CN113982850B - Fan comprehensive health analysis method and system integrating high-low frequency signals - Google Patents
Fan comprehensive health analysis method and system integrating high-low frequency signals Download PDFInfo
- Publication number
- CN113982850B CN113982850B CN202111060718.6A CN202111060718A CN113982850B CN 113982850 B CN113982850 B CN 113982850B CN 202111060718 A CN202111060718 A CN 202111060718A CN 113982850 B CN113982850 B CN 113982850B
- Authority
- CN
- China
- Prior art keywords
- monitoring data
- fan
- frequency monitoring
- frequency
- low
- 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.)
- Active
Links
- 230000036541 health Effects 0.000 title claims abstract description 64
- 238000004458 analytical method Methods 0.000 title claims abstract description 26
- 238000012544 monitoring process Methods 0.000 claims abstract description 201
- 238000000034 method Methods 0.000 claims abstract description 45
- 230000005856 abnormality Effects 0.000 claims abstract description 29
- 238000012502 risk assessment Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 12
- 238000001303 quality assessment method Methods 0.000 claims abstract description 8
- 238000012216 screening Methods 0.000 claims abstract description 7
- 238000001514 detection method Methods 0.000 claims description 24
- 230000007246 mechanism Effects 0.000 claims description 20
- 238000013441 quality evaluation Methods 0.000 claims description 17
- 230000000007 visual effect Effects 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 238000010586 diagram Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 2
- 230000005477 standard model Effects 0.000 claims description 2
- 239000000758 substrate Substances 0.000 claims 2
- 238000003745 diagnosis Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 3
- 230000005802 health problem Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000012847 principal component analysis method Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005461 lubrication Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B10/00—Integration of renewable energy sources in buildings
- Y02B10/30—Wind power
Abstract
The invention relates to a fan comprehensive health analysis method and system integrating high-low frequency signals, wherein the method comprises the following steps: collecting low-frequency monitoring data and high-frequency monitoring data, performing time alignment and quality assessment, and eliminating data which do not accord with quality indexes; screening out monitoring data under a preset working condition; carrying out windowing treatment on the monitoring data; extracting features of the monitoring data under each time window, combining the extracted features to obtain a feature subset of the fan under the corresponding time window, and forming a feature set; model training is carried out according to the feature set, and a fan abnormity monitoring model is obtained; and inputting the feature set corresponding to the current monitoring data of the fan into the model to obtain a current health risk assessment value of the fan, and determining whether the fan is in fault currently according to the health risk assessment value. The invention makes full use of the data foundation, builds the model and detects the abnormality, and meets the requirement of users on the fan to realize real system-level health analysis.
Description
Technical Field
The invention relates to the technical field of fan fault detection, in particular to a fan comprehensive health analysis method and system integrating high-frequency signals and low-frequency signals.
Background
Along with the reduction of the cost of the sensor and the continuous improvement of calculation force, the health status monitoring and operation and maintenance of the wind driven generator are also developed from pure digitization to intelligent. The wind turbine generator system fault early warning system monitors blades, a transmission mechanism, a generator, an electric control system and the like of a fan by using SCADA low-frequency signals (the sampling rate of the SCADA low-frequency signals is usually at most 1 Hz) and CMS high-frequency vibration signals (the frequency of the CMS high-frequency vibration signals is at least 10 KHz) which are widely adopted in the wind power industry at present. However, the functions provided by the two types of signal monitoring systems are relatively independent, the existing fan fault early warning system rarely has a fan health assessment function of combining the two types of signal monitoring systems into a user, and the existing fan fault early warning system cannot completely meet the requirement of the user on realizing real system-level intelligent health analysis of the wind driven generator.
Disclosure of Invention
In order to solve the technical problems or at least partially solve the technical problems, the invention provides a fan comprehensive health analysis method and system integrating high-frequency signals and low-frequency signals.
In a first aspect, the present invention provides a fan comprehensive health analysis method for fusing high-low frequency signals, including:
collecting low-frequency monitoring data and high-frequency monitoring data of a fan in a historical time period, performing time alignment on the low-frequency monitoring data and the high-frequency monitoring data, performing quality assessment on the low-frequency monitoring data and the high-frequency monitoring data, and eliminating data which do not accord with quality indexes;
screening out monitoring data under a preset working condition from the low-frequency monitoring data and the high-frequency monitoring data which are reserved after the quality evaluation; carrying out window division processing on the monitoring data to obtain monitoring data under a plurality of time windows; respectively extracting features of the low-frequency monitoring data and the high-frequency monitoring data under each time window, combining the extracted features to obtain feature subsets of the fan under the corresponding time windows, and forming feature sets of the feature subsets under the time windows according to time sequences;
training a model according to the feature set to obtain a fan abnormity monitoring model; and inputting the characteristic sets corresponding to the current low-frequency monitoring data and the high-frequency monitoring data of the fan into the fan abnormal monitoring model to obtain the current health risk assessment value of the fan, and determining whether the fan is in fault or not according to the health risk assessment value.
In a second aspect, the present invention provides a fan integrated health analysis system that fuses high and low frequency signals, comprising:
the data acquisition module is used for acquiring low-frequency monitoring data and high-frequency monitoring data of the fan in a historical time period, carrying out time alignment on the low-frequency monitoring data and the high-frequency monitoring data, carrying out quality assessment on the low-frequency monitoring data and the high-frequency monitoring data, and eliminating data which do not accord with quality indexes;
the characteristic extraction module is used for screening out monitoring data under a preset working condition from the low-frequency monitoring data and the high-frequency monitoring data which are reserved after the quality evaluation; carrying out window division processing on the monitoring data to obtain monitoring data under a plurality of time windows; respectively extracting features of the low-frequency monitoring data and the high-frequency monitoring data under each time window, combining the extracted features to obtain feature subsets of the fan under the corresponding time windows, and forming feature sets of the feature subsets under the time windows according to time sequences;
the health analysis module is used for carrying out model training according to the feature set to obtain a fan abnormality monitoring model; and inputting the characteristic sets corresponding to the current low-frequency monitoring data and the high-frequency monitoring data of the fan into the fan abnormal monitoring model to obtain the current health risk assessment value of the fan, and determining whether the fan is in fault or not according to the health risk assessment value.
According to the fan comprehensive health analysis method and system integrating high-low frequency signals, low-frequency monitoring data and high-frequency monitoring data of a fan in a historical time period are collected, time alignment and quality evaluation are carried out on the monitoring data, monitoring data under a preset working condition are screened out, window division processing is carried out on the monitoring data, feature extraction is carried out on the monitoring data under each time window, the extracted features are combined to obtain feature subsets of the fan under the corresponding time windows, and the feature subsets under each time window are formed into feature sets according to time sequence; and training the fan abnormality monitoring model according to the feature set, and further carrying out fault identification monitoring by using the trained fan abnormality monitoring model. According to the method, data quality evaluation is introduced, so that modeling usability of the data can be ensured, and after the low-frequency monitoring data and the high-frequency monitoring data are fused, unsupervised learning is performed, a fault sample is not required, and only explicit and sufficient fan state data are required. The method has the advantages that the data base possibly existing in the existing wind driven generator is fully utilized, the abnormality detection and early warning are carried out aiming at the health problem of the wind driven generator, and the requirement of a user on realizing real system-level intelligent health analysis of the wind driven generator can be met.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, and it will be obvious to a person skilled in the art that other drawings can be obtained from these drawings without inventive effort.
Fig. 1 to 3 are schematic flow diagrams of a fan comprehensive health analysis method for fusing high-low frequency signals;
FIG. 4 is a block diagram of a fan integrated health assessment system of a wind farm booster station monitoring center of the present invention;
FIG. 5 is a block diagram of a fan integrated health assessment system of a group or provincial level central control center of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In a first aspect, the present invention provides a method for analyzing fan integrated health by integrating high-frequency signals and low-frequency signals, as shown in fig. 1 to 3, the method includes:
s110, collecting low-frequency monitoring data and high-frequency monitoring data of a fan in a historical time period, performing time alignment on the low-frequency monitoring data and the high-frequency monitoring data, performing quality assessment on the low-frequency monitoring data and the high-frequency monitoring data, and eliminating data which do not accord with quality indexes;
in a specific implementation, the collecting the low-frequency monitoring data and the high-frequency monitoring data of the fan in the historical time period may include: acquiring low frequency monitoring data of the fan from a data acquisition and monitoring control system (supervisory control and data acquisition, SCADA), wherein the low frequency monitoring data comprises at least one of fan bearing temperature, fan rotating speed, cabin temperature, wind speed and wind power; the high frequency monitoring data of the fan is obtained from a state monitoring system (i.e. condition monitoring system, CMS), and comprises a bearing high frequency vibration signal of the fan.
The sampling frequency of the low-frequency monitoring data does not exceed 1HZ, and the frequency of the high-frequency monitoring data does not fall below 10KHZ.
The monitoring data acquisition is mainly completed by a data acquisition module and is mainly responsible for acquiring, accessing, transmitting and storing low-frequency monitoring and high-frequency monitoring data of the wind driven generator. Since the low frequency monitoring data and the high frequency monitoring data are mainly collected in an independent mode in the fan, the time stamps are not aligned, and the data collection module also needs to time align the low frequency monitoring data and the high frequency monitoring data.
The purpose of performing quality evaluation on the low-frequency monitoring data and the high-frequency monitoring data is to detect whether data which do not meet the quality requirements exist in the detection data or not, and then delete the data which do not meet the quality requirements. The quality evaluation of the monitoring data can be realized by a data quality evaluation module, and is mainly responsible for respectively judging and evaluating the quality of the high-frequency monitoring data and the low-frequency monitoring data so as to ensure that the modeled data are available. For low frequency monitoring data, a general data quality check term for time series is generally employed. For high-frequency monitoring data, since such data has a strong mechanism analysis value, such as vibration, audio and the like, a mechanism data quality detection item which is suitable for the signal characteristics is generally adopted.
In a specific implementation, the quality evaluation method for the low-frequency monitoring data may include: at least one of a singular value detection method, a missing point proportion detection method and a data overrun detection method. The singular value in the low-frequency detection data can be detected and removed by the singular value detection method. The missing point proportion detection method can detect the proportion of missing data, the whole data is available when the proportion is not higher than a threshold value, and the whole data is unavailable when the proportion is higher than the threshold value. The data overrun detection method is to detect whether the data exceeds the upper limit value and the lower limit value in the detected data and reject the data exceeding the upper limit value and the lower limit value. The purpose of this is to reject some data that often fluctuate because of external interference factor, avoid these data to influence the fault identification rate of accuracy.
In a specific implementation, the method for evaluating the quality of the high-frequency detection data may include: at least one of a validity checking method, a mean shift checking method, a positive-negative point proportion checking method and a continuous value proportion checking method. The detection methods are also used for detecting and deleting the abnormal fluctuation data in the monitoring data, and are not described here.
S120, screening out monitoring data under a preset working condition from the low-frequency monitoring data and the high-frequency monitoring data which are reserved after the quality evaluation; carrying out window division processing on the monitoring data to obtain monitoring data under a plurality of time windows; respectively extracting features of the low-frequency monitoring data and the high-frequency monitoring data under each time window, combining the extracted features to obtain feature subsets of the fan under the corresponding time windows, and forming feature sets of the feature subsets under the time windows according to time sequences;
the preset working condition can be the working condition of the fan except the shutdown working condition and the power limiting working condition. That is, the preset operating condition is an operating condition under non-human interference. Under the preset working condition, the fan can run healthily, and also can malfunction. The monitoring data under the shutdown working condition and the electricity limiting working condition are deleted, and only the monitoring data under the preset working condition are reserved for subsequent abnormality detection. The monitoring data under the preset working conditions can be screened out according to the conditions of wind speed, generator rotation speed and the like, and the data are suitable for modeling.
In particular implementations, a data wash may be performed prior to windowing the data. In the windowing, the low-frequency monitoring data and the high-frequency monitoring data may be subjected to windowing, for example, data slicing is performed every 1 hour, so as to implement windowing. In the data of the time window every 1 hour, the statistic characteristics of the SCADA data are calculated. In the data of the time window every 1 hour, the time-frequency domain characteristics of the CMS data are calculated.
That is, the feature of extracting the low frequency monitoring data under each time window may include: and extracting statistic characteristics of the low-frequency monitoring data under each time window, wherein the statistic characteristics comprise at least one of a mean value, a variance, a maximum value, a minimum value and a peak value. The feature of extracting the high-frequency monitoring data under each time window comprises the following steps: and extracting time-frequency domain mechanism characteristics of the high-frequency monitoring data under each time window, wherein the time-frequency domain mechanism characteristics comprise at least one of frequency domain energy size, a passband effective value and kurtosis corresponding to fault characteristic frequency. The feature extraction can be realized by a feature preparation module.
And (3) obtaining statistic characteristics and time-frequency domain mechanism characteristics under each time window, combining the statistic characteristics and the time-frequency domain mechanism characteristics to form a characteristic subset under one time window, and forming a characteristic set according to a time sequence by the characteristic subset under each time window.
It is understood that the statistic feature is a statistical feature, and the time-frequency domain mechanism feature is a mechanism feature, and the statistic feature and the mechanism feature are provided under each time window.
S130, training a model according to the feature set to obtain a fan abnormity monitoring model; and inputting the characteristic sets corresponding to the current low-frequency monitoring data and the high-frequency monitoring data of the fan into the fan abnormal monitoring model to obtain the current health risk assessment value of the fan, and determining whether the fan is in fault or not according to the health risk assessment value.
The method comprises the steps of taking the current monitoring data as a time window for windowing, extracting feature subsets in each time window, and combining the feature subsets in each time window to form the current corresponding feature set. The current feature set is identical to the formation of the feature set over the historical period.
As shown in fig. 2 and 3, in S130, an abnormality detection module may be specifically used to implement abnormality detection on the fan. The abnormality detection module is used for evaluating the abnormality risk of the fan and pushing the abnormality risk of the fan to the visual interface for display. The basic idea of anomaly detection is: based on the baseline model of the health state, the degree of deviation between the current feature set and the baseline model is compared, so that the change of the health state of the current fan is measured. Such a degree of offset may be obtained based on a method (e.g., a residual method, a similarity calculation, etc.) capable of quantifying the difference between distributions represented by the data. The health risk assessment value may be a statistic that may be indicative of the overall health level of the blower, or may be a value between 0 and 100 after normalization.
The feature set corresponding to the historical time period is used for training a fan abnormality monitoring model, and the fan abnormality monitoring model can be constructed by adopting a principal component analysis method.
In particular implementations, the health risk assessment process of the fan anomaly monitoring model may include:
and the fan abnormity monitoring model determines the deviation degree between the current feature set and the baseline model, and determines the current health risk assessment value of the fan according to the deviation degree.
The baseline model is a health standard model constructed by adopting a main component analysis method and adopting a health characteristic set of a fan.
It is understood that both the fan anomaly monitoring model and the baseline model may be constructed using a principal component analysis method. Training data adopted by the fan abnormality monitoring model is obtained by training monitoring data in a historical time period, and the fan may be in fault in the time period. The baseline model is obtained by training health data in a time period, and provides a standard line of health. And comparing the current feature set with the healthy standard line to obtain the offset degree between the current feature set and the healthy standard line, and further determining the current health risk assessment value of the fan according to the offset degree, and further considering that the fan is in fault currently when the health risk assessment value is higher than a preset threshold value.
When the fan anomaly monitoring model operates online, the model projects in a principal component space according to the current feature set and the baseline model, and takes Hotelling's T (namely Hotelling statistics) or SPE (namely q statistics) as an anomaly risk assessment value.
In specific implementation, the method provided by the invention can further comprise the following steps: when determining that the fan is in failure currently, calculating contribution degree of each feature in the feature set to residual errors, taking the feature with the largest contribution degree as a root cause of the current health risk of the fan, and displaying the health risk evaluation value and the root cause on a visual interface.
The residual is data representing the offset degree between the current feature set and the healthy standard line, the contribution of some features to the residual is larger, the contribution of some features to the residual is smaller, the contribution degree of each feature in the feature set to the residual is calculated, and then the components with faults can be judged according to the order of the contribution degree from large to small, for example, if the related feature of the generator bearing is ranked at the top, the abnormality is likely to be caused by the generator bearing, and the feature is taken as the root cause of the fan fault. In order to enable the user to intuitively know the current condition of the fan, the health risk assessment value and the root cause of the fan can be displayed on a visual interface.
In specific implementation, the method provided by the invention can further comprise the following steps: and comparing the mechanism characteristic corresponding to the characteristic with the largest contribution degree with a plurality of preset fault level thresholds, determining the current fault level of the fan, and providing a maintenance decision according to the fault level.
That is, when a fault occurs, the mechanism characteristic (for example, the outer ring fault frequency of the bearing) corresponding to the characteristic with the largest contribution degree (for example, the related characteristic of the generator bearing) is screened, the fault level corresponding to the mechanism characteristic, namely, the fault level of the current bearing abnormality of the fan, is determined according to the mechanism characteristic and a plurality of preset fault level thresholds which are set in advance, and then a corresponding maintenance decision (for example, lubrication or replacement) can be provided according to the fault level, and the maintenance decision is displayed on a visual interface.
In specific implementation, the method provided by the invention can further comprise the following steps: and when determining that the fan is in fault currently, displaying the low-frequency monitoring data and the high-frequency monitoring data in a time window corresponding to the current fault on the visual interface, and displaying a contrast scatter diagram of the projection of the feature set input in a principal component space and the projection of the health feature set in the principal component space on the visual interface.
Referring to fig. 2 and 3, an anomaly diagnosis module may be employed to enable diagnosis of anomalies. The abnormality diagnosis module is mainly responsible for carrying out root cause analysis aiming at abnormal conditions, helping a user to quickly locate possible causes of the abnormality, judging the fault level and supporting maintenance decision. Root cause analysis is determined mainly by calculating the contribution of the abnormality. The main idea of calculating the contribution degree is generally as follows: the degree of anomaly (i.e., degree of distribution shift) is calculated as a measure of the weight of each type of feature. The definition of the fault level needs to firstly screen out the characteristic with large abnormal contribution degree, and then define the fault level according to the degree of the corresponding mechanism characteristic, such as vibration intensity, bearing vibration signal, harmonic magnitude of a certain fault frequency and the like. And judging the overall fault severity of the fan according to the set threshold rule.
The data acquisition module, the data quality evaluation module, the feature preparation module, the abnormality detection module and the abnormality diagnosis module can be integrated and borne on a special server, and the server can be flexibly and selectively deployed in a wind field booster station monitoring center, a provincial level centralized control center or a group monitoring center. See fig. 4 and 5. For example, the modules are carried on a special server of a monitoring center of a wind farm booster station, and the server performs data transmission with a low-frequency Scada data server and a transmission chain CMS system data server through a switch and a Modbus protocol.
That is, when a fault occurs, the monitoring data in the time window with the current fault, namely the original data, is displayed on the visual interface, and then the contrast scatter diagram of the projection of the current feature set and the health feature set on the principal component space is displayed on the visual interface, so that a user can more intuitively know the difference between the current condition and the health condition of the fan.
The main innovation point of the invention is that: (1) Introducing data quality assessment into the method, so that modeling usability of the data can be ensured; (2) After the low-frequency monitoring data and the high-frequency monitoring data are fused, non-supervision learning is carried out, a fault sample is not required, and only definite and sufficient fan state data are required; (3) When the fan is abnormal, determining a root cause by adopting the contribution degree of the characteristics to the residual error; (4) And (5) auxiliary judging the fault grade according to the degree of the mechanism characteristic.
The invention aims to provide a fan health assessment method integrating low-frequency monitoring data and high-frequency monitoring data of a wind driven generator, which fully utilizes the data base possibly existing in the current wind driven generator, carries out abnormality detection and early warning on fan health problems, and carries out preliminary diagnosis on abnormal root causes by integrating mechanism characteristics and statistical characteristics, thereby rapidly positioning the problems.
The invention provides a fan comprehensive health analysis method for fusing high-low frequency signals, which is characterized in that low-frequency monitoring data and high-frequency monitoring data of a fan in a historical time period are collected, time alignment and quality evaluation are carried out on the monitoring data, monitoring data under a preset working condition are screened out, window division processing is carried out on the monitoring data, feature extraction is carried out on the monitoring data under each time window, extracted features are combined to obtain feature subsets of the fan under corresponding time windows, and the feature subsets under each time window are formed into feature sets according to time sequence; and training the fan abnormality monitoring model according to the feature set, and further carrying out fault identification monitoring by using the trained fan abnormality monitoring model. According to the method, data quality evaluation is introduced, so that modeling usability of the data can be ensured, and after the low-frequency monitoring data and the high-frequency monitoring data are fused, unsupervised learning is performed, a fault sample is not required, and only explicit and sufficient fan state data are required. The method has the advantages that the data base possibly existing in the existing wind driven generator is fully utilized, the abnormality detection and early warning are carried out aiming at the health problem of the wind driven generator, and the requirement of a user on realizing real system-level intelligent health analysis of the wind driven generator can be met.
In a second aspect, the present invention provides a fan integrated health analysis system that fuses high and low frequency signals, comprising:
the data acquisition module is used for acquiring low-frequency monitoring data and high-frequency monitoring data of the fan in a historical time period, carrying out time alignment on the low-frequency monitoring data and the high-frequency monitoring data, carrying out quality assessment on the low-frequency monitoring data and the high-frequency monitoring data, and eliminating data which do not accord with quality indexes;
the characteristic extraction module is used for screening out monitoring data under a preset working condition from the low-frequency monitoring data and the high-frequency monitoring data which are reserved after the quality evaluation; carrying out window division processing on the monitoring data to obtain monitoring data under a plurality of time windows; respectively extracting features of the low-frequency monitoring data and the high-frequency monitoring data under each time window, combining the extracted features to obtain feature subsets of the fan under the corresponding time windows, and forming feature sets of the feature subsets under each time window according to time sequences;
and the health analysis module is used for inputting the characteristic set into a fan abnormality monitoring model to obtain a current health risk assessment value of the fan, and determining whether the fan is in fault currently according to the health risk assessment value.
It will be appreciated that the second aspect provides a system in which reference is made to corresponding parts of the first aspect for examples, embodiments, advantages and the like.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present invention and the scope of the claims, which are to be protected by the present invention.
Claims (10)
1. A fan comprehensive health analysis method integrating high-low frequency signals is characterized by comprising the following steps:
collecting low-frequency monitoring data and high-frequency monitoring data of a fan in a historical time period, performing time alignment on the low-frequency monitoring data and the high-frequency monitoring data, performing quality assessment on the low-frequency monitoring data and the high-frequency monitoring data, and eliminating data which do not accord with quality indexes;
screening out monitoring data under a preset working condition from the low-frequency monitoring data and the high-frequency monitoring data which are reserved after the quality evaluation; carrying out window division processing on the monitoring data to obtain monitoring data under a plurality of time windows; respectively extracting features of the low-frequency monitoring data and the high-frequency monitoring data under each time window, combining the extracted features to obtain feature subsets of the fan under the corresponding time windows, and forming feature sets of the feature subsets under the time windows according to time sequences;
training a model according to the feature set to obtain a fan abnormity monitoring model; and inputting the characteristic sets corresponding to the current low-frequency monitoring data and the high-frequency monitoring data of the fan into the fan abnormal monitoring model to obtain the current health risk assessment value of the fan, and determining whether the fan is in fault or not according to the health risk assessment value.
2. The method as recited in claim 1, further comprising:
when determining that the fan is in fault currently, calculating the contribution degree of each feature in the current feature set to the residual error, taking the feature with the largest contribution degree as the root cause of the current health risk of the fan, and displaying the health risk evaluation value and the root cause on a visual interface.
3. The method as recited in claim 2, further comprising:
and comparing the mechanism characteristic corresponding to the characteristic with the largest contribution degree with a plurality of preset fault level thresholds, determining the current fault level of the fan, and providing a maintenance decision according to the fault level.
4. The method of claim 1, wherein the health risk assessment process of the fan anomaly monitoring model comprises:
determining the current deviation degree between the characteristic set and a baseline model by the fan abnormality monitoring model, and determining a current health risk assessment value of the fan according to the deviation degree; the baseline model is a health standard model constructed by adopting a main component analysis method for a health feature set of the fan, and the fan abnormality monitoring model is constructed by adopting the main component analysis method.
5. The method as recited in claim 4, further comprising:
when the fan is determined to be faulty currently, displaying the low-frequency monitoring data and the high-frequency monitoring data in a time window corresponding to the current fault on a visual interface, and displaying a contrast scatter diagram of the projection of the current feature set in a principal component space and the projection of the health feature set in the principal component space on the visual interface.
6. The method of claim 1, wherein the step of determining the position of the substrate comprises,
the quality evaluation method for the low-frequency monitoring data comprises the following steps: at least one of a singular value detection method, a missing point proportion detection method and a data overrun detection method;
the quality evaluation method for the high-frequency monitoring data comprises the following steps: at least one of a validity checking method, a mean shift checking method, a positive-negative point proportion checking method and a continuous value proportion checking method.
7. The method of claim 1, wherein the preset operating condition is an operating condition of the blower other than a shutdown operating condition and a power limit operating condition.
8. The method of claim 1, wherein the step of determining the position of the substrate comprises,
the feature of extracting the low frequency monitoring data under each time window comprises: extracting statistic characteristics of the low-frequency monitoring data under each time window, wherein the statistic characteristics comprise at least one of mean value, variance, maximum value, minimum value and peak value;
the feature of extracting the high-frequency monitoring data under each time window comprises the following steps: and extracting time-frequency domain mechanism characteristics of the high-frequency monitoring data under each time window, wherein the time-frequency domain mechanism characteristics comprise at least one of frequency domain energy size, a passband effective value and kurtosis corresponding to fault characteristic frequency.
9. The method of claim 1, wherein the collecting low frequency monitoring data and high frequency monitoring data of the blower over the historical period of time comprises:
acquiring low-frequency monitoring data of the fan from a data acquisition and monitoring control system, wherein the low-frequency monitoring data comprises at least one of fan bearing temperature, fan rotating speed, cabin temperature, wind speed and wind power; and acquiring high-frequency monitoring data of the fan from a state monitoring system, wherein the high-frequency monitoring data comprises a bearing high-frequency vibration signal of the fan.
10. A fan comprehensive health analysis system integrating high-low frequency signals is characterized by comprising:
the data acquisition module is used for acquiring low-frequency monitoring data and high-frequency monitoring data of the fan in a historical time period, carrying out time alignment on the low-frequency monitoring data and the high-frequency monitoring data, carrying out quality assessment on the low-frequency monitoring data and the high-frequency monitoring data, and eliminating data which do not accord with quality indexes;
the characteristic extraction module is used for screening out monitoring data under a preset working condition from the low-frequency monitoring data and the high-frequency monitoring data which are reserved after the quality evaluation; carrying out window division processing on the monitoring data to obtain monitoring data under a plurality of time windows; respectively extracting features of the low-frequency monitoring data and the high-frequency monitoring data under each time window, combining the extracted features to obtain feature subsets of the fan under the corresponding time windows, and forming feature sets of the feature subsets under the time windows according to time sequences;
the health analysis module is used for carrying out model training according to the feature set to obtain a fan abnormality monitoring model; and inputting the characteristic sets corresponding to the current low-frequency monitoring data and the high-frequency monitoring data of the fan into the fan abnormal monitoring model to obtain the current health risk assessment value of the fan, and determining whether the fan is in fault or not according to the health risk assessment value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111060718.6A CN113982850B (en) | 2021-09-10 | 2021-09-10 | Fan comprehensive health analysis method and system integrating high-low frequency signals |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111060718.6A CN113982850B (en) | 2021-09-10 | 2021-09-10 | Fan comprehensive health analysis method and system integrating high-low frequency signals |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113982850A CN113982850A (en) | 2022-01-28 |
CN113982850B true CN113982850B (en) | 2023-11-10 |
Family
ID=79735594
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111060718.6A Active CN113982850B (en) | 2021-09-10 | 2021-09-10 | Fan comprehensive health analysis method and system integrating high-low frequency signals |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113982850B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114996923A (en) * | 2022-05-24 | 2022-09-02 | 烟台杰瑞石油装备技术有限公司 | Equipment fault detection method based on baseline data space |
CN115013261B (en) * | 2022-08-08 | 2022-12-06 | 国网浙江省电力有限公司舟山供电公司 | State monitoring method and system for offshore wind farm |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102768115A (en) * | 2012-06-27 | 2012-11-07 | 华北电力大学 | Method for dynamically monitoring health status of wind turbine gearbox in real time |
CN104503399A (en) * | 2014-12-09 | 2015-04-08 | 华电电力科学研究院 | Group stage wind power generator set state monitoring and fault diagnosis platform |
WO2016086360A1 (en) * | 2014-12-02 | 2016-06-09 | Abb Technology Ltd | Wind farm condition monitoring method and system |
CN106662072A (en) * | 2014-11-18 | 2017-05-10 | Abb瑞士股份有限公司 | Wind turbine condition monitoring method and system |
CN110219816A (en) * | 2018-03-02 | 2019-09-10 | 国家能源投资集团有限责任公司 | Method and system for Fault Diagnosis of Fan |
CN110688617A (en) * | 2019-10-09 | 2020-01-14 | 北京天泽智云科技有限公司 | Fan vibration abnormity detection method and device |
CN112177863A (en) * | 2020-09-07 | 2021-01-05 | 上海电气风电集团股份有限公司 | Vibration monitoring system, wind power generation system and wind power plant |
CN112727702A (en) * | 2020-12-11 | 2021-04-30 | 中国大唐集团科学技术研究院有限公司火力发电技术研究院 | Health management and fault early warning method for wind turbine generator |
CN112945531A (en) * | 2021-02-03 | 2021-06-11 | 西人马(西安)测控科技有限公司 | Method, device and equipment for detecting cracks of fan blade and computer storage medium |
-
2021
- 2021-09-10 CN CN202111060718.6A patent/CN113982850B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102768115A (en) * | 2012-06-27 | 2012-11-07 | 华北电力大学 | Method for dynamically monitoring health status of wind turbine gearbox in real time |
CN106662072A (en) * | 2014-11-18 | 2017-05-10 | Abb瑞士股份有限公司 | Wind turbine condition monitoring method and system |
WO2016086360A1 (en) * | 2014-12-02 | 2016-06-09 | Abb Technology Ltd | Wind farm condition monitoring method and system |
CN104503399A (en) * | 2014-12-09 | 2015-04-08 | 华电电力科学研究院 | Group stage wind power generator set state monitoring and fault diagnosis platform |
CN110219816A (en) * | 2018-03-02 | 2019-09-10 | 国家能源投资集团有限责任公司 | Method and system for Fault Diagnosis of Fan |
CN110688617A (en) * | 2019-10-09 | 2020-01-14 | 北京天泽智云科技有限公司 | Fan vibration abnormity detection method and device |
CN112177863A (en) * | 2020-09-07 | 2021-01-05 | 上海电气风电集团股份有限公司 | Vibration monitoring system, wind power generation system and wind power plant |
CN112727702A (en) * | 2020-12-11 | 2021-04-30 | 中国大唐集团科学技术研究院有限公司火力发电技术研究院 | Health management and fault early warning method for wind turbine generator |
CN112945531A (en) * | 2021-02-03 | 2021-06-11 | 西人马(西安)测控科技有限公司 | Method, device and equipment for detecting cracks of fan blade and computer storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN113982850A (en) | 2022-01-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109524139B (en) | Real-time equipment performance monitoring method based on equipment working condition change | |
CN113982850B (en) | Fan comprehensive health analysis method and system integrating high-low frequency signals | |
EP2950177A1 (en) | Asset condition monitoring | |
CN112925279A (en) | Fault comprehensive analysis system based on MES system | |
CN111336100A (en) | Water pump fault diagnosis system | |
CN111209934B (en) | Fan fault pre-alarm method and system | |
US20230162484A1 (en) | Apparatus and method for generating learning data for artificial intelligence model | |
CN112286771B (en) | Alarm method for monitoring global resources | |
CN114781476B (en) | System and method for analyzing faults of measuring equipment | |
CN110580492A (en) | Track circuit fault precursor discovery method based on small fluctuation detection | |
CN116383633A (en) | Method and system for detecting faults of machine-made sand vibrating screen through multi-factor comprehensive analysis | |
KR20210006832A (en) | Method and apparatus for machine fault diagnosis | |
CN113849774A (en) | Intelligent equipment maintenance platform based on life analysis and health monitoring | |
CN110687851A (en) | Terminal operation monitoring system and method | |
CN116384977A (en) | Underground coal mine operation and maintenance method and system based on big data analysis and self-diagnosis | |
CN111224468B (en) | Photovoltaic equipment safe operation and maintenance platform based on cloud computing | |
CN113487189A (en) | Petrochemical equipment fault probability risk assessment system and assessment method | |
CN108199482B (en) | Maintenance prompting method and device | |
CN113129160A (en) | Electric power communication network inspection method based on equipment state perception and intellectualization | |
CN116484263B (en) | Intelligent self-service machine fault detection system and method | |
CN107765123A (en) | Detected rule update method and Electrical Safety monitoring system | |
US11047833B2 (en) | Method for automatic determination of trend in graphic analysis of turbomachines | |
CN115982665B (en) | Quality anomaly auditing method and system for water turbine measurement data | |
CN117589444B (en) | Wind driven generator gear box fault diagnosis method based on federal learning | |
CN113225219B (en) | Heartbeat data acquisition and storage method for server monitoring |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |