference data segments is UsStrM, the serial number of the interference data segment is i, and the UsStr (i) is the interference intensity of the ith interference data segment; judging each UsStr (i) in sequence:
If the average vibration signal value of the interference data segment corresponding to UsStr (i) is smaller than the average vibration signal value of the interference data segment corresponding to UsStr (i-1), the value of UsStr (i) is smaller than the value of UsStr (i-1), and if the average vibration signal value of the interference data segment corresponding to UsStr (i) is larger than the average vibration signal value of the interference data segment corresponding to UsStr (i+1), the value of UsStr (i) is larger than the value of UsStr (i+1), and the value of UsStr (i) is larger than UsStrM, then the surge occurs in the interference data segment corresponding to UsStr (i) during acquisition;
If the average vibration signal value of the interference data segment corresponding to the UsStr (i) is larger than that of the interference data segment corresponding to UsStr (i-1), the value of the UsStr (i) is larger than that of UsStr (i-1), and if the average vibration signal value of the interference data segment corresponding to the UsStr (i) is smaller than that of the interference data segment corresponding to UsStr (i+1), the value of the UsStr (i) is smaller than that of UsStr (i+1), and the value of the UsStr (i) is smaller than UsStrM, the external oscillation occurs to the interference data segment corresponding to the UsStr (i) during acquisition;
J is the serial number of the vibration signal value in the interference data segment corresponding to UsStr (i), and Usi (j) is the vibration signal value with the serial number j in the interference data segment corresponding to UsStr (i);
If the interference data segment corresponding to UsStr (i) is surging during acquisition, respectively obtaining a surging offset sequence corresponding to each interference data segment according to the interference intensity of each interference data segment, wherein the surging offset sequence specifically comprises the following steps:
Calculating a surge offset (j) of each vibration signal value Usi (j) in the interference data segment corresponding to the UsStr (i):
surge(j) = UsStr(i)×|UsiMax-Max(Usi(j), Usi(j+1))|；
wherein UsiMax is the maximum vibration signal value in the interference data segment corresponding to UsStr (i), and the Max function is the maximum value;
sequentially forming each surge offset into a surge offset sequence;
sequentially adding the values with the same serial numbers in the surge offset sequence and the corresponding interference data segment to obtain vibration signal correction data;
if the interference data segment corresponding to UsStr (i) generates external oscillation during acquisition, respectively obtaining oscillation offset sequences corresponding to each interference data segment according to the interference intensity of each interference data segment, specifically:
Calculating oscillation offset shock (j) of each vibration signal value Usi (j) in the interference data segment corresponding to UsStr (i):
shock(j)= UsStr(i)×|UsiMin-Min(Usi(j-1), Usi(j))|；
Wherein UsiMin is the minimum vibration signal value in the corresponding interference data segment of UsStr (i), and the Min function is the minimum value;
Sequentially forming the oscillation offset values into an oscillation offset sequence;
And sequentially adding the values with the same serial numbers in the oscillation offset sequence and the corresponding interference data segment to obtain vibration signal correction data.
The method can identify vibration data acquired at the moment of surge phenomenon or external vibration phenomenon in the sailing process, and can greatly reduce the data distortion problem of the two strong interference phenomena according to small-amplitude correction of the numerical value of each vibration signal; the surge offset sequence and the oscillation offset sequence counteract the fault intensity distortion caused by local surge or oscillation, eliminate false filtering problems or missing data influence caused by non-serious surge or external oscillation, and improve the diagnosis precision and reliability of the system.
The invention also provides a turbine equipment vibration data early warning system, which comprises: the processor executes the computer program to implement steps in the method for correcting vibration data of turbine equipment, the system for early warning vibration data of turbine equipment can be operated in computing equipment such as desktop computers, notebooks, palm computers and cloud data centers, and the operable system can include, but is not limited to, a processor, a memory and a server cluster, and the processor executes the computer program to operate in units of the following systems:
The vibration signal acquisition unit is used for acquiring vibration signal data of the turbine equipment;
the interference data scanning unit is used for scanning each interference data segment in the vibration signal data in sequence;
The vibration signal correction unit is used for carrying out data correction on each interference data segment in the vibration signal data to obtain vibration signal correction data;
and the early warning signal pushing unit is used for sending out a fault signal of the gas turbine if the vibration signal correction data is greater than the threshold value.
