CN111307493B - Knowledge-based fault diagnosis method for tower type solar molten salt heat storage system - Google Patents
Knowledge-based fault diagnosis method for tower type solar molten salt heat storage system Download PDFInfo
- Publication number
- CN111307493B CN111307493B CN202010390259.7A CN202010390259A CN111307493B CN 111307493 B CN111307493 B CN 111307493B CN 202010390259 A CN202010390259 A CN 202010390259A CN 111307493 B CN111307493 B CN 111307493B
- Authority
- CN
- China
- Prior art keywords
- molten salt
- knowledge
- freezing
- storage system
- heat storage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 150000003839 salts Chemical class 0.000 title claims abstract description 98
- 238000003745 diagnosis Methods 0.000 title claims abstract description 41
- 238000005338 heat storage Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000008014 freezing Effects 0.000 claims abstract description 63
- 238000007710 freezing Methods 0.000 claims abstract description 63
- 230000000903 blocking effect Effects 0.000 claims abstract description 20
- 238000013528 artificial neural network Methods 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 8
- 239000006096 absorbing agent Substances 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 8
- 238000003062 neural network model Methods 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims 1
- 238000011002 quantification Methods 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 abstract description 9
- 230000000694 effects Effects 0.000 abstract description 5
- 238000012423 maintenance Methods 0.000 abstract description 3
- 238000004364 calculation method Methods 0.000 description 8
- 238000010248 power generation Methods 0.000 description 6
- 238000010521 absorption reaction Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000008646 thermal stress Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003749 cleanliness Effects 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/002—Thermal testing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/004—Testing the effects of speed or acceleration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention discloses a knowledge-based fault diagnosis method for a tower type solar molten salt heat storage system. Based on knowledge, the method has the advantages that on the basis of monitoring of vibration characteristics of the molten salt freezing blockage diagnosis, the matching degree of actually measured associated data and a database is combined, compared with a traditional vibration monitoring mode, the fault prediction is carried out on the molten salt heat storage system on the basis of the principle of influencing the molten salt freezing blockage, and the prediction effect is improved; the vibration fault knowledge is acquired based on neural network learning training, compared with other algorithms, the method has real-time performance and robustness, the problems of 'infinite recursion' and the like are avoided, and the accuracy of prediction is ensured; the method can realize vibration monitoring of the tower type solar heat storage system, predict the occurrence and position of the fused salt freezing and blocking fault, guide the dredging of the fused salt and the maintenance of the system, reduce the economic loss and potential safety hazard caused by the fused salt freezing and blocking and improve the economical efficiency and safety of the operation of the tower type solar power station.
Description
Technical Field
The invention belongs to the technical field of tower type solar molten salt heat storage systems, and particularly relates to a knowledge-based fault diagnosis method for a tower type solar molten salt heat storage system.
Background
The tower type solar thermal power generation system utilizes a certain number of heliostats to focus sunlight into a heat absorber of an absorption tower, and high-temperature steam is generated through heat exchange of working media to push a steam turbine to generate power, wherein the heat storage system is a key component of the tower type solar thermal power generation system. The fused salt is a fused mass formed after the salt is melted, and becomes a novel heat exchange working medium capable of replacing water due to superior physical properties such as high heat capacity, better fluidity and the like. However, the higher freezing point of the molten salt makes the system easily have freezing and blocking faults during operation, reduces the heat transfer efficiency, increases the thermal stress of a heated surface, and seriously influences the normal work of the heat storage system, so the monitoring and diagnosis of the freezing and blocking conditions of the molten salt of the heat storage system during design and operation have a key effect on improving the economy and the safety of a power generation system.
The detection of the prior art shows that the fault diagnosis research for the heat storage system of the tower-type solar power station is less, the common fault diagnosis of the superheater is mostly researched based on the phenomenon of uneven thermal stress of the heating surface, but the monitoring and the calculation of the temperature of the power generation system are difficult due to the high-temperature state of the power generation system during normal operation. At present, fault diagnosis based on vibration signals is researched more, but the dependency on process data is strong, and once data deviation occurs, the diagnosis effect is not ideal enough, and even the diagnosis is wrong. The fault diagnosis based on knowledge utilizes expert knowledge to carry out reasoning on actual problems, and has better diagnosis effect and practicability. By utilizing the neural network model, the knowledge-based fused salt freezing and plugging fault diagnosis is carried out by combining the correlation factors influencing the fused salt temperature on the basis of carrying out vibration characteristic monitoring on the tower type solar heat storage system, the fused salt freezing and plugging fault and the position where the fault occurs are predicted in time, the dredging of the fused salt and the maintenance of the system are guided, the prediction accuracy is greatly improved, the risk caused by the fused salt freezing and plugging is reduced, and the economical efficiency and the safety of the operation of the tower type solar power station are improved.
Disclosure of Invention
Aiming at the situation, in order to overcome the defects of the prior art, the invention provides a knowledge-based fault diagnosis method for a tower type solar molten salt heat storage system.
In order to achieve the purpose, the invention provides the following technical scheme:
the knowledge-based fault diagnosis method for the tower type solar molten salt heat storage system comprises the following steps:
first, vibration failure knowledge is obtained. According to the mode of historical cases, experiments and the like, acquiring a time domain spectrogram of molten salt freezing and plugging faults and establishing a vibration sample database, wherein the time domain spectrogram comprises the freezing and plugging faults and freezing and plugging degrees at different positions, extracting the characteristics of samples in the database, and training a neural network on the samples containing the characteristics of the freezing and plugging degrees to acquire the knowledge of the vibration faults;
and secondly, establishing a freezing and blocking associated knowledge base. Establishing a knowledge base aiming at freezing and blocking factors related to the knowledge base based on the knowledge acquired by the vibration fault, and realizing the regular expression of the molten salt freezing and blocking diagnosis knowledge, wherein the freezing and blocking factors comprise temperature, wind speed, irradiance, molten salt flow, cloud cover conditions and system operation conditions;
and thirdly, diagnosing the frozen block based on knowledge. The method comprises the following specific steps:
①, a sensor acquires a vibration signal of the molten salt heat storage system, and the vibration signal and the real-time acquired associated data form original data together;
②, the original data is processed by a data processing module to obtain real-time characteristic data;
③ substituting the acquired real-time characteristic data into the trained neural network model to diagnose the freezing and blocking of the neural network and determine the frozen and blocked state of the molten salt;
④ transmits the diagnosis result data to the user terminal.
Further, the vibration sample database comprises time domain spectrograms of various fault modes or normal operation of the heat storage system fused salt freezing and plugging, and respectively corresponds to single or multiple freezing and plugging types of a heat absorber pipeline, a fused salt storage tank, a fused salt circulating pump and a fused salt pipe network, wherein the freezing and plugging output of the heat absorber pipeline is represented as A, the freezing and plugging output of the fused salt storage tank is represented as B, the freezing and plugging output of the fused salt circulating pump is represented as C, the freezing and plugging output of the fused salt pipe network is represented as D, an output vector of 1 represents that a fault exists, and 0 represents that the;
further, the indexes of the features extracted from the time domain spectrogram in the vibration sample database mainly comprise an amplitude state and a waveform state. The characteristic data representing the amplitude state is amplitude, peak value and root mean square value, and the characteristic data representing the waveform state is waveform, pulse and kurtosis;
further, the feature data in the first step all need to be normalized.
Further, a radial basis function RBF is adopted in neural network training, a characteristic index which is extracted from a time-frequency spectrogram and contains the characteristic of the freezing and plugging degree is used as an input characteristic of the neural network, and a learning algorithm model is as follows:
① selecting a basic function, adopting a Gaussian radial basic function;
② calculation inputs and outputs;
③ calculating global errorE. If the global error is within the specified precision range, the learning process is finished, otherwise, the learning process of the next learning sample is carried out.
Furthermore, the sensor is an acceleration sensor;
further, the acquisition mode of the associated data is as follows: the temperature and irradiance are acquired through a real-time data server, an anemoscope arranged at the top end of a fused salt heat absorber transmits wind speed data in real time, the fused salt flow is acquired through an ultrasonic flowmeter, the cloud shading condition and the system operation condition are quantified through influence factors, and the cloud shading factor is calibrated to be [0,1 ]]According to the discontinuous numerical value with the historical data defined as the precision of 0.01, the calibration of the system operation factor is as follows: the system failure is defined as the coefficientωThe coefficient is 1 when the system normally runs;
further, knowledge reasoning based on the freezing blockage associated knowledge base adopts a factor associated analysis method, and the similarity between associated characteristic data and characteristic data in the database is calculated, wherein the calculation method comprises the following steps:
① determining the data string the obtained real-time associated feature data is an observation string
The characteristic data in the database is a reference string
；
② calculating correlation coefficient
。
③ solving the degree of association
. The degree of correlation represents the degree of similarity between the acquired real-time correlation characteristic data and the characteristic data in the database, and the higher the degree of similarity between the real-time correlation characteristic data and the characteristic data in the database is, the larger the calculated degree of correlation value is. The calculation formula is as follows:
furthermore, the freezing and blocking positions of the fused salt in the heat storage system obtained by diagnosis are four, namely a heat absorber pipeline, a fused salt storage tank, a fused salt circulating pump and a fused salt pipe network.
The invention has the beneficial effects that:
(1) based on knowledge, the method has the advantages that on the basis of monitoring of vibration characteristics of the molten salt freezing blockage diagnosis, the matching degree of actually measured associated data and a database is combined, compared with a traditional vibration monitoring mode, the fault prediction is carried out on the molten salt heat storage system on the basis of the principle of influencing the molten salt freezing blockage, and the prediction effect is improved;
(2) the vibration fault knowledge is acquired based on neural network learning training, compared with other algorithms, the method has real-time performance and robustness, the problems of 'infinite recursion' and the like are avoided, and the accuracy of prediction is ensured;
(3) the method can realize vibration monitoring of the tower type solar heat storage system, predict the occurrence and position of the fused salt freezing and blocking fault, guide the dredging of the fused salt and the maintenance of the system, reduce the economic loss and potential safety hazard caused by the fused salt freezing and blocking and improve the economical efficiency and safety of the operation of the tower type solar power station.
Drawings
FIG. 1 shows a fault diagnosis method of a knowledge-based tower type solar molten salt heat storage system.
FIG. 2 shows a heat storage system structure of the knowledge-based fault diagnosis method for the tower-type solar molten salt heat storage system.
FIG. 3 is a schematic diagram of an exemplary RBF neural network.
In fig. 2: 1. the heat absorber pipeline, 2, fused salt storage tank, 3, fused salt circulating pump, 4, fused salt pipe network.
Detailed Description
The technical solutions of the present invention are described in detail below with reference to the accompanying drawings and specific embodiments, and it should be noted that the detailed description is only for describing the present invention and should not be construed as limiting the present invention.
The method for diagnosing the fault of the tower type solar molten salt heat storage system based on knowledge (figure 1) comprises the following steps:
first, vibration failure knowledge is obtained. According to the mode of historical cases, experiments and the like, acquiring a time domain spectrogram of molten salt freezing and plugging faults and establishing a vibration sample database, wherein the time domain spectrogram comprises the freezing and plugging faults and freezing and plugging degrees at different positions, extracting the characteristics of samples in the database, and training a neural network on the samples containing the characteristics of the freezing and plugging degrees to acquire the knowledge of the vibration faults;
and secondly, establishing a freezing and blocking associated knowledge base. Establishing a knowledge base aiming at freezing and plugging factors related to the knowledge base based on the knowledge acquired by the vibration fault, and realizing the regular expression of the molten salt freezing and plugging diagnosis knowledge, wherein the freezing and plugging factors comprise temperature, wind speed, irradiance, molten salt flow, cloud shading condition and system operation condition, and the related freezing and plugging factors such as humidity, heat absorber coating absorption rate, heat absorber material heat conductivity coefficient, heliostat cleanliness and the like can also be increased according to the actual condition of the tower type solar power generation system;
and thirdly, diagnosing the frozen block based on knowledge. The method comprises the following specific steps:
①, a sensor acquires a vibration signal of the molten salt heat storage system, and the vibration signal and the real-time acquired associated data form original data together;
②, the original data is processed by a data processing module to obtain real-time characteristic data;
③ substituting the acquired real-time characteristic data into the trained neural network model to diagnose the freezing and blocking of the neural network and determine the frozen and blocked state of the molten salt;
④ transmits the diagnosis result data to the user terminal.
Further, the vibration sample database comprises time domain spectrograms of various fault modes or normal operation of the heat storage system fused salt freezing and plugging, and respectively corresponds to a single or multiple freezing and plugging types of a heat absorber pipeline 1, a fused salt storage tank 2, a fused salt circulating pump 3 and a fused salt pipe network 4 in the graph 2, wherein the frozen and plugging output of the heat absorber pipeline is represented as A, the frozen and plugging output of the fused salt storage tank is represented as B, the frozen and plugging output of the fused salt circulating pump is represented as C, the frozen and plugging output of the fused salt pipe network is represented as D, the output vector is 1, which indicates that a fault exists, and 0 indicates; the freezing and plugging fault type table is shown as the following table:
TABLE 1 Freeze-blocking fault type table
Note: a-frozen blockage of heat absorber pipeline, B-frozen blockage of molten salt storage tank, C-molten salt circulating pump and D-molten salt pipe network
Further, the characteristic indexes extracted from the time domain spectrogram in the vibration sample database mainly comprise an amplitude state and a waveform state. Wherein, the characteristic data representing the amplitude state is amplitude, peak value and root mean square value, the characteristic data representing the waveform state is waveform, pulse and kurtosis, and the vibration signal is assumed to be
The calculation formula is as follows:
further, the characteristic indexes extracted by the time domain spectrogram can be replaced by time domain indexes such as an absolute average value, a square root amplitude value, a peak value factor, a margin and the like according to specific conditions;
further, the feature data in the first step all need to be normalized, and the data to be processed is assumed to be
The processing method comprises the following steps:
further, the neural network training adopts a Radial Basis Function (RBF), the characteristic index which is extracted from the time-frequency spectrogram and contains the characteristic of the freezing and plugging degree is used as the input characteristic of the neural network, the RBF neural network is shown in figure 3, and the learning algorithm model is as follows:
① selecting a basis function, adopting a Gaussian radial basis function
The expression is as follows:
the RBF network is constructed bynOne input, 1 output,Nthe hidden node, the model of which can be expressed as:
wherein,xas an input to the RBF network,
；yfor the output of the RBF network,
；
is as followskThe connection weight of each hidden node;
is an offset constant;
in the form of a data center, the data center,
；
is an expansion constant;
② inputs and outputs are calculated, the training sample data set for the fault diagnosis is
The input sample is
Output is
The corresponding neural network output is:
wherein,pin order to train the number of samples,
；
② calculating global errorEThe calculation method comprises the following steps:
wherein,min order to be the maximum number of iterations,iis the number of randomly selected samples. If the global error is within the specified precision range, the learning process is finished, otherwise, the learning process of the next learning sample is carried out.
Furthermore, the sensor is an acceleration sensor, and can be replaced by a speed sensor;
further, the acquisition mode of the associated data is as follows: the temperature and irradiance are obtained through a real-time data server, and the anemoscope arranged at the top end of the molten salt heat absorber transmits in real timeWind speed data and molten salt flow are obtained through an ultrasonic flowmeter, cloud cover conditions and system operation conditions are quantified through influence factors, and the cloud cover factors are calibrated to be 0,1]According to the discontinuous numerical value with the historical data defined as the precision of 0.01, the calibration of the system operation factor is as follows: the system failure is defined as the coefficientωThe coefficient is 1 when the system normally runs;
further, knowledge reasoning based on the freezing blockage associated knowledge base adopts a factor associated analysis method, and the similarity between associated characteristic data and characteristic data in the database is calculated, wherein the calculation method comprises the following steps:
① determining the data string the obtained real-time associated feature data is an observation string
The characteristic data in the database is a reference string
；
② calculating correlation coefficient
。
③ solving the degree of association
. The degree of correlation represents the degree of similarity between the acquired real-time correlation characteristic data and the characteristic data in the database, and the higher the degree of similarity between the real-time correlation characteristic data and the characteristic data in the database is, the larger the calculated degree of correlation value is. The calculation formula is as follows:
furthermore, the freezing and blocking positions of the fused salt in the heat storage system obtained by diagnosis are four, namely a heat absorber pipeline, a fused salt storage tank, a fused salt circulating pump and a fused salt pipe network.
Claims (10)
1. A knowledge-based fault diagnosis method for a tower type solar molten salt heat storage system is characterized by comprising the following steps:
acquiring a time domain spectrogram of a fused salt freezing and plugging fault, establishing a vibration sample database comprising the freezing and plugging faults at different positions and freezing and plugging degrees, extracting the characteristics of samples in the database, and training a neural network on the samples containing the characteristics of the freezing and plugging degrees to acquire knowledge of the vibration fault;
establishing a knowledge base aiming at freezing and blocking factors related to the knowledge base based on the knowledge acquired by the vibration fault, and realizing the regular expression of the molten salt freezing and blocking diagnosis knowledge, wherein the freezing and blocking factors comprise temperature, wind speed, irradiance, molten salt flow, cloud cover conditions and system operation conditions;
and (5) performing knowledge-based frozen block diagnosis.
2. The knowledge-based fault diagnosis method for the tower type solar molten salt heat storage system according to claim 1, wherein the vibration sample database comprises time domain spectrograms of various fault modes or normal operation of the heat storage system molten salt freezing blockage, and the time domain spectrograms respectively correspond to single or multiple freezing blockage types of a heat absorber pipeline, a molten salt storage tank, a molten salt circulating pump and a molten salt pipe network.
3. The knowledge-based fault diagnosis method for the tower type solar molten salt heat storage system according to claim 2, wherein the indexes of the features extracted from the time domain spectrogram mainly comprise an amplitude state and a waveform state, the feature data representing the amplitude state comprise amplitude, a peak value and a root mean square value, and the feature data representing the waveform state comprise a waveform, a pulse and a kurtosis.
4. The knowledge-based fault diagnosis method for the tower-type solar molten salt heat storage system according to claim 3, wherein the characteristic data are normalized.
5. The knowledge-based fault diagnosis method for the tower-type solar molten salt heat storage system according to claim 1, wherein the neural network is a Radial Basis Function (RBF) network, a characteristic index which is extracted from a time-frequency spectrogram and contains a freezing blockage degree characteristic is used as an input characteristic of the neural network, and a learning process of the neural network is as follows:
selecting a basis function, and adopting a Gaussian radial basis function;
computing inputs and outputs;
calculating global errorEIf the global error is within the specified precision range, the learning process is finished, otherwise, the learning process is repeated.
6. The knowledge-based tower type solar molten salt heat storage system fault diagnosis method according to claim 1, wherein the step of freezing blockage diagnosis comprises:
acquiring a vibration signal of the molten salt heat storage system through a sensor, and forming original data together with the associated data acquired in real time;
processing the original data to obtain real-time characteristic data;
determining the frozen and blocked state of the molten salt through a neural network model;
performing correlation factor freezing blockage reasoning based on a knowledge base, and determining the freezing blockage position of the molten salt in the heat storage system;
and transmitting the diagnosis result data to the user side.
7. The knowledge-based tower solar molten salt thermal storage system fault diagnosis method of claim 6, wherein the sensor is an acceleration sensor.
8. The knowledge-based fault diagnosis method for the tower-type solar molten salt heat storage system according to claim 6, wherein the associated data is obtained in a manner that: acquiring temperature and irradiance through a real-time data server;
acquiring wind speed data in real time through an anemometer;
obtaining the flow of molten salt through an ultrasonic flowmeter;
the cloud cover condition and the system operation condition are obtained through quantification of the influence factors, wherein the cloud cover factor is calibrated to be [0, 1%]According to the discontinuous numerical value with the historical data defined as the precision of 0.01, the calibration of the system operation factor is as follows: the system failure is defined as the coefficientωThe coefficient is 1 when the system is in normal operation.
9. The knowledge-based fault diagnosis method for the tower-type solar molten salt heat storage system according to claim 6, wherein a factor correlation analysis method is adopted for correlation factor freezing and blocking reasoning based on the knowledge base to calculate similarity between correlation characteristic data and characteristic data in the database.
10. The knowledge-based fault diagnosis method for the tower type solar molten salt heat storage system according to claim 6, wherein the possible freezing and blocking positions of the molten salt in the heat storage system obtained through diagnosis are four positions, namely a heat absorber pipeline, a molten salt storage tank, a molten salt circulating pump and a molten salt pipe network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010390259.7A CN111307493B (en) | 2020-05-11 | 2020-05-11 | Knowledge-based fault diagnosis method for tower type solar molten salt heat storage system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010390259.7A CN111307493B (en) | 2020-05-11 | 2020-05-11 | Knowledge-based fault diagnosis method for tower type solar molten salt heat storage system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111307493A CN111307493A (en) | 2020-06-19 |
| CN111307493B true CN111307493B (en) | 2020-08-07 |
Family
ID=71150164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010390259.7A Active CN111307493B (en) | 2020-05-11 | 2020-05-11 | Knowledge-based fault diagnosis method for tower type solar molten salt heat storage system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111307493B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102243135A (en) * | 2011-04-15 | 2011-11-16 | 河海大学 | Method for diagnosing and analyzing failures of heliostat of tower-type solar power plant |
| CN103267649B (en) * | 2013-04-19 | 2016-01-20 | 河海大学 | Tower type solar energy thermal power generation heat dump superheater operation troubles diagnostic analysis method |
| CN103743972A (en) * | 2013-12-25 | 2014-04-23 | 青海中控太阳能发电有限公司 | Fault diagnosis method for tower type solar energy heat power generation system |
| WO2019132263A1 (en) * | 2017-12-29 | 2019-07-04 | (주)이맥스시스템 | Solar thermal equipment management system |
| CN110849467A (en) * | 2020-01-15 | 2020-02-28 | 杭州锅炉集团股份有限公司 | Vibration monitoring method for tower type solar molten salt heat absorber |
-
2020
- 2020-05-11 CN CN202010390259.7A patent/CN111307493B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111307493A (en) | 2020-06-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106529719B (en) | Wind power prediction method based on particle swarm optimization algorithm wind speed fusion | |
| CN108897286B (en) | Fault detection method based on distributed nonlinear dynamic relation model | |
| CN108446529B (en) | Organic Rankine cycle system fault detection method based on generalized mutual entropy-DPCA algorithm | |
| CN108131848B (en) | A kind of DSG slot type photo-thermal power station heat collecting field fluid properties prediction technique | |
| CN106936627B (en) | Thermal power equipment performance monitoring method based on big data analysis and mining | |
| CN102135021B (en) | Method for predicting shaft power of industrial extraction condensing steam turbine | |
| CN109724820B (en) | Method for calculating working efficiency of water turbine of hydroelectric generating set online monitoring system | |
| CN106979126A (en) | Wind power generating set high wind speed section effective wind speed method of estimation based on SVR | |
| CN110009135B (en) | Wind power prediction method based on width learning | |
| CN107045574B (en) | SVR-based effective wind speed estimation method for low wind speed section of wind generating set | |
| CN110363334B (en) | Grid line loss prediction method of photovoltaic grid connection based on gray neural network model | |
| CN109460621A (en) | Based on the gas turbine blades fault detection method for improving neural network | |
| CN109539596B (en) | GA-GRNN-based solar heat collection system photo-thermal efficiency prediction method | |
| CN115510904B (en) | Boiler heating area ash monitoring method based on time sequence prediction | |
| CN102494895B (en) | Analyzing method for energy saving and optimization of steam turbine set of power station | |
| CN101825869A (en) | Method for identifying superheater model parameters based on data drive | |
| CN103926079B (en) | A kind of mixed-flow Hydropower Unit is exerted oneself method for detecting abnormality | |
| CN111307493B (en) | Knowledge-based fault diagnosis method for tower type solar molten salt heat storage system | |
| CN102539823A (en) | Method for forecasting wind speed distribution of WTG (wind turbine generator) | |
| CN106289754B (en) | A kind of fired power generating unit component capabilities variation determination method based on Statistical Control Technique | |
| CN103793746A (en) | Method for identifying parameters of coal-fired power plant boiler superheater model | |
| CN110674605A (en) | Fan power modeling method based on operation parameters | |
| CN110849467A (en) | Vibration monitoring method for tower type solar molten salt heat absorber | |
| CN106121744B (en) | A kind of method of estimation of the turbine for wet steam parameter based on data harmonization | |
| CN116502408A (en) | Dynamic model-based turbine stage set economical efficiency online evaluation method |
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 | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 1216, danionggang Road, Jianggan District, Hangzhou City, Zhejiang Province, 310021 Patentee after: Xizi clean energy equipment manufacturing Co.,Ltd. Address before: 1216, danionggang Road, Jianggan District, Hangzhou City, Zhejiang Province, 310021 Patentee before: HANGZHOU BOILER GROUP Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |