CN117874471B - Water and electricity safety early warning and fault diagnosis method and system - Google Patents
Water and electricity safety early warning and fault diagnosis method and system Download PDFInfo
- Publication number
- CN117874471B CN117874471B CN202410270830.XA CN202410270830A CN117874471B CN 117874471 B CN117874471 B CN 117874471B CN 202410270830 A CN202410270830 A CN 202410270830A CN 117874471 B CN117874471 B CN 117874471B
- Authority
- CN
- China
- Prior art keywords
- signal
- matrix
- vibration
- vibration signal
- fault diagnosis
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 43
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000005611 electricity Effects 0.000 title claims description 10
- 239000011159 matrix material Substances 0.000 claims abstract description 86
- 230000002087 whitening effect Effects 0.000 claims abstract description 28
- 238000001228 spectrum Methods 0.000 claims description 18
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000011478 gradient descent method Methods 0.000 claims description 6
- 238000001845 vibrational spectrum Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 108010076504 Protein Sorting Signals Proteins 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000002243 precursor Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Control Of Water Turbines (AREA)
Abstract
The invention relates to the field of hydroelectric data processing, and provides a method and a system for safety pre-warning and fault diagnosis of a hydroelectric motor, wherein the method comprises the steps of collecting vibration signals corresponding to a plurality of hydroelectric motors under the same operation environment; forming a vibration signal matrix by the vibration signals, wherein each row corresponds to a water motor, and each column corresponds to a time point; performing a centering operation on the vibration signal matrix to eliminate a direct current component of the signal; performing whitening treatment on the centralized signal to obtain a whitened signal matrix; restoring a hydraulic vibration signal and a mechanical vibration signal by using the whitening signal matrix; and carrying out safety early warning and fault diagnosis according to the mechanical vibration signals. The scheme can accurately and rapidly analyze the mechanical vibration signals of the equipment, thereby improving the accuracy and efficiency of equipment safety early warning and fault diagnosis.
Description
Technical Field
The invention relates to the field of hydroelectric data processing, in particular to a method and a system for safety pre-warning and fault diagnosis of a hydroelectric power plant.
Background
The most critical equipment in hydropower projects is a hydropower unit, and vibration signals of the hydropower unit are monitored by using vibration sensors and other equipment in the prior art. The vibration signal contains important information of the running state of the unit, and abnormal vibration can be a precursor of failure.
However, the vibration signal of the hydroelectric generating set typically includes a superposition of various signals, such as a hydraulic signal, a mechanical vibration signal of the apparatus, an electrical vibration, an impeller vibration, etc., where the hydraulic signal, the mechanical vibration signal of the apparatus, are the main signal components. In order to locate faults in the prior art, the noise removal operation needs to be carried out on vibration signals through various means, so that the mechanical vibration signals of equipment are highlighted as much as possible. However, the existing denoising operation generally only considers the signal of a single water motor, and on one hand, the denoising algorithm is complex, and on the other hand, the denoising effect is poor.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a method and a system for safety pre-warning and fault diagnosis of a water motor.
In one aspect of the present invention, a method for safety precaution and fault diagnosis of a water motor is provided, comprising: collecting vibration signals corresponding to a plurality of hydroelectric motors under the same operation environment; forming a vibration signal matrix by the vibration signals, wherein each row corresponds to a water motor, and each column corresponds to a time point; performing a centering operation on the vibration signal matrix to eliminate a direct current component of the signal; performing whitening treatment on the centralized signal to obtain a whitened signal matrix; the method for restoring the hydraulic vibration signal and the mechanical vibration signal by using the whitening signal matrix specifically comprises the following steps: let whitened signal matrix beThe hydraulic vibration signal is/>The mechanical vibration signal is/>Then there is/>Random initialization/>Iteratively performing: calculation/>; Pair/>Performing Fourier transform on each component in the spectrum to obtain a frequency spectrum, extracting a main frequency component from the frequency spectrum, acquiring corresponding phase information, comparing the phase information of each component, and finding/>, if the phase difference of each component is within a preset threshold value/>Otherwise update/>, using gradient descent methodRecalculate/>; And carrying out safety early warning and fault diagnosis according to the mechanical vibration signals.
Further, the centering operation includes:
Firstly, calculating the average value of vibration signals of each water motor, calculating the average value of vibration signals of each row in a vibration signal matrix X, setting n as the number of time points and j as the number of signal columns, and then calculating the average value of vibration signals of the ith water motor
For each elementSubtracting the mean of the rows it holds is:
。
Further, the whitening process includes:
For the vibration signal matrix X after centering, calculating a covariance matrix thereof Element of covariance matrix/>Representing covariance of ith and jth columns
Computing the whitening matrix W causesWherein I is an identity matrix;
multiplying the centralized vibration signal matrix X with the whitening matrix W to obtain a whitened signal matrix
。
Further, features are extracted from the mechanical vibration signal, the features being used to describe frequency and/or time domain characteristics of the mechanical vibration signal, the features comprising at least one of vibration spectrum, peak, root mean square, kurtosis.
Further, when the equipment is operated, vibration signals are monitored in real time, vibration signal characteristics acquired in real time are compared with reference model signal characteristics, whether abnormal conditions exist or not is detected, if the abnormal conditions are detected, a pre-established fault diagnosis model is utilized, the characteristics of mechanical vibration signals are analyzed through comparison, fault reasons are located, and early warning is carried out.
The invention also provides a system for safety pre-warning and fault diagnosis of the hydroelectric machine, which comprises the following components: the acquisition module is used for acquiring vibration signals corresponding to a plurality of water motors in the same operation environment; forming a vibration signal matrix by the vibration signals, wherein each row corresponds to a water motor, and each column corresponds to a time point; the data processing module is used for carrying out centering operation on the vibration signal matrix so as to eliminate the direct current component of the signal; performing whitening treatment on the centralized signal to obtain a whitened signal matrix; the method for restoring the hydraulic vibration signal and the mechanical vibration signal by using the whitening signal matrix specifically comprises the following steps: let whitened signal matrix beThe hydraulic vibration signal is/>The mechanical vibration signal is/>Then there isRandom initialization/>Iteratively performing: calculation/>; Pair/>Performing Fourier transform on each component in the spectrum to obtain a frequency spectrum, extracting a main frequency component from the frequency spectrum, acquiring corresponding phase information, comparing the phase information of each component, and finding/>, if the phase difference of each component is within a preset threshold value/>Otherwise update/>, using gradient descent methodRecalculate/>; And the diagnosis module is used for carrying out safety early warning and fault diagnosis according to the mechanical vibration signals.
Further, the centering operation includes: firstly, calculating the average value of vibration signals of each water motor, calculating the average value of vibration signals of each row in a vibration signal matrix X, setting n as the number of time points and j as the number of signal columns, and then calculating the average value of vibration signals of the ith water motor
For each elementSubtracting the mean of the rows it holds is:
。
Further, the whitening process includes:
For the vibration signal matrix X after centering, calculating a covariance matrix thereof Element of covariance matrix/>Representing covariance of ith and jth columns
Computing the whitening matrix W causesWherein I is an identity matrix;
multiplying the centralized vibration signal matrix X with the whitening matrix W to obtain a whitened signal matrix
。
Further, features are extracted from the mechanical vibration signal, the features being used to describe frequency and/or time domain characteristics of the mechanical vibration signal, the features comprising at least one of vibration spectrum, peak, root mean square, kurtosis.
Further, when the equipment is operated, vibration signals are monitored in real time, vibration signal characteristics acquired in real time are compared with reference model signal characteristics, whether abnormal conditions exist or not is detected, if the abnormal conditions are detected, a pre-established fault diagnosis model is utilized, the characteristics of mechanical vibration signals are analyzed through comparison, fault reasons are located, and early warning is carried out.
Through the technical scheme, the invention can produce the following beneficial effects:
According to the principle that hydraulic noises of a plurality of water motors with similar operating environments are similar, the hydraulic noises and the respective mechanical vibration noises are determined according to the vibration data of the plurality of water motors, and fault early warning is carried out through the mechanical vibration noises, so that the processing accuracy and the processing efficiency of the vibration data are improved, and the accuracy and the processing efficiency of the fault early warning are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of the method of the present invention.
Detailed Description
The invention will be described with reference to the drawings and detailed description.
The present embodiment solves the above problem by:
In one embodiment, referring to fig. 1, the present invention provides a method for early warning and diagnosing faults of a hydroelectric machine, which specifically includes:
and collecting vibration signals corresponding to a plurality of water motors under the same running environment.
The hydroelectric generating set is one of key equipment in hydroelectric projects and is responsible for converting kinetic energy of water flow into mechanical energy so as to drive a generator to generate electricity. Vibration analysis of hydroelectric generating sets is a common technology, and can be used for monitoring health conditions of the generating sets, and carrying out safety early warning and fault diagnosis. The vibration of the water-motor unit is caused by various factors such as water power, machinery and the like, and is the result of superposition of a plurality of vibration sources. In modern hydro-electric projects, particularly small-sized hydro-electric projects, in order to adapt to the installation of modularized hydro-electric units, different flow channels are usually constructed with the same specification, so that vibration signals caused by hydraulic power of the hydro-electric units in the different flow channels are generally similar, hydraulic power vibration signals in the different flow channels are separated based on the embodiment, and therefore the same operation environment in the embodiment refers to the same specification of the flow channels.
For the same hydropower project, a plurality of flow channels with the same specification correspond to a plurality of water motors, vibration data acquisition is carried out on each water motor, and a vibration signal sequence can be obtained.
During collection, vibration sensors can be installed at the same position of each hydroelectric motor, so that the positions and the directions of the sensors are consistent on each unit, and compared vibration data can be obtained. And connecting the vibration signals of the sensor to the corresponding NI acquisition card through a cable, performing data acquisition setting by using a related software tool (such as LabVIEW) of the NI acquisition card, and remembering acquired data to obtain vibration signal data.
Further, the collected vibration signals are subjected to necessary preprocessing including trending, filtering, normalization, etc. to eliminate possible interference or noise and to ensure that the vibration signals of different water motors have the same time scale, for example, all signals are processed into 1024HZ vibration signals.
And forming a vibration signal matrix by the vibration signals, wherein each row corresponds to a water motor, and each column corresponds to a time point.
Each of the vibration signals corresponds to a signal source of a water motor, each can be regarded as a vibration combination of hydraulic + mechanical, and the hydraulic parts have a high degree of similarity. In order to perform correlation analysis on signals, a vibration matrix is constructed by a plurality of signals, so that comparison analysis, statistical analysis and pattern recognition can be more conveniently performed, and the follow-up steps are facilitated to find abnormal vibration and fault patterns.
Performing a centering operation on the vibration signal matrix to eliminate a direct current component of the signal;
The centering operation is to subtract the mean value of the data to eliminate the direct current component of the signal, and centering the vibration signal matrix can help to highlight the dynamic characteristics of the signal so as to facilitate subsequent analysis.
The centering operation specifically comprises the following steps:
the mean value of the vibration signal of each hydroelectric motor is calculated firstly, and the mean value of each line in the vibration signal matrix X is calculated. If m is the number of the water motors and n is the number of time points, calculating the mean value of vibration signals of the ith water motor
For each elementSubtracting the mean of the rows it holds is:
Performing whitening treatment on the centralized signal to enable the covariance matrix of the signal to be a unit matrix, and further independent signals;
To facilitate subsequent signal separation, the signals are further independent, and the covariance matrix of the centered vibration signal matrix X is calculated Element of protocol difference matrix/>Representing covariance of ith and jth columns
Computing the whitening matrix W causesWherein I is an identity matrix.
Multiplying the centralized vibration signal matrix X with the whitening matrix W to obtain a whitened signal matrix
The covariance matrix of the whitened signal matrix should be close to the identity matrix, so that the correlation between signals is reduced, and the dimensions are uniform, so that the covariance matrix is more independent and the wanted signal is easier to separate by linear superposition.
Restoring a hydraulic vibration signal and a mechanical vibration signal by using the whitening signal matrix;
The whitened signal matrix is The hydraulic vibration signal is/>The mechanical vibration signal is/>;
Then there is
Random initialization。
The following steps are performed iteratively:
Calculation of ;
For a pair ofEach component in the spectrum is subjected to Fourier transformation to obtain a frequency spectrum, a main frequency component is extracted from the frequency spectrum, corresponding phase information is acquired, the phase information of each component is compared, and if the phase difference of each component is within a preset threshold value, the phase difference of each component is found/>Otherwise update/>, using gradient descent methodRecalculate/>。
In this step, the vibration signals are separated according to the principle that each vibration signal data contains a similar hydraulic vibration signal, and the subsequent operation is performed.
And carrying out safety early warning and fault diagnosis according to the mechanical vibration signals.
The analysis of the mechanical vibration signal is widely applied to safety precaution and fault diagnosis of the hydroelectric equipment, and the vibration signal is separated in the previous steps, so that the most difficult part is completed. For safety precautions and fault diagnosis, features may be extracted from the vibration signal, which may be used to describe the frequency and time domain characteristics of the vibration signal. Common features include vibration spectrum, peak, root Mean Square (RMS), kurtosis, etc. And establishing a reference model by using vibration data acquired during normal operation. May be a vibration characteristic of the device in its normal operating state. The vibration signal is monitored in real time as the device is operated. And comparing the vibration signals acquired in real time with a reference model, and detecting whether abnormal conditions exist. If an abnormality is detected, a possible cause of the fault is located by comparing and analyzing the characteristics of the vibration signal using a pre-established fault diagnosis model. When a possible fault sign is detected, a safety early warning system is triggered, and an alarm is sent to an operator so as to take necessary measures in time and avoid damage caused by equipment faults.
The pre-established fault diagnosis model may be any means in the prior art, for example, a method of detecting abnormal vibration of the hydroelectric generating set based on support vector data description and identifying vibration faults of the hydroelectric generating set based on feature fusion, or other models based on neural networks, which are mentioned in the "stability monitoring and vibration fault diagnosis study of the hydroelectric generating set" Zhao Zhilu, and the embodiment of the specific model is not limited specifically.
On the other hand, the invention also provides a system for safety pre-warning and fault diagnosis of the hydroelectric machine, which comprises the following components:
the acquisition module is used for acquiring vibration signals corresponding to a plurality of water motors in the same operation environment; forming a vibration signal matrix by the vibration signals, wherein each row corresponds to a water motor, and each column corresponds to a time point;
The data processing module is used for carrying out centering operation on the vibration signal matrix so as to eliminate the direct current component of the signal; performing whitening treatment on the centralized signal to obtain a whitened signal matrix; the method for restoring the hydraulic vibration signal and the mechanical vibration signal by using the whitening signal matrix specifically comprises the following steps:
let whitened signal matrix be The hydraulic vibration signal is/>The mechanical vibration signal is/>Then there isRandom initialization/>,
Iteratively performing:
Calculation of ;
For a pair ofEach component in the spectrum is subjected to Fourier transformation to obtain a frequency spectrum, a main frequency component is extracted from the frequency spectrum, corresponding phase information is acquired, the phase information of each component is compared, and if the phase difference of each component is within a preset threshold value, the phase difference of each component is found/>Otherwise update/>, using gradient descent methodRecalculate/>;
And the diagnosis module is used for carrying out safety early warning and fault diagnosis according to the mechanical vibration signals.
Furthermore, the specific implementation method of the water and electricity motor safety pre-warning and fault diagnosis system is the same as that of the water and electricity motor safety pre-warning and fault diagnosis method, and all the further technical schemes in the water and electricity motor safety pre-warning and fault diagnosis method are completely introduced into the water and electricity motor safety pre-warning and fault diagnosis system.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
The present invention is not limited to the specific partial module structure described in the prior art. The prior art to which this invention refers in the preceding background section as well as in the detailed description section can be used as part of the invention for understanding the meaning of some technical features or parameters. The protection scope of the present invention is subject to what is actually described in the claims.
Claims (10)
1. A water and electricity motor safety early warning and fault diagnosis method is characterized in that:
Collecting vibration signals corresponding to a plurality of hydroelectric motors under the same operation environment;
forming a vibration signal matrix by the vibration signals, wherein each row corresponds to a water motor, and each column corresponds to a time point;
performing a centering operation on the vibration signal matrix to eliminate a direct current component of the signal;
performing whitening treatment on the centralized signal to obtain a whitened signal matrix;
The method for restoring the hydraulic vibration signal and the mechanical vibration signal by using the whitening signal matrix specifically comprises the following steps:
let whitened signal matrix be The hydraulic vibration signal is/>The mechanical vibration signal is/>Then there isRandom initialization/>,
Iteratively performing:
Calculation of ;
For a pair ofPerforming Fourier transform on each component in the spectrum to obtain a frequency spectrum, extracting a main frequency component from the frequency spectrum, acquiring corresponding phase information, comparing the phase information of each component, and finding/>, if the phase difference of each component is within a preset threshold value/>Otherwise update/>, using gradient descent methodRecalculate/>;
And carrying out safety early warning and fault diagnosis according to the mechanical vibration signals.
2. The method for safety precaution and fault diagnosis of a water and electricity machine according to claim 1, characterized in that said centralizing operation comprises:
Firstly, calculating the average value of vibration signals of each water motor, calculating the average value of vibration signals of each row in a vibration signal matrix X, setting n as the number of time points and j as the number of signal columns, and then calculating the average value of vibration signals of the ith water motor
,
For each elementSubtracting the mean of the rows it holds is:
。
3. a method of safety precaution and fault diagnosis of a hydroelectric machine according to claim 2, characterised in that the whitening treatment comprises:
For the vibration signal matrix X after centering, calculating a covariance matrix thereof Element of covariance matrix/>Representing covariance of ith and jth columns
,
Computing the whitening matrix W causesWherein I is an identity matrix;
multiplying the centralized vibration signal matrix X with the whitening matrix W to obtain a whitened signal matrix
。
4. The method for safety precaution and fault diagnosis of a hydroelectric machine according to claim 1, characterized in that: features are extracted from the mechanical vibration signal, the features describing frequency and/or time domain characteristics of the mechanical vibration signal, the features including at least one of vibration spectrum, peak value, root mean square, kurtosis.
5. The method for safety precaution and fault diagnosis of a hydroelectric machine according to claim 4, characterized in that: when the equipment operates, vibration signals are monitored in real time, vibration signal characteristics acquired in real time are compared with reference model signal characteristics, whether abnormal conditions exist or not is detected, if the abnormal conditions are detected, a pre-established fault diagnosis model is utilized, the characteristics of mechanical vibration signals are analyzed through comparison, fault reasons are located, and early warning is carried out.
6. A system for safety precaution and fault diagnosis of a hydroelectric power plant, characterized in that the system comprises:
the acquisition module is used for acquiring vibration signals corresponding to a plurality of water motors in the same operation environment; forming a vibration signal matrix by the vibration signals, wherein each row corresponds to a water motor, and each column corresponds to a time point;
The data processing module is used for carrying out centering operation on the vibration signal matrix so as to eliminate the direct current component of the signal; performing whitening treatment on the centralized signal to obtain a whitened signal matrix; the method for restoring the hydraulic vibration signal and the mechanical vibration signal by using the whitening signal matrix specifically comprises the following steps:
let whitened signal matrix be The hydraulic vibration signal is/>The mechanical vibration signal is/>Then there isRandom initialization/>,
Iteratively performing:
Calculation of ;
For a pair ofPerforming Fourier transform on each component in the spectrum to obtain a frequency spectrum, extracting a main frequency component from the frequency spectrum, acquiring corresponding phase information, comparing the phase information of each component, and finding/>, if the phase difference of each component is within a preset threshold value/>Otherwise update/>, using gradient descent methodRecalculate/>;
And the diagnosis module is used for carrying out safety early warning and fault diagnosis according to the mechanical vibration signals.
7. The hydro-motor safety precaution and fault diagnosis system of claim 6, wherein the centering operation comprises:
Firstly, calculating the average value of vibration signals of each water motor, calculating the average value of vibration signals of each row in a vibration signal matrix X, setting n as the number of time points and j as the number of signal columns, and then calculating the average value of vibration signals of the ith water motor
,
For each elementSubtracting the mean of the rows it holds is:
。
8. A hydroelectric machine safety precaution and fault diagnosis system according to claim 7, wherein said whitening treatment comprises:
For the vibration signal matrix X after centering, calculating a covariance matrix thereof Element of covariance matrix/>Representing covariance of ith and jth columns
,
Computing the whitening matrix W causesWherein I is an identity matrix;
multiplying the centralized vibration signal matrix X with the whitening matrix W to obtain a whitened signal matrix
。
9. The system for safety precaution and fault diagnosis of a water and electricity machine according to claim 6, wherein: features are extracted from the mechanical vibration signal, the features describing frequency and/or time domain characteristics of the mechanical vibration signal, the features including at least one of vibration spectrum, peak value, root mean square, kurtosis.
10. The hydro-electric machine safety precaution and fault diagnosis system of claim 9, wherein: when the equipment operates, vibration signals are monitored in real time, vibration signal characteristics acquired in real time are compared with reference model signal characteristics, whether abnormal conditions exist or not is detected, if the abnormal conditions are detected, a pre-established fault diagnosis model is utilized, the characteristics of mechanical vibration signals are analyzed through comparison, fault reasons are located, and early warning is carried out.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410270830.XA CN117874471B (en) | 2024-03-11 | 2024-03-11 | Water and electricity safety early warning and fault diagnosis method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410270830.XA CN117874471B (en) | 2024-03-11 | 2024-03-11 | Water and electricity safety early warning and fault diagnosis method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117874471A CN117874471A (en) | 2024-04-12 |
CN117874471B true CN117874471B (en) | 2024-05-14 |
Family
ID=90593288
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410270830.XA Active CN117874471B (en) | 2024-03-11 | 2024-03-11 | Water and electricity safety early warning and fault diagnosis method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117874471B (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103575523A (en) * | 2013-11-14 | 2014-02-12 | 哈尔滨工程大学 | Rotating machine fault diagnosis method based on Fast ICA-spectrum kurtosis-envelope spectrum analysis |
WO2014128437A2 (en) * | 2013-02-20 | 2014-08-28 | Trw Limited | Motor control circuit and method of monitoring a motor |
CN110174281A (en) * | 2019-06-05 | 2019-08-27 | 北京博识创智科技发展有限公司 | A kind of electromechanical equipment fault diagnosis method and system |
EP3595115A1 (en) * | 2018-07-13 | 2020-01-15 | Kohler Co. | Ground fault minimization |
CN111174903A (en) * | 2019-12-31 | 2020-05-19 | 北京化工大学 | Method for diagnosing faults of turbomachinery |
CN112082793A (en) * | 2020-08-31 | 2020-12-15 | 洛阳师范学院 | Rotating machinery coupling fault diagnosis method based on SCA and FastICA |
CN114755010A (en) * | 2022-05-05 | 2022-07-15 | 厦门纵行信息科技有限公司 | Rotary machine vibration fault diagnosis method and system |
CN114861726A (en) * | 2022-05-13 | 2022-08-05 | 北京信息科技大学 | Method and system for predicting wear fault trend of high-speed gear of wind driven generator |
CN116296364A (en) * | 2022-11-30 | 2023-06-23 | 苏州汇川控制技术有限公司 | Gear fault diagnosis method, system, motor controller and computer medium |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP4338022A2 (en) * | 2021-05-06 | 2024-03-20 | Strong Force IoT Portfolio 2016, LLC | Quantum, biological, computer vision, and neural network systems for industrial internet of things |
-
2024
- 2024-03-11 CN CN202410270830.XA patent/CN117874471B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014128437A2 (en) * | 2013-02-20 | 2014-08-28 | Trw Limited | Motor control circuit and method of monitoring a motor |
CN103575523A (en) * | 2013-11-14 | 2014-02-12 | 哈尔滨工程大学 | Rotating machine fault diagnosis method based on Fast ICA-spectrum kurtosis-envelope spectrum analysis |
EP3595115A1 (en) * | 2018-07-13 | 2020-01-15 | Kohler Co. | Ground fault minimization |
CN110174281A (en) * | 2019-06-05 | 2019-08-27 | 北京博识创智科技发展有限公司 | A kind of electromechanical equipment fault diagnosis method and system |
CN111174903A (en) * | 2019-12-31 | 2020-05-19 | 北京化工大学 | Method for diagnosing faults of turbomachinery |
CN112082793A (en) * | 2020-08-31 | 2020-12-15 | 洛阳师范学院 | Rotating machinery coupling fault diagnosis method based on SCA and FastICA |
CN114755010A (en) * | 2022-05-05 | 2022-07-15 | 厦门纵行信息科技有限公司 | Rotary machine vibration fault diagnosis method and system |
CN114861726A (en) * | 2022-05-13 | 2022-08-05 | 北京信息科技大学 | Method and system for predicting wear fault trend of high-speed gear of wind driven generator |
CN116296364A (en) * | 2022-11-30 | 2023-06-23 | 苏州汇川控制技术有限公司 | Gear fault diagnosis method, system, motor controller and computer medium |
Non-Patent Citations (4)
Title |
---|
40MW灯泡贯流式机组水导轴承烧瓦事故分析及预防措施;李永强;《云南水力发电》;20221215;第38卷(第12期);第236-239页 * |
Data Fusion for the Diagnostics, Prognostics, and Health Management of Aircraft Systems;Zheng Liu等;《Advances in Intelligent Systems and Computing》;20140930;第215卷;第389-399页 * |
EPS电机位置传感器故障诊断策略设计;郑虎 等;《上海汽车》;20170810;第2017卷(第8期);第21-24页 * |
柔性直流输电线路保护与故障测距方法研究;槐青;《学位论文》;20220527;摘要 * |
Also Published As
Publication number | Publication date |
---|---|
CN117874471A (en) | 2024-04-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Abid et al. | Robust interpretable deep learning for intelligent fault diagnosis of induction motors | |
Abid et al. | Distinct bearing faults detection in induction motor by a hybrid optimized SWPT and aiNet-DAG SVM | |
Soualhi et al. | Pattern recognition method of fault diagnostics based on a new health indicator for smart manufacturing | |
Henriquez et al. | Review of automatic fault diagnosis systems using audio and vibration signals | |
Pandarakone et al. | Deep neural network based bearing fault diagnosis of induction motor using fast Fourier transform analysis | |
Amanuel et al. | Comparative analysis of signal processing techniques for fault detection in three phase induction motor | |
CN115688018B (en) | Method for monitoring state and diagnosing faults of bearing under multiple working conditions | |
Heydarzadeh et al. | A wavelet-based fault diagnosis approach for permanent magnet synchronous motors | |
CN112098088B (en) | Rolling bearing fault diagnosis method based on KICA-fractal theory | |
Hwang et al. | SVM-RBM based predictive maintenance scheme for IoT-enabled smart factory | |
CN115437358A (en) | Intelligent state monitoring and fault diagnosis system and fault diagnosis method for industrial robot | |
CN111639852B (en) | Real-time evaluation method and system for vibration state of hydroelectric generating set based on wavelet singular value | |
Mubaraali et al. | Intelligent fault diagnosis in microprocessor systems for vibration analysis in roller bearings in whirlpool turbine generators real time processor applications | |
CN117874471B (en) | Water and electricity safety early warning and fault diagnosis method and system | |
CN112986821B (en) | Fault diagnosis method for broken blade of variable pitch motor rotor of offshore wind turbine generator | |
CN110441081B (en) | Intelligent diagnosis method and intelligent diagnosis system for faults of rotating machinery | |
CN117672255A (en) | Abnormal equipment identification method and system based on artificial intelligence and equipment operation sound | |
Wang et al. | Fault diagnosis for bearing based on Mahalanobis-Taguchi system | |
CN116335892A (en) | Wind turbine generator blade abnormality detection method and system | |
CN116625654A (en) | Vibration signal fault diagnosis method, device, equipment and storage medium | |
CN113298133B (en) | Method for diagnosing explosion tube fault of supercritical unit boiler | |
Fumagalli et al. | Agile diagnostic tool based on electrical signature analysis | |
CN115221914A (en) | Rotating machinery fault diagnosis method based on enhanced octyl geometric modal decomposition | |
Vishwakarma et al. | Intelligent bearing fault monitoring system using support vector machine and wavelet packet decomposition for induction motors | |
Senanayaka et al. | Autoencoders and data fusion based hybrid health indicator for detecting bearing and stator winding faults in electric motors |
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 |