The beneficial effects of the invention are as follows: the invention provides a turbine equipment vibration data correction method and an early warning system, which are used for correspondingly correcting the interference elimination influence of each vibration data, wherein the corrected result can eliminate most outlier points and cannot lose real abnormal data in a data segment due to the influence of a large amount of interference data, so that the data has higher reduction degree and cannot generate data distortion; according to the small-amplitude correction which is constructed to be accurate to the numerical value of each oscillation signal, the data distortion problem of the two strong interference phenomena can be greatly reduced; the surge offset sequence and the oscillation offset sequence are used for counteracting the fault intensity distortion caused by local surge or oscillation, and eliminating the false filtering problem or the data leakage influence caused by non-serious surge or external oscillation.
Drawings
The above and other features of the present invention will become more apparent from the detailed description of the embodiments thereof given in conjunction with the accompanying drawings, in which like reference characters designate like or similar elements, and it is apparent that the drawings in the following description are merely some examples of the present invention, and other drawings may be obtained from these drawings without inventive effort to those of ordinary skill in the art, in which:
FIG. 1 is a block diagram of a turbine plant vibration data early warning system.
Detailed Description
The conception, specific structure, and technical effects produced by the present application will be clearly and completely described below with reference to the embodiments and the drawings to fully understand the objects, aspects, and effects of the present application. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other.
Example 1
S100, acquiring vibration signal data of turbine equipment;
s200, scanning each interference data segment in the vibration signal data in sequence;
s300, data correction is carried out on each interference data segment in the vibration signal data to obtain vibration signal correction data.
Further, the method for acquiring the vibration signal data of the turbine equipment comprises the following steps: and acquiring vibration signals of the gas turbine in real time through a laser vibration meter.
Wherein the gas turbine is a dual rotor gas turbine.
Further, in S200, the method of scanning each interference data segment in the vibration signal data sequentially includes:
dividing all vibration signal data into N data segments on average; setting a variable q epsilon [1, N ], and taking a q-th data segment as Vib (q), wherein an average vibration signal in the Vib (q) is MVib (q); wherein N is set to 30;
In the value range of q, sequentially calibrating interference data of each Vib (q), specifically: in each Vib (q), marking the acquisition time of the vibration signal which is larger than the vibration signal in MVib (q) for the first time as right mark time RT according to reverse time sequence, and acquiring the vibration signal as RVib according to RT; sequentially judging each vibration signal in MVib (q) from RT time to reverse time sequence, and marking the acquisition time of the vibration signal with the vibration signal being larger than RVib for the first time as left mark time LT; vibration signals acquired by LT are LVib; taking a data segment formed by all data acquired in a time period between LT and RT in MVib (q) as an interference data segment; and obtaining the interference data segments of each Vib (q) which are the interference data segments in the vibration signal data.
The data segments are defined as vibration signal value data arranged in time sequence.
Further, in S300, the method for obtaining the vibration signal correction data by performing data correction on each interference data segment in the vibration signal data includes:
the method for calculating the interference intensity of each interference data segment comprises the following steps of:
The total number of increases between every two adjacent vibration signal values in each vibration signal value recorded in the data segment is UsAdd, and the total number of decreases between every two adjacent vibration signal values is UsSub; then calculate the interference intensity UsStr = UsAdd ++ (UsAdd + UsSub) ×100 for the data segment;
Respectively obtaining stable offset sequences corresponding to the interference data segments according to the interference intensity of the interference data segments, wherein the stable offset sequences are specifically as follows:
taking the acquisition time of the median of each interference data segment as the median time; taking the median time of the current interference data segment as MBT;
Acquiring the median time MAT of the nearest interference data segment before the distance T1; marking an interference data segment corresponding to the MAT as a prepositive interference data segment;
taking a data segment from MAT to MBT in vibration signal data, and calculating the interference intensity of the data segment as the continuous interference intensity of the current interference data segment, wherein the method for calculating the interference intensity of the data segment comprises the following steps:
The total number of increases between every two adjacent vibration signal values in each vibration signal value recorded in the data segment is UsAdd, and the total number of decreases between every two adjacent vibration signal values is UsSub; then calculate the interference intensity UsStr = UsAdd ++ (UsAdd + UsSub) ×100 for the data segment;
If the interference intensity of the current interference data segment is larger than the continuous interference intensity, taking the interference intensity of the current interference data segment as trend intensity, otherwise, taking the average value of the interference intensity of the pre-interference data segment and the interference intensity of the current interference data segment as trend intensity;
Sequencing all vibration signal values in the current interference data segment and the pre-interference data segment according to the acquired time sequence;
Subtracting the vibration signal values with the same serial numbers in the current interference data segment and the pre-interference data segment to obtain difference values, marking the result of multiplying each difference value by the trend intensity value as a stable offset, and sequentially forming each stable offset into a stable offset sequence;
And respectively carrying out data correction on each interference data segment according to the corresponding stable offset sequence to obtain vibration signal correction data.
The specific method for respectively carrying out data correction on each interference data segment according to the corresponding stable offset sequence to obtain vibration signal correction data comprises the following steps: and sequentially adding the stable offset sequence and the numerical value with the same serial number in the corresponding interference data segment to obtain vibration signal correction data.
Example 2
The following technical scheme is added in step S300 on the basis of example 1:
in S300, the method for obtaining vibration signal correction data by performing data correction on each interference data segment in the vibration signal data includes:
respectively calculating the interference intensity of each interference data segment;
The average value of the interference intensity of all the interference data segments is UsStrM, the serial number of the interference data segment is i, and the UsStr (i) is the interference intensity of the ith interference data segment; judging each UsStr (i) in sequence:
If the average vibration signal value of the interference data segment corresponding to UsStr (i) is smaller than the average vibration signal value of the interference data segment corresponding to UsStr (i-1), the value of UsStr (i) is smaller than the value of UsStr (i-1), and if the average vibration signal value of the interference data segment corresponding to UsStr (i) is larger than the average vibration signal value of the interference data segment corresponding to UsStr (i+1), the value of UsStr (i) is larger than the value of UsStr (i+1), and the value of UsStr (i) is larger than UsStrM, then the surge occurs in the interference data segment corresponding to UsStr (i) during acquisition;
J is the serial number of the vibration signal value in the interference data segment corresponding to UsStr (i), and Usi (j) is the vibration signal value with the serial number j in the interference data segment corresponding to UsStr (i);
Calculating a surge offset (j) of each vibration signal value Usi (j) in the interference data segment corresponding to the UsStr (i):
surge(j) = UsStr(i)×|UsiMax-Max(Usi(j), Usi(j+1))|；
wherein UsiMax is the maximum vibration signal value in the interference data segment corresponding to UsStr (i), and the Max function is the maximum value;
sequentially forming each surge offset into a surge offset sequence;
and sequentially adding the values with the same serial numbers in the surge offset sequence and the corresponding interference data segment to obtain vibration signal correction data.
Example 3
The following technical scheme is added in step S300 on the basis of example 1:
in S300, the method for obtaining vibration signal correction data by performing data correction on each interference data segment in the vibration signal data includes:
respectively calculating the interference intensity of each interference data segment;
The average value of the interference intensity of all the interference data segments is UsStrM, the serial number of the interference data segment is i, and the UsStr (i) is the interference intensity of the ith interference data segment; judging each UsStr (i) in sequence:
If the average vibration signal value of the interference data segment corresponding to the UsStr (i) is larger than that of the interference data segment corresponding to UsStr (i-1), the value of the UsStr (i) is larger than that of UsStr (i-1), and if the average vibration signal value of the interference data segment corresponding to the UsStr (i) is smaller than that of the interference data segment corresponding to UsStr (i+1), the value of the UsStr (i) is smaller than that of UsStr (i+1), and the value of the UsStr (i) is smaller than UsStrM, the external oscillation occurs to the interference data segment corresponding to the UsStr (i) during acquisition;
J is the serial number of the vibration signal value in the interference data segment corresponding to UsStr (i), and Usi (j) is the vibration signal value with the serial number j in the interference data segment corresponding to UsStr (i);
if the interference data segment corresponding to UsStr (i) generates external oscillation during acquisition, respectively obtaining oscillation offset sequences corresponding to each interference data segment according to the interference intensity of each interference data segment, specifically:
Calculating oscillation offset shock (j) of each vibration signal value Usi (j) in the interference data segment corresponding to UsStr (i):
shock(j)= UsStr(i)×|UsiMin-Min(Usi(j-1), Usi(j))|；
Wherein UsiMin is the minimum vibration signal value in the corresponding interference data segment of UsStr (i), and the Min function is the minimum value;
Sequentially forming the oscillation offset values into an oscillation offset sequence;
And sequentially adding the values with the same serial numbers in the oscillation offset sequence and the corresponding interference data segment to obtain vibration signal correction data.
The invention also provides an embodiment of a computer system, the embodiment is a turbine equipment vibration data early warning system, as shown in fig. 1, which is a structural diagram of the turbine equipment vibration data early warning system of the invention, the turbine equipment vibration data early warning system of the embodiment comprises: a processor, a memory, and a computer program stored in the memory and executable on the processor, which when executed implements the steps of one of the turbine apparatus vibration data early warning system embodiments described above.
The system comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to run in units of the following system:
The vibration signal acquisition unit is used for acquiring vibration signal data of the turbine equipment;
the interference data scanning unit is used for scanning each interference data segment in the vibration signal data in sequence;
The vibration signal correction unit is used for carrying out data correction on each interference data segment in the vibration signal data to obtain vibration signal correction data;
and the early warning signal pushing unit is used for sending out a fault signal of the gas turbine if the vibration signal correction data is greater than the threshold value.
Wherein the threshold is set to 1.5 times the highest value of the vibration signal values of the nearest 24-hour in-wheel machine.
The turbine equipment vibration data early warning system can be operated in computing equipment such as a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The turbine equipment vibration data early warning system can comprise, but is not limited to, a processor and a memory. It will be appreciated by those skilled in the art that the example is merely an example of a turbine device vibration data pre-warning system, and is not meant to be limiting of a turbine device vibration data pre-warning system, and may include more or fewer components than examples, or may combine certain components, or different components, e.g., the turbine device vibration data pre-warning system may further include input and output devices, network access devices, buses, etc.
The processor may be a central processing unit (CentralProcessingUnit, CPU), or other general purpose processor, digital signal processor (DigitalSignalProcessor, DSP), application specific integrated circuit (ApplicationSpecificIntegratedCircuit, ASIC), field programmable gate array (Field-ProgrammableGateArray, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. The general processor may be a microprocessor or the processor may be any conventional processor, etc., and the processor is a control center of the running system of the vibration data early warning system of the turbine equipment, and various interfaces and lines are used to connect various parts of the running system of the vibration data early warning system of the whole turbine equipment.
The memory may be used to store the computer program and/or module, and the processor may implement various functions of the turbine plant vibration data early warning system by running or executing the computer program and/or module stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart memory card (SMARTMEDIACARD, SMC), secure digital (SecureDigital, SD) card, flash memory card (FLASHCARD), at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.
Although the present invention has been described in considerable detail and with particularity with respect to several described embodiments, it is not intended to be limited to any such detail or embodiment or any particular embodiment so as to effectively cover the intended scope of the invention. Furthermore, the foregoing description of the invention has been presented in its embodiments contemplated by the inventors for the purpose of providing a useful description, and for the purposes of providing a non-essential modification of the invention that may not be presently contemplated, may represent an equivalent modification of the invention.
What is not described in detail in the present specification belongs to the known technology of those skilled in the art.
Claims (9)
1. A method for modifying vibration data of a turbine apparatus, said method comprising the steps of:
S100, acquiring vibration signal data of turbine equipment;
s200, scanning each interference data segment in the vibration signal data in sequence;
S300, carrying out data correction on each interference data segment in the vibration signal data to obtain vibration signal correction data;
In S300, the specific method is as follows:
respectively calculating the interference intensity of each interference data segment;
Respectively obtaining stable offset sequences corresponding to the interference data segments according to the interference intensity of the interference data segments;
And respectively carrying out data correction on each interference data segment according to the corresponding stable offset sequence to obtain vibration signal correction data.
2. The method for correcting vibration data of a turbine apparatus according to claim 1, wherein in S200, the method for sequentially scanning each disturbance data segment in the vibration signal data comprises:
Dividing all vibration signal data into N data segments on average; setting a variable q epsilon [1, N ], and taking a q-th data segment as Vib (q), wherein an average vibration signal in the Vib (q) is MVib (q); wherein N is an integer greater than 3; in the value range of q, sequentially calibrating interference data of each Vib (q), specifically: in each Vib (q), marking the acquisition time of the vibration signal which is larger than the vibration signal in MVib (q) for the first time as right mark time RT according to reverse time sequence, and acquiring the vibration signal as RVib according to RT; sequentially judging each vibration signal in MVib (q) from RT time to reverse time sequence, and marking the acquisition time of the vibration signal with the vibration signal being larger than RVib for the first time as left mark time LT; vibration signals acquired by LT are LVib; taking a data segment formed by all data acquired in a time period between LT and RT in MVib (q) as an interference data segment; and obtaining the interference data segments of each Vib (q) which are the interference data segments in the vibration signal data.
3. The method for correcting vibration data of turbine equipment according to claim 1, wherein the method for calculating the disturbance intensity of the data segment is specifically as follows: the total number of increases between every two adjacent vibration signal values in each vibration signal value recorded in the data segment is UsAdd, and the total number of decreases between every two adjacent vibration signal values is UsSub; the interference strength UsStr = UsAdd ≡ (UsAdd + UsSub) ×100 of the data segment is calculated.
4. The method for correcting vibration data of turbine equipment according to claim 1, wherein the stationary offset sequences corresponding to the respective disturbance data segments are obtained according to the disturbance intensities of the respective disturbance data segments, specifically:
taking the acquisition time of the median of each interference data segment as the median time; taking the median time of the current interference data segment as MBT;
Acquiring the median time MAT of the nearest interference data segment before the distance T1; marking an interference data segment corresponding to the MAT as a prepositive interference data segment;
taking a data segment from MAT to MBT in vibration signal data, and calculating the interference intensity of the data segment as the continuous interference intensity of the current interference data segment;
If the interference intensity of the current interference data segment is larger than the continuous interference intensity, taking the interference intensity of the current interference data segment as trend intensity, otherwise, taking the average value of the interference intensity of the pre-interference data segment and the interference intensity of the current interference data segment as trend intensity;
Sequencing all vibration signal values in the current interference data segment and the pre-interference data segment according to the acquired time sequence;
And subtracting the vibration signal values with the same serial numbers in the current interference data segment and the pre-interference data segment to obtain difference values, marking the result of multiplying each difference value by the trend intensity value as a stable offset, and sequentially forming each stable offset into a stable offset sequence.
5. The method for correcting vibration data of turbine equipment according to claim 1, wherein the specific method for respectively carrying out data correction on each interference data segment according to the corresponding stable offset sequence to obtain vibration signal correction data comprises the following steps: and sequentially adding the stable offset sequence and the numerical value with the same serial number in the corresponding interference data segment to obtain vibration signal correction data.
6. The method for correcting vibration data of a turbine apparatus according to claim 1, wherein in S300, the method for data correcting each disturbance data segment in the vibration signal data to obtain vibration signal correction data includes:
respectively calculating the interference intensity of each interference data segment;
The average value of the interference intensity of all the interference data segments is UsStrM, the serial number of the interference data segment is i, and the UsStr (i) is the interference intensity of the ith interference data segment; judging each UsStr (i) in sequence:
If the average vibration signal value of the interference data segment corresponding to UsStr (i) is smaller than the average vibration signal value of the interference data segment corresponding to UsStr (i-1), the value of UsStr (i) is smaller than the value of UsStr (i-1), and if the average vibration signal value of the interference data segment corresponding to UsStr (i) is larger than the average vibration signal value of the interference data segment corresponding to UsStr (i+1), the value of UsStr (i) is larger than the value of UsStr (i+1), and the value of UsStr (i) is larger than UsStrM, then the surge occurs in the interference data segment corresponding to UsStr (i) during acquisition;
J is the serial number of the vibration signal value in the interference data segment corresponding to UsStr (i), and Usi (j) is the vibration signal value with the serial number j in the interference data segment corresponding to UsStr (i);
Calculating a surge offset (j) of each vibration signal value Usi (j) in the interference data segment corresponding to the UsStr (i):
surge(j) = UsStr(i)×|UsiMax-Max(Usi(j), Usi(j+1))|；
wherein UsiMax is the maximum vibration signal value in the interference data segment corresponding to UsStr (i), and the Max function is the maximum value;
sequentially forming each surge offset into a surge offset sequence;
and sequentially adding the values with the same serial numbers in the surge offset sequence and the corresponding interference data segment to obtain vibration signal correction data.
7. The method for correcting vibration data of a turbine apparatus according to claim 1, wherein in S300, the method for data correcting each disturbance data segment in the vibration signal data to obtain vibration signal correction data includes:
respectively calculating the interference intensity of each interference data segment;
The average value of the interference intensity of all the interference data segments is UsStrM, the serial number of the interference data segment is i, and the UsStr (i) is the interference intensity of the ith interference data segment; judging each UsStr (i) in sequence:
If the average vibration signal value of the interference data segment corresponding to the UsStr (i) is larger than that of the interference data segment corresponding to UsStr (i-1), the value of the UsStr (i) is larger than that of UsStr (i-1), and if the average vibration signal value of the interference data segment corresponding to the UsStr (i) is smaller than that of the interference data segment corresponding to UsStr (i+1), the value of the UsStr (i) is smaller than that of UsStr (i+1), and the value of the UsStr (i) is smaller than UsStrM, the external oscillation occurs to the interference data segment corresponding to the UsStr (i) during acquisition;
J is the serial number of the vibration signal value in the interference data segment corresponding to UsStr (i), and Usi (j) is the vibration signal value with the serial number j in the interference data segment corresponding to UsStr (i);
if the interference data segment corresponding to UsStr (i) generates external oscillation during acquisition, respectively obtaining oscillation offset sequences corresponding to each interference data segment according to the interference intensity of each interference data segment, specifically:
Calculating oscillation offset shock (j) of each vibration signal value Usi (j) in the interference data segment corresponding to UsStr (i):
shock(j)= UsStr(i)×|UsiMin-Min(Usi(j-1), Usi(j))|；
Wherein UsiMin is the minimum vibration signal value in the corresponding interference data segment of UsStr (i), and the Min function is the minimum value;
Sequentially forming the oscillation offset values into an oscillation offset sequence;
And sequentially adding the values with the same serial numbers in the oscillation offset sequence and the corresponding interference data segment to obtain vibration signal correction data.
8. The method for correcting vibration data of a turbine apparatus according to claim 1, wherein the method for acquiring vibration signal data of the turbine apparatus comprises: and acquiring vibration signals of the gas turbine in real time through a Gager vibration meter, an accelerometer or a laser vibration meter.
9. A turbine equipment vibration data pre-warning system, characterized in that the turbine equipment vibration data pre-warning system comprises: a processor, a memory and a computer program stored in the memory and executable on the processor, the processor implementing the steps of a method for correcting vibration data of a turbine plant according to any one of claims 1 to 8 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410584932.9A CN118171048A (en) | 2024-05-13 | 2024-05-13 | Turbine equipment vibration data correction method and early warning system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410584932.9A CN118171048A (en) | 2024-05-13 | 2024-05-13 | Turbine equipment vibration data correction method and early warning system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118171048A true CN118171048A (en) | 2024-06-11 |
Family
ID=91355059
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410584932.9A Pending CN118171048A (en) | 2024-05-13 | 2024-05-13 | Turbine equipment vibration data correction method and early warning system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118171048A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6314083B1 (en) * | 1997-04-04 | 2001-11-06 | Nippon Columbia Co., Ltd. | Frequency control device and method for frequency synchronization with multiplex signal by OFDM, receiving device, and communication device |
| JP2016223970A (en) * | 2015-06-02 | 2016-12-28 | トヨタ自動車株式会社 | Balance correction device |
| CN117213864A (en) * | 2023-09-15 | 2023-12-12 | 中国航发控制系统研究所 | Intelligent detection method and system for lubricating oil metal chip particles suitable for engine |
| CN117743759A (en) * | 2023-12-01 | 2024-03-22 | 国家电网有限公司 | Ceramic post insulator vibration signal denoising method |
-
2024
- 2024-05-13 CN CN202410584932.9A patent/CN118171048A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6314083B1 (en) * | 1997-04-04 | 2001-11-06 | Nippon Columbia Co., Ltd. | Frequency control device and method for frequency synchronization with multiplex signal by OFDM, receiving device, and communication device |
| JP2016223970A (en) * | 2015-06-02 | 2016-12-28 | トヨタ自動車株式会社 | Balance correction device |
| CN117213864A (en) * | 2023-09-15 | 2023-12-12 | 中国航发控制系统研究所 | Intelligent detection method and system for lubricating oil metal chip particles suitable for engine |
| CN117743759A (en) * | 2023-12-01 | 2024-03-22 | 国家电网有限公司 | Ceramic post insulator vibration signal denoising method |
Non-Patent Citations (1)
| Title |
|---|
| 罗绵辉;梁平;: "基于高斯混合模型的汽轮机振动故障诊断", 核动力工程, no. 06, 15 December 2009 (2009-12-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110131193B (en) | Method and system for monitoring surge fault of aircraft engine | |
| CN109667728B (en) | Fault detection method and device for wind generating set rotating speed sensor | |
| CN108361207B (en) | Device and method for vibration monitoring and fault early warning of centrifugal pump | |
| CN110735669B (en) | Method and device for judging rotating stall of aviation gas turbine engine | |
| EP3788328B1 (en) | System and process for pattern matching bearing vibration diagnostics | |
| US20190332102A1 (en) | Machine health monitoring of rotating machinery | |
| CN111027426B (en) | Method for calculating fundamental frequency amplitude of vibration signal of aero-engine | |
| CN112326213B (en) | Abnormal data detection method and device and mechanical fault detection method and device | |
| US10197594B2 (en) | Tachometer signal jitter reduction system and method | |
| CN111504450A (en) | Equipment fault alarm method and device | |
| JP2019100756A (en) | Abnormality detection apparatus, abnormality detection method and abnormality detection computer program | |
| CN112628006A (en) | Engine intake pressure credibility detection method, device, equipment and storage medium | |
| CN112733455A (en) | Correction method, system, device and storage medium of water turbine modeling data | |
| CN117113200B (en) | Rotor fault diagnosis method, device, electronic equipment and medium | |
| CN118171048A (en) | Turbine equipment vibration data correction method and early warning system | |
| CN111351628B (en) | Hypersonic wind tunnel continuous variable attack angle test data processing method | |
| CN116558840B (en) | Method, device, equipment and storage medium for monitoring aero-engine blade | |
| CN111120203B (en) | Method and equipment for determining yaw wind deviation angle of wind generating set | |
| Zhang et al. | Research on the identification of asynchronous vibration parameters of rotating blades based on blade tip timing vibration measurement theory | |
| CN115833836A (en) | Digital signal processing method, system, terminal and storage medium | |
| KR101752298B1 (en) | Health monitoring apparatus based on configuration information and method thereof | |
| CN112487563B (en) | Underwater vehicle propeller damage detection method based on wavelet analysis | |
| CN114692298A (en) | Method for extracting fan structure dynamic characteristics through vibration signals | |
| CN112407321B (en) | Method for generating azimuth angle signal based on helicopter rotor rotation speed | |
| CN112733880A (en) | Aircraft engine fault diagnosis method and system and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |