CN118088666A - Distributed intelligent lubrication monitoring and fault early warning system for wind power gearbox - Google Patents
Distributed intelligent lubrication monitoring and fault early warning system for wind power gearbox Download PDFInfo
- Publication number
- CN118088666A CN118088666A CN202410518630.1A CN202410518630A CN118088666A CN 118088666 A CN118088666 A CN 118088666A CN 202410518630 A CN202410518630 A CN 202410518630A CN 118088666 A CN118088666 A CN 118088666A
- Authority
- CN
- China
- Prior art keywords
- state parameter
- state
- lubrication
- lubricating oil
- early warning
- 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
- 238000005461 lubrication Methods 0.000 title claims abstract description 102
- 238000012544 monitoring process Methods 0.000 title claims abstract description 41
- 239000010687 lubricating oil Substances 0.000 claims abstract description 96
- 238000011156 evaluation Methods 0.000 claims abstract description 32
- 238000012423 maintenance Methods 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000013500 data storage Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims description 23
- 230000001050 lubricating effect Effects 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 17
- 230000002159 abnormal effect Effects 0.000 claims description 16
- 230000005856 abnormality Effects 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 13
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 12
- 239000003921 oil Substances 0.000 claims description 11
- 238000010606 normalization Methods 0.000 claims description 9
- 239000000314 lubricant Substances 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 8
- 238000010586 diagram Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 239000002253 acid Substances 0.000 claims description 6
- 230000015572 biosynthetic process Effects 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 6
- 238000003786 synthesis reaction Methods 0.000 claims description 6
- 238000005299 abrasion Methods 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 5
- 230000004069 differentiation Effects 0.000 claims description 4
- 238000013112 stability test Methods 0.000 claims description 4
- 238000007476 Maximum Likelihood Methods 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 230000006872 improvement Effects 0.000 description 10
- 238000007726 management method Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000010248 power generation Methods 0.000 description 4
- 239000012208 gear oil Substances 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 230000003449 preventive effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000001744 unit root test Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a distributed intelligent lubrication monitoring and fault early warning system of a wind power gear box, which relates to the technical field of wind power gear box monitoring and comprises a data acquisition module, a data storage module, a data processing module, a lubrication monitoring module, a lubrication evaluation module, a fault early warning module and a user interface module, wherein the data acquisition module is used for acquiring state parameters of a lubrication system of the wind power gear box; the data storage module is used for storing the acquired state parameters; the data processing module is used for preprocessing the state parameters; the lubrication monitoring module is used for carrying out risk prompt according to the predicted state parameter value; the lubrication evaluation module is used for comprehensively evaluating the state of the lubricating oil; the fault early warning module is used for early warning in advance. The invention can prompt possible risks in advance, thereby reducing the times of equipment maintenance and replacement, lowering the maintenance cost and equipment failure rate, and facilitating the timely arrangement of maintenance plans by operation and maintenance personnel according to the comprehensive evaluation state of lubricating oil.
Description
Technical Field
The invention relates to the technical field of wind power gear box monitoring, in particular to a distributed intelligent lubrication monitoring and fault early warning system of a wind power gear box.
Background
With the rapid development of wind energy industry, the specific gravity of wind power is continuously increased, the productivity is increasingly increased, the wind power generation system becomes the main power of power generation, and the requirements of wind power generation sets, especially large megawatt wind power generation sets, on equipment reliability, availability and operation and maintenance cost are increasingly high. The wind power gear box is used as a core transmission component of the wind turbine generator, huge torque and dynamic load are born, lubrication of the wind power gear is a basic condition for ensuring normal operation of the gear box, and the lubrication condition directly influences the stability and the service life of the whole system. The oil monitoring is the most direct and effective means for evaluating the lubrication and abrasion states of the gear box, the traditional lubrication management and fault early warning means often rely on a periodic manual inspection and centralized monitoring system, and the early warning is triggered when the monitored data exceeds a threshold value in a comparison mode mainly, so that maintenance personnel are reminded of paying attention, and the early warning mode is simple and quick, but has the problems of lag response, low precision, single consideration factor and the like. Meanwhile, the complicated working condition inside the wind power gear box makes the change of the state of the lubricating oil very sensitive, and any fine lubrication problem can cause serious abrasion and even sudden faults.
The prior China patent with publication number CN114607571A discloses a method and a system for identifying faults of an offshore wind power gear box monitored by a lubrication system, wherein the method comprises the steps of removing and acquiring abnormal data and wind curtailment electricity limiting data in SCADA historical operation data of a wind turbine by utilizing a wind speed power curve relation and a quartile method; extracting gear oil pump outlet pressure and gear box inlet oil pressure in the history normal data after cleaning, expanding the data according to the slope relation of the gear oil pump outlet pressure and the gear box inlet oil pressure, substituting the original data and the expanded data into a single-classification support vector machine model, training and obtaining boundary curves of two parameter distributions of the gear oil pump outlet pressure and the gear box inlet oil pressure under normal conditions; substituting the normal historical data into the trained model, and calculating an upper threshold value and a lower threshold value of the normal data; for the unit data to be tested, obtaining a smoothed output value, and indicating that a fan gear box is normal when an output index is within a threshold range, otherwise, the gear box is abnormal; the invention can find out the fault of the gear box in time and reduce the workload and operation cost of operation and maintenance personnel of the wind power plant.
According to the wind power gear box oil pump inlet and outlet pressure parameter distribution curve training method based on the support vector machine model, the calculated result is compared with the threshold value, and the fault abnormality of the gear box is judged, so that although the gear box fault can be found in time, the gear box fault is judged only through the inlet and outlet pressure of the gear box, the false alarm rate can be increased, and the lubrication state of the lubrication system cannot be comprehensively evaluated.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a distributed intelligent lubrication monitoring and fault early warning system for a wind power gear box.
In order to achieve the above purpose, the present invention provides the following technical solutions: the system comprises a data acquisition module, a data storage module, a data processing module, a lubrication monitoring module, a lubrication evaluation module, a fault early warning module and a user interface module, wherein:
The data acquisition module is used for acquiring state parameters of the lubricating oil system of the wind power gear box in real time through a sensor according to an acquisition mode;
The data storage module is used for integrating, encrypting and storing the lubricating oil state parameters acquired by the data acquisition module according to time sequences;
the data processing module is used for preprocessing the state parameter value of the lubricating oil;
The lubrication monitoring module is used for training a state parameter prediction model according to the preprocessed historical offline lubrication state parameter values, predicting lubrication state parameter values in a future period by inputting real-time acquisition data into the trained data, and carrying out risk prompt according to abnormal data;
the lubrication evaluation module is used for evaluating the current lubrication state through dynamic weight and fuzzy comprehensive evaluation according to the real-time acquired lubrication oil state parameter value under the condition of risk prompt;
the fault early warning module is used for generating early warning information according to the state of the lubricating oil;
The user interface module is used for displaying related early warning information to operation and maintenance personnel in an intuitive mode and simultaneously providing data query and report generation functions.
As a further improvement of the invention, the sensor comprises a temperature sensor, a pressure sensor, an oil product sensor, a moisture sensor and a granularity sensor;
The state parameters of the lubrication system comprise temperature, pressure, flow, viscosity, acid value, moisture and abrasion granularity of the lubricating oil;
Acquiring the latest lubrication system state parameters from each sensor according to preset acquisition frequency;
The controlled collection is carried out according to event triggering, and the event triggering specifically comprises manual collection of staff and increasing of collection frequency when collection state parameters exceed a safety threshold range.
As a further improvement of the present invention, the determination mode of the safety threshold range specifically includes:
s1: forming a time state sequence for the running state parameter value of the lubricating system according to the acquisition time;
s2: drawing probability density distribution diagrams of all state parameters according to the collected state parameter values, and calculating to obtain standard deviation of each state parameter value:
Wherein, Represents the standard deviation of the i-th lubricating oil state parameter value,The jth measurement representing the ith lubricant condition parameter, k being the total number of collected condition parameter values,Is the average value of the i-th lubricating oil state parameter measurement value;
S3: determining a safety threshold according to the standard deviation, wherein the safety threshold comprises a first safety threshold and a second safety threshold which are respectively:
Wherein, A first safety threshold representing an ith state parameter,A second safety threshold representing an ith state parameter,A threshold coefficient for the i-th state parameter; determining the safety threshold range as。
As a further improvement of the present invention, the preprocessing specifically includes dividing the acquired data into intervals, and performing outlier rejection, missing value filling, and data normalization on the state parameter value of each interval, where:
the interval division is carried out by setting time intervals;
abnormal point elimination comprises determining a safety threshold value of each lubricating oil state parameter value of each interval, defining the state parameter value as an abnormal data point when the acquired state parameter value exceeds the safety threshold value of the interval, and replacing the abnormal data point by the average value of the interval;
The filling of the missing values comprises the step of replacing the missing values by the previous state parameter values for the state parameter values missing in the acquisition process;
The data normalization is calculated by a normalization formula.
As a further improvement of the present invention, the lubrication monitoring module specifically further includes: model training unit, real-time prediction unit, risk suggestion unit, wherein:
the model training unit is used for training a state parameter prediction model through the historical offline state parameter values;
The real-time prediction unit is used for inputting the state parameter values of the lubricating oil collected in real time according to the trained state parameter prediction model and outputting the predicted values of each state parameter of the lubricating oil in a future period of time;
the risk prompting unit is used for performing advanced risk prompting according to the state parameter predicted value output by the real-time predicting unit.
As a further improvement of the invention, the state parameter prediction model adopts an ARIMA model, and the training mode specifically comprises the following steps:
s10: constructing a time sequence of each state parameter value of the wind power gear box lubricating oil;
The preprocessed lubrication state parameter values are obtained from the data processing module, and a time sequence of each lubrication state parameter value is respectively established, wherein the time sequence is as follows:
；
Wherein G represents a time sequence of any one of temperature, pressure, flow, viscosity, acid value and granularity of the lubricating oil; ，，，， Lubricating oil state parameter values at times 1,2, … … and n are respectively shown; n is the maximum number of lubricating oil state parameter values in the time series G;
s20: carrying out stability test on each lubricating oil state parameter value, and determining a differential order d;
s30: determining a hysteresis order of the ARIMA model;
S40: estimating parameters of the ARIMA model by adopting a maximum likelihood estimation method, wherein the parameters to be estimated comprise a constant parameter c and an autoregressive parameter Running average parameterError term; Thereby completing the training of the state parameter prediction model.
As a further improvement of the present invention: the prompting mode of the risk prompting unit comprises the following steps:
The total number of state parameters acquired in the prediction time period is N;
when one or more than one predicted value of the lubricant condition parameters exceeds the safety threshold range, the number of abnormal data points is ；
Calculating state parameter anomaly rateConfiguring a state parameter anomaly rate threshold;
When the abnormality rate is greater than or equal to the abnormality rate threshold value, performing risk prompt in advance; and when the abnormality rate is smaller than the abnormality rate threshold, continuously predicting each state parameter predicted value of the lubricating oil through the model.
As a further improvement of the present invention: the lubrication state evaluation method comprises the following steps:
S100: constructing a state parameter set of the index of the lubricating oil comprehensive evaluation system, and marking as The form is as follows:
Wherein, I=1, 2, & i, l is the total number of the lubricating oil state parameters;
s200: constructing a wind power gear box lubrication state grade set, namely Q, in the following form:
Wherein, Indicating a normal state of the device,The state of attention is indicated and,The early warning state is indicated,Indicating the state of vigilance,Representing a fault condition;
S300: calculating dynamic weights of all the lubrication state parameters, and constructing a weight set of the state parameters through the calculated dynamic weights, wherein the weight set is formed as follows:
Wherein, Dynamic weights representing the i-th state parameter; i=1, 2,;
S400: selecting a normal membership function, calculating membership degree of each state parameter to each state grade, and recording as ，，，，Respectively represent state parametersFor state grade~Membership degree of (3); forming a membership degree into a relation fuzzy matrix R;
s500: according to the weight set of each lubrication state parameter and the relation fuzzy matrix, performing matrix synthesis calculation to obtain the comprehensive evaluation grade of the lubrication state, wherein the matrix synthesis calculation formula is as follows:
Wherein, ，To sequentially correspond to the lubrication state grade of the wind power gear boxAnd (3) selecting the lubricating oil state grade with the largest membership as a comprehensive judgment result of the lubricating state of the wind power gear box, and realizing grade division of the current lubricating state.
As a further improvement of the present invention, the dynamic weight is calculated as follows:
The information entropy of each state parameter is calculated, and the calculation formula is as follows:
Wherein, Information entropy representing k state parameter values of the ith state parameter acquisition,For the normalized coefficient to be a function of the normalized coefficient,Is the value of the state parameterIs a normalized value of (2);
The information entropy weight of each state parameter is determined, and the calculation formula is as follows:
Wherein, Information entropy weight of the ith state parameter;
Obtaining dynamic weights through the information entropy weights of each state parameter;
Wherein, Is the dynamic weight of the i-th state parameter,、Representing the maximum and minimum values respectively for which the ith state parameter is capable of allowing the wind power gearbox lubrication system to function properly,Representing the average value of the i-th state parameter measurement,Representing penalty coefficients.
As a further improvement of the invention, the fault early warning module is used for controlling the lubrication state grade to beAnd generating early warning information to staff, wherein the early warning information comprises all collected state parameters and early warning levels of the lubricating oil.
As a further improvement of the invention, the user interface module specifically comprises:
Providing a lubricating oil state parameter instrument panel updated in real time, and displaying trend changes of key parameters in a chart form;
The fault case library records historical fault information, a processing process and effect evaluation and provides historical fault data for operation and maintenance personnel;
and providing self-defined alarm categories and priorities, and carrying out color coding and label differentiation on the early warning information with different degrees.
The invention has the beneficial effects that:
The method has the advantages that the wind power gear box lubricating oil is collected in real time, the wind power gear box lubricating oil is monitored online, the collected historical state parameters are stored according to time sequences, and a state parameter prediction model is built through historical offline state data training, so that the state parameters of the lubricating oil in a period of time in the future can be predicted, the possible risk is prompted in advance, the monitoring of the lubricating oil state is changed into active monitoring and risk early warning, a sufficient time window is provided for operation and maintenance personnel, so that the smooth and safe operation of a wind power gear box lubricating system can be ensured by taking preventive measures in advance for the possible problems, and the unexpected shutdown and maintenance cost is reduced;
According to the risk prompt of future time period, the real-time state parameter value of the wind power gear box is collected, the further evaluation of the wind power gear box lubricating oil is realized by combining a fuzzy comprehensive evaluation mode with dynamic weight, the influence of the state parameter change of lubricating oil on the whole lubricating state can be more accurately quantized, fault early warning is timely sent out according to the lubricating oil state, the service life of the lubricating oil can be prolonged by reasonably and timely monitoring the state parameter of the wind power gear box lubricating oil, the equipment maintenance and replacement times are reduced, the maintenance cost and the equipment fault rate are reduced, and meanwhile, the operation and maintenance personnel can conveniently arrange an overhaul plan in time according to the comprehensive evaluation state of the lubricating oil, so that the equipment lubrication management refinement degree and the fault prevention capability are remarkably improved.
Drawings
FIG. 1 is a schematic diagram of a distributed intelligent lubrication monitoring and fault early warning system for a wind power gearbox;
fig. 2 is a diagram of an interaction process of the distributed intelligent lubrication monitoring and fault early warning system of the wind power gear box.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which can be made by a person skilled in the art without creative efforts, based on the described embodiments of the present invention fall within the protection scope of the present invention.
Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
In order to keep the following description of the embodiments of the present invention clear and concise, the detailed description of known functions and known components thereof have been omitted.
Referring to fig. 1 to 2, a specific embodiment of a distributed intelligent lubrication monitoring and fault early warning system for a wind power gearbox according to the present invention includes a data acquisition module, a data storage module, a data processing module, a lubrication monitoring module, a lubrication evaluation module, a fault early warning module, and a user management module, wherein:
the data acquisition module is used for acquiring state parameters of the wind power gear box lubrication system in real time through the sensor, wherein:
The sensor comprises an oil product sensor, a granularity sensor, a moisture sensor, a temperature sensor and a pressure sensor;
The state parameters of the lubrication system comprise temperature, pressure, flow, viscosity, acid value, moisture and abrasion granularity of the lubricating oil;
The acquisition mode comprises automatic acquisition and controlled acquisition, wherein:
Acquiring the latest lubrication system state parameters from each sensor according to preset acquisition frequency;
The controlled acquisition is carried out according to event triggering, wherein the event triggering specifically comprises manual acquisition of a worker, and the acquisition frequency is increased when the acquisition state parameter exceeds the safety threshold range;
the determination mode of the safety threshold specifically comprises the following steps:
s1: forming a time state sequence for the running state parameter value of the lubricating system according to the acquisition time;
s2: drawing probability density distribution diagrams of all state parameters according to the collected state parameter values, and calculating to obtain standard deviation of each state parameter value:
Wherein, Represents the standard deviation of the i-th lubricating oil state parameter value,The j-th measured value representing the i-th lubricant condition parameter, k being the total amount of the collected condition parameter values,Is the average value of the i-th lubricating oil state parameter measurement value,=；
S3: determining a safety threshold according to the standard deviation, wherein the safety threshold comprises a first safety threshold and a second safety threshold which are respectively:
Wherein, A first safety threshold representing an ith state parameter,A second safety threshold representing an ith state parameter,For the threshold coefficient of the ith state parameter, the threshold coefficient can be set according to the characteristics of the state parameter, and the safety threshold range is determined as。
The data storage module is used for integrating, encrypting and storing the lubricating oil state parameters acquired by the data acquisition module according to time sequences;
the data processing module is used for preprocessing the state parameter values of the lubricating oil, specifically comprises interval division, and performs outlier rejection, missing value filling and data normalization on the state parameter values of each interval, wherein:
the interval division is carried out by setting time intervals;
Determining a safety threshold value for each lubricant status parameter value for each interval;
defining the state parameter value as an abnormal data point when the acquired state parameter value exceeds the safety threshold value of the interval, and replacing the abnormal data point by the average value of the interval;
The filling of the missing values comprises the step of replacing the missing values by the previous state parameter values for the state parameter values missing in the acquisition process;
Data normalization is calculated by the following formula:
Wherein, Representing the normalized value of the i-th state parameter,Representing the initial acquisition value of the i-th state parameter,Represents the standard value of each state parameter,AndRespectively representing the maximum value and the minimum value of each state parameter;
The lubrication monitoring module is used for training a state parameter prediction model according to the preprocessed historical offline lubrication state parameter value, predicting the lubrication state parameter value for a period of time in the future by inputting real-time acquisition data into the trained data, and specifically further comprises a model training unit, a real-time prediction unit and a risk prompting unit, wherein:
the model training unit is used for training a state parameter prediction model through a historical offline state parameter value, the state parameter prediction model is an ARIMA model, and the training mode specifically comprises the following steps of:
s10: constructing a time sequence of each state parameter value of the wind power gear box lubricating oil;
The preprocessed lubrication state parameter values are obtained from the data processing module, and a time sequence of each lubrication state parameter value is respectively established, wherein the time sequence is as follows:
；
Wherein G represents a time sequence of any one of temperature, pressure, flow, viscosity, acid value and granularity of the lubricating oil; ，，，， Lubricating oil state parameter values at times 1,2, … … and n are respectively shown; n is the maximum number of lubricating oil state parameter values in the time series G;
s20: carrying out stability test on each lubricating oil state parameter value, and determining a differential order d;
adopting ADF unit root test, if the time sequence G of the lubricant state parameter value is not stable, carrying out first-order difference on G, and recording as delta G; ADF unit root test is carried out on the delta G, if the delta G is not stable, differential order is sequentially increased, and stability test is carried out; finding the minimum difference order d of the time sequence stability after difference, wherein d is a non-negative integer; taking the stable lubricating oil state parameter value time sequence after d times of differentiation as a data set for training an ARIMA model, and recording as G, the form is as follows:
；
Wherein, ，，……，Respectively represent，，，D times of differentiation is carried out to obtain a value;
s30: determining a hysteresis order of the ARIMA model;
determining an autoregressive hysteresis order p and a moving average hysteresis order q of the ARIMA model based on the autocorrelation diagrams and the partial autocorrelation diagrams; drawing time series G's autocorrelation and partial autocorrelation; the autocorrelation graph drops sharply after a hysteresis order p and truncates at p; the partial autocorrelation map PACF image drops sharply after the lag order q and truncates at q;
s40: performing parameter estimation on the ARIMA model;
The equation for the ARIMA model is as follows:
；
Wherein, Is a time sequenceThe t element of g; c is a constant parameter; the value range of i is 1,2, … … and p as autoregressive parameters; The value range of j is 1,2, … … and q as the moving average parameter; ，……，， Is an error term in which ，……，Represented by a residual error, which is represented by a residual error,Is a parameter to be estimated;
estimating parameters of ARIMA model by adopting a maximum likelihood estimation method, wherein the parameters to be estimated comprise constant parameter c and autoregressive parameters Running average parameterError term; Thereby completing the training of the state parameter prediction model.
The real-time prediction unit is used for inputting the state parameter values of the lubricating oil collected in real time according to the trained state parameter prediction model and outputting the predicted values of each state parameter of the lubricating oil in a future period of time;
The risk prompting unit is used for performing advanced risk prompting according to the state parameter predicted value output by the real-time predicting unit, and the specific risk prompting mode comprises the following steps:
The total number of state parameters acquired in the prediction time period is N;
when one or more than one predicted value of the lubricant condition parameters exceeds the safety threshold range, the number of abnormal data points is ；
Calculating state parameter anomaly rateConfiguring a state parameter anomaly rate threshold;
When the abnormality rate is greater than or equal to the abnormality rate threshold value, performing risk prompt in advance; and when the abnormality rate is smaller than the abnormality rate threshold, continuously predicting each state parameter predicted value of the lubricating oil through the model.
The future period of each state parameter of the lubricating oil is predicted in advance through the constructed state parameter prediction model, the monitoring evolution of the state of the lubricating oil is changed into active monitoring and risk early warning, and sufficient time windows are provided for operation and maintenance personnel, so that the smooth and safe operation of a lubrication system of the wind power gear box can be ensured by taking preventive measures in advance aiming at possible problems, and the unexpected shutdown and maintenance cost is reduced.
The state evaluation module is used for evaluating the current lubrication state according to the real-time collected lubrication oil state parameter value through dynamic weight and fuzzy comprehensive evaluation under the condition that an advanced risk prompt exists, and the lubrication state evaluation mode comprises the following steps:
S100: constructing a state parameter set of the index of the lubricating oil comprehensive evaluation system, and marking as The form is as follows:
Wherein, I=1, 2, & i, l is the total number of the lubricating oil state parameters;
s200: constructing a wind power gear box lubrication state grade set, namely Q, in the following form:
Wherein, Indicating a normal state of the device,The state of attention is indicated and,The early warning state is indicated,Indicating the state of vigilance,Representing a fault condition;
S300: calculating dynamic weights of all the lubrication state parameters, and constructing a weight set of the state parameters through the calculated dynamic weights, wherein the weight set is formed as follows:
Wherein, Dynamic weights representing the i-th state parameter; i=1, 2,;
The dynamic weight calculates the dynamic weight of each state parameter through an entropy weight method and a variable weight theory, and the different weights are distributed for different state parameters to represent the difference degree of the different state parameters affecting the lubrication state, so that the deviation degree of each lubricating oil state parameter can be highlighted, and the assessment capability of the lubrication state is improved, and the specific calculation mode is as follows:
calculating the information entropy of each state parameter, wherein the calculation formula is as follows;
Wherein, Information entropy representing k state parameter values of the ith state parameter acquisition,For the normalized coefficient to be a function of the normalized coefficient,Is the value of the state parameterIs used for the normalization of the values of (c),；
The information entropy weight of each state parameter is determined, and the calculation formula is as follows:
Wherein, Information entropy weight of the ith state parameter;
Obtaining dynamic weights through the information entropy weights of each state parameter;
Wherein, Is the dynamic weight of the i-th state parameter,Indicating the maximum value that the ith state parameter can allow the wind power gearbox lubrication system to function properly,Indicating the minimum value that the ith state parameter can allow the wind power gearbox lubrication system to function properly,Representing the average value of the i-th state parameter measurement,Expressed as penalty coefficients, determined based on the characteristics and properties of the respective state parameters, whenThe larger the penalty effect is, the more obvious the penalty effect is, and the state result of the lubricating oil is changed when the slight variation exists.
S400: selecting a normal membership function, calculating membership degree of each state parameter to each state grade, and recording as，，，，Respectively represent state parametersFor state grade~Membership degree of (3);
Membership degree is formed into a relation fuzzy matrix R in the following form:
R=
s500: according to the weight set of each lubrication state parameter and the relation fuzzy matrix, performing matrix synthesis calculation to obtain the comprehensive evaluation grade of the lubrication state, wherein the matrix synthesis calculation formula is as follows:
Wherein, ，To sequentially correspond to the lubrication state gradesAnd (3) selecting the lubricating oil state grade with the largest membership as a comprehensive judgment result of the lubricating state of the wind power gear box, and realizing grade division of the current lubricating state.
If the state gradeAnd the state parameters of the lubricating oil of the wind power gear box are in a normal operation interval, so that the lubricating system of the wind power gear box can normally operate for a long time, and maintenance can be temporarily omitted.
If the state gradeAnd the condition that the lubricating oil state parameters of the wind power gear box have obvious fluctuation is indicated, but the continuous operation of the lubricating system of the wind power gear box is not influenced, and the maintenance is arranged according to the normal period.
If the state gradeThe lubricating oil state parameter of the wind power gear box indicates that the individual state parameter possibly exceeds the normal operation interval, and the wind power gear box still can continue to operate, but the maintenance period is shortened.
If the state gradeAnd the condition that a plurality of state parameters exist in the lubricating oil state parameters of the wind power gear box exceeds a normal operation interval and the lubricating system of the wind power gear box is influenced to play a role, and maintenance should be arranged as soon as possible.
If the state gradeAnd the condition parameters of the lubricating oil of the wind power gear box are obviously beyond the normal operation interval, so that the normal operation of the wind power gear box is affected, and the power failure maintenance is required to be immediately arranged.
The real-time state parameters acquired in the time period of generating the risk prompt are subjected to fuzzy comprehensive evaluation through the lubrication evaluation module, different dynamic weights are given to each state parameter, the influence of the change of each state parameter of the lubricating oil on the overall performance of the lubricating oil can be accurately quantified, the risk prompt is timely sent out, the refinement degree and the fault prevention capability of the lubrication management of the wind power gear box are greatly improved, and the fault identification rate is reduced.
The fault early warning module is used for generating corresponding early warning information according to the state of the lubricating oil, and when the lubrication state grade isAnd early warning information is generated for operation and maintenance personnel, wherein the early warning information specifically comprises: and analyzing various collected state parameters, early warning levels and possible faults of the lubricating oil.
The user interface module is used for displaying related early warning information to operation and maintenance personnel in an intuitive mode, and simultaneously provides data query and report generation functions, and specifically comprises the following steps:
Providing a lubricating oil state parameter instrument panel updated in real time, displaying trend changes of key parameters in a chart form, and facilitating operation and maintenance personnel to monitor the overall condition of a wind power gear box lubricating system in real time;
providing self-defined alarm categories and priorities, and carrying out color coding and label distinguishing on the early warning information with different degrees so as to be convenient for rapidly responding to emergency;
A fault case library is established, historical fault information, a processing process and effect evaluation are recorded, historical fault data are provided for operation and maintenance personnel, and fault processing efficiency is improved.
Working principle and effect:
According to the method, the wind power gear box lubricating oil is collected in real time, the wind power gear box lubricating oil is monitored online, the collected historical state parameters are stored according to a time sequence, a state parameter prediction model is built through historical offline state data training, and the state parameters of the lubricating oil in a future period can be predicted, so that possible risks are prompted in advance, the monitoring of the lubricating oil state is changed into active monitoring and risk early warning, a sufficient time window is provided for operation and maintenance personnel, so that smooth and safe operation of a wind power gear box lubricating system can be ensured by taking preventive measures in advance for possible problems, and unexpected shutdown and maintenance cost are reduced;
According to the risk prompt of future time period, the real-time state parameter value of the wind power gear box is collected, the further evaluation of the wind power gear box lubricating oil is realized by combining a fuzzy comprehensive evaluation mode with dynamic weight, the influence of the state parameter change of lubricating oil on the whole lubricating state can be more accurately quantized, fault early warning is timely sent out according to the lubricating oil state, the service life of the lubricating oil can be prolonged by reasonably and timely monitoring the state parameter of the wind power gear box lubricating oil, the equipment maintenance and replacement times are reduced, the maintenance cost and the equipment fault rate are reduced, and meanwhile, the operation and maintenance personnel can conveniently arrange an overhaul plan in time according to the comprehensive evaluation state of the lubricating oil, so that the equipment lubrication management refinement degree and the fault prevention capability are remarkably improved.
Furthermore, although exemplary embodiments have been described in the present disclosure, the scope thereof includes any and all embodiments having equivalent elements, modifications, omissions, combinations (e.g., of the various embodiments across), adaptations or alterations as would be appreciated by those in the art. The elements in the claims are to be construed broadly based on the language employed in the claims and are not limited to examples described in the present specification or during the practice of the application, which examples are to be construed as non-exclusive. It is intended, therefore, that the specification and examples be considered as exemplary only, with a true scope and spirit being indicated by the following claims and their full scope of equivalents.
The above description is intended to be illustrative and not restrictive. For example, the above-described examples (or one or more aspects thereof) may be used in combination with each other. For example, other embodiments may be used by those of ordinary skill in the art upon reading the above description. In addition, in the above detailed description, various features may be grouped together to streamline the invention. This is not to be interpreted as an intention that the disclosed features not being claimed are essential to any claim. Rather, inventive subject matter may lie in less than all features of a particular disclosed embodiment. Thus, the following claims are hereby incorporated into the detailed description as examples or embodiments, with each claim standing on its own as a separate embodiment, and it is contemplated that these embodiments may be combined with one another in various combinations or permutations. The scope of the invention should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.
The above embodiments are only exemplary embodiments of the present invention and are not intended to limit the present invention, the scope of which is defined by the claims. Various modifications and equivalent arrangements of this invention will occur to those skilled in the art, and are intended to be within the spirit and scope of the invention.
Claims (11)
1. A distributed intelligent lubrication monitoring and fault early warning system for a wind power gear box is characterized in that: the system comprises a data acquisition module, a data storage module, a data processing module, a lubrication monitoring module, a lubrication evaluation module, a fault early warning module and a user interface module, wherein:
The data acquisition module is used for acquiring state parameters of the lubricating oil system of the wind power gear box in real time through a sensor according to an acquisition mode;
The data storage module is used for integrating, encrypting and storing the lubricating oil state parameters acquired by the data acquisition module according to time sequences;
the data processing module is used for preprocessing the state parameter value of the lubricating oil;
The lubrication monitoring module is used for training a state parameter prediction model according to the preprocessed historical offline lubrication state parameter values, predicting lubrication state parameter values in a future period by inputting real-time acquisition data into the trained data, and carrying out risk prompt according to abnormal data;
the lubrication evaluation module is used for evaluating the current lubrication state through dynamic weight and fuzzy comprehensive evaluation according to the real-time acquired lubrication oil state parameter value under the condition of risk prompt;
the fault early warning module is used for generating early warning information according to the state of the lubricating oil;
The user interface module is used for displaying related early warning information to operation and maintenance personnel in an intuitive mode and simultaneously providing data query and report generation functions.
2. The distributed intelligent lubrication monitoring and fault early warning system for a wind power gearbox according to claim 1, wherein the system is characterized in that: the sensor comprises a temperature sensor, a pressure sensor, an oil product sensor, a moisture sensor and a granularity sensor;
The state parameters of the lubrication system comprise temperature, pressure, flow, viscosity, acid value, moisture and abrasion granularity of the lubricating oil;
Acquiring the latest lubrication system state parameters from each sensor according to preset acquisition frequency;
The controlled collection is carried out according to event triggering, and the event triggering specifically comprises manual collection of staff and increasing of collection frequency when collection state parameters exceed a safety threshold range.
3. The distributed intelligent lubrication monitoring and fault early warning system for a wind power gearbox according to claim 2, wherein the system is characterized in that: the determination mode of the safety threshold range specifically comprises the following steps:
s1: forming a time state sequence for the running state parameter value of the lubricating system according to the acquisition time;
s2: drawing probability density distribution diagrams of all state parameters according to the collected state parameter values, and calculating to obtain standard deviation of each state parameter value:
；
Wherein, Represents the standard deviation of the i-th lubricating oil state parameter value,/>The j-th measurement value representing the i-th lubricant condition parameter, k being the total number of collected condition parameter values,/>Is the average value of the i-th lubricating oil state parameter measurement value;
S3: determining a safety threshold according to the standard deviation, wherein the safety threshold comprises a first safety threshold and a second safety threshold which are respectively:
；
；
Wherein, A first safety threshold value representing an ith state parameter,/>A second safety threshold value representing an ith state parameter,/>A threshold coefficient for the i-th state parameter; determining the safety threshold range as/>。
4. A distributed intelligent lubrication monitoring and fault early warning system for a wind power gearbox according to claim 3, wherein: the preprocessing specifically comprises interval division of acquired data, and abnormal point elimination, missing value filling and data normalization of state parameter values of each interval, wherein:
the interval division is carried out by setting time intervals;
abnormal point elimination comprises determining a safety threshold value of each lubricating oil state parameter value of each interval, defining the state parameter value as an abnormal data point when the acquired state parameter value exceeds the safety threshold value of the interval, and replacing the abnormal data point by the average value of the interval;
The filling of the missing values comprises the step of replacing the missing values by the previous state parameter values for the state parameter values missing in the acquisition process;
The data normalization is calculated by a normalization formula.
5. The distributed intelligent lubrication monitoring and fault early warning system for a wind power gearbox according to claim 4, wherein the system is characterized in that: the lubrication monitoring module specifically further comprises: model training unit, real-time prediction unit, risk suggestion unit, wherein:
the model training unit is used for training a state parameter prediction model through the historical offline state parameter values;
The real-time prediction unit is used for inputting the state parameter values of the lubricating oil collected in real time according to the trained state parameter prediction model and outputting the predicted values of each state parameter of the lubricating oil in a future period of time;
the risk prompting unit is used for performing advanced risk prompting according to the state parameter predicted value output by the real-time predicting unit.
6. The distributed intelligent lubrication monitoring and fault early warning system for a wind power gearbox according to claim 5, wherein the system is characterized in that: the state parameter prediction model adopts an ARIMA model, and the training mode specifically comprises the following steps:
s10: constructing a time sequence of each state parameter value of the wind power gear box lubricating oil;
The preprocessed lubrication state parameter values are obtained from the data processing module, and a time sequence of each lubrication state parameter value is respectively established, wherein the time sequence is as follows:
；
Wherein G represents a time sequence of any one of temperature, pressure, flow, viscosity, acid value and granularity of the lubricating oil; ，/>，/>，/>，/> Lubricating oil state parameter values at times 1,2, … … and n are respectively shown; n is the maximum number of lubricating oil state parameter values in the time series G;
s20: carrying out stability test on each lubricating oil state parameter value, and determining a differential order d;
s30: determining a hysteresis order of the ARIMA model;
S40: estimating parameters of the ARIMA model by adopting a maximum likelihood estimation method, wherein the parameters to be estimated comprise a constant parameter c and an autoregressive parameter Moving average parameter/>Error term/>; Thereby completing the training of the state parameter prediction model.
7. The distributed intelligent lubrication monitoring and fault early warning system for a wind power gearbox of claim 6, wherein: the prompting mode of the risk prompting unit comprises the following steps:
The total number of state parameters acquired in the prediction time period is N;
when one or more than one predicted value of the lubricant condition parameters exceeds the safety threshold range, the number of abnormal data points is ；
Calculating state parameter anomaly rateConfiguring a state parameter anomaly rate threshold;
When the abnormality rate is greater than or equal to the abnormality rate threshold value, performing risk prompt in advance; and when the abnormality rate is smaller than the abnormality rate threshold, continuously predicting each state parameter predicted value of the lubricating oil through the model.
8. The distributed intelligent lubrication monitoring and fault early warning system for a wind power gearbox according to claim 7, wherein: the lubrication state evaluation method comprises the following steps:
S100: constructing a state parameter set of the index of the lubricating oil comprehensive evaluation system, and marking as The form is as follows:
；
Wherein, I=1, 2, & i, l is the total number of the lubricating oil state parameters;
s200: constructing a wind power gear box lubrication state grade set, namely Q, in the following form:
；
Wherein, Indicates a normal state,/>Representing the attention status,/>Representing early warning state,/>Representing an alert state,/>Representing a fault condition;
S300: calculating dynamic weights of all the lubrication state parameters, and constructing a weight set of the state parameters through the calculated dynamic weights, wherein the weight set is formed as follows:
；
Wherein, Dynamic weights representing the i-th state parameter; i=1, 2,;
S400: selecting a normal membership function, calculating membership degree of each state parameter to each state grade, and recording as ，/>，，/>，/>Respectively represent state parameters/>For state class/>~/>Membership degree of (3); forming a membership degree into a relation fuzzy matrix R;
s500: according to the weight set of each lubrication state parameter and the relation fuzzy matrix, performing matrix synthesis calculation to obtain the comprehensive evaluation grade of the lubrication state, wherein the matrix synthesis calculation formula is as follows:
；
Wherein, ，/>To correspond to the lubrication state grade/>, of the wind power gear box in sequenceAnd (3) selecting the lubricating oil state grade with the largest membership as a comprehensive judgment result of the lubricating state of the wind power gear box, and realizing grade division of the current lubricating state.
9. The distributed intelligent lubrication monitoring and fault early warning system for a wind power gearbox of claim 8, wherein: the dynamic weight is calculated as follows:
The information entropy of each state parameter is calculated, and the calculation formula is as follows:
；
Wherein, Information entropy representing k state parameter values acquired by ith state parameter,/>For the normalized coefficient to be a function of the normalized coefficient,Is the state parameter value/>Is a normalized value of (2);
The information entropy weight of each state parameter is determined, and the calculation formula is as follows:
；
Wherein, Information entropy weight of the ith state parameter;
Obtaining dynamic weights through the information entropy weights of each state parameter;
；
Wherein, Dynamic weighting for the i-th state parameter,/>、/>Respectively representing the maximum value and the minimum value of the ith state parameter which can allow the normal operation of the lubrication system of the wind power gear box,/>Represents the average of the i < th > state parameter measurements,/>Representing penalty coefficients.
10. The distributed intelligent lubrication monitoring and fault early warning system for a wind power gearbox according to claim 9, wherein: the fault early warning module is used for controlling the lubrication state grade to beAnd generating early warning information to staff, wherein the early warning information comprises all collected state parameters and early warning levels of the lubricating oil.
11. The distributed intelligent lubrication monitoring and fault early warning system for a wind power gearbox of claim 10, wherein: the user interface module specifically includes:
Providing a lubricating oil state parameter instrument panel updated in real time, and displaying trend changes of key parameters in a chart form;
The fault case library records historical fault information, a processing process and effect evaluation and provides historical fault data for operation and maintenance personnel;
and providing self-defined alarm categories and priorities, and carrying out color coding and label differentiation on the early warning information with different degrees.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410518630.1A CN118088666A (en) | 2024-04-28 | 2024-04-28 | Distributed intelligent lubrication monitoring and fault early warning system for wind power gearbox |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410518630.1A CN118088666A (en) | 2024-04-28 | 2024-04-28 | Distributed intelligent lubrication monitoring and fault early warning system for wind power gearbox |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118088666A true CN118088666A (en) | 2024-05-28 |
Family
ID=91153616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410518630.1A Pending CN118088666A (en) | 2024-04-28 | 2024-04-28 | Distributed intelligent lubrication monitoring and fault early warning system for wind power gearbox |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118088666A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111537219A (en) * | 2020-01-20 | 2020-08-14 | 内蒙古工业大学 | Fan gearbox performance detection and health assessment method based on temperature parameters |
| CN113742932A (en) * | 2021-09-13 | 2021-12-03 | 华能新能源股份有限公司 | Method for predicting and diagnosing faults of gearbox of wind turbine generator |
| CN113916531A (en) * | 2021-10-26 | 2022-01-11 | 辽宁科技学院 | Fault diagnosis and prediction system for on-line monitoring of vibration and oil of nuclear power gearbox |
| US20220065142A1 (en) * | 2020-09-02 | 2022-03-03 | Caterpillar Energy Solutions Gmbh | Engine Lubrication Oil Consumption and Condition Monitoring |
| CN114777003A (en) * | 2022-05-30 | 2022-07-22 | 华能重庆珞璜发电有限责任公司 | Power plant auxiliary engine lubricating oil monitoring system and method |
| CN114813105A (en) * | 2022-04-11 | 2022-07-29 | 西安热工研究院有限公司 | Gear box fault early warning method and system based on working condition similarity evaluation |
-
2024
- 2024-04-28 CN CN202410518630.1A patent/CN118088666A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111537219A (en) * | 2020-01-20 | 2020-08-14 | 内蒙古工业大学 | Fan gearbox performance detection and health assessment method based on temperature parameters |
| US20220065142A1 (en) * | 2020-09-02 | 2022-03-03 | Caterpillar Energy Solutions Gmbh | Engine Lubrication Oil Consumption and Condition Monitoring |
| CN113742932A (en) * | 2021-09-13 | 2021-12-03 | 华能新能源股份有限公司 | Method for predicting and diagnosing faults of gearbox of wind turbine generator |
| CN113916531A (en) * | 2021-10-26 | 2022-01-11 | 辽宁科技学院 | Fault diagnosis and prediction system for on-line monitoring of vibration and oil of nuclear power gearbox |
| CN114813105A (en) * | 2022-04-11 | 2022-07-29 | 西安热工研究院有限公司 | Gear box fault early warning method and system based on working condition similarity evaluation |
| CN114777003A (en) * | 2022-05-30 | 2022-07-22 | 华能重庆珞璜发电有限责任公司 | Power plant auxiliary engine lubricating oil monitoring system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110414155B (en) | Fan component temperature abnormity detection and alarm method with single measuring point | |
| CN111597682B (en) | Method for predicting remaining life of bearing of gearbox of wind turbine | |
| CN110926809B (en) | Big data analysis-based wind turbine generator transmission chain fault early warning method | |
| CN107291991B (en) | Early defect early warning method for wind turbine generator based on dynamic network sign | |
| CN107153929A (en) | Gearbox of wind turbine fault monitoring method and system based on deep neural network | |
| CN110763997A (en) | Early fault early warning method for synchronous motor stator | |
| CN111648992B (en) | Gas turbine compressor fault identification early warning method | |
| CN112487910A (en) | Fault early warning method and system for nuclear turbine system | |
| CN110969185A (en) | Equipment abnormal state detection method based on data reconstruction | |
| CN113036913B (en) | Method and device for monitoring state of comprehensive energy equipment | |
| CN111415070A (en) | Wind turbine generator gearbox oil temperature over-temperature fault early warning method based on SCADA data | |
| CN111103137A (en) | Wind turbine gearbox fault diagnosis method based on deep neural network | |
| CN116914917A (en) | Big data-based monitoring and management system for operation state of power distribution cabinet | |
| CN112926656A (en) | Method, system and equipment for predicting state of circulating water pump of nuclear power plant | |
| CN117151684A (en) | Wind power fan data analysis early warning method, system, device and readable storage medium | |
| CN110209144A (en) | Two layers of real-time monitoring and alarm source tracing method based on sound collaboration variance analysis | |
| CN112633614A (en) | Real-time fault degree diagnosis system and method based on feature extraction | |
| CN111723449A (en) | Performance degradation evaluation method for constant deceleration braking system of mine hoist | |
| CN108416386A (en) | A kind of method and system judged extremely for Hydropower Unit bearing temperature | |
| De Oliveira-Filho et al. | Condition monitoring of wind turbine main bearing using SCADA data and informed by the principle of energy conservation | |
| CN111563685B (en) | Power generation equipment state early warning method based on auto-associative kernel regression algorithm | |
| CN112308391A (en) | Real-time monitoring and anomaly detection method for equipment state based on neural network | |
| CN111192163B (en) | Generator reliability medium-short term prediction method based on wind turbine generator operating data | |
| CN117634179A (en) | Wind turbine generator health assessment method based on multi-source heterogeneous data model | |
| CN113158535A (en) | Wind turbine generator main bearing temperature prediction method based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |