CN118171224A - Health evaluation method and device for hydroelectric generating set - Google Patents
Health evaluation method and device for hydroelectric generating set Download PDFInfo
- Publication number
- CN118171224A CN118171224A CN202410606977.1A CN202410606977A CN118171224A CN 118171224 A CN118171224 A CN 118171224A CN 202410606977 A CN202410606977 A CN 202410606977A CN 118171224 A CN118171224 A CN 118171224A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- data set
- calculation
- hydroelectric generating
- component
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 216
- 230000036541 health Effects 0.000 title claims abstract description 66
- 238000004364 calculation method Methods 0.000 claims abstract description 81
- 238000012545 processing Methods 0.000 claims abstract description 66
- 238000000034 method Methods 0.000 claims abstract description 27
- 238000013210 evaluation model Methods 0.000 claims abstract description 13
- 238000013528 artificial neural network Methods 0.000 claims abstract description 11
- 238000000513 principal component analysis Methods 0.000 claims abstract description 10
- 230000015556 catabolic process Effects 0.000 claims description 101
- 238000006731 degradation reaction Methods 0.000 claims description 101
- 238000012360 testing method Methods 0.000 claims description 38
- 238000012544 monitoring process Methods 0.000 claims description 36
- 239000011159 matrix material Substances 0.000 claims description 29
- 230000003449 preventive effect Effects 0.000 claims description 25
- 238000010276 construction Methods 0.000 claims description 10
- 230000009467 reduction Effects 0.000 claims description 10
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 10
- 230000002829 reductive effect Effects 0.000 claims description 8
- 230000001133 acceleration Effects 0.000 claims description 2
- 239000000306 component Substances 0.000 abstract description 74
- 239000008358 core component Substances 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 25
- 238000004891 communication Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 238000001816 cooling Methods 0.000 description 3
- 238000012806 monitoring device Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000010355 oscillation Effects 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 239000004215 Carbon black (E152) Substances 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 238000000137 annealing Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013506 data mapping Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 150000002430 hydrocarbons Chemical class 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000011428 standard deviation standardization method Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a health evaluation method and a device for a hydroelectric generating set, and relates to the technical field of hydroelectric generation, wherein the method comprises the following steps: acquiring an original data set; performing correlation calculation on the original data set to obtain a first processed data set; performing principal component analysis on the first processed data set to obtain a second processed data set; inputting the second processing data set into a preset time sequence prediction neural network to obtain component state parameters in a plurality of hydroelectric generating sets; calculating component state parameters in all the hydroelectric generating sets through a preset evaluation model to obtain an evaluation information set; and calculating the evaluation information set through a preset arrangement model to obtain the health evaluation value of the hydroelectric generating set. According to the invention, on one hand, the influence of the relevance among different components on the evaluation of the whole equipment is comprehensively considered, and on the other hand, the different evaluation index items of the core component are comprehensively considered, so that the evaluation precision is ensured.
Description
Technical Field
The invention relates to the technical field of hydroelectric generation, in particular to a health evaluation method and device for a hydroelectric generating set.
Background
In the existing evaluation of the running state of the hydroelectric generating set, a plurality of monitoring devices are usually arranged in the assembly, then data collected by the monitoring devices are compared with historical data one by one, and when the monitoring data are not matched with the historical data, faults exist in the assembly. However, the method only carries out health evaluation of the hydroelectric generating set from the angle of a single index item, does not consider the relevance between components, and cannot comprehensively and truly reflect the state of the hydroelectric generating set. Therefore, there is a need for a health evaluation method for a hydroelectric generating set, which needs to comprehensively consider the influence of the relevance between different components on the evaluation of the whole equipment on one hand, and comprehensively consider different evaluation index items of the core component on the other hand, so as to ensure the evaluation accuracy.
Disclosure of Invention
The invention aims to provide a health evaluation method and a device for a hydroelectric generating set, so as to solve the problems. In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
in a first aspect, the present application provides a method for health assessment of a hydro-generator set, the method comprising:
Acquiring an original data set, wherein the original data set comprises on-line monitoring data and preventive test data collected in a preset time;
performing correlation calculation on the online monitoring data and the preventive test data to obtain a first processing data set;
performing principal component analysis on the first processed data set to obtain a second processed data set;
inputting the second processing data set into a preset time sequence prediction neural network to obtain component state parameters in a plurality of water turbine generator sets;
calculating all component state parameters in the hydroelectric generating set through a preset evaluation model to obtain an evaluation information set;
and calculating the evaluation information set through a preset arrangement model to obtain a health evaluation value of the hydroelectric generating set, wherein the health evaluation value is used for feeding back the health state of the hydroelectric generating set.
In a second aspect, the present application also provides a health evaluation device for a hydroelectric generating set, the device comprising:
The acquisition module is used for acquiring an original data set, wherein the original data set comprises on-line monitoring data and preventive test data which are collected in a preset time;
The first calculation module is used for carrying out correlation calculation on the online monitoring data and the preventive test data to obtain a first processing data set;
the second calculation module is used for carrying out principal component analysis on the first processing data set to obtain a second processing data set;
the prediction module is used for inputting the second processing data set into a preset time sequence prediction neural network to obtain component state parameters in a plurality of hydroelectric generating sets;
The third calculation module is used for calculating all the component state parameters in the hydroelectric generating set through a preset evaluation model to obtain an evaluation information set;
And the fourth calculation module is used for calculating the evaluation information set through a preset arrangement model to obtain a health evaluation value of the hydroelectric generating set, wherein the health evaluation value is used for feeding back the health state of the hydroelectric generating set.
The beneficial effects of the invention are as follows:
According to the invention, the online monitoring data and the preventive test data collected in the preset time are introduced, and a second processing data set is obtained after correlation calculation and principal component analysis, wherein the second processing data set is key data affecting the hydroelectric generating set, so that the influence of redundant data on evaluation is avoided; then inputting the second processing data set into a preset time sequence prediction neural network, so that the evaluation accuracy is ensured; and then calculating the state parameters of all the components in the water-turbine generator set through a preset evaluation model to obtain an evaluation information set, wherein the evaluation influence of different degradation index items on the whole equipment is comprehensively considered in the evaluation information set, and the evaluation information set also considers the evaluation index items of the weight of the components in the water-turbine generator set, so that the method can reflect the evaluation influence of the relevance between the components on the whole equipment.
Drawings
Fig. 1 is a schematic flow chart of a health evaluation method for a hydroelectric generating set according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a health evaluation device for a hydroelectric generating set according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating a third computing module according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a health evaluation device for a hydroelectric generating set according to an embodiment of the present invention;
The marks in the figure: 1. an acquisition module; 2. a first computing module; 3. a second computing module; 4. a prediction module; 5.a third calculation module; 6. a fourth calculation module; 21. a first calculation unit; 22. a second calculation unit; 23. a third calculation unit; 24. a fourth calculation unit; 31. a fifth calculation unit; 32. a sixth calculation unit; 33. a seventh calculation unit; 34. an eighth calculation unit; 51. a first processing unit; 52. a second processing unit; 53. a third processing unit; 511. a first acquisition unit; 512. a first processing subunit; 513. a second processing subunit; 514. a third processing subunit; 515. a fourth processing subunit; 521. a second acquisition unit; 522. a fifth processing subunit; 523. a sixth processing subunit; 800. health evaluation equipment for a hydroelectric generating set; 801. a processor; 802. a memory; 803. a multimedia component; 804. an I/O interface; 805. a communication component.
Detailed Description
Specific embodiments of the present invention will now be described in order to provide a clearer understanding of the technical features, objects and effects of the present invention. It should be understood that the particular embodiments described herein are illustrative only and are not intended to limit the invention, i.e., the embodiments described are merely some, but not all, of the embodiments of the invention. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present invention.
Example 1:
the embodiment provides a health evaluation method for a hydroelectric generating set.
Referring to fig. 1, the method includes steps S1 to S6, specifically:
s1, acquiring an original data set, wherein the original data set comprises on-line monitoring data and preventive test data which are collected in a preset time;
In step S1, the on-line monitoring data includes runout on-line monitoring data, air gap on-line monitoring data, partial discharge on-line monitoring data, and main color spectrum on-line monitoring data.
The preventive test data includes a rotor system test report, a stator system test report, an air cooling system test report, an upper guide bearing test report, and an overcurrent component test report.
S2, performing correlation calculation on the online monitoring data and the preventive test data to obtain a first processing data set;
to clarify the specific procedure of the correlation calculation, step S2 includes S21 to S24, specifically:
s21, carrying out standardized calculation on the online monitoring data to obtain a standard set of the online monitoring data;
In this step, the normalization calculation uses the standard deviation normalization method, which can be understood as: and carrying out module-by-module calculation on different data modules in the online monitoring data, such as: and finding out a maximum vibration value and a minimum vibration value corresponding to the data set from the vibration on-line monitoring data, and carrying out standardized calculation on each vibration monitoring data in the vibration on-line monitoring data through the maximum vibration value and the minimum vibration value to obtain standardized data corresponding to each vibration monitoring data. In this process, the normalized calculation formula is:
;(1)
In the above-mentioned formula (1), Representing standardized data corresponding to each runout monitoring data,/>Representing data before normalization of each runout monitoring data,/>Representing the minimum value of the oscillation,/>Indicating the maximum oscillation value.
And sequentially carrying out corresponding standard deviation normalization operation in different data modules, and finally constructing a standard set for obtaining on-line monitoring data.
S22, carrying out standardized calculation on the preventive test data to obtain a standard set of the preventive test data;
In this step, different test reports are first sorted to obtain a preventive test data table, taking the rotor system test report as an example: firstly, all parameters of the rotor are subjected to data table arrangement, wherein the classification of the parameters of the rotor can be subjected to multi-dimensional classification according to the change of the rotating speed of the rotor, the change of the oil temperature of the rotor, the change of the rotor along with the temperature of a medium, the change of the rotor along with the pressure, the change of the rotor along with the flow and the change of the rotor along with the load. And in each classification dimension, carrying out data standardization processing by adopting a standard deviation standardization method so as to obtain standardized data corresponding to each classification dimension. And then, sequentially carrying out data standardization calculation on a stator system test report, an air cooling system test report, an upper guide bearing test report and an overcurrent component test report, wherein the calculation principle is the same as that of a rotor system test report, and finally summarizing standardized data tables corresponding to different test reports to obtain a standard set of preventive test data.
S23, solving the standard set of the on-line monitoring data and the standard set of the preventive test data through a preset correlation model to obtain a plurality of correlation characteristic values;
In step S23, the preset correlation model is:
;(2)
In the above-mentioned (2), Represents the/>Personal relevance feature value,/>Vector corresponding to standard set for representing on-line monitoring data,/>Vector corresponding to the standard set representing preventive test data,/>Vector modular length corresponding to standard set for representing on-line monitoring data,/>Vector modulo length corresponding to the standard set of preventive test data is represented.
And S24, comparing and mapping each correlation characteristic value with a preset correlation characteristic value in sequence to obtain a first processing data set.
In this step, when the calculated correlation characteristic value is greater than a preset correlation characteristic value, it indicates that the data has strong correlation, and the standard set of the online monitoring data and the standard set of the preventive test data corresponding to the correlation characteristic value may be subjected to data mapping to obtain a first processed data set.
S3, performing principal component analysis on the first processing data set to obtain a second processing data set; to clarify the specific procedure of principal component analysis, step S3 includes S31 to S34, specifically:
S31, carrying out coefficient matrix calculation on the first processing data set to obtain a correlation coefficient matrix;
In step S31, matrix elements in the correlation coefficient matrix are calculated according to formula (3):
;(3)
In the above-mentioned (3), Represents the/>, of the correlation coefficient matrixLine and/>Column elements; /(I)Representing the/>, in the first processed datasetThe/>, in the downstream data moduleA correlation feature value; /(I)Representing the/>, in the first processed datasetAverage value of the forward data modules; /(I)Representing the/>, in the first processed datasetThe/>, in the reverse data moduleA correlation feature value; /(I)Representing the/>, in the first processed datasetAverage value of the reverse data modules; /(I)Representing the number of rows and columns of the correlation coefficient matrix.
S32, carrying out feature solution on the correlation coefficient matrix to obtain a feature value of the correlation coefficient matrix;
In step S32, the correlation coefficient matrix is subjected to feature solution, and in the solution process, calculation is performed according to formula (4):
;(4)
In the above-mentioned (4), Characteristic value representing correlation coefficient matrix,/>Representing an identity matrix,/>Representing a matrix of correlation coefficients,/>Representing eigenvalues/>The corresponding feature vector is the feature vector of the correlation coefficient.
S33, calculating the eigenvalues of the correlation coefficient matrix through a preset principal component solving model to obtain the number of principal components;
in step S33, the preset principal component solving model is:
;(5)
In the above-mentioned (5), the above-mentioned, Represents the/>Main component contribution rate corresponding to each characteristic value,/>Represents the/>Characteristic value/>Representing the number of the characteristic values; when/>If the contribution rate is larger than the preset contribution rate, the main component is determined, and the preset contribution rate can be set to 90%.
And S34, constructing data according to the number of the main components to obtain a second processing data set.
In this step, if the number of principal components obtained in step S33 is p, matrix data corresponding to the p principal components is retained to obtain a second processed data set.
S4, inputting the second processing data set into a preset time sequence prediction neural network to obtain component state parameters in a plurality of hydroelectric generating sets;
In step S4, the preset time series prediction neural network adopts the existing LSTM cyclic neural network, wherein normal data of the hydro-generator set is collected and trained, the activating function adopts sigmoid, the initial learning rate in the training process is e -4, the learning rate is adjusted by using a cosine annealing algorithm, the maximum learning rate and the minimum learning rates e -3 and e -6 are 10000 times, and the time series prediction neural network is obtained after training is completed. And inputting the second processing data set, and correspondingly outputting component state parameters in the hydroelectric generating set when abnormal data occur.
S5, calculating all component state parameters in the hydroelectric generating set through a preset evaluation model to obtain an evaluation information set;
in the method, in order to define a specific calculation process of the evaluation information set, the evaluation model includes a preset first evaluation function and a preset second evaluation function, the evaluation information set includes a first evaluation data set and a second evaluation data set, and step S5 includes steps S51 to S53, specifically includes:
S51, carrying out degradation degree calculation on all component state parameters in the hydroelectric generating set through the first evaluation function to obtain a first evaluation data set;
In step S51, step S51 includes S511 to S515, specifically:
S511, acquiring degradation degree evaluation index items, wherein the degradation degree evaluation index items comprise a proportion degradation index item, an acceleration degradation index item and a reduction degradation index item;
S512, carrying out degradation degree calculation on all component state parameters and proportion degradation index items in the hydroelectric generating set through the first evaluation function to obtain a proportion degradation degree evaluation data set;
in step S512, if the accelerated degradation indicator term and the reduced degradation indicator term are set to be predetermined constants, the first evaluation function is:
;(6)
in the above-mentioned (6), A first evaluation function for calculating the degree of degradation of the scale; /(I)Represents the/>, of the scale deterioration index itemsA child item; /(I)All sub-items in the scale degradation index item are represented, which may include an upper lead degree of degradation, an upper frame vibration degree of degradation, and the like; /(I)Indicating that the accelerated degradation indicator term is set to be constant,/>The degradation index item is set to be constant.
S513, carrying out degradation degree calculation on all component state parameters and accelerated degradation index items in the hydroelectric generating set through the first evaluation function to obtain an accelerated degradation degree evaluation data set;
in step S513, setting the proportional degradation index item and the reduction degradation index item to be preset constants, the first evaluation function is:
;(7)
In the above-mentioned (7), A first evaluation function for performing an accelerated degradation degree calculation; /(I)Represents the/>, of the accelerated degradation indicatorsA child item; /(I)All sub-items in the accelerated degradation index item are represented, which may include a minimum air gap degradation degree, a positive discharge amount degradation degree, and the like; /(I)The index item representing the proportion degradation is set to be constant,/>The degradation index item is set to be constant.
S514, carrying out degradation degree calculation on all component state parameters and degradation degree reduction and adjustment degradation index items in the hydroelectric generating set through the first evaluation function to obtain a degradation degree reduction and adjustment evaluation data set;
In step S514, the first evaluation function is that:
;(8)
In the above-mentioned (8), A first evaluation function for performing degradation degree calculation; /(I)Represents reduction of the first/>, in the degradation index itemA child item; /(I)Representing all sub-items in the reduced degradation index item, which may include a total hydrocarbon content degradation degree, a rotor centrifugal force degradation degree, and the like;
the index item representing the proportion degradation is set to be constant,/> The accelerated degradation indicator term is set to be constant.
And S515, carrying out data construction according to the proportion degradation degree evaluation data set, the accelerated degradation degree evaluation data set and the reduced degradation degree evaluation data set to obtain a first evaluation data set.
The influence of each single degradation degree evaluation index item on all component state parameters in the water turbine generator set is comprehensively considered in the first evaluation data set, so that the health state of the water turbine generator set can be accurately evaluated from the degradation degree angle.
S52, carrying out weight calculation on all component state parameters in the hydroelectric generating set through the second evaluation function to obtain a second evaluation data set;
In step S52, step S52 includes S521 to S523, specifically:
S521, acquiring a component weight evaluation index item in the hydroelectric generating set;
in step S521, the component weight evaluation index items in the hydro-generator set include a rotor system weight evaluation index item, a stator system weight evaluation index item, an air cooling system weight evaluation index item, an upper guide bearing weight evaluation index item, and an overcurrent component weight evaluation index item.
S522, carrying out weight calculation on all component state parameters and component weight evaluation index items in the hydroelectric generating set through the second evaluation function to obtain component evaluation characteristic values;
In step S522, the second evaluation function is:
;(9)
in the above-mentioned (9), Representing a second evaluation function,/>Represents the/>Component state parameters in water turbine generator set,/>Represents the/>And (5) evaluating index items by the weight of each component.
And S523, when the component evaluation characteristic value is larger than a preset weight value, reserving the corresponding component state parameters in the water turbine generator set to obtain a second evaluation data set.
The influence of the criticality of the different components on the integrity of the hydro-generator set has been comprehensively considered in the second evaluation data set.
And S53, carrying out data construction according to the first evaluation data set and the second evaluation data set to obtain an evaluation information set.
And S6, calculating the evaluation information set through a preset arrangement model to obtain a health evaluation value of the hydroelectric generating set, wherein the health evaluation value is used for feeding back the health state of the hydroelectric generating set.
In step S6, the preset arrangement model is:
;(10)
In the above-mentioned (10), Representing the health evaluation value of the hydroelectric generating set,/>Representing the mean value of the first evaluation dataset,Preset weight coefficient representing the first evaluation dataset,/>Representing the mean of the second evaluation dataset,/>Representing preset weight coefficients of the second evaluation dataset.
When different component weight evaluation index items are combined, the health evaluation value of the corresponding hydroelectric generating set can be obtained. When D is larger than the preset health evaluation value, the highest weighted item in the component weight evaluation index items in the surface current hydroelectric generating set is a component which is easy to fail, so that the health state of the component in the hydroelectric generating set is fed back.
Example 2:
As shown in fig. 2, the present embodiment provides a health evaluation device for a hydroelectric generating set, the device includes:
An acquisition module 1 for acquiring a raw data set including on-line monitoring data and preventive test data collected within a preset time;
the first calculation module 2 is used for carrying out correlation calculation on the online monitoring data and the preventive test data to obtain a first processing data set;
A second calculation module 3, configured to perform principal component analysis on the first processing data set to obtain a second processing data set;
The prediction module 4 is used for inputting the second processing data set into a preset time sequence prediction neural network to obtain component state parameters in a plurality of hydroelectric generating sets;
The third calculation module 5 is used for calculating the state parameters of all the components in the hydroelectric generating set through a preset evaluation model to obtain an evaluation information set;
And the fourth calculation module 6 is used for calculating the evaluation information set through a preset arrangement model to obtain a health evaluation value of the hydroelectric generating set, wherein the health evaluation value is used for feeding back the health state of the hydroelectric generating set.
In one disclosed implementation of the invention, the first computing module 2 comprises:
A first calculating unit 21, configured to perform standardized calculation on the online monitoring data, so as to obtain a standard set of the online monitoring data;
A second calculation unit 22, configured to perform a standardized calculation on the preventive test data, to obtain a standard set of preventive test data;
a third calculation unit 23, configured to solve the standard set of the online monitoring data and the standard set of the preventive test data through a preset correlation model, so as to obtain a plurality of correlation characteristic values;
and a fourth calculating unit 24, configured to sequentially compare and map each correlation characteristic value with a preset correlation characteristic value, so as to obtain a first processing data set.
In one disclosed implementation of the invention, the second computing module 3 comprises:
A fifth calculating unit 31, configured to perform coefficient matrix calculation on the first processed data set to obtain a correlation coefficient matrix;
a sixth calculation unit 32, configured to perform feature solution on the correlation coefficient matrix to obtain a feature value of the correlation coefficient matrix;
A seventh calculation unit 33, configured to calculate the eigenvalues of the correlation coefficient matrix by using a preset principal component solution model, so as to obtain the number of principal components;
an eighth calculating unit 34 is configured to perform data construction according to the number of principal components, so as to obtain a second processed data set.
As shown in fig. 3, in one implementation method disclosed in the present invention, in the third computing module 5, the evaluation model includes a preset first evaluation function and a preset second evaluation function, the evaluation information set includes a first evaluation data set and a second evaluation data set, and the third computing module 5 includes:
A first processing unit 51, configured to calculate degradation degrees of all component state parameters in the hydro-generator set through the first evaluation function, so as to obtain a first evaluation data set;
The second processing unit 52 is configured to perform weight calculation on all component state parameters in the hydro-generator set through the second evaluation function, so as to obtain a second evaluation data set;
And a third processing unit 53, configured to perform data construction according to the first evaluation data set and the second evaluation data set, so as to obtain an evaluation information set.
In one disclosed embodiment of the present invention, the first processing unit 51 includes:
a first acquisition unit 511 for acquiring degradation degree evaluation index items including a proportional degradation index item, an accelerated degradation index item, and a reduced degradation index item;
A first processing subunit 512, configured to calculate a degradation degree of all component state parameters and proportional degradation index items in the hydro-generator set through the first evaluation function, so as to obtain a proportional degradation degree evaluation data set;
The second processing subunit 513 is configured to calculate a degradation degree of all component state parameters and accelerated degradation index items in the hydro-generator set through the first evaluation function, so as to obtain an accelerated degradation degree evaluation data set;
A third processing subunit 514, configured to calculate a degradation degree of all component state parameters and degradation index items in the hydro-generator set through the first evaluation function, so as to obtain a degradation degree evaluation dataset;
a fourth processing subunit 515, configured to perform data construction according to the proportional degradation degree evaluation data set, the accelerated degradation degree evaluation data set, and the reduced degradation degree evaluation data set, to obtain a first evaluation data set.
In one disclosed embodiment, the second processing unit 52 includes:
A second obtaining unit 521, configured to obtain a component weight evaluation index item in the hydro-generator set;
A fifth processing subunit 522, configured to perform weight calculation on all component state parameters and component weight evaluation index items in the hydro-generator set through the second evaluation function, so as to obtain a component evaluation feature value;
And a sixth processing subunit 523, configured to, when the component evaluation feature value is greater than a preset weight value, reserve a corresponding component state parameter in the hydro-generator set, to obtain a second evaluation data set.
It should be noted that, regarding the apparatus in the above embodiments, the specific manner in which the respective modules perform the operations has been described in detail in the embodiments regarding the method, and will not be described in detail herein.
Example 3:
corresponding to the above method embodiment, a health evaluation device for a hydro-generator set is further provided in this embodiment, and a health evaluation device for a hydro-generator set described below and a health evaluation method for a hydro-generator set described above may be referred to correspondingly.
Fig. 4 is a block diagram illustrating a health assessment apparatus 800 for a hydro-generator set, according to an exemplary embodiment. As shown in fig. 4, the health evaluation apparatus 800 for a hydro-generator set may include: a processor 801, a memory 802. The health assessment device 800 for a hydro-generator set may also include one or more of a multimedia component 803, an i/O interface 804, and a communication component 805.
The processor 801 is configured to control the overall operation of the health assessment apparatus 800 for a hydro-generator set, so as to perform all or part of the steps in a health assessment method for a hydro-generator set. The memory 802 is used to store various types of data to support operation at the one health assessment device 800 for a hydro-generator set, which may include, for example, instructions for any application or method operating on the one health assessment device 800 for a hydro-generator set, as well as application-related data, such as contact data, messages, pictures, audio, video, and so forth.
The Memory 802 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM for short), electrically erasable programmable Read-Only Memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ-Only Memory, EEPROM for short), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM for short), programmable Read-Only Memory (Programmable Read-Only Memory, PROM for short), read-Only Memory (ROM for short), magnetic Memory, flash Memory, magnetic disk, or optical disk.
The multimedia component 803 may include a screen and an audio component. Wherein the screen may be, for example, a touch screen, the audio component being for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted through the communication component 805. The audio assembly further comprises at least one speaker for outputting audio signals.
The I/O interface 804 provides an interface between the processor 801 and other interface modules, which may be a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons.
The communication component 805 is configured to perform wired or wireless communication between the health assessment device 800 for a hydro-generator set and other devices. Wireless communication, such as Wi-Fi, bluetooth, near field communication (Near FieldCommunication, NFC for short), 2G, 3G, or 4G, or a combination of one or more thereof, the corresponding communication component 805 may therefore include: wi-Fi module, bluetooth module, NFC module.
In an exemplary embodiment, a health assessment device 800 for a hydro-generator set may be implemented by one or more Application Specific Integrated Circuits (ASIC), digital signal processor (DIGITALSIGNAL PROCESSOR DSP), digital signal processing device (DIGITAL SIGNAL Processing Device DSPD), programmable logic device (Programmable Logic Device PLD), field programmable gate array (Field Programmable GATE ARRAY FPGA), controller, microcontroller, microprocessor, or other electronic component for performing a health assessment method for a hydro-generator set as described above.
In another exemplary embodiment, a computer readable storage medium is also provided, comprising program instructions which, when executed by a processor, implement the steps of a health assessment method for a hydro-generator set as described above. For example, the computer readable storage medium may be the memory 802 including program instructions described above, which are executable by the processor 801 of a health assessment device 800 for a hydro-generator set to perform a health assessment method for a hydro-generator set as described above.
Example 4:
corresponding to the above method embodiment, a readable storage medium is further provided in this embodiment, and a readable storage medium described below and a health evaluation method for a hydro-generator set described above may be referred to correspondingly.
A readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of a method for health assessment of a hydro-generator set according to the above method embodiments.
The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, which may store various program codes.
It should be noted that, for the sake of simplicity of description, the foregoing method embodiments are expressed as a series of combinations of actions, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously according to the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present application.
Claims (10)
1. A health evaluation method for a hydro-generator set, comprising:
Acquiring an original data set, wherein the original data set comprises on-line monitoring data and preventive test data collected in a preset time;
performing correlation calculation on the online monitoring data and the preventive test data to obtain a first processing data set;
performing principal component analysis on the first processed data set to obtain a second processed data set;
inputting the second processing data set into a preset time sequence prediction neural network to obtain component state parameters in a plurality of water turbine generator sets;
calculating all component state parameters in the hydroelectric generating set through a preset evaluation model to obtain an evaluation information set;
and calculating the evaluation information set through a preset arrangement model to obtain a health evaluation value of the hydroelectric generating set, wherein the health evaluation value is used for feeding back the health state of the hydroelectric generating set.
2. The method for health assessment of a hydro-generator set according to claim 1, wherein performing principal component analysis on the first processed data set to obtain a second processed data set comprises:
performing coefficient matrix calculation on the first processing data set to obtain a correlation coefficient matrix;
Carrying out feature solution on the correlation coefficient matrix to obtain a feature value of the correlation coefficient matrix;
calculating the eigenvalues of the correlation coefficient matrix through a preset principal component solving model to obtain the number of principal components;
and constructing data according to the number of the main components to obtain a second processing data set.
3. The method of claim 1, wherein the evaluation model comprises a first preset evaluation function and a second preset evaluation function, and the evaluation information set comprises a first evaluation data set and a second evaluation data set; calculating all component state parameters in the hydroelectric generating set through a preset evaluation model to obtain an evaluation information set, wherein the evaluation information set comprises the following components:
Carrying out degradation degree calculation on all component state parameters in the hydroelectric generating set through the first evaluation function to obtain a first evaluation data set;
Performing weight calculation on all component state parameters in the water turbine generator set through the second evaluation function to obtain a second evaluation data set;
and carrying out data construction according to the first evaluation data set and the second evaluation data set to obtain an evaluation information set.
4. A health evaluation method for a hydro-generator unit according to claim 3 wherein performing degradation degree calculation on all component state parameters in the hydro-generator unit by the first evaluation function to obtain a first evaluation data set comprises:
Acquiring degradation degree evaluation index items including a proportion degradation index item, an acceleration degradation index item, and a reduction degradation index item;
Carrying out degradation degree calculation on all component state parameters and proportion degradation index items in the hydroelectric generating set through the first evaluation function to obtain a proportion degradation degree evaluation data set;
carrying out degradation degree calculation on all component state parameters and accelerated degradation index items in the hydroelectric generating set through the first evaluation function to obtain an accelerated degradation degree evaluation data set;
carrying out degradation degree calculation on all component state parameters and degradation degree reduction and adjustment degradation index items in the water turbine generator set through the first evaluation function to obtain a degradation degree reduction and adjustment evaluation data set;
and carrying out data construction according to the proportion degradation degree evaluation data set, the accelerated degradation degree evaluation data set and the reduced degradation degree evaluation data set to obtain a first evaluation data set.
5. A health evaluation method for a hydro-generator unit according to claim 3 wherein weight calculation is performed on all component state parameters in the hydro-generator unit by the second evaluation function to obtain a second evaluation data set, comprising:
acquiring a component weight evaluation index item in the hydroelectric generating set;
performing weight calculation on all component state parameters and component weight evaluation index items in the hydroelectric generating set through the second evaluation function to obtain component evaluation characteristic values;
When the component evaluation characteristic value is larger than a preset weight value, the corresponding component state parameters in the hydroelectric generating set are reserved, and a second evaluation data set is obtained.
6. A health evaluation device for a hydro-generator set, comprising:
The acquisition module is used for acquiring an original data set, wherein the original data set comprises on-line monitoring data and preventive test data which are collected in a preset time;
The first calculation module is used for carrying out correlation calculation on the online monitoring data and the preventive test data to obtain a first processing data set;
the second calculation module is used for carrying out principal component analysis on the first processing data set to obtain a second processing data set;
the prediction module is used for inputting the second processing data set into a preset time sequence prediction neural network to obtain component state parameters in a plurality of hydroelectric generating sets;
The third calculation module is used for calculating all the component state parameters in the hydroelectric generating set through a preset evaluation model to obtain an evaluation information set;
And the fourth calculation module is used for calculating the evaluation information set through a preset arrangement model to obtain a health evaluation value of the hydroelectric generating set, wherein the health evaluation value is used for feeding back the health state of the hydroelectric generating set.
7. The health assessment device for a hydro-generator unit as defined by claim 6, wherein the second computing module comprises:
A fifth calculation unit, configured to perform coefficient matrix calculation on the first processed data set, to obtain a correlation coefficient matrix;
the sixth calculation unit is used for carrying out feature solution on the correlation coefficient matrix to obtain a feature value of the correlation coefficient matrix;
A seventh calculation unit, configured to calculate the eigenvalue of the correlation coefficient matrix through a preset principal component solution model, to obtain the number of principal components;
and an eighth calculation unit, configured to perform data construction according to the number of the principal components, to obtain a second processing data set.
8. The health evaluation device for a hydro-generator unit as defined by claim 6 wherein in the third calculation module, the evaluation model includes a preset first evaluation function and a preset second evaluation function, the evaluation information set includes a first evaluation data set and a second evaluation data set, and the third calculation module includes:
The first processing unit is used for carrying out degradation degree calculation on all component state parameters in the water turbine generator set through the first evaluation function to obtain a first evaluation data set;
the second processing unit is used for carrying out weight calculation on all component state parameters in the water turbine generator set through the second evaluation function to obtain a second evaluation data set;
And the third processing unit is used for carrying out data construction according to the first evaluation data set and the second evaluation data set to obtain an evaluation information set.
9. The health assessment device for a hydro-generator unit as defined in claim 8, wherein the first processing unit comprises:
a first acquisition unit configured to acquire a degradation degree evaluation index item including a proportional degradation index item, an accelerated degradation index item, and a reduced degradation index item;
the first processing subunit is used for carrying out degradation degree calculation on all component state parameters and proportion degradation index items in the hydroelectric generating set through the first evaluation function to obtain a proportion degradation degree evaluation data set;
The second processing subunit is used for carrying out degradation degree calculation on all component state parameters and accelerated degradation index items in the hydroelectric generating set through the first evaluation function to obtain an accelerated degradation degree evaluation data set;
The third processing subunit is used for carrying out degradation degree calculation on all component state parameters and degradation degree reduction and degradation index items in the hydroelectric generating set through the first evaluation function to obtain a degradation degree reduction and degradation degree evaluation data set;
And the fourth processing subunit is used for carrying out data construction according to the proportion degradation degree evaluation data set, the accelerated degradation degree evaluation data set and the reduced degradation degree evaluation data set to obtain a first evaluation data set.
10. The health assessment device for a hydro-generator unit as defined in claim 8, wherein the second processing unit comprises:
the second acquisition unit is used for acquiring component weight evaluation index items in the hydroelectric generating set;
The fifth processing subunit is used for carrying out weight calculation on all the component state parameters and the component weight evaluation index items in the hydroelectric generating set through the second evaluation function to obtain component evaluation characteristic values;
And the sixth processing subunit is used for reserving corresponding component state parameters in the hydroelectric generating set when the component evaluation characteristic value is larger than a preset weight value to obtain a second evaluation data set.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410606977.1A CN118171224A (en) | 2024-05-16 | 2024-05-16 | Health evaluation method and device for hydroelectric generating set |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410606977.1A CN118171224A (en) | 2024-05-16 | 2024-05-16 | Health evaluation method and device for hydroelectric generating set |
Publications (1)
Publication Number | Publication Date |
---|---|
CN118171224A true CN118171224A (en) | 2024-06-11 |
Family
ID=91355060
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410606977.1A Pending CN118171224A (en) | 2024-05-16 | 2024-05-16 | Health evaluation method and device for hydroelectric generating set |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118171224A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070288199A1 (en) * | 2006-06-09 | 2007-12-13 | Teruyoshi Washizawa | Regression analysis apparatus and method |
CN114282761A (en) * | 2021-11-24 | 2022-04-05 | 华电电力科学研究院有限公司 | Hydroelectric generating set health evaluation method and system based on characteristic statistical analysis |
CN115906602A (en) * | 2021-09-30 | 2023-04-04 | 国家电投集团广西金紫山风电有限公司 | Wind turbine generator tower barrel dumping monitoring and evaluating method based on deep learning Transformer self-coding |
CN116976191A (en) * | 2023-06-15 | 2023-10-31 | 南方电网调峰调频发电有限公司储能科研院 | Method for predicting shafting stability degradation trend of hydroelectric generating set |
CN117391499A (en) * | 2023-10-07 | 2024-01-12 | 中国华能集团清洁能源技术研究院有限公司 | Photovoltaic power station reliability evaluation method and device |
-
2024
- 2024-05-16 CN CN202410606977.1A patent/CN118171224A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070288199A1 (en) * | 2006-06-09 | 2007-12-13 | Teruyoshi Washizawa | Regression analysis apparatus and method |
CN115906602A (en) * | 2021-09-30 | 2023-04-04 | 国家电投集团广西金紫山风电有限公司 | Wind turbine generator tower barrel dumping monitoring and evaluating method based on deep learning Transformer self-coding |
CN114282761A (en) * | 2021-11-24 | 2022-04-05 | 华电电力科学研究院有限公司 | Hydroelectric generating set health evaluation method and system based on characteristic statistical analysis |
CN116976191A (en) * | 2023-06-15 | 2023-10-31 | 南方电网调峰调频发电有限公司储能科研院 | Method for predicting shafting stability degradation trend of hydroelectric generating set |
CN117391499A (en) * | 2023-10-07 | 2024-01-12 | 中国华能集团清洁能源技术研究院有限公司 | Photovoltaic power station reliability evaluation method and device |
Non-Patent Citations (1)
Title |
---|
王惠杰;张家宁;王雷雨;赵立坤;: "基于模糊分析与信息熵的大型机组故障诊断基准值研究", 热力发电, no. 03, 20 March 2018 (2018-03-20), pages 36 - 41 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Lu et al. | Dominant feature selection for the fault diagnosis of rotary machines using modified genetic algorithm and empirical mode decomposition | |
CN112052890B (en) | Method and device for predicting vibration of water supply pump | |
EP3761133A1 (en) | Diagnosis device and diagnosis method | |
CN109145256B (en) | Process monitoring method based on normative variable nonlinear principal component analysis | |
CN112116262A (en) | Evaluation method for health degree of wind generating set equipment | |
CN118171224A (en) | Health evaluation method and device for hydroelectric generating set | |
CN116029617B (en) | Quality acceptance form generation method, device, equipment and readable storage medium | |
CN116032016B (en) | Intelligent wind power plant running state on-line monitoring and early warning system and early warning method | |
CN108629077B (en) | Fault diagnosis device, monitoring device, fault diagnosis method, and recording medium | |
CN116170200A (en) | Power monitoring system time sequence abnormality detection method, system, equipment and storage medium | |
CN116090216A (en) | Power generation power prediction method and system based on typical correlation analysis | |
CN114124456A (en) | Safety detection method and device for comprehensive energy system, electronic equipment and storage medium | |
CN112836990A (en) | Tunnel monitoring equipment fault judgment method and device and electronic equipment | |
CN113347014A (en) | Industrial control system situation combined prediction method based on time sequence | |
Chou et al. | Economic design of variable sampling intervals charts with B&L switching rule | |
JP7325557B2 (en) | Abnormality diagnosis method and abnormality diagnosis device | |
US20230244959A1 (en) | Data processing device, data processing system, and data processing method | |
US20240104344A1 (en) | Hybrid-conditional anomaly detection | |
CN115683631B (en) | Bearing fault detection method and device | |
CN115267614B (en) | Detection method and system for intelligent transformer | |
CN112766059B (en) | Method and device for detecting product processing quality | |
CN115983663A (en) | New energy-based power generation analysis method and related equipment | |
CN117648650A (en) | Monitoring data anomaly detection method, system, equipment and readable storage medium | |
Chunliang et al. | Research on Prediction Method of Life Cycle of Nuclear Power Equipment Based on Fuzzy Clustering | |
CN112733289A (en) | Novel machine learning method for diagnosing motor bearing fault based on multi-scale permutation entropy |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination |