CN117009828A - Hydropower equipment fault diagnosis method based on fault matching algorithm - Google Patents
Hydropower equipment fault diagnosis method based on fault matching algorithm Download PDFInfo
- Publication number
- CN117009828A CN117009828A CN202311271118.3A CN202311271118A CN117009828A CN 117009828 A CN117009828 A CN 117009828A CN 202311271118 A CN202311271118 A CN 202311271118A CN 117009828 A CN117009828 A CN 117009828A
- Authority
- CN
- China
- Prior art keywords
- fault
- matching
- algorithm
- value
- characteristic data
- 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.)
- Granted
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title claims abstract description 24
- 208000024891 symptom Diseases 0.000 claims abstract description 47
- 238000004364 calculation method Methods 0.000 claims abstract description 13
- 238000010606 normalization Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 2
- 230000004927 fusion Effects 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000001502 supplementing effect Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000001845 vibrational spectrum Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The method comprises the steps of establishing a fault case library based on a fault matching algorithm and acquiring running data of the hydropower equipment in real time; calculating the credibility value of various fault symptoms by combining the acquired characteristic data; calculating the reliability value of the fault mode according to the calculated reliability value of the fault symptom; matching calculation is carried out on the cosine similarity algorithm and the cases of the fault case library to obtain a matching degree value of each case; combining the characteristic data into a two-dimensional array to obtain a plurality of groups of subsequences, and calculating a case matching degree value by using a gray correlation degree algorithm in combination with the weight of the characteristic data and the parent sequence; combining the calculated matching degree values, and obtaining a final matching result by means of weighted average according to certain weight fusion; generating fault diagnosis preliminary information and synchronously updating a fault case library. The method combines a cosine matching algorithm and a gray correlation algorithm, and the final result is fused through weighted average, so that the diagnosis result is more accurate by matching the historical fault cases from multiple angles.
Description
Technical Field
The invention relates to the technical field of hydroelectric equipment fault diagnosis, in particular to a hydroelectric equipment fault diagnosis method based on a fault matching algorithm.
Background
The existing hydropower equipment fault diagnosis technology fails to fully consider the existing fault condition, does not summarize past fault experience and cases of precipitation and lacks fault matching case support, so that accurate and reliable judgment on equipment faults cannot be made. In recent years, fault diagnosis of hydroelectric equipment by using an artificial intelligence technology becomes a research hot spot, but an artificial intelligence algorithm needs a large amount of data to perform model training, and in practical application, the situation of insufficient data often exists, so that the trained model has the problems of low accuracy, insufficient diagnosis refinement degree and the like. In addition, the existing fault diagnosis method cannot fully combine with the historical fault case library to perform case matching, and cannot obtain accurate and reliable diagnosis results.
Disclosure of Invention
In order to solve the technical problems, the invention provides a hydropower equipment fault diagnosis method based on a fault matching algorithm, which combines a cosine matching algorithm and a gray correlation algorithm, and the diagnosis result is more accurate by matching historical fault cases from multiple angles through weighting average fusion of final results.
The technical scheme adopted by the invention is as follows:
the hydropower equipment fault diagnosis method based on the fault matching algorithm comprises the following steps:
step one, a fault case library is established according to historical fault experience and typical fault problems, wherein the fault case library comprises fault modes, fault symptoms, characteristic parameters, fault phenomena and treatment measure information, each fault symptom corresponds to different algorithm logics, and the fault of the hydropower equipment is maximally covered;
acquiring hydropower equipment operation data in real time from an industrial Internet data platform, wherein the hydropower equipment operation data comprise characteristic data such as stator temperature, upper guide X-direction swing peak value and the like;
step three, calculating the credibility value of various fault symptoms by combining the characteristic data obtained in the step two; each symptom corresponds to different computational logic;
step four, according to the fault symptom credibility value calculated in the step three, carrying out normalization processing by combining the corresponding symptom fixed weight in the fault mode, and calculating the fault mode credibility value;
step five, according to the fault mode reliability value calculated in the step four, sequentially carrying out matching calculation with the cases of the fault case library in the step one by utilizing a cosine similarity algorithm to obtain a matching degree value of each case;
step six, calculating the median of the characteristic data when the fault occurs according to the characteristic data obtained in the step two in real time, and obtaining a group of series as a parent sequence;
inquiring cases with related characteristic data in a fault case library, combining the characteristic data into a two-dimensional array to obtain a plurality of groups of subsequences, and calculating a case matching degree value by using a gray correlation degree algorithm in combination with the weight and the parent sequence of the characteristic data;
combining the cosine similarity algorithm in the fifth step with the gray correlation algorithm in the seventh step to calculate a matching degree value, and fusing according to a certain weight by using a weighted average mode to obtain a final matching result;
and step nine, based on the final matching result of the step eight, combining other components to jointly confirm the fault cause, generating fault diagnosis preliminary information, manually supplementing and perfecting the fault information to form fault diagnosis final information, managing the hydroelectric equipment based on the fault diagnosis final information, remotely outputting the information, and synchronously updating a fault case library.
In the third step, the step of the method,
aiming at the fault symptoms of large down-lead swing, the reliability calculation formula is as follows:
cf=min(1.0,1.2*LowerGuideThrow/LowerGuideThrowDanger)
the lowguide window is a passband amplitude value for setting a downscaling degree, and the lowguide window Danger is a channel danger value;
aiming at the fault symptoms of large frequency conversion in the vibration frequency spectrum, the reliability calculation formula is as follows:
cf=fyp1*fyp1/(fyp1*fyp1+fyp1bj*fyp1bj)
wherein fyp is the frequency conversion amplitude of the vibration swing degree channel, and fyp1bj is the frequency conversion early warning value.
In the fourth step, the fault mode comprises breaking of the breaking pin, running fault of the shafting of the hydroelectric generating set and fault of the fan.
In the fifth step, the cosine similarity algorithm is as follows:
；
wherein X is the fault symptom credibility value calculated in the step three, Y is the fault symptom credibility value bound by the cases in the fault case library, and i is the number of the fault symptoms.
In the eighth step, the gray correlation algorithm is:
；
wherein X is 0 As parent sequence, X i For the subsequences, k is the characteristic data in each subsequence, ρ is an adjustable coefficient, 0.5 is taken, i is the case number, w i (k) Is the weight of the feature data.
The invention relates to a hydropower equipment fault diagnosis method based on a fault matching algorithm, which has the following technical effects:
1) The fault case library of the invention is used as a diagnostic tool of the bottom layer, and mainly provides case matching service for advanced application (fault diagnosis). The advanced application (fault diagnosis) initiates a diagnosis request, which comprises parameters such as KKS, time sequence time period and the like, the fault case library extracts time sequence data according to the parameters, data characteristics and symptoms are calculated, the data characteristics and the symptoms are matched and calculated in a combined mode through a plurality of matching algorithms, matching is carried out on the data characteristics and the symptoms, the data characteristics and the symptoms are matched with the related contents in the case library, the fault case which is most matched is inquired, and a diagnosis conclusion is obtained.
2) The method combines a cosine matching algorithm and a gray correlation algorithm, and the final result is fused through weighted average, so that the diagnosis result is more accurate by matching the historical fault cases from multiple angles.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The invention provides a hydropower equipment fault diagnosis method based on a fault matching algorithm, which is shown in figure 1 and comprises the following steps:
step one: according to the historical fault cases and typical fault problems of the hydropower equipment, a fault case library is organized, and the cases comprise information such as fault modes, fault symptoms, characteristic parameters, fault phenomena, treatment measures and the like.
Step two: acquiring running data of hydroelectric equipment in real time from an industrial Internet data platform, wherein the data comprise characteristic data such as stator temperature, upward-guiding X-direction swing degree peak value and the like;
step three: and calculating the credibility value of various symptoms by combining the characteristic data, wherein each symptom corresponds to different calculation logics.
Step four, carrying out normalization processing according to the fault symptom credibility value calculated in the step three and the corresponding symptom fixed weight in the fault mode, and calculating the fault mode credibility value;
step five: and (3) according to the fault symptom credibility value calculated in the step (III), sequentially carrying out matching calculation with the cases in the fault case library in the step (II) by utilizing a cosine similarity algorithm to obtain a matching degree value of each case.
Step six: and (3) calculating the median according to the characteristic data obtained in the step two in real time, and obtaining a group of sequences as a parent sequence.
Step seven: and inquiring cases with related characteristic data in the case library, and combining the characteristic data into a two-dimensional array to obtain a plurality of groups of subsequences. And combining the weight and the parent sequence of the feature data, and calculating a case matching degree value by using a gray correlation degree algorithm.
Step eight: and fusing the matching degree values calculated by the two algorithms by using a weighted average mode to obtain a final matching result.
Step nine: and combining other components to jointly confirm the fault cause, generating case preliminary information, manually supplementing and perfecting the fault information, forming a final case, and storing the final case in a fault case library.
And in the fourth step, according to the fault symptom credibility value calculated in the third step, carrying out normalization processing by combining the corresponding symptom fixed weight in the fault mode.
The normalization is to map data to a range of 0-1 for processing in vector normalization. For example, there are three symptoms in a failure mode, and the reliability is 0.85,0.6,1. The fixed weights are 0.15,0.3,0.15 respectively. The weights are normalized, 0.15+0.3+0.15= 0.6,0.15/0.6= 0.25,0.3/0.6= 0.5,0.15/0.6=0.25. After treatment 0.25,0.5,0.25 was obtained. And then, calculating the reliability of the three symptoms by combining weights: 0.85 x 0.25+0.6 x 0.5+1 x 0.15= 0.6625; the result is the reliability of the failure mode.
In the eighth step, the matching degree values calculated by the two algorithms are fused by using a weighted average mode to obtain a final matching result.
For example, the calculated result of gray correlation is 0.7, the cosine similarity is 0.8, the general weight value is the weight of gray correlation of 0.4, and the weight of cosine similarity of 0.6 is 0.7x0.4+0.8x0.6=0.676. And the final fusion result is obtained. The case with the largest fusion result is the final matching result of the case.
In the step eight, the fault cause is jointly confirmed by combining other components, and the fault diagnosis preliminary information is generated.
Other components are referred to as: FTA fault tree: the method for performing the deductive failure analysis from top to bottom by utilizing the Boolean logic combination low-order event can perform qualitative analysis and quantitative analysis, and is one of important analysis methods of safety system engineering; knowledge venation map: a technical method for describing knowledge and modeling association relation between world everything by using a graph model. The knowledge graph consists of nodes and edges. The knowledge graph is used as a new knowledge representation method and a new knowledge management idea.
The fault diagnosis preliminary information includes:
failure mode: unbalanced mass; probability of occurrence: 83.9%; severity of: high;
fault cause and handling measure 1: unstable operation and equipment replacement;
fault cause and handling measure 2: the rotating part shifts, the equipment is closed, and maintenance is notified;
fault cause and handling measure 3: the rotor is sleeved with asymmetric parts, equipment is closed, and maintenance is notified;
fault cause and handling measure 4: coupling misalignment.
Aiming at the analysis of the field of the failure of the hydroelectric equipment, the failure modes and symptoms of various related equipment failures are combined, and each symptom corresponds to specific algorithm logic. The credibility of various fault modes is obtained by fusing credibility of various symptoms according to fixed weights.
The part symptom credibility calculating method comprises the following steps:
1) The conversion in the vibration spectrum is larger: if the rotational speed of the unit reaches more than 50% of the rated rotational speed, the rotation frequency amplitude fyp1 of the vibration swing degree channel is greater than the reference value fyp base (30% of the upper limit) of rotation frequency, and then the rotation frequency early warning value is as follows: fyp1bj (45% of the upper limit) cf= fyp1× fyp 1/(fyp 1× fyp1+ fyp1bj× fyp1 bj).
2) Vibration increases linearly with the square of the rotational speed: during the speed up of the unit, the vibration swing amplitudes of 40-60% (set as speed 1) and 80-100% of the rated rotation speed (set as speed 2) are taken as fypp1 and fypp2 respectively, the changes of the rotation speed and the vibration swing are calculated as speed b and fyppb respectively, then speed b= (speed 2/speed 1) 2, fyppp 2/fyppp 1 if fyppb/speed b >0.75 and fyppb/speed b <1.5 are taken, and otherwise, cf= 0. And when a plurality of groups of data meeting the condition exist, taking the maximum value of the credibility.
3) The lower guiding swing degree is large: let the passband amplitude lowerguide window of the downswing, the channel danger value: lowguide database;
the confidence coefficient calculation formula is: cf=min (1.0, 1.2×lowertreauthow/lowuidrethreddanger.
4) Vibration is mainly frequency conversion: if the rotation frequency fyp (1X amplitude) of the vibration amplitude channel is larger than the reference value of the frequency band, the reliability calculation formula is given by taking the through-frequency amplitude fypp (peak-to-peak value) as a reference: cf=min (1.0, 1.2×fyp1/fypp).
The cosine similarity algorithm is as follows:
；
x is the reliability of the fault symptoms calculated in the step three, Y is the reliability value of the fault symptoms bound by the cases in the fault case library, and i is the number of the fault symptoms. For example: and step three, calculating symptoms: the lower frame vibrates greatly, and the reliability is 1; the downswing degree is large, and the credibility is 0.87. The fault symptoms bound in a certain case are: the lower frame vibrates greatly, and the reliability is 1; the lower guiding swing degree is large, and the reliability is 0.97; vibration is mainly frequency conversion, and the reliability is 0.94. The calculation formula is:
；
the result is a matching degree value 0.8277, which is closer to 1, indicating a higher matching degree.
Gray correlation algorithm:
；
X 0 as parent sequence, X i For the subsequences, k is the characteristic data in each subsequence, ρ is an adjustable coefficient, typically 0.5, i is the case number, w i (k) Is the weight of the feature data. The specific operation is as follows:
A. the normalization processing of the parent sequence and the child sequence aims at eliminating the influence of different characteristics and different units on the final result, and adopts a normalization method as vector normalization.
B. Subtracting the normalized sequences to obtain a group of difference sequences, finding the maximum value and the minimum value, and obtaining the molecules in the formula through min+0.5xmax.
C. And B, summing the difference sequence in the step B with 0.5 max to obtain a formula denominator, dividing the formula denominator by the formula denominator, multiplying the formula denominator by each characteristic data weight, and finally obtaining the matching degree value of the subsequence and the parent sequence through summation.
Specific cases:
the characteristic data acquired in real time form a set of parent sequences: [159.7,0.0, 75.1, 49.0,5.3, 240.1, 778.3],
two cases are provided in the case library for matching calculation:
[[161.5，0.0，76.5，50.0，6.2，252.6，780.0]，
[229.5，0.0，104.4，79.9，9.8，342.8，847.4]]；
the weight of the corresponding characteristic data is as follows:
[[0.15，0.15，0.15，0.15，0.15，0.2，0.05]；
[0.15，0.15，0.15，0.15，0.15，0.2，0.05]]；
and (3) carrying out normalization treatment in the step A to obtain a parent sequence: [0.4945, 0.0, 0.5018, 0.4612, 0.4156, 0.4911, 0.5599]
Subsequence: [ [0.5001, 0.0, 0.5112, 0.4706, 0.4862, 0.5167, 0.5611], [0.7107, 0.0, 0.6976, 0.7521, 0.7686, 0.7012, 0.6096] ];
obtaining a difference sequence from the step B: [ [0.0056, 0.0, 0.0094, 0.0094, 0.0706, 0.0256, 0.0012], [0.2162, 0.0, 0.1958, 0.2909, 0.353, 0.2101, 0.0497] ], maximum: 0.353, minimum: 0.
and finally, calculating the matching degree value of the two cases by the step C, wherein the matching degree value is as follows: 0.9114 and 0.5253.
Fault case library: the historical fault experience is summarized and organized into a typical fault case library which is the same type of equipment, and fault cases are rapidly matched according to diagnosis rules in fault diagnosis, so that the efficiency of fault diagnosis and a fault removing method are improved.
Symptoms are: it is understood that a phenomenon, such as a large upward swing and a large water swing, is generally defined quantitatively by the fact that the value of the relevant measuring point falls within a defined value interval.
Fault-matching similarity: refers to the overall similarity of the symptoms of the fault to the symptoms in the fault case, the closer the value is to 1, the more similar.
Failure mode: manifestation of failure. More specifically, a failure mode is a canonical description of a failure phenomenon for a set of devices. For example: breaking the breaking pin, running faults of the shafting of the hydroelectric generating set, faults of a fan and the like.
The current fault diagnosis method does not combine past fault case experience, so that the diagnosis result has larger difference from the expected result, and an accurate result cannot be obtained. The invention combines the cosine matching algorithm and the gray correlation algorithm, and the final result is fused through weighted average, so that the diagnosis result is more accurate by matching the historical fault cases from multiple angles.
Claims (5)
1. The hydropower equipment fault diagnosis method based on the fault matching algorithm is characterized by comprising the following steps of:
step one, a fault case library is established according to historical fault experience and typical fault problems, wherein the fault case library comprises fault modes, fault symptoms, characteristic parameters, fault phenomena and treatment measure information;
acquiring operation data of the hydropower equipment in real time, wherein the operation data of the hydropower equipment comprise stator temperature and upper-guide X-direction swing degree peak-to-peak characteristic data;
step three, calculating the credibility value of various fault symptoms by combining the characteristic data obtained in the step two;
step four, according to the fault symptom credibility value calculated in the step three, carrying out normalization processing by combining the corresponding symptom fixed weight in the fault mode, and calculating the fault mode credibility value;
step five, according to the fault mode reliability value calculated in the step four, sequentially carrying out matching calculation with the cases of the fault case library in the step one by utilizing a cosine similarity algorithm to obtain a matching degree value of each case;
step six, calculating the median of the characteristic data when the fault occurs according to the characteristic data obtained in the step two in real time, and obtaining a group of series as a parent sequence;
inquiring cases with related characteristic data in a fault case library, combining the characteristic data into a two-dimensional array to obtain a plurality of groups of subsequences, and calculating a case matching degree value by using a gray correlation degree algorithm in combination with the weight and the parent sequence of the characteristic data;
combining the cosine similarity algorithm in the fifth step with the gray correlation algorithm in the seventh step to calculate a matching degree value, and fusing according to a certain weight by using a weighted average mode to obtain a final matching result;
and step nine, based on the final matching result of the step eight, combining other components to jointly confirm the fault cause, generating fault diagnosis preliminary information, and synchronously updating a fault case library.
2. The method for diagnosing a hydropower device failure based on a failure matching algorithm according to claim 1, wherein: in the third step, aiming at the fault sign with large down-lead swing, the reliability calculation formula is as follows:
cf=min(1.0,1.2*LowerGuideThrow/LowerGuideThrowDanger)
the lowguide window is a passband amplitude value for setting a downscaling degree, and the lowguide window Danger is a channel danger value;
aiming at the fault symptoms of large frequency conversion in the vibration frequency spectrum, the reliability calculation formula is as follows:
cf=fyp1*fyp1/(fyp1*fyp1+fyp1bj*fyp1bj)
wherein fyp is the frequency conversion amplitude of the vibration swing degree channel, and fyp1bj is the frequency conversion early warning value.
3. The method for diagnosing a hydropower device failure based on a failure matching algorithm according to claim 1, wherein: in the fourth step, the fault mode comprises breaking of the breaking pin, running fault of the shafting of the hydroelectric generating set and fault of the fan.
4. The method for diagnosing a hydropower device failure based on a failure matching algorithm according to claim 1, wherein: in the fifth step, the cosine similarity algorithm is as follows:
；
wherein X is the fault symptom credibility value calculated in the step three, Y is the fault symptom credibility value bound by the cases in the fault case library, and i is the number of the fault symptoms.
5. The method for diagnosing a hydropower device failure based on a failure matching algorithm according to claim 1, wherein: in the eighth step, the gray correlation algorithm is:
；
wherein X is 0 As parent sequence, X i For the subsequences, k is the characteristic data in each subsequence, ρ is the adjustable coefficient, i is the case number, w i (k) Is the weight of the feature data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311271118.3A CN117009828B (en) | 2023-09-28 | 2023-09-28 | Hydropower equipment fault diagnosis method based on fault matching algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311271118.3A CN117009828B (en) | 2023-09-28 | 2023-09-28 | Hydropower equipment fault diagnosis method based on fault matching algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117009828A true CN117009828A (en) | 2023-11-07 |
| CN117009828B CN117009828B (en) | 2023-12-12 |
Family
ID=88562133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311271118.3A Active CN117009828B (en) | 2023-09-28 | 2023-09-28 | Hydropower equipment fault diagnosis method based on fault matching algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117009828B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117373556A (en) * | 2023-12-04 | 2024-01-09 | 山东清控生态环境产业发展有限公司 | Tracing instrument and system based on multidimensional data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090276136A1 (en) * | 2008-04-30 | 2009-11-05 | Steven Wayne Butler | Method for calculating confidence on prediction in fault diagnosis systems |
| CN109783500A (en) * | 2019-01-21 | 2019-05-21 | 北京邮电大学 | A kind of method for diagnosing faults based on fault tree and case similitude |
| CN109919495A (en) * | 2019-03-12 | 2019-06-21 | 中国计量大学 | Photovoltaic plant monitoring data exception and degree judgment method based on threshold calculations |
| CN111076962A (en) * | 2020-01-03 | 2020-04-28 | 中国电建集团华东勘测设计研究院有限公司 | Electromechanical equipment fault diagnosis method for intelligent hydraulic power plant |
| CN113592012A (en) * | 2021-08-06 | 2021-11-02 | 北京石油化工学院 | Fault diagnosis method and system for maintenance auxiliary equipment |
-
2023
- 2023-09-28 CN CN202311271118.3A patent/CN117009828B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090276136A1 (en) * | 2008-04-30 | 2009-11-05 | Steven Wayne Butler | Method for calculating confidence on prediction in fault diagnosis systems |
| CN109783500A (en) * | 2019-01-21 | 2019-05-21 | 北京邮电大学 | A kind of method for diagnosing faults based on fault tree and case similitude |
| CN109919495A (en) * | 2019-03-12 | 2019-06-21 | 中国计量大学 | Photovoltaic plant monitoring data exception and degree judgment method based on threshold calculations |
| CN111076962A (en) * | 2020-01-03 | 2020-04-28 | 中国电建集团华东勘测设计研究院有限公司 | Electromechanical equipment fault diagnosis method for intelligent hydraulic power plant |
| CN113592012A (en) * | 2021-08-06 | 2021-11-02 | 北京石油化工学院 | Fault diagnosis method and system for maintenance auxiliary equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117373556A (en) * | 2023-12-04 | 2024-01-09 | 山东清控生态环境产业发展有限公司 | Tracing instrument and system based on multidimensional data |
| CN117373556B (en) * | 2023-12-04 | 2024-02-13 | 山东清控生态环境产业发展有限公司 | Tracing instrument and system based on multidimensional data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117009828B (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111596604B (en) | Intelligent fault diagnosis and self-healing control system and method for engineering equipment based on digital twinning | |
| JP2021064370A (en) | Method and system for semi-supervised deep abnormality detection for large-scale industrial monitoring system based on time-series data utilizing digital twin simulation data | |
| CN117009828B (en) | Hydropower equipment fault diagnosis method based on fault matching algorithm | |
| CN106529719B (en) | Wind power prediction method based on particle swarm optimization algorithm wind speed fusion | |
| Zhang et al. | Semisupervised momentum prototype network for gearbox fault diagnosis under limited labeled samples | |
| CN104200396B (en) | A kind of wind turbine component fault early warning method | |
| CN110994604B (en) | Power system transient stability assessment method based on LSTM-DNN model | |
| CN107609574A (en) | Wind turbines fault early warning method based on data mining | |
| CN115859077A (en) | Multi-feature fusion motor small sample fault diagnosis method under variable working conditions | |
| CN113408068A (en) | Random forest classification machine pump fault diagnosis method and device | |
| CN111680875A (en) | Unmanned aerial vehicle state risk fuzzy comprehensive evaluation method based on probability baseline model | |
| CN116502072B (en) | Robust fault diagnosis method for key components of wind generating set under complex variable working conditions | |
| CN115791174B (en) | Rolling bearing abnormality diagnosis method, system, electronic equipment and storage medium | |
| Zhou et al. | Structural health monitoring of offshore wind power structures based on genetic algorithm optimization and uncertain analytic hierarchy process | |
| CN111060779A (en) | Power grid partition fault diagnosis method and system based on probabilistic neural network | |
| CN115758083A (en) | Motor bearing fault diagnosis method based on time domain and time-frequency domain fusion | |
| CN116311594A (en) | Ship subsystem state analysis method, device and storage medium | |
| CN117232809A (en) | Fan main shaft fault pre-diagnosis method based on DEMATEL-ANP-CRITIC combined weighting | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| CN110441081A (en) | A kind of intelligent diagnosing method and intelligent diagnosis system of rotating machinery fault | |
| CN114320773B (en) | Wind turbine generator system fault early warning method based on power curve analysis and neural network | |
| Dinh et al. | Implementation of Digital Twin-Assisted Condition Monitoring and Fault Diagnosis for Wind Turbines | |
| CN115560962A (en) | Fan abnormal state detection method based on multi-level space-time diagram neural network | |
| CN103020006B (en) | A kind of equipment state prediction method excavated based on mass data | |
| Gelman et al. | Novel anomaly detection technique based on the nearest neighbour and sequential methods |
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 |