CN111860599A - Method for diagnosing machine pump fault - Google Patents
Method for diagnosing machine pump fault Download PDFInfo
- Publication number
- CN111860599A CN111860599A CN202010563986.9A CN202010563986A CN111860599A CN 111860599 A CN111860599 A CN 111860599A CN 202010563986 A CN202010563986 A CN 202010563986A CN 111860599 A CN111860599 A CN 111860599A
- Authority
- CN
- China
- Prior art keywords
- parameters
- signal
- multidimensional
- characteristic parameters
- equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 239000011159 matrix material Substances 0.000 claims abstract description 15
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 238000000605 extraction Methods 0.000 claims description 7
- 230000009467 reduction Effects 0.000 claims description 5
- 238000001228 spectrum Methods 0.000 claims description 5
- 230000035939 shock Effects 0.000 claims description 2
- 238000007619 statistical method Methods 0.000 claims description 2
- 238000005065 mining Methods 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 claims 1
- 238000003745 diagnosis Methods 0.000 abstract description 21
- 230000000694 effects Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a method for diagnosing a pump fault, which comprises the following steps: obtaining characteristic parameters of the pump equipment; forming a multi-dimensional parameter matrix by the characteristic parameters; extracting multi-dimensional parameters of signals in the multi-dimensional parameter matrix; processing the signal multidimensional parameters by using a KNN algorithm so as to judge the type of the signal multidimensional parameters and identify the equipment state; the fault diagnosis method based on the multidimensional parameters and the KNN can well achieve the diagnosis fault classification effect of test data, so that the real-time data of the pump can be analyzed by the method in the subsequent fault diagnosis work, and qualitative fault diagnosis can be carried out on pump equipment.
Description
Technical Field
The invention relates to the field of equipment fault diagnosis, in particular to a fault diagnosis method based on multidimensional parameters and KNN.
Background
After obtaining parameters such as thermal performance, vibration and noise signals of the pump equipment, the parameters are comprehensively considered to form a multi-dimensional parameter matrix, dimension reduction is performed on the parameter characteristics by using a dimension reduction method to obtain a characteristic distribution diagram, and it can be seen from the diagram that the parameter characteristics of the equipment are concentrated in a certain space in the same state, but the indexing ratio is higher in different states.
Disclosure of Invention
In order to solve the problems in the prior art, the embodiment of the invention provides a fault diagnosis method based on multidimensional parameters and KNN. The technical scheme is as follows:
in one aspect, a fault diagnosis method based on multidimensional parameters and KNN is provided, which includes:
obtaining characteristic parameters of the pump equipment;
forming a multi-dimensional parameter matrix by the characteristic parameters;
extracting multi-dimensional parameters of signals in the multi-dimensional parameter matrix;
and processing the signal multidimensional parameters by using a KNN algorithm, thereby judging the type of the signal multidimensional parameters and identifying the equipment state.
Further, the characteristic parameters include: time domain characteristics, frequency domain characteristics, thermal performance parameters, and noise signal parameters.
Further, the extracting the multi-dimensional parameters of the signals in the multi-dimensional parameter matrix comprises:
extracting time domain features; extracting frequency domain features; and extracting thermal performance parameters and noise signal parameters.
Further, the extracting the multidimensional parameters of the signal in the multidimensional parameter matrix specifically includes:
and reducing the dimension of the multi-dimensional parameter matrix characteristic by adopting a dimension reduction method to obtain the characteristic distribution of the pump equipment under normal and fault conditions.
Further, the step of processing the signal multidimensional parameter by using the KNN algorithm to judge the type of the signal multidimensional parameter to identify the device state specifically includes:
the KNN algorithm can be used for identifying the distance between the data and a certain characteristic, so that the type of the data is judged to identify the state of the equipment.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
the fault diagnosis method based on the multidimensional parameters and the KNN can well achieve the diagnosis fault classification effect of test data, so that the real-time data of the pump can be analyzed by the method in the subsequent fault diagnosis work, and qualitative fault diagnosis can be carried out on pump equipment.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flow chart of a method for diagnosing a pump failure according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
The invention provides a fault diagnosis method based on multidimensional parameters and KNN, and the fault diagnosis method is shown in figure 1 and comprises the following steps:
s100: obtaining characteristic parameters of the pump equipment;
s200: forming a multi-dimensional parameter matrix by the characteristic parameters;
s300: extracting multi-dimensional parameters of signals in the multi-dimensional parameter matrix;
s400: and processing the signal multidimensional parameters by using a KNN algorithm, thereby judging the type of the signal multidimensional parameters and identifying the equipment state.
In this embodiment, kNN (K-nearest neighbor, neighbor algorithm), or K nearest neighbor classification algorithm, belongs to one of the data mining classification techniques. By K nearest neighbors is meant the K nearest neighbors, i.e. each sample can be represented by its nearest K neighbors.
The core idea of the KNN algorithm is that if most of K nearest neighbor samples of a sample in the feature space belong to a certain class, the sample is also judged to belong to the class and has the characteristics of the sample on the class. The method only determines the category of the sample to be classified according to the category of the nearest sample or samples in the determination of classification decision. The KNN method is only related to a very small number of adjacent samples when the classification is decided. Because the KNN method mainly depends on the limited adjacent samples around, but not on the method of distinguishing the class domain to determine the class, for the sample set to be classified with more cross or overlap of the class domain, the KNN method can effectively classify and can perform qualitative and quantitative diagnosis on the data.
Further, the characteristic parameters include: time domain characteristics, frequency domain characteristics, thermal performance parameters, and noise signal parameters.
Further, the extracting the multi-dimensional parameters of the signals in the multi-dimensional parameter matrix comprises:
extracting time domain features; extracting frequency domain features; and extracting thermal performance parameters and noise signal parameters.
Specifically, the extraction of the multidimensional parameters of the signal comprises the following steps:
(1) time domain feature extraction
And various characteristic parameters obtained by performing statistical analysis on the time domain signals are the time domain characteristic parameters of the signals. The time domain characteristic parameters commonly used in the current fault diagnosis comprise dimensional parameters and dimensionless parameters, wherein the dimensional parameters mainly comprise kurtosis, root mean square values, maximum values, minimum values, peak-to-peak values, standard deviations, rectification average values and the like, and the dimensionless parameters mainly comprise wave type factors, pulse factors, kurtosis factors and the like. The root mean square value can reflect the signal energy and is sensitive to vibration waveforms generated by faults such as surface cracks in equipment parts; the kurtosis factor and the pulse factor are sensitive to shock faults; when the early surface of a bearing in the device is damaged, the peak-to-peak value changes obviously; the time domain characteristic parameters represent various information which is closely related to faults and contained in the vibration signals, and the characteristic parameters express the equipment operation state information, so that the time domain characteristic parameters can be used as a basis for distinguishing the equipment operation state.
(2) Frequency domain feature extraction
Frequency domain analysis is one of the most common fault diagnosis methods for rotary machines, and the characteristic parameters obtained by performing frequency domain analysis on signals are called frequency domain characteristic parameters. Fourier transformation is carried out on the signal time domain waveform to obtain an amplitude spectrum, frequency domain features in the amplitude spectrum are extracted, and relevant information implicit in the signal is fully mined. The current common frequency domain characteristics mainly comprise center of gravity frequency, mean square frequency, root mean square frequency, frequency standard deviation and the like, and in addition, the total energy characteristic of an amplitude spectrum is increased. The frequency domain characteristic parameters are used as the basis of fault diagnosis, so that the defect that the information content in the time domain characteristic parameters is insufficient can be made up, and the accuracy of fault diagnosis is improved.
(3) Thermal performance parameter and noise signal parameter extraction
When the equipment is in operation, the performance parameters of the equipment are also in close relation with the operation state of the equipment, such as the pressure, the temperature and other performance parameters of each part in the pump, and the fluctuation condition of the numerical values directly indicates the operation condition of the equipment. In the fault diagnosis of the variable load equipment, the influence of the performance parameters of the equipment needs to be considered, so the performance parameters of the equipment are used as characteristic parameters in signals in a report to realize the fault diagnosis under the variable working condition. In addition, during the operation of the device, the magnitude of the noise signal is significantly related to whether the device is normal, so that the noise signal needs to be taken into account to extract the parameters.
Further, the extracting the multidimensional parameters of the signal in the multidimensional parameter matrix specifically includes:
and reducing the dimension of the multi-dimensional parameter matrix characteristic by adopting a dimension reduction method to obtain the characteristic distribution of the pump equipment under normal and fault conditions.
Further, the step of processing the signal multidimensional parameter by using the KNN algorithm to judge the type of the signal multidimensional parameter to identify the device state specifically includes:
the KNN algorithm can be used for identifying the distance between the data and a certain characteristic, so that the type of the data is judged to identify the state of the equipment.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalent replacements, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (2)
1. A method for diagnosing a pump failure, comprising:
characteristic parameters are obtained by monitoring the pump equipment;
forming a multi-dimensional parameter matrix by the characteristic parameters;
performing dimensionality reduction processing on the multidimensional parameter matrix characteristics to obtain signal multidimensional parameters in characteristic distribution of the pump equipment under normal and fault conditions;
and processing the signal multidimensional parameters by using a KNN algorithm, thereby judging the type of the signal multidimensional parameters and identifying the equipment state.
2. The method for diagnosing the pump failure as claimed in claim 1, wherein the signal multi-dimensional parameter extraction includes the following steps:
(1) time domain feature extraction
Various characteristic parameters obtained by performing statistical analysis on the time domain signals are the time domain characteristic parameters of the signals; wherein: the root mean square value can reflect the signal energy and is sensitive to vibration waveforms generated by faults such as surface cracks in equipment parts; the kurtosis factor and the pulse factor are sensitive to shock faults; when the early surface of a bearing in the device is damaged, the peak-to-peak value changes obviously;
(2) frequency domain feature extraction
The characteristic parameters obtained by performing frequency domain analysis on the signals are called frequency domain characteristic parameters: carrying out Fourier transform on the signal time domain waveform to obtain an amplitude spectrum, extracting frequency domain characteristics in the amplitude spectrum, and fully mining relevant information implied in the signal;
(3) and extracting thermal performance parameters and noise signal parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010563986.9A CN111860599A (en) | 2020-06-19 | 2020-06-19 | Method for diagnosing machine pump fault |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010563986.9A CN111860599A (en) | 2020-06-19 | 2020-06-19 | Method for diagnosing machine pump fault |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111860599A true CN111860599A (en) | 2020-10-30 |
Family
ID=72987709
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010563986.9A Pending CN111860599A (en) | 2020-06-19 | 2020-06-19 | Method for diagnosing machine pump fault |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111860599A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104931263A (en) * | 2015-06-18 | 2015-09-23 | 东南大学 | Bearing fault diagnosis method based on symbolic probabilistic finite state machine |
| CN105760839A (en) * | 2016-02-22 | 2016-07-13 | 重庆大学 | Bearing fault diagnosis method based on multi-feature manifold learning and support vector machine |
| CN108073158A (en) * | 2017-12-05 | 2018-05-25 | 上海电机学院 | Based on PCA and KNN density algorithm Wind turbines Method for Bearing Fault Diagnosis |
| EP3483584A1 (en) * | 2016-10-06 | 2019-05-15 | Kabushiki Kaisha Kobe Seiko Sho (Kobe Steel, Ltd.) | Rotating machine abnormality detection device and method, and rotating machine |
| CN109871862A (en) * | 2018-12-28 | 2019-06-11 | 北京航天测控技术有限公司 | A kind of failure prediction method based on synthesis minority class over-sampling and deep learning |
| CN111060337A (en) * | 2019-12-05 | 2020-04-24 | 杭州哲达科技股份有限公司 | Running equipment real-time fault diagnosis method based on expert system |
-
2020
- 2020-06-19 CN CN202010563986.9A patent/CN111860599A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104931263A (en) * | 2015-06-18 | 2015-09-23 | 东南大学 | Bearing fault diagnosis method based on symbolic probabilistic finite state machine |
| CN105760839A (en) * | 2016-02-22 | 2016-07-13 | 重庆大学 | Bearing fault diagnosis method based on multi-feature manifold learning and support vector machine |
| EP3483584A1 (en) * | 2016-10-06 | 2019-05-15 | Kabushiki Kaisha Kobe Seiko Sho (Kobe Steel, Ltd.) | Rotating machine abnormality detection device and method, and rotating machine |
| CN108073158A (en) * | 2017-12-05 | 2018-05-25 | 上海电机学院 | Based on PCA and KNN density algorithm Wind turbines Method for Bearing Fault Diagnosis |
| CN109871862A (en) * | 2018-12-28 | 2019-06-11 | 北京航天测控技术有限公司 | A kind of failure prediction method based on synthesis minority class over-sampling and deep learning |
| CN111060337A (en) * | 2019-12-05 | 2020-04-24 | 杭州哲达科技股份有限公司 | Running equipment real-time fault diagnosis method based on expert system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gowid et al. | A novel robust automated FFT-based segmentation and features selection algorithm for acoustic emission condition based monitoring systems | |
| CN113927371A (en) | Cutter wear prediction method based on multi-sensor feature fusion | |
| CN107350900B (en) | A kind of tool condition monitoring method extracted based on the chip breaking time | |
| CN111521687B (en) | Inhaul cable broken wire distinguishing method and system based on acoustic emission signal analysis | |
| CN113579851B (en) | Non-stationary drilling process monitoring method based on adaptive segmented PCA | |
| CN109141625B (en) | Online state monitoring method for ball screw pair | |
| CN109190598A (en) | A kind of rotating machinery monitoring data noise detection method based on SES-LOF | |
| CN112207631B (en) | Method for generating tool detection model, method, system, device and medium for detecting tool detection model | |
| CN113532848A (en) | Fault diagnosis system for planetary gear box | |
| Shi et al. | Generalized variable-step multiscale lempel-ziv complexity: A feature extraction tool for bearing fault diagnosis | |
| CN113075512A (en) | Sound detection-based transformer discharge fault diagnosis method and system | |
| Saini et al. | Predictive monitoring of incipient faults in rotating machinery: a systematic review from data acquisition to artificial intelligence | |
| Du et al. | Intelligent turning tool monitoring with neural network adaptive learning | |
| Zaman et al. | Broken rotor bar fault diagnosis for induction motors using power spectral density and complex continuous wavelet transform methods | |
| CN114417924A (en) | Rolling bearing fault diagnosis method based on undirected graph adjacency matrix of mixed features | |
| Fang et al. | Reciprocating compressors intelligent fault diagnosis under multiple operating conditions based on adaptive variable scale morphological filter | |
| CN111860599A (en) | Method for diagnosing machine pump fault | |
| Jobi-Taiwo et al. | Mahalanobis-Taguchi system for multiclass classification of steel plates fault | |
| CN117093938A (en) | Fan bearing fault detection method and system based on deep learning | |
| CN116699400A (en) | Generator rotor short-circuit fault monitoring system, method and readable storage medium | |
| CN112525337B (en) | Pretreatment method for vibration monitoring data of mechanical press | |
| Agrawal et al. | Induction motor bearing fault classification using WPT, PCA and DSVM | |
| CN114036973A (en) | Series arc fault identification method of extreme learning machine based on dynamic online sequence | |
| Song et al. | Rolling Bearing Fault Diagnosis Under Different Severity Based on Statistics Detection Index and Canonical Discriminant Analysis | |
| CN111157812A (en) | Power equipment fault monitoring method based on electromagnetic induction |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20201030 |