CN103743972A - Fault diagnosis method for tower type solar energy heat power generation system - Google Patents
Fault diagnosis method for tower type solar energy heat power generation system Download PDFInfo
- Publication number
- CN103743972A CN103743972A CN201310727502.XA CN201310727502A CN103743972A CN 103743972 A CN103743972 A CN 103743972A CN 201310727502 A CN201310727502 A CN 201310727502A CN 103743972 A CN103743972 A CN 103743972A
- Authority
- CN
- China
- Prior art keywords
- diagnosis
- diagnosis object
- observed reading
- type solar
- fault diagnosis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- 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
- Photovoltaic Devices (AREA)
Abstract
The invention discloses a fault diagnosis method for a tower type solar energy heat power generation system. The method comprises the following steps: installing a sensor for measuring test data of a diagnosis object at a position where the diagnosis object is disposed in a system; establishing a diagnosis object fault diagnosis identification model, and according to the diagnosis object fault diagnosis identification model, establishing an artificial nerve network observed value model; calculating the observed value of the diagnosis object by use of the artificial nerve network observed value; and comparing the observed value and the value actually measured by the sensor so as to realize fault diagnosis of the diagnosis object. The fault diagnosis provided by the invention is of real time performance and robustness, also has the advantages of on-line training and multi-sensor diagnosis and the like, and can realize fault diagnosis of a whole power generation system.
Description
Technical field
The present invention relates to a kind of tower-type solar thermal power generating system field, particularly a kind of tower-type solar thermal power generating system method for diagnosing faults
Background technology
Tower type solar energy thermal power generation technology is a kind of advanced person, efficient generation technology, because it can provide reliably, green clean substitute energy is paid close attention to by people gradually relatively efficiently.
Tower type solar energy thermal power generation gathers solar energy by heliostat the collecting apparatus of high top of tower, and collecting apparatus is collected solar energy and changed into heat energy and be transferred to thermal storage equipment, and thermal storage equipment outputs to generator by energy, drives generator generating.
According to the not same-action in tower type solar power generation process, electricity generation system is divided into 5 subsystems, that is: condenser system, collecting system, hold over system, electricity generation system, energy backup system, all subsystem collaborative works complete gathering, the conversion of energy, in the gathering and transfer process of energy, equipment, pipeline and heat storage medium etc. all under high temperature and high pressure environment, the too low or too high safety and stability that all can affect system of environmental parameter in generating link.
Develop a set of tower type solar power house fault diagnosis system and efficiently move for the stability and safety of electricity generation system, the prevention of electricity generation system fault, after fault occurs, timely and effective dealing with has great importance.
At present, at the early-stage to the research of tower type solar power house fault diagnosis both at home and abroad, patent CN102289595A provides a kind of tower type solar heat dump local overheating evaluation model, by model, can effectively judge heat dump superheat state, for heat dump safe and stable operation provides foundation, but the security of heat dump is only paid close attention in this patented invention, do not consider electricity generation system miscellaneous equipment, the fault diagnosis of electricity generation system is had to limitation.The research > > of paper < < tower type solar energy thermal power generation station failure diagnostic expert system provides a kind of fuzzy expert diagnostic method based on solar heat power generation system sign and fault signature, and use the developing instruments such as VS and CLIPS to complete diagnostic system exploitation, its diagnostic result represents with fault credibility and trend map, ACESS database shows that to the analog result of fault this method has certain feasibility, but expert diagnostic system cannot detect regular undefined fault type.
Summary of the invention
The invention provides a kind of tower-type solar thermal power generating system method for diagnosing faults, it comprises the following steps:
Install for measuring the sensor of the test data of described diagnosis object position in the system of diagnosis object place;
Set up diagnosis object fault diagnosis identification model, and set up artificial neural network observed reading model according to described diagnosis object fault diagnosis identification model;
Utilize artificial neural network observed reading model to calculate the observed reading of diagnosis object;
Compare the measured value that described observed reading and described sensor record, realize the fault diagnosis to described diagnosis object.
Preferably, described diagnosis object Fault Identification model is:
y(k+1)=f(x
1(k),...,x
2(k-N
1+1),...,x
n(k),...,x
n(k-N
n+1),y(k),...,y(k-N
y+1))，
Wherein, x
1, x
2..., x
nbe respectively the input correlative of diagnosis object observed reading y, N
1, N
2..., N
nbe respectively input quantity time delay, N
yfor output time postpones.
Preferably, described artificial neural network observed reading model is:
y'(k+1)=f'(x
1(k),...,x
2(k-N
1+1),...,x
n(k),...,x
n(k-N
n+1),y'(k),...,y'(k-N
y+1))，
When f' is linear function, observed reading model y'(k+1) be linear model, when f' is nonlinear function, observed reading model y'(k+1) be nonlinear model.
Preferably, the described observed reading process of utilizing artificial neural network observed reading model to calculate diagnosis object comprises:
Step 1, netinit connects weights and composes respectively the random number in an interval (1,1), specification error function e, precision threshold ε to each
mwith maximum iteration time M;
Step 2, chooses k input sample and desired output at random;
d
o(k)=(d
1(k),d
2(k),…,d
q(k))x(k)=(x
1(k),x
2(k),…,x
n(k))，
Step 4, utilizes network desired output and actual output, error of calculation function each neuronic partial derivative δ to output layer
o(k) a;
Step 5, utilizes hidden layer to the connection weights of output layer, the δ of output layer
o(k) and the output error of calculation function of hidden layer to each neuronic partial derivative δ of hidden layer
h(k);
Step 8, calculates global error
Step 9, judges whether network error meets the demands; If so, finish algorithm, otherwise select next learning sample and desired output, return to step 3, start next round iteration.
Preferably, the measured value that the described observed reading of described comparison and described sensor record, realize the process of the fault diagnosis of described diagnosis object is comprised:
The observed reading of obtaining diagnosis object is y
nn, the measured value of diagnosis object is y
m, detection time, width was M, so the y of M in the time period
nnand y
mbe respectively
{y
nn(k),y
nn(k+1),...,y
nn(k+M)}，{y
m(k),y
m(k+1),...,y
m(k+M)}，
In M observation time, observed difference is
{e(k),e(k+1),...,e(k+M)}，
Wherein, e (i)=| y
nn(i)-y
m(i) |, i=k, k+1 ..., k+M,
K+M moment observational error is ε=min{e (k), e (k+1) ..., e (k+M) }, specification error threshold value is ε
mif, ε > ε
m, decision-making system fault so, on the contrary system is normal.
Preferably, described diagnosis object place system is condenser system, collecting system, hold over system, electricity generation system.
Preferably, described diagnosis object comprises temperature, the pressure of collecting system, the temperature of hold over system, pressure, the delivery outlet air pressure of collecting system, temperature, the input port delivery outlet air pressure of hold over system, temperature, the input port air pressure of electricity generation system, temperature.
Preferably, described sensor comprises temperature sensor and pressure transducer.
Preferably, described sensor can be placed in the pipeline that collecting system, hold over system, electricity generation system inside and collecting system be communicated with electricity generation system with hold over system, hold over system, and described number of sensors can be one or more.
The present invention includes following beneficial effect:
(1) the present invention, at whole power station different sub-systems module arrangement sensor, arranges corresponding sensor observer, realizes multi-object and detects, and makes diagnosis object be not limited to the single parameter of individual equipment, the security of protection power station integral body;
(2) the present invention utilizes the online training characteristic of artificial neural network, has real-time and robustness, has the advantages such as online training and multisensor diagnosis concurrently, becomes error in the time of can reducing, and improves fault diagnosis precision;
(3) diagnosis method for system fault provided by the invention is practical, simple to operation, is adapted at large-scale tower type solar energy thermal power generation station.
Certainly, implement arbitrary product of the present invention and might not need to reach above-described all advantages simultaneously.
Accompanying drawing explanation
The steady and sure solar heat power generation system structural representation that Fig. 1 provides for the embodiment of the present invention;
The Neural Network Observer fundamental diagram that Fig. 2 provides for the embodiment of the present invention;
Fig. 3 for the embodiment of the present invention provide diagnosis object at sample measured value and observed reading changing trend diagram in the time;
The diagnosis object that Fig. 4 provides for the embodiment of the present invention is at sample observational error changing trend diagram in the time.
Specific embodiment
The embodiment of the present invention provides a kind of tower-type solar thermal power generating system method for diagnosing faults, it is for the fault diagnosis of tower-type solar thermal power generating system, and this electricity generation system comprises condenser system, collecting system, hold over system, electricity generation system, 5 subsystems of control system; Certainly the solar heat power generation system of the present invention's diagnosis can also comprise the subsystem of other functions, the present embodiment only just comprises that the solar heat power generation system of condenser system, collecting system, hold over system, electricity generation system, 5 subsystems of control system describes, but the present invention does not limit the concrete composition of the diagnostic heat generating system of this diagnostic method.
The diagnosis object of the tower-type solar thermal power generating system method for diagnosing faults that the present embodiment provides mainly comprises: collecting system temperature, pressure, hold over system temperature, pressure, collecting system delivery outlet air pressure, temperature, hold over system input port delivery outlet air pressure, temperature, electricity generation system input port air pressure, temperature.Certainly the present invention also can be used for the diagnosis of above-mentioned other diagnosis object beyond having enumerated, and the present embodiment only be take the above-mentioned diagnosis object of enumerating and described as example, and the present invention does not limit the scope of diagnosis object.
The measured value of the diagnosis object that the present embodiment is surveyed by sensor, the sensor that the present embodiment is used comprises temperature sensor, pressure transducer, can be placed in the pipeline that collecting system, hold over system, electricity generation system inside and collecting system be communicated with electricity generation system with hold over system, hold over system, number of sensors, according to actual conditions setting, can be one or more.Certainly the kind of sensor of the present invention specifically will be selected according to diagnosis object, and the diagnosis object that the present embodiment provides for the present embodiment is selected sensor, and the present invention is the type of functionality of limit sensor not.
In the present embodiment, the measured value of all fault diagnosis objects carrys out self-corresponding sensor, the observed reading of all fault diagnosis objects is carried out self-corresponding Neural Network Observer, the foundation of Neural Network Observer is relevant to fault diagnosis Properties of Objects, in tower-type solar thermal power generating system, the identification system model of diagnosis object mostly is nonlinear model.
The tower-type solar thermal power generating system method for diagnosing faults that the present embodiment provides, specifically comprises the following steps:
Install for measuring the sensor of the test data of described diagnosis object position in the system of diagnosis object place;
Set up diagnosis object fault diagnosis identification model, and set up artificial neural network observed reading model according to described diagnosis object fault diagnosis identification model;
Utilize artificial neural network observed reading model to calculate the observed reading of diagnosis object;
Compare the measured value that described observed reading and described sensor record, realize the fault diagnosis to described diagnosis object.
In the present embodiment, described diagnosis object Fault Identification model is:
y(k+1)=f(x
1(k),...,x
2(k-N
1+1),...,x
n(k),...,x
n(k-N
n+1),y(k),...,y(k-N
y+1))，
Wherein, x
1, x
2..., x
nbe respectively the input correlative of diagnosis object observed reading y, N
1, N
2..., N
nbe respectively input quantity time delay, N
yfor output time postpones.
Described artificial neural network observed reading model is:
y'(k+1)=f'(x
1(k),...,x
2(k-N
1+1),...,x
n(k),...,x
n(k-N
n+1),y'(k),...,y'(k-N
y+1))，
When f' is linear function, observed reading model y'(k+1) be linear model, when f' is nonlinear function, observed reading model y'(k+1) be nonlinear model.
The wherein said observed reading process of utilizing artificial neural network observed reading model to calculate diagnosis object comprises:
Step 1, netinit connects weights and composes respectively the random number in an interval (1,1), specification error function e, precision threshold ε to each
mwith maximum iteration time M;
Step 2, chooses k input sample and desired output at random;
d
o(k)=(d
1(k),d
2(k),…,d
q(k))x(k)=(x
1(k),x
2(k),…,x
n(k))，
Step 4, utilizes network desired output and actual output, error of calculation function each neuronic partial derivative δ to output layer
o(k) a;
Step 5, utilizes hidden layer to the connection weights of output layer, the δ of output layer
o(k) and the output error of calculation function of hidden layer to each neuronic partial derivative δ of hidden layer
h(k);
Step 8, calculates global error
Step 9, judges whether network error meets the demands; If so, finish algorithm, otherwise select next learning sample and desired output, return to step 3, start next round iteration.
In the present embodiment, compare the measured value that described observed reading and described sensor record, realize the process of the fault diagnosis of described diagnosis object is comprised:
The observed reading of obtaining diagnosis object is y
nn, the measured value of diagnosis object is y
m, detection time, width was M, so the y of M in the time period
nnand y
mbe respectively
{y
nn(k),y
nn(k+1),...,y
nn(k+M)}，{y
m(k),y
m(k+1),...,y
m(k+M)}，
In M observation time, observed difference is
{e(k),e(k+1),...,e(k+M)}，
Wherein, e (i)=| y
nn(i)-y
m(i) |, i=k, k+1 ..., k+M,
K+M moment observational error is ε=min{e (k), e (k+1) ..., e (k+M) }, specification error threshold value is ε
mif, ε > ε
m, decision-making system fault so, on the contrary system is normal.
As shown in Figure 2, observed reading and input quantity, the output quantity of the fault diagnosis object that the present embodiment provides have relation, and all input quantities, output quantity all postpone if having time; Such as input quantity relevant to heat dump temperature observation value in collecting system is current solar radiation mirror field gross energy, the reflected energy loss of mirror field, collecting system absorption loss, the current air pressure of heat dump etc., output quantity is heat dump temperature, and current observed reading is by by N1, the solar radiation mirror field gross energy in the time period, the N2 reflected energy loss of mirror field, collecting system absorption loss, N4 heat dump time period in current air pressure and N5 heat dump observed temperature time period in of N3 in the time period in the time period determines.
As shown in Figure 2, in the observed reading and the measured value difference that judge that whether diagnosis object need to add up M time inner segment during fault, according to M difference, calculate the observational error of current time, utilize observational error to complete fault diagnosis.
Fig. 3 is tower-type solar thermal power generating system observed reading and measured value statistics in certain diagnosis object sample time in reality operation, and from figure, curve is not difficult to find out, after about 100s, observed reading and measured value occur compared with big difference.
Fig. 4 is tower-type solar thermal power generating system observed reading measured value difference and error threshold statistics in certain diagnosis object sample time in reality operation, and from figure, curve is not difficult to find out, after about 100s, difference is greater than specification error threshold value.
In conjunction with Fig. 3, Fig. 4 and Fig. 2, real-time rate and accuracy rate to fault diagnosis play a major role, in Fig. 4, can find that observation time M and error threshold are less than 0.8 when error threshold, so M after the time system fault will be detected, when error threshold is 0.9, if it is excessive that M value arranges, system cannot detect a M time period observed reading measured value difference and be greater than error threshold so, and fault detect will failure.
The present invention includes following beneficial effect:
The present invention, at whole power station different sub-systems module arrangement sensor, arranges corresponding sensor observer, realizes multi-object and detects, and makes diagnosis object be not limited to the single parameter of individual equipment, the security of protection power station integral body;
The present invention utilizes the online training characteristic of artificial neural network, has real-time and robustness, has the advantages such as online training and multisensor diagnosis concurrently, becomes error in the time of can reducing, and becomes error while reducing, and improves fault diagnosis precision;
Diagnosis method for system fault provided by the invention is practical, simple to operation, is adapted at large-scale tower type solar energy thermal power generation station.
The disclosed preferred embodiment of the present invention is just for helping to set forth the present invention above.Preferred embodiment does not have all details of detailed descriptionthe, and also not limiting this invention is only described embodiment.Obviously, according to the content of this instructions, can make many modifications and variations.These embodiment are chosen and specifically described to this instructions, is in order to explain better principle of the present invention and practical application, thereby under making, technical field technician can understand and utilize the present invention well.The present invention is only subject to the restriction of claims and four corner and equivalent.
Claims (9)
1. a tower-type solar thermal power generating system method for diagnosing faults, is characterized in that, comprises the following steps:
Install for measuring the sensor of the test data of described diagnosis object position in the system of diagnosis object place;
Set up diagnosis object fault diagnosis identification model, and set up artificial neural network observed reading model according to described diagnosis object fault diagnosis identification model;
Utilize artificial neural network observed reading model to calculate the observed reading of diagnosis object;
Compare the measured value that described observed reading and described sensor record, realize the fault diagnosis to described diagnosis object.
2. tower type solar generating fault diagnosis system diagnostic method as claimed in claim 1, is characterized in that, described diagnosis object Fault Identification model is:
y(k+1)=f(x
1(k),...,x
2(k-N
1+1),...,x
n(k),...,x
n(k-N
n+1),y(k),...,y(k-N
y+1))，
Wherein, x
1, x
2..., x
nbe respectively the input correlative of diagnosis object observed reading y, N
1, N
2..., N
nbe respectively input quantity time delay, N
yfor output time postpones.
3. tower type solar generating fault diagnosis system diagnostic method as claimed in claim 2, is characterized in that, described artificial neural network observed reading model is:
y'(k+1)=f'(x
1(k),...,x
2(k-N
1+1),...,x
n(k),...,x
n(k-N
n+1),y'(k),...,y'(k-N
y+1))，
When f' is linear function, observed reading model y'(k+1) be linear model, when f' is nonlinear function, observed reading model y'(k+1) be nonlinear model.
4. tower type solar generating fault diagnosis system diagnostic method as claimed in claim 3, is characterized in that, the described observed reading process of utilizing artificial neural network observed reading model to calculate diagnosis object comprises:
Step 1, netinit connects weights and composes respectively the random number in an interval (1,1), specification error function e, precision threshold ε to each
mwith maximum iteration time M;
Step 2, chooses k input sample and desired output at random;
d
o(k)=(d
1(k),d
2(k),…,d
q(k))x(k)=(x
1(k),x
2(k),…,x
n(k))，
Step 3, calculates each neuronic input and output of hidden layer;
Step 4, utilizes network desired output and actual output, error of calculation function each neuronic partial derivative δ to output layer
o(k) a;
Step 5, utilizes hidden layer to the connection weights of output layer, the δ of output layer
o(k) and the output error of calculation function of hidden layer to each neuronic partial derivative δ of hidden layer
h(k);
Step 6, utilizes each neuronic δ of output layer
o(k) and each neuronic output of hidden layer revise connection weight w
ho(k);
Step 7, utilizes each neuronic δ of hidden layer
hand each neuronic input correction connection weight of input layer (k);
Step 8, calculates global error
Step 9, judges whether network error meets the demands; If so, finish algorithm, otherwise select next learning sample and desired output, return to step 3, start next round iteration.
5. tower type solar generating fault diagnosis system diagnostic method as claimed in claim 4, is characterized in that, the measured value that the described observed reading of described comparison and described sensor record, and realization comprises the process of the fault diagnosis of described diagnosis object:
The observed reading of obtaining diagnosis object is y
nn, the measured value of diagnosis object is y
m, detection time, width was M, so the y of M in the time period
nnand y
mbe respectively
{y
nn(k),y
nn(k+1),...,y
nn(k+M)}，{y
m(k),y
m(k+1),...,y
m(k+M)}，
In M observation time, observed difference is
{e(k),e(k+1),...,e(k+M)}，
Wherein, e (i)=| y
nn(i)-y
m(i) |, i=k, k+1 ..., k+M,
K+M moment observational error is ε=min{e (k), e (k+1) ..., e (k+M) }, specification error threshold value is ε
mif, ε > ε
m, decision-making system fault so, on the contrary system is normal.
6. the tower-type solar thermal power generating system method for diagnosing faults as described in claim 1-5 any one, is characterized in that, described diagnosis object place system is condenser system, collecting system, hold over system, electricity generation system.
7. tower-type solar thermal power generating system method for diagnosing faults as claimed in claim 6, it is characterized in that, described diagnosis object comprises temperature, the pressure of collecting system, the temperature of hold over system, pressure, the delivery outlet air pressure of collecting system, temperature, the input port delivery outlet air pressure of hold over system, temperature, the input port air pressure of electricity generation system, temperature.
8. tower-type solar thermal power generating system method for diagnosing faults as claimed in claim 7, is characterized in that, described sensor comprises temperature sensor and pressure transducer.
9. tower-type solar thermal power generating system method for diagnosing faults as claimed in claim 8, it is characterized in that, described sensor can be placed in the pipeline that collecting system, hold over system, electricity generation system inside and collecting system be communicated with electricity generation system with hold over system, hold over system, and described number of sensors can be one or more.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310727502.XA CN103743972A (en) | 2013-12-25 | 2013-12-25 | Fault diagnosis method for tower type solar energy heat power generation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310727502.XA CN103743972A (en) | 2013-12-25 | 2013-12-25 | Fault diagnosis method for tower type solar energy heat power generation system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103743972A true CN103743972A (en) | 2014-04-23 |
Family
ID=50501007
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310727502.XA Pending CN103743972A (en) | 2013-12-25 | 2013-12-25 | Fault diagnosis method for tower type solar energy heat power generation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103743972A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104378065A (en) * | 2014-11-07 | 2015-02-25 | 吕政良 | Photovoltaic power station fault diagnosis method |
| CN111307493A (en) * | 2020-05-11 | 2020-06-19 | 杭州锅炉集团股份有限公司 | Knowledge-based fault diagnosis method for tower type solar molten salt heat storage system |
| CN114894346A (en) * | 2022-04-27 | 2022-08-12 | 天津大学 | Phase-change heat storage monitoring system and method based on neural network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000089806A (en) * | 1998-09-11 | 2000-03-31 | Nissin Electric Co Ltd | Controller using solar radiation intensity prediction |
| CN101017191A (en) * | 2007-03-01 | 2007-08-15 | 华北电力大学 | On-line fault diagnoses method on rotor winding inter turn short-circuit of turbine generator |
| 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 |
| CN102289595A (en) * | 2011-08-22 | 2011-12-21 | 南京科远自动化集团股份有限公司 | Model for evaluating local overheating of tower type solar heat absorber |
| WO2013064963A1 (en) * | 2011-11-01 | 2013-05-10 | Idus Controls Ltd. | A remote sensing device and system for agricultural and other applications |
-
2013
- 2013-12-25 CN CN201310727502.XA patent/CN103743972A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000089806A (en) * | 1998-09-11 | 2000-03-31 | Nissin Electric Co Ltd | Controller using solar radiation intensity prediction |
| CN101017191A (en) * | 2007-03-01 | 2007-08-15 | 华北电力大学 | On-line fault diagnoses method on rotor winding inter turn short-circuit of turbine generator |
| 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 |
| CN102289595A (en) * | 2011-08-22 | 2011-12-21 | 南京科远自动化集团股份有限公司 | Model for evaluating local overheating of tower type solar heat absorber |
| WO2013064963A1 (en) * | 2011-11-01 | 2013-05-10 | Idus Controls Ltd. | A remote sensing device and system for agricultural and other applications |
Non-Patent Citations (5)
| Title |
|---|
| 万定生 等: "太阳能热发电站故障诊断专家系统应用研究", 《计算机工程与设计》, vol. 30, no. 23, 31 December 2009 (2009-12-31), pages 5485 - 5488 * |
| 张良均,曹晶: "《神经网络实用教程 》", 31 December 2008 * |
| 杨伟 等: "《容错飞行控制系统》", 31 March 2007 * |
| 王耀南: "《智能控制系统 模糊逻辑 专家系统 神经网络控制》", 30 October 1996 * |
| 马华杰 等: "塔式太阳能热发电站故障诊断专家系统的研究", 《电测与仪表》, vol. 50, no. 567, 31 March 2013 (2013-03-31), pages 16 - 19 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104378065A (en) * | 2014-11-07 | 2015-02-25 | 吕政良 | Photovoltaic power station fault diagnosis method |
| CN104378065B (en) * | 2014-11-07 | 2016-08-17 | 北京清芸阳光能源科技有限公司 | A kind of photovoltaic plant method for diagnosing faults |
| CN111307493A (en) * | 2020-05-11 | 2020-06-19 | 杭州锅炉集团股份有限公司 | Knowledge-based fault diagnosis method for tower type solar molten salt heat storage system |
| CN114894346A (en) * | 2022-04-27 | 2022-08-12 | 天津大学 | Phase-change heat storage monitoring system and method based on neural network |
| CN114894346B (en) * | 2022-04-27 | 2023-01-17 | 天津大学 | Phase-change heat storage monitoring system and method based on neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Peng et al. | A deep belief network based health indicator construction and remaining useful life prediction using improved particle filter | |
| Ayodeji et al. | Knowledge base operator support system for nuclear power plant fault diagnosis | |
| Hasni et al. | Estimating global solar radiation using artificial neural network and climate data in the south-western region of Algeria | |
| Benli | Determination of thermal performance calculation of two different types solar air collectors with the use of artificial neural networks | |
| Yan et al. | The performance prediction of ground source heat pump system based on monitoring data and data mining technology | |
| Li et al. | An intelligent method for fault diagnosis in photovoltaic array | |
| Casteleiro-Roca et al. | An intelligent fault detection system for a heat pump installation based on a geothermal heat exchanger | |
| CN102830250B (en) | Method for diagnosing faults of wind speed sensor at wind power plant based on spatial relevancy | |
| CN103322416B (en) | Pipeline weak leakage detecting device and detecting method based on fuzzy hyperbolic chaos model | |
| CN104318077A (en) | Quantitative analysis method for river runoff change caused by climate change and human activity | |
| CN106014877A (en) | Multi-fault diagnosis and fault-tolerant control of wind turbine system | |
| Mohammed et al. | Hourly solar radiation prediction based on nonlinear autoregressive exogenous (Narx) neural network | |
| Badawi et al. | Weibull probability distribution of wind speed for gaza strip for 10 years | |
| CN103743972A (en) | Fault diagnosis method for tower type solar energy heat power generation system | |
| CN117212077B (en) | Wind wheel fault monitoring method, device and equipment of wind turbine and storage medium | |
| CN106127184A (en) | A kind of gear case of blower method for diagnosing faults | |
| CN101813920B (en) | Virtual redundancy method for temperature sensor of power station turboset | |
| CN111797888A (en) | Heat storage and supply system and leakage detection method | |
| Ruiz-Moreno et al. | A deep learning-based strategy for fault detection and isolation in parabolic-trough collectors | |
| CN112240595B (en) | Heat storage and supply system and leakage detection method | |
| Rohaimi et al. | 3 Hours ahead of time flood water level prediction using NNARX structure: Case study pahang | |
| Garnier et al. | Missing data estimation for energy resources management in tertiary buildings | |
| Tong et al. | Prediction of parameters of boiler superheater based on transfer learning method | |
| CN109934378A (en) | A kind of power forecasting method and device | |
| Akbar et al. | Solar Thermal Process Parameters Forecasting for Evacuated Tubes Collector (ETC) Based on RNN-LSTM |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140423 |
|
| RJ01 | Rejection of invention patent application after publication |