CN113885607B - Steam temperature control method and device, electronic equipment and computer storage medium - Google Patents
Steam temperature control method and device, electronic equipment and computer storage medium Download PDFInfo
- Publication number
- CN113885607B CN113885607B CN202111220384.4A CN202111220384A CN113885607B CN 113885607 B CN113885607 B CN 113885607B CN 202111220384 A CN202111220384 A CN 202111220384A CN 113885607 B CN113885607 B CN 113885607B
- Authority
- CN
- China
- Prior art keywords
- steam temperature
- temperature control
- model
- control system
- action
- 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
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D23/00—Control of temperature
- G05D23/19—Control of temperature characterised by the use of electric means
- G05D23/20—Control of temperature characterised by the use of electric means with sensing elements having variation of electric or magnetic properties with change of temperature
Abstract
The invention provides a steam temperature control method, a steam temperature control device, electronic equipment and a computer storage medium, wherein the method comprises the following steps: acquiring detection data of a steam temperature control system; inputting detection data into a pre-established steam temperature control optimization model, and processing the detection data based on the steam temperature control optimization model to obtain a steam temperature control recommended value, wherein the steam temperature control optimization model is constructed by a steam temperature control behavior strategy model and a steam temperature control system comprehensive dynamic characteristic model; and controlling the steam temperature control system to execute the action corresponding to the steam temperature control recommended value based on the steam temperature control recommended value. In the embodiment of the invention, the steam temperature control optimization model constructed by the steam temperature control behavior strategy model and the steam temperature control system comprehensive dynamic characteristic model is used for processing the detection data so as to obtain the steam temperature control recommended value, and the steam temperature control is carried out by the above method, so that the steam temperature of the boiler can be accurately controlled.
Description
Technical Field
The invention relates to the technical field of thermal power generation processing, in particular to a steam temperature control method and device, electronic equipment and a computer storage medium.
Background
With the continuous development of thermal power generation calculation, in thermal control of a thermal power plant, the temperature of superheated steam at the outlet of a boiler (main steam temperature or superheated steam temperature) and the temperature of steam at the outlet of a reheater (reheated steam temperature) are key parameters in the operation of a coal-fired boiler, so that the safe and economic operation of the power plant is greatly influenced, equipment can be damaged when the steam temperature is too high, the cycle efficiency of a unit can be reduced when the steam temperature is too low, and the safe and stable operation of a steam turbine can be influenced.
At present, the conventional (proportional-integral-derivative controller) PID is widely adopted in the steam temperature control system of the normal-temperature electric machine set to control the operation parameters such as desuperheating water, a flue gas baffle and the like based on the error between the parameter strategy result and the demand result of the steam temperature control system so as to maintain the superheated steam temperature and the reheated steam temperature within the rated range. Because the control of the superheated steam temperature and the reheated steam temperature has the characteristics of large lag and large inertia, the steam temperature of the boiler cannot be accurately controlled by the method.
Disclosure of Invention
In view of this, embodiments of the present invention provide a steam temperature control method, apparatus, electronic device, and computer storage medium, so as to solve the problem in the prior art that the steam temperature of a boiler cannot be accurately controlled.
In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:
the first aspect of the embodiment of the invention shows a steam temperature control method, which comprises the following steps:
acquiring detection data of a steam temperature control system;
inputting the detection data into a pre-established steam temperature control optimization model, and processing the detection data based on the steam temperature control optimization model to obtain a steam temperature control recommended value, wherein the pre-established steam temperature control optimization model is constructed by a steam temperature control behavior strategy model and a steam temperature control system comprehensive dynamic characteristic model, and the steam temperature control behavior strategy model and the steam temperature control system comprehensive dynamic characteristic model are obtained based on historical data training;
and controlling the steam temperature control system to execute the action corresponding to the steam temperature control recommended value based on the steam temperature control recommended value.
Optionally, the processing the detection data based on the steam temperature control optimization model to obtain a steam temperature control recommended value includes:
processing the detection data by utilizing a steam temperature control behavior strategy model and a steam temperature control system comprehensive dynamic characteristic model to obtain a behavior action sequence;
sampling the action series to obtain a plurality of target action sequences;
aiming at each target action sequence, calculating based on a comprehensive optimization objective function to obtain an accumulated reward value corresponding to each group of target action sequences, wherein the comprehensive optimization objective function is obtained by calculating based on the target action sequences and state characteristic sequences which are output by the comprehensive dynamic characteristic model of the steam temperature control system and correspond to the target action sequences;
ordering the sequence of target actions based on the magnitude of the jackpot value;
selecting a set of target action sequences to be optimized based on the sequencing sequence corresponding to the target action sequences;
and performing iterative optimization on the set of the target action sequences to be optimized until the optimization times are equal to the preset iteration times, and determining the current target action sequence as a steam temperature control recommended value.
Optionally, the process of obtaining the steam temperature control behavior strategy model based on historical data training includes:
collecting historical data of the operation of the thermal power generating unit;
processing the historical data to obtain a steam temperature control offline data set;
and training a deep neural network model based on the state characteristics and the action characteristics in the steam temperature control off-line data set to obtain a steam temperature control behavior strategy model.
Optionally, the steam temperature control system comprehensive dynamic characteristic model includes a superheated steam temperature change dynamic characteristic model and a reheated steam temperature change dynamic characteristic model, and the process of obtaining the steam temperature control system comprehensive dynamic characteristic model based on historical data training includes:
collecting historical data of the operation of the thermal power generating unit;
processing the historical data to obtain a steam temperature control offline data set;
determining an initial LSTM network model;
training the initial LSTM network model based on state characteristics and action characteristics related to the superheated steam temperature change in the steam temperature control offline data set to obtain a superheated steam temperature change dynamic characteristic model;
and training the initial LSTM network model based on the state characteristics and action characteristics related to the reheat steam temperature change in the steam temperature control offline data set to obtain a reheat steam temperature change dynamic characteristic model.
A second aspect of an embodiment of the present invention shows a steam temperature control device, including:
the acquisition unit is used for acquiring detection data of the steam temperature control system;
the steam temperature control optimization model is used for inputting the detection data into a pre-established steam temperature control optimization model and processing the detection data based on the steam temperature control optimization model to obtain a steam temperature control recommended value, wherein the pre-established steam temperature control optimization model is constructed by a steam temperature control behavior strategy model and a steam temperature control system comprehensive dynamic characteristic model, and the steam temperature control behavior strategy model and the steam temperature control system comprehensive dynamic characteristic model are both constructed based on a construction unit;
and the execution unit is used for controlling the steam temperature control system to execute the action corresponding to the steam temperature control recommended value based on the steam temperature control recommended value.
Optionally, the steam temperature control optimization model is specifically configured to:
processing the detection data by utilizing a steam temperature control behavior strategy model and a steam temperature control system comprehensive dynamic characteristic model to obtain a behavior action sequence; sampling the action series to obtain a plurality of target action sequences; aiming at each target action sequence, calculating based on a comprehensive optimization objective function to obtain a cumulative reward value corresponding to each group of target action sequences, wherein the comprehensive optimization objective function is obtained by calculating based on the target action sequences and state characteristic sequences which are output by the comprehensive dynamic characteristic model of the steam temperature control system and correspond to the target action sequences; ordering the sequence of target actions based on the magnitude of the jackpot value; selecting a set of target action sequences to be optimized based on the sequencing sequence corresponding to the target action sequences; and performing iterative optimization on the set of the target action sequences to be optimized until the optimization times are equal to the preset iteration times, and determining the current target action sequence as a steam temperature control recommended value.
Optionally, the building unit is configured to collect historical data of operation of the thermal power generating unit; processing the historical data to obtain a steam temperature control offline data set; and training a deep neural network model based on the state characteristics and the action characteristics in the steam temperature control offline data set to obtain a steam temperature control behavior strategy model.
Optionally, the building unit is further configured to: determining an initial LSTM network model; training the initial LSTM network model based on the state characteristics and the action characteristics related to the superheated steam temperature change in the steam temperature control offline data set to obtain a superheated steam temperature change dynamic characteristic model; and training the initial LSTM network model based on the state characteristics and action characteristics related to the reheat steam temperature change in the steam temperature control offline data set to obtain a reheat steam temperature change dynamic characteristic model.
A third aspect of the embodiments of the present invention shows an electronic device, where the electronic device is configured to run a program, where the program is executed to perform the steam temperature control method shown in the first aspect of the embodiments of the present invention.
A fourth aspect of the embodiments of the present invention shows a computer storage medium, where the storage medium includes a storage program, and when the program runs, the apparatus on which the storage medium is located is controlled to execute the steam temperature control method shown in the first aspect of the embodiments of the present invention.
Based on the steam temperature control method, the steam temperature control device, the electronic equipment and the computer storage medium, provided by the embodiment of the invention, the method comprises the following steps: acquiring detection data of a steam temperature control system; inputting detection data into a pre-established steam temperature control optimization model, and processing the detection data based on the steam temperature control optimization model to obtain a steam temperature control recommended value, wherein the pre-established steam temperature control optimization model is constructed by a steam temperature control behavior strategy model and a steam temperature control system comprehensive dynamic characteristic model, and the steam temperature control behavior strategy model and the steam temperature control system comprehensive dynamic characteristic model are obtained based on historical data training; and controlling the steam temperature control system to execute the action corresponding to the steam temperature control recommended value based on the steam temperature control recommended value. In the embodiment of the invention, the steam temperature control optimization model constructed by the steam temperature control behavior strategy model and the steam temperature control system comprehensive dynamic characteristic model is used for processing the detection data so as to obtain the steam temperature control recommended value, and the steam temperature control is carried out by the above method, so that the steam temperature of the boiler can be accurately controlled.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic diagram of a steam temperature automatic control network according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a steam temperature control method according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart illustrating a steam temperature control optimization model architecture for determining a steam temperature control recommendation value according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a method for determining a recommended value for steam temperature control according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a steam temperature control device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In this application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
In the embodiment of the invention, the steam temperature control optimization model constructed by the steam temperature control behavior strategy model and the steam temperature control system comprehensive dynamic characteristic model is used for processing the detection data so as to obtain the steam temperature control recommended value, and the steam temperature control is carried out by the above method, so that the steam temperature of the boiler can be accurately controlled.
The steam temperature control method disclosed in the embodiment of the present invention may be used in a Distributed Control System (DCS) of a boiler, and as shown in fig. 1, is a schematic diagram of an automatic steam temperature control network shown in the embodiment of the present invention.
On the premise that the first DCS system 10 of the plant is not modified, i.e., the original DCS system is not modified, a communication interface standard (OLE for process Control, OPC) station 20, a server 30, a second DCS system 40, and a steam temperature Control system 50 are further provided.
One end of the first DCS system 10 is connected to the OPC station 20, and the other end is connected to the second DCS system 40. The OPC station 20 is connected to the server 30 via a unidirectional isolation gatekeeper, and the second DCS system 40 is also connected to the server 30. The server 30 is connected to the steam temperature control system 50.
The steam temperature control system 50 includes an exchanger 51, a display 52, an application server 53, a first big data server 54, and a second big data server 55.
In a specific implementation, the server 30 is connected to a display 52, an application server 53, a first big data server 54 and a second big data server 55 through a switch 51.
The server 30 is an engineer station, an interface station, and a strategy research server, and the server 30 is configured to obtain detection data sent by the steam temperature control system 50, input the detection data into a steam temperature control optimization model established in advance, and process the detection data based on the steam temperature control optimization model to obtain a steam temperature control recommended value; and the steam temperature control recommended value, that is, the optimized control instruction recommended value is accessed to the first DCS system 10, and the first DCS system 10 controls the superheated steam temperature and the reheated steam temperature under the guidance of the latest optimized recommended control value, that is, the steam temperature control recommended value.
In the embodiment of the invention, the communication between the steam temperature control optimization model in the server and the DCS is realized on the premise of not modifying the DCS, the control signal corresponding to the optimized steam temperature control recommended value is transmitted to the DCS, and the control signal can directly participate in the control, so that the convenience and the operation safety of the steam temperature control are ensured. The steam temperature control system aims to solve the problems that a steam temperature control system is difficult to automatically input, the manual adjustment workload is large, and the adjustment economy is poor.
Referring to fig. 2, a schematic flow chart of a steam temperature control method according to an embodiment of the present invention is shown, where the method includes:
s201: and acquiring detection data of the steam temperature control system.
In step S201, the detection data refers to the current time state feature.
In the process of implementing step S201 specifically, the current time state characteristic of the steam temperature control system is obtained.
It should be noted that the state characteristics are used for reflecting the conditions of each state index in the operation of the steam temperature control system, and specifically include data such as furnace flue gas temperature, total air volume, boiler load, feed water flow, total coal volume, oxygen volume, steam temperature before (after) first (second) stage superheater spray attemperation, final superheater outlet main steam temperature, first (second) stage attemperation water flow, superheater attemperation water temperature, low temperature superheater inlet flue gas temperature, main steam flow, main steam pressure, main steam temperature, reheater spray attemperation front (after) steam temperature, reheater outlet steam temperature, reheater attemperation water temperature, horizontal reheater outlet (inlet) flue gas temperature, reheater pressure, reheater steam temperature, and the like.
S202: and inputting the detection data into a pre-established steam temperature control optimization model, and processing the detection data based on the steam temperature control optimization model to obtain a steam temperature control recommended value.
In S202, the pre-established steam temperature control optimization model is constructed by a steam temperature control behavior strategy model and a steam temperature control system comprehensive dynamic characteristic model, both of which are trained based on historical data.
In the process of specifically implementing the step S202, the input current time state characteristics are processed through the pre-established steam temperature control optimization model, that is, the current time state characteristics are processed through the steam temperature control optimization model established by the efficient gradient-free optimization method disclosed by the embodiment of the invention, and finally, the steam temperature control recommended value is output.
It should be noted that the steam temperature control recommended value refers to a limited time domain H, that is, an optimal target action sequence at H moments in future
Wherein the content of the first and second substances,
refers to the action characteristic corresponding to the current time,
refers to the action characteristics corresponding to the next moment, and so on,
refers to the action characteristic corresponding to the time H-1.
It should be further noted that the finite time domain H is set by the skilled person according to experience, and is not limited by the embodiment of the present invention.
The action characteristics refer to the related quantity which can be operated in the steam temperature control system and is used for adjusting the superheated steam temperature and the reheated steam temperature, and specifically comprise data such as a temperature-reducing water spray regulating valve position on the left (right) side of the primary (secondary) superheater, an overheated flue gas baffle, a reheater temperature-reducing water regulating valve position, a reheater flue gas baffle and the like.
In the embodiment of the present invention, based on the flow diagram of steam temperature control shown in fig. 2, correspondingly, the embodiment of the present invention further discloses a schematic flow diagram of determining a steam temperature control recommended value by using a steam temperature control optimization model architecture, as shown in fig. 3.
It should be noted that the process of training and obtaining the steam temperature control behavior strategy model based on historical data includes the following steps:
s11: and collecting historical data of the operation of the thermal power generating unit.
In the specific implementation process of step S11, the collected historical state characteristics and historical action characteristics of the thermal power generating unit are collected from the power plant system.
S12: and processing the historical data to obtain a steam temperature control offline data set.
In the process of implementing step S12, the historical data is cleaned, outlier samples are detected and removed, and the missing data is filled and the data noise is smoothed. Specifically, in order to meet the requirements of subsequent system model construction and training, state characteristics and action characteristics required by subsequent modeling are selected based on a unit overheating and reheating steam temperature related change mechanism, historical data are processed based on the selected state characteristics and action characteristics, namely data abnormal characteristic points are deleted, data sparse characteristic points are deleted, data are filled, and the like, and therefore the processed historical state characteristics and historical action characteristics serve as a steam temperature control offline data set.
The data in the steam temperature control offline data set are arranged according to a time sequence, each piece of data has the same time interval, and each piece of data comprises a numerical value of a historical state characteristic S and a historical action characteristic a of the steam temperature control system at a certain historical moment.
The time interval is set according to actual conditions, and may be generally 20s.
S13: and training a deep neural network model based on the state characteristics and the action characteristics in the steam temperature control off-line data set to obtain a steam temperature control behavior strategy model.
In the process of implementing step S13 specifically, the deep neural network model is determined as an initial model, the state features in the steam temperature control offline data set are used as the input of the initial model, and the motion features are the output of the initial model, in the stage of performing initial model training, the motion feature data in the data set are used as labels to train the initial model, and the initial model obtained by current training is determined as a trained steam temperature control behavior strategy model, as shown in fig. 3.
It can be understood that the temperature control behavior strategy model can be used to accurately identify the input state characteristics s of the steam temperature control system t Thereby outputting the action characteristic a of the steam temperature control system at the corresponding moment t That is, the steam temperature control behavior strategy model may be represented by equation (1).
Formula (1):
a t ＝f b (s t ) (1)
wherein s is t Is a state characteristic of the steam temperature control system at any time, a t The action characteristics of the steam temperature control system at the corresponding moment are output.
In the embodiment of the invention, the comprehensive dynamic characteristic model of the steam temperature control system comprises a superheated steam temperature change dynamic characteristic model and a reheated steam temperature change dynamic characteristic model. The process of training the superheated steam temperature change dynamic characteristic model and the reheated steam temperature change dynamic characteristic model based on the historical data comprises the following steps:
s21: and collecting historical data of the operation of the thermal power generating unit.
S22: and processing the historical data to obtain a steam temperature control offline data set.
It should be noted that the specific implementation process of steps S21 to S22 is the same as the specific implementation process of steps S11 to S12 described above, and reference may be made to each other.
S23: an initial LSTM network model is determined.
In the process of specifically realizing the step S23, the time lag of the system steam temperature change is considered, so that the long-term and short-term memory network LSTM is used to construct the superheated steam temperature change dynamic characteristic model and the reheated steam temperature change dynamic characteristic model, so as to accurately predict the change trends of the superheated steam temperature and the reheated steam temperature in a future period of time.
S24: and training the initial LSTM network model based on the state characteristics and the action characteristics related to the change of the superheated steam temperature in the steam temperature control offline data set to obtain a dynamic characteristic model of the change of the superheated steam temperature.
In the process of specifically implementing step S24, based on the historical state characteristics S 'related to the superheated steam temperature change in the steam temperature control offline data set, such as the furnace smoke temperature, the total air volume, the boiler load, the feed water flow, the total coal volume, the oxygen volume, the steam temperature before (after) the first (second) stage superheater spray water for temperature reduction, the main steam temperature at the outlet of the last stage superheater, the water flow of the first (second) stage desuperheating water, the temperature of the superheater desuperheating water, the temperature of the low-temperature superheater inlet flue gas, the main steam flow, the main steam pressure, and the main steam temperature, the initial LSTM network model is trained with the historical action characteristics a', such as the valve position of the desuperheating water spray regulating valve at the left (right) side of the first (second) stage superheater, and the superheated steam damper, to obtain the superheated steam temperature change dynamic characteristic model, as shown in fig. 3.
It is understood that the superheated steam temperature change dynamic characteristics model can be used for the state-action characteristic pairs { (s } for the past t moments' 1 ,a' 1 ),(s' 2 ,a' 2 ),...,(s' t ,a' t ) Processing and outputting a state feature s 'at the next moment' t+1 That is, the superheated steam temperature change dynamic characteristic model can be expressed by equation (2).
Formula (2):
s' t+1 ＝f m1 ((s',a') 1～t ) (2)
wherein, ((s ', a') 1～t ) Is a state-motion characteristic pair {(s) } at past t times' 1 ,a' 1 ),(s' 2 ,a' 2 ),...,(s' t ,a' t )}。
In the embodiment of the invention, the trained initial LSTM network model can accurately depict the change characteristics of the relevant state characteristics of the superheated steam temperature system under the action of the control quantity, and the characteristics of large lag, large inertia and the like of the superheated steam temperature are fully considered.
S25: and training the initial LSTM network model based on the state characteristics and action characteristics related to the reheat steam temperature change in the steam temperature control offline data set to obtain a reheat steam temperature change dynamic characteristic model.
In the process of specifically implementing step S25, based on historical state characteristics S "related to the reheat steam temperature change in the steam temperature control offline data set, such as boiler load, main steam flow, reheater pre (post) steam temperature before (after) water spray attemperation, reheