CN115596696A - Real-time online estimation method for running state of fan based on data mining - Google Patents
Real-time online estimation method for running state of fan based on data mining Download PDFInfo
- Publication number
- CN115596696A CN115596696A CN202211337037.4A CN202211337037A CN115596696A CN 115596696 A CN115596696 A CN 115596696A CN 202211337037 A CN202211337037 A CN 202211337037A CN 115596696 A CN115596696 A CN 115596696A
- Authority
- CN
- China
- Prior art keywords
- fan
- stall
- inlet
- state
- parameters
- 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
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04D—NON-POSITIVE-DISPLACEMENT PUMPS
- F04D27/00—Control, e.g. regulation, of pumps, pumping installations or pumping systems specially adapted for elastic fluids
- F04D27/001—Testing thereof; Determination or simulation of flow characteristics; Stall or surge detection, e.g. condition monitoring
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Mechanical Engineering (AREA)
- Control Of Positive-Displacement Air Blowers (AREA)
Abstract
The invention discloses a real-time online estimation method for the running state of a fan based on data mining, which comprises the following steps: acquiring historical operating state parameters of the unit and the fan; extracting data under a plurality of normal and stable operation conditions to construct a sample set; obtaining a change relation prediction model of the load of a random group of the inlet flow of the draught fan or the main steam flow, and a change relation prediction model of the system resistance from the hearth to the inlet section of the draught fan and the system resistance from the outlet of the draught fan to the outlet section of the chimney along with the smoke amount; acquiring state operation parameters of the fan based on the two prediction models; calculating a theoretical stall safety factor, a pressure margin coefficient and a flow margin coefficient of the fan; and evaluating whether the running state of the fan is safe after the state parameters of the flue gas system are changed by comparing the theoretical stall safety factor, the pressure margin coefficient and the deviation between the flow margin coefficient and the threshold value. The method and the device can improve the rationality of the anti-stall regulation strategy of the fan and improve the operation safety and the economical efficiency of the fan.
Description
Technical Field
The invention relates to an axial flow fan (comprising a static blade adjustable axial flow fan, a movable blade adjustable axial flow fan and the like) used by a flue gas system of a coal-fired power plant, in particular to a fan operation state real-time online estimation method based on data mining.
Background
At present, along with the deep implementation of policies such as flexibility deep adjustment, a power station fan faces the requirement of frequent adjustment of wide load, and after the unit is subjected to ultralow emission modification, along with the increasingly high requirement of environmental protection indexes, the number of environmental protection devices in a flue gas system is increased, in actual operation, due to the improvement of the environmental protection requirement, the ammonia escape amount of the flue gas system is increased, the phenomenon of abnormal blockage of the devices in the flue gas system due to the existence of ammonium bisulfate is more and more serious, the operating parameters of the flue gas system deviate from the design parameters, and the phenomena of high-load working condition stall of a draught fan and the reduction of the load carrying capacity of the unit are caused frequently. Aiming at the phenomenon of high-load stall of the induced draft fan, generally, a power plant operator prevents the fan from stalling by limiting the opening degree and the current of the fan, however, the blockage condition of a flue gas system and the running state of the induced draft fan cannot be accurately estimated, so that the anti-wind-fan stall method for limiting the opening degree and the current of the fan is too conservative, even after the flue gas system is overhauled and cleared, the resistance of the flue gas system is obviously reduced, and the load carrying capacity of a unit is also limited due to the anti-stall running strategy of the fan. The existing power station fan monitoring system monitors state parameters such as fan inlet and outlet pressure, flow, current, inlet temperature and the like in real time, and can evaluate the real-time performance state of the fan in real time, so that a set of on-line estimation method for the operating state of the power station fan based on data mining of historical state parameters of the power station fan is very necessary to be established, the operating state of the fan after the flue gas system is blocked is accurately evaluated, and a basis is provided for the establishment of a fan anti-stall operating strategy and the operation adjustment of the fan; aiming at the change of state parameters of the flue gas system after the flue gas system is newly added with equipment, the output state of the fan is accurately predicted, and a basis is provided for making a related technical transformation scheme of the flue gas system.
Disclosure of Invention
In order to accurately estimate the running state of the fan after the running state of the flue gas system changes, the invention provides a real-time online estimation method for the running state of the fan based on data mining.
The invention is realized by adopting the following technical scheme:
a real-time online estimation method for the running state of a fan based on data mining comprises the following steps:
1) Acquiring historical operating state parameters of the unit and the fan based on an online fan monitoring system and a DCS (distributed control system);
2) Processing the historical operating state parameters of the fan by adopting a data analysis technology, extracting data under a plurality of normal and stable operating conditions, and constructing a sample set;
3) Training the extracted sample set based on an artificial neural network to obtain a variation relation prediction model of the random group load of the flow of the inlet of the draught fan or the main steam flow, and a variation relation prediction model of the system resistance from the hearth to the inlet section of the draught fan and the system resistance from the outlet of the draught fan to the outlet section of the chimney along with the smoke volume;
4) Giving a change predicted value of the state parameter of the flue gas system, and acquiring the state operation parameter of the fan based on two prediction models;
5) Calculating a theoretical stall safety factor, a pressure margin coefficient and a flow margin coefficient of the fan based on the fan performance curve and the fan operation parameter predicted value;
6) Setting the threshold value of each stall margin coefficient based on historical stall condition analysis and a large number of stall test statistical analysis, and evaluating whether the running state of the fan is safe after the state parameters of the flue gas system are changed by comparing the theoretical stall safety coefficient, the pressure margin coefficient and the deviation between the flow margin coefficient and the threshold value.
The further improvement of the invention is that in the step 1), the historical operating state parameters of the unit and the fan comprise:
load L of unit and evaporation capacity D of boiler b Fan inlet temperature T in Volume flow Q of fan inlet v Full pressure P at inlet of fan t,in Full pressure P at the outlet of the fan t,out Fan opening beta and fan inlet static pressure P e,in And static pressure P at the outlet of the fan e,out The time period t is 10-30 days, and the time interval delta t =1 min-5 min.
The further improvement of the invention is that in the step 2), when constructing the sample set, the concrete steps are as follows:
according to boiler evaporation D b Set of data points with time t { (t) j ,D b,j ) And (5) screening data in a time interval delta t =2h, and selecting all data points { D ] in a given time interval i The set of intervals satisfying the following condition (t) j ,t j +2h)}:
Wherein j =1,2.., m, i =1,2, …, k;
in the screened data set, the { (t) is proposed j +0.5h,t j +1.5 h) } time period, and performing mean value calculation to obtain a sample point set:
the further improvement of the invention is that in the step 3), based on the sample point set, the artificial neural network is adopted to respectively train, and the volume flow Q of the inlet of the fan is obtained v With main steam flow D b Change relation model Q of v =f(D b ) Static pressure P at inlet of fan e,in And fan inlet volume flow Q v Change relation model P of e,in =f(Q v ) Static pressure P at the outlet of the fan e,out And fan inlet volume flow Q v Is generated by the variation relation model P e,out =f(Q v ) Inlet full pressure P of fan t,in And fan inlet volume flow Q v Change relation model P of t,in =f(Q v ) And fan outlet full pressure P t,out And fan inlet volume flow Q v Is generated by the variation relation model P t,out =f(Q v )。
The further improvement of the invention is that in the step 3), the state change of the smoke wind system is predicted, and the change value of the front and rear resistance of the induced draft fan under the corresponding operation condition, namely (D '), is obtained' b ,ΔP in )、(D’ b ,ΔP out )。
The further improvement of the invention is that in the step 4), the state operation parameters of the fan comprise:
determining a boiler evaporation capacity interval [ D ] within a unit wide load regulation range according to basic boiler design parameters and the actual operation condition of the unit b,min ,D b,BMCR ]Selecting m typical working conditions in the interval to obtain a boiler evaporation capacity set { D b,i And calculating to obtain a state parameter point set under each working condition according to each parameter relation model, namely { (D) b ,T in ,Q v ,P e,in ,P e,out ,P t,in ,P t,out ,…) i I =1,2,3,. M, m>=3;
Based on a smoke system resistance variation value (D' b ,ΔP in )、(D’ b ,ΔP out ) Each is obtained by calculationEstimation of fan state parameters under typical conditions, i.e., { (Q) v ,P e,in -ΔP in ,P e,out +ΔP out ,P t,in +ΔP in ,P t,in +ΔP in ) i } (i =1,2,3, … m), in which:
correcting the volume flow of the inlet of the fan according to the changes of the smoke temperature and the static pressure of the inlet of the fan, calculating to obtain the total pressure Pt and the specific pressure Y of the fan according to the estimated values of the state parameters of the fan under various typical working conditions, and then obtaining the estimated parameter of the operation of the fan as { (Q' v ,P’ t ,Y’) i }。
According to the further improvement, in the step 5), estimating point parameters { (Q ') according to the operation of the fan' v ,P’ t ,Y’) i And (i =1,2,3, … m) marked on the fan performance curve, and acquiring the opening beta corresponding to each operating condition fan operating point i And identifying and obtaining the intersection point of the equal opening degree line and the theoretical stall line { (Q) v,s ,P t,s ) i };
Calculating each stall margin coefficient according to the fan operation estimated point and the stall point p ,k q ,k s ) i };
The fan stall pressure margin coefficient is as follows:
k p =p t,s /p' t
the fan stall flow margin coefficient is as follows:
k q =Q' v /Q v,s
the fan stalling safety coefficient is as follows:
the further improvement of the invention is that in the step 6), in order to ensure the safe and stable operation of the fan, the fan operation parameters of each working condition point all meet the following conditions:
k s k is not less than 1.35 p ≥1.15、k q ≥1.08;
If the estimated operating point parameters of each fan do not meet the conditions, the condition that the fan cannot meet the full load range condition after the resistance of the flue gas system is increased is indicated, anti-stall regulation and control of the fan are required, and the resistance increase value delta P of the flue gas system is reduced in And Δ P out And evaluating again until the operating state parameters meeting the conditions are obtained, and further monitoring the static pressure difference delta P of the inlet and the outlet of the actual fan e And blower opening degree beta 0 And formulating a control strategy for preventing the stalling of the fan, namely meeting the following requirements:
ΔP e <(P e,out +ΔP out ) BMCR –(P e,in -ΔP in ) BMCR ;
β 0 <0.8β max 。
the invention has at least the following beneficial technical effects:
the invention provides a real-time online estimation method for the running state of a fan based on data mining, which comprises the steps of mining and utilizing historical monitoring data of the fan, constructing a prediction model of each state parameter, obtaining main running state parameters of the fan under typical working conditions, further accurately predicting the running state parameters of the fan after the resistance of a flue gas system changes by estimating the change value of the resistance of the flue gas system, calculating a stall safety system, a stall pressure margin coefficient and a stall flow margin coefficient which correspond to the running state parameters of the fan under a plurality of working conditions based on a fan design performance curve, evaluating the running safety of the fan based on the stall margin coefficient and the opening degree of the fan, judging whether the fan can run safely and stably, providing a basis for the running regulation and control of the fan, improving the rationality of a fan anti-stall regulation and control strategy, and improving the running safety and the economical efficiency of the fan.
Drawings
FIG. 1 is a schematic diagram of the principles of the present invention;
FIG. 2 is a schematic view of the distribution of operating points and corresponding stall points of a wind turbine according to the present invention on a wind turbine performance curve.
Fig. 3 is a schematic distribution diagram of actual fan operating points and estimated operating points on a performance curve under a typical operating condition.
Wherein, in FIG. 1, L is the generating load of the unit, kW, D b Is the boiler evaporation capacity in units of T/h, T in Is the temperature of smoke at the inlet of the fan, unit degree centigrade, Q v Is the volume flow at the inlet of the fan, and has unit m 3 /s,P t,in Is the inlet full pressure of the fan in Pa, P t,out Is the total pressure at the outlet of the fan in Pa, P e,in Is static pressure at the inlet of the fan in Pa, P e,out Is the total pressure at the outlet of the fan in Pa, P t The unit is the full pressure of the fan, the unit Pa and the Y are the specific pressure energy of the fan, the unit kJ/kg, the beta is the DCS fan opening degree feedback value, the unit DEG, the unit l is the data point serial number (l =1,2, …, n), the unit j is the time interval (j =1,2, …, n), the unit i is the load working condition number (i =1,2, …, m), the unit S is the standard variance, and the unit k is the DCS fan opening degree feedback value s For the stall safety factor, kp is the stall pressure margin coefficient, and kq is the stall flow margin coefficient, beta min Is the minimum opening value of the fan, unit degree, beta max Is the maximum opening value of the fan, unit degree and beta BMCR And the opening value of the operating point of the fan under the BMCR working condition is in unit.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
The invention provides a real-time online estimation method for the running state of a fan based on data mining, which is characterized in that historical running state parameters of a unit and the fan are obtained based on an online monitoring system and a DCS of the fan; processing the historical operating state parameters of the fan by adopting a data analysis technology, extracting data under a plurality of normal and stable operating conditions, and constructing a sample set; training the extracted sample set based on an artificial neural network to obtain a variation relation prediction model of the random group load of the flow of the inlet of the draught fan or the main steam flow, and a variation relation prediction model of the system resistance from the hearth to the inlet section of the draught fan and the system resistance from the outlet of the draught fan to the outlet section of the chimney along with the smoke volume; giving a change predicted value of the state parameter of the flue gas system, and acquiring the state operation parameter of the fan based on two prediction models; calculating a theoretical stall safety factor, a pressure margin coefficient and a flow margin coefficient of the fan based on the fan performance curve and the fan operation parameter predicted value; setting the threshold value of each stall margin coefficient based on historical stall condition analysis and a large number of stall test statistical analysis, and evaluating whether the running state of the fan is safe after the state parameters of the flue gas system are changed by comparing the theoretical stall safety coefficient, the pressure margin coefficient and the deviation between the flow margin coefficient and the threshold value. The specific implementation method of the invention is as follows:
1. extracting main monitoring parameter data sets of a recent boiler and a fan from a power station fan online monitoring system and a DCS (distributed control System), wherein the main monitoring parameter data sets comprise unit load L and boiler evaporation capacity D b Fan inlet temperature T in Fan inlet volume flow Q v Inlet full pressure P of fan t,in Full pressure P at outlet of fan t,out Fan opening beta and fan inlet static pressure P e,in Static pressure P at the outlet of the fan e,out And (3) the data set should cover most of the normal operation load region according to the parameters, wherein the time period t is 10-30 days, and the time interval delta t = 1-5 min.
2. And (4) carrying out data combing on the history, providing a plurality of main monitoring parameters under the stable load working condition, and constructing a sample set.
(1) According to boiler evaporation D b Set of data points with time t { (t) j ,D b,j ) } (j =1,2..,.., m), data screening is performed with a time interval Δ t =2h, and all data points { D ] are selected within a given time interval i } (i =1,2, …, k) a set of intervals satisfying the following condition { (t) j ,t j +2h)}(j=1,2,...,n):
(2) In the screened data set, the { (t) is proposed j +0.5h,t j +1.5 h) } (j =1,2,. Once, n) time period, and performing mean value calculation to obtain a sample point set:
3. based on the sample point set, respectively training by adopting an artificial neural network to obtain the volume flow Q of the inlet of the fan v With main steam flow D b Change relation model Q of v =f(D b ) Static pressure P at inlet of fan e,in And fan inlet volume flow Q v Is generated by the variation relation model P e,in =f(Q v ) Static pressure P at the outlet of the fan e,out And fan inlet volume flow Q v Change relation model P of e,out =f(Q v ) Full pressure P at inlet of fan t,in And fan inlet volume flow Q v Is generated by the variation relation model P t,in =f(Q v ) And fan outlet full pressure P t,out And fan inlet volume flow Q v Is generated by the variation relation model P t,out =f(Q v )。
4. Predicting the state change of the smoke and air system by combining the actual running condition of the unit and a planned transformation scheme, and obtaining the change value of the front and rear resistances of the induced draft fan under the corresponding running working condition, namely (D' b ,ΔP in )、(D’ b ,ΔP out )。
5. And obtaining the state operation parameters of the fan based on the resistance change value of the flue gas system and the parameter relation models.
(1) Determining a boiler evaporation capacity interval [ D ] within a unit wide load regulation range according to basic boiler design parameters and the actual operation condition of the unit b,min ,D b,BMCR ]Selecting m typical working conditions (m of them) in the interval>= 3), a set of boiler evaporation amounts { D) is obtained b,i And (i =1,2,3, … m), and calculating according to each parameter relation model to obtain a state parameter point set under each working condition, namely { (D) b ,T in ,Q v ,P e,in ,P e,out ,P t,in ,P t,out ,…) i }(i=1,2,3,..m)。
(2) Based on a smoke system resistance variation value (D' b ,ΔP in )、(D’ b ,ΔP out ) Calculating to obtain the fan state parameter estimated value under each typical working condition, namely { (Q) v ,P e,in -ΔP in ,P e,out +ΔP out ,P t,in +ΔP in ,P t,in +ΔP in ) i (i =1,2,3, … m), wherein:
(3) correcting the volume flow of the inlet of the fan according to the changes of the smoke temperature and the static pressure of the inlet of the fan, calculating to obtain the total pressure Pt and the specific pressure Y of the fan according to the estimated values of the state parameters of the fan under various typical working conditions, and then obtaining the estimated parameter of the operation of the fan as { (Q' v ,P’ t ,Y’) i }(i=1,2,3,…m)。
6. Based on the fan design performance curve and the fan operation pre-estimated parameters, calculating a stall safety coefficient, a stall flow margin coefficient and a stall pressure margin coefficient corresponding to the fan operation point under each typical working condition.
(1) According to the estimated point parameter of fan operation { (Q' v ,P’ t ,Y’) i And (i =1,2,3, … m) marked on the fan performance curve, and acquiring the opening beta corresponding to each operating condition fan operating point i And identifying and obtaining the intersection point of the equal-opening line and the theoretical stall line { (Q) v,s ,P t,s ) i }(i=1,2,3,…,m)。
(2) Calculating each stall margin coefficient { (k) according to the fan operation estimated point and the stall point p ,k q ,k s ) i }(i=1,2,3,…,m)。
The fan stall pressure margin coefficient is as follows:
k p =p t,s /p' t
the fan stall flow margin coefficient is as follows:
k q =Q' v /Q v,s
the fan stalling safety coefficient is as follows:
k s =k p k q 2
7. and evaluating the operation safety of the fan based on the fan operation estimated point, the stall margin coefficient and the opening. In order to ensure the safe and stable operation of the fan, the fan operation parameters of all the working condition points all meet the following conditions:
1)k s k is not less than 1.35 p ≥1.15、k q ≥1.08
If the estimated operating point parameters of each fan do not meet the conditions, the situation that the fan cannot meet the full load range conditions after the resistance of the flue gas system is increased is shown, the fan anti-stall regulation and control are needed, and the resistance increase value delta P of the flue gas system is reduced in And Δ P out And re-evaluating until obtaining the running state parameters meeting the conditions, and further monitoring the static pressure difference delta P of the inlet and the outlet of the actual fan e And blower opening degree beta 0 To make a control strategy for preventing the stall of the fanSlightly, the following conditions are satisfied:
1)ΔP e <(P e,out +ΔP out ) BMCR –(P e,in -ΔP in ) BMCR
2)β 0 <0.8β max 。
5. the method has the characteristics of high efficiency, high reliability and strong robustness, and is suitable for anti-stall monitoring and fan running state estimation of the induced draft fan of the large coal-fired unit.
Examples
A certain domestic 300MW unit draught fan is movable vane adjustable axial fan, because each environmental protection equipment of flue gas system that the existence of ammonium bisulfate leads to blocks up to different extents, make the stall condition have appeared under the high load operating mode, therefore, in order to guarantee unit safety and stability operation, the power plant adopts restriction aperture and electric current mode to regulate and control, the unit takes the load capacity to be restricted, and after unit overhaul and clear stifled, because there is not reliable aassessment foundation, the unit still goes on according to the fan regulation and control mode of having formulated, the output of unit has been restricted. The method is realized by adopting an object-oriented programming language, and the functional module is embedded into an induced draft fan on-line monitoring and fault early warning system, so that the estimation of the running state and the running safety evaluation of the induced draft fan are realized in real time according to the resistance change condition of a smoke and wind system, early warning is carried out in advance, a more reliable fan regulation and control mode is established according to the method, reliable basis is provided for the fan regulation and control by comprehensively monitoring the resistance change of equipment which is easy to block in the smoke and wind system, static pressure difference of an inlet and an outlet of the fan, the opening degree of the fan, current and the like, and the output of the fan and the load carrying capacity of a unit are improved. The algorithm of the invention is efficient and reliable in operation, the distribution of the actual fan operating points and the estimated operating points on the performance curve of the actual fan operating points and the estimated operating points under typical operating conditions is shown in figure 3, and the state evaluation calculation results of the operating points are shown in table 1.
TABLE 1 State evaluation calculation results of the respective operation prediction points
Although the invention has been described in detail hereinabove with respect to a general description and specific embodiments thereof, it will be apparent to those skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.
Claims (8)
1. A real-time online estimation method for the running state of a fan based on data mining is characterized by comprising the following steps:
1) Acquiring historical operating state parameters of the unit and the fan based on an online fan monitoring system and a DCS (distributed control system);
2) Processing the historical operating state parameters of the fan by adopting a data analysis technology, extracting data under a plurality of normal and stable operating conditions, and constructing a sample set;
3) Training the extracted sample set based on an artificial neural network to obtain a variation relation prediction model of the random group load of the flow of the inlet of the draught fan or the main steam flow, and a variation relation prediction model of the system resistance from the hearth to the inlet section of the draught fan and the system resistance from the outlet of the draught fan to the outlet section of the chimney along with the smoke volume;
4) Giving a change predicted value of the state parameter of the flue gas system, and obtaining the state operation parameter of the fan based on two prediction models;
5) Calculating a theoretical stall safety factor, a pressure margin coefficient and a flow margin coefficient of the fan based on the fan performance curve and the fan operation parameter predicted value;
6) Setting the threshold value of each stall margin coefficient based on historical stall condition analysis and a large number of stall test statistical analysis, and evaluating whether the running state of the fan is safe after the state parameters of the flue gas system are changed by comparing the theoretical stall safety coefficient, the pressure margin coefficient and the deviation between the flow margin coefficient and the threshold value.
2. The method for real-time online estimation of the operating state of the wind turbine based on data mining according to claim 1, wherein in the step 1), the historical operating state parameters of the wind turbine and the unit comprise:
load L of unit and evaporation capacity D of boiler b Fan inlet temperature T in Fan inlet volume flow Q v Full pressure P at inlet of fan t,in Full pressure P at outlet of fan t,out Fan opening beta, fan inlet static pressure P e,in Static pressure P at outlet of fan e,out The time period t is 10-30 days, and the time interval delta t =1 min-5 min.
3. The method for real-time online estimation of the running state of the wind turbine based on data mining according to claim 2, wherein in the step 2), when a sample set is constructed, the method specifically comprises the following steps:
according to boiler evaporation D b Set of data points with time t { (t) j ,D b,j ) And (5) screening data in a time interval delta t =2h, and selecting all data points { D ] in a given time interval i A set of intervals satisfying the following condition { (t) j ,t j +2h)}:
Wherein j =1,2.., m, i =1,2, …, k;
in the screened data set, the { (t) is proposed j +0.5h,t j +1.5 h) } time period, and performing mean value calculation to obtain a sample point set:
4. the method according to claim 3, wherein in the step 3), based on the sample point set, the artificial neural network is adopted to respectively train, and the fan inlet volume flow Q is obtained v With main steam flow D b Change relation model Q of v =f(D b ) Static pressure P at inlet of fan e,in And fan inlet volume flow Q v Is generated by the variation relation model P e,in =f(Q v ) Static pressure P at the outlet of the fan e,out And fan inlet volume flow Q v Is generated by the variation relation model P e,out =f(Q v ) Inlet full pressure P of fan t,in And fan inlet volume flow Q v Is generated by the variation relation model P t,in =f(Q v ) And fan outlet full pressure P t,out And fan inlet volume flow Q v Is generated by the variation relation model P t,out =f(Q v )。
5. The method for real-time online estimation of the operating state of the draught fan based on the data mining as claimed in claim 4, wherein in the step 3), the state change of the smoke and air system is predicted, and the change value of the front and rear resistances of the draught fan under the corresponding operating condition, namely (D' b ,ΔP in )、(D’ b ,ΔP out )。
6. The method for real-time online estimation of the operating state of the wind turbine based on data mining as claimed in claim 5, wherein in the step 4), the operating parameters of the state of the wind turbine include:
determining a boiler evaporation capacity interval [ D ] within a unit wide load regulation range according to basic boiler design parameters and the actual operation condition of the unit b,min ,D b,BMCR ]Selecting m typical working conditions in the interval to obtain a boiler evaporation capacity set { D b,i And calculating to obtain a state parameter point set under each working condition according to each parameter relation model, namely { (D) b ,T in ,Q v ,P e,in ,P e,out ,P t,in ,P t,out ,…) i I =1,2,3,. M, m>=3;
Based on a smoke system resistance variation value (D' b ,ΔP in )、(D’ b ,ΔP out ) Calculating to obtain a fan state parameter estimated value under each typical working condition, namely { (Q) v ,P e,in -ΔP in ,P e,out +ΔP out ,P t,in +ΔP in ,P t,in +ΔP in ) i (i =1,2,3, … m), wherein:
correcting the volume flow of the inlet of the fan according to the changes of the smoke temperature and the static pressure of the inlet of the fan, calculating to obtain the total pressure Pt and the specific pressure Y of the fan according to the estimated values of the state parameters of the fan under various typical working conditions, and then obtaining the estimated parameter of the operation of the fan as { (Q' v ,P’ t ,Y’) i }。
7. The method of claim 6, wherein in the step 5), the wind turbine operation state real-time online estimation method based on data mining is implemented according to a wind turbine operation estimation point parameter { (Q' v ,P’ t ,Y’) i And (i =1,2,3, … m) marked on the fan performance curve, and acquiring the opening beta corresponding to each operating condition fan operating point i And identifying and obtaining the intersection point of the equal opening degree line and the theoretical stall line { (Q) v,s ,P t,s ) i };
Calculating each stall margin coefficient according to the fan operation estimated point and the stall point p ,k q ,k s ) i };
The fan stall pressure margin coefficient is as follows:
k p =p t,s /p' t
the fan stall flow margin coefficient is as follows:
k q =Q' v /Q v,s
the fan stalling safety coefficient is as follows:
8. the method for real-time online estimation of the running state of the wind turbine based on data mining as claimed in claim 7, wherein in step 6), in order to ensure safe and stable running of the wind turbine, the running parameters of the wind turbine at each working condition point all satisfy the following conditions:
k s k is not less than 1.35 p ≥1.15、k q ≥1.08;
If the estimated operating point parameters of each fan do not meet the conditions, the situation that the fan cannot meet the full load range conditions after the resistance of the flue gas system is increased is shown, the fan anti-stall regulation and control are needed, and the resistance increase value delta P of the flue gas system is reduced in And Δ P out And evaluating again until the operating state parameters meeting the conditions are obtained, and further monitoring the static pressure difference delta P of the inlet and the outlet of the actual fan e And blower opening degree beta 0 And formulating a control strategy for preventing the stalling of the fan, namely meeting the following requirements:
ΔP e <(P e,out +ΔP out ) BMCR –(P e,in -ΔP in ) BMCR ;
β 0 <0.8β max 。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211337037.4A CN115596696A (en) | 2022-10-28 | 2022-10-28 | Real-time online estimation method for running state of fan based on data mining |
PCT/CN2023/090359 WO2024087552A1 (en) | 2022-10-28 | 2023-04-24 | Method for performing real-time online estimation on operating state of fan on basis of data mining |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211337037.4A CN115596696A (en) | 2022-10-28 | 2022-10-28 | Real-time online estimation method for running state of fan based on data mining |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115596696A true CN115596696A (en) | 2023-01-13 |
Family
ID=84850068
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211337037.4A Pending CN115596696A (en) | 2022-10-28 | 2022-10-28 | Real-time online estimation method for running state of fan based on data mining |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN115596696A (en) |
WO (1) | WO2024087552A1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117090758A (en) * | 2023-08-31 | 2023-11-21 | 上海宏赛自动化电气有限公司 | Energy-saving control method and system for air compressor |
WO2024087552A1 (en) * | 2022-10-28 | 2024-05-02 | 西安热工研究院有限公司 | Method for performing real-time online estimation on operating state of fan on basis of data mining |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109826816B (en) * | 2018-12-29 | 2020-04-24 | 浙江大学 | Intelligent early warning system and method for fan stall |
CN111737910A (en) * | 2020-06-10 | 2020-10-02 | 大连理工大学 | Axial flow compressor stall surge prediction method based on deep learning |
CN111946651B (en) * | 2020-08-12 | 2022-04-12 | 中国大唐集团科学技术研究院有限公司华东电力试验研究院 | Fan stall early warning method and system |
CN111985096B (en) * | 2020-08-12 | 2023-09-15 | 浙江浙能技术研究院有限公司 | Draught fan stall intelligent early warning method based on actual critical stall curve of draught fan |
CN113653607B (en) * | 2021-08-10 | 2022-10-14 | 浙江浙能数字科技有限公司 | Intelligent power station fan stall early warning diagnosis method based on system efficiency model |
CN114776619B (en) * | 2022-04-29 | 2024-08-30 | 西安热工研究院有限公司 | Actual stall line calibration method for axial flow fan of power station in running state |
CN114992150B (en) * | 2022-05-19 | 2024-07-26 | 西安热工研究院有限公司 | Early warning method, device and storage medium for stall of fan of coal-fired power plant |
CN115596696A (en) * | 2022-10-28 | 2023-01-13 | 西安热工研究院有限公司(Cn) | Real-time online estimation method for running state of fan based on data mining |
-
2022
- 2022-10-28 CN CN202211337037.4A patent/CN115596696A/en active Pending
-
2023
- 2023-04-24 WO PCT/CN2023/090359 patent/WO2024087552A1/en unknown
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024087552A1 (en) * | 2022-10-28 | 2024-05-02 | 西安热工研究院有限公司 | Method for performing real-time online estimation on operating state of fan on basis of data mining |
CN117090758A (en) * | 2023-08-31 | 2023-11-21 | 上海宏赛自动化电气有限公司 | Energy-saving control method and system for air compressor |
CN117090758B (en) * | 2023-08-31 | 2024-03-12 | 上海宏赛自动化电气有限公司 | Energy-saving control method and system for air compressor |
Also Published As
Publication number | Publication date |
---|---|
WO2024087552A1 (en) | 2024-05-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115596696A (en) | Real-time online estimation method for running state of fan based on data mining | |
US8135653B2 (en) | Power plant control device which uses a model, a learning signal, a correction signal, and a manipulation signal | |
CN112288296B (en) | Real-time evaluation system for operation performance and economy of desulfurization device and application method | |
CN100370117C (en) | Online controlling method for steam turbine rotator equivalent stress safety margin coefficient | |
CN110426953B (en) | AGC performance evaluation method based on thermal power generating unit power generation model | |
CN105317476A (en) | Turbine flow curve identification and optimization method based on feature flow area | |
DE102007061604A1 (en) | Optimization of the operation of a power plant | |
CN115111601A (en) | Multi-target boiler combustion optimization control method with embedded algorithm fusion under variable loads | |
CN117073154A (en) | Refrigerating air conditioner operation efficiency detecting system based on Internet of things | |
CN105240058A (en) | Steam turbine flow curve identifying and optimizing method based on spray nozzle flow calculation | |
CN113722656B (en) | Real-time health evaluation method and system for thermal generator set | |
JPH08339204A (en) | Autonomous adaptive optimization control system for thermal power station | |
CN117348648A (en) | Automatic control method and device for sheep hurdle environment | |
CN113653607B (en) | Intelligent power station fan stall early warning diagnosis method based on system efficiency model | |
CN111275320A (en) | Performance adjustment data processing method and system of generator set and storage medium | |
CN111946651B (en) | Fan stall early warning method and system | |
CN113325700A (en) | Fan opening and efficiency online calculation method based on fan performance curve | |
CN113887116A (en) | Power station boiler dynamic operation main steam temperature delay characteristic modeling method | |
DE112017006305T5 (en) | GAS TURBINE CONTROL DEVICE AND GAS TURBINE CONTROL METHOD | |
CN118411007B (en) | Efficient comprehensive energy station AI intelligent management system | |
KR20160063839A (en) | Intelligent Pigsty Air Vent Method Of Control | |
CN113591283B (en) | Method and device for adjusting operating oxygen amount of gas boiler and computer equipment | |
CN111852596B (en) | Method for predicting operation parameters and relative power generation coal consumption rate of boiler steam turbine generator unit | |
CN109492855B (en) | Condenser type steam turbine exhaust temperature prediction method based on data model | |
CN115681020A (en) | Axial flow type power station fan stall early warning method based on stall safety margin assessment |
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 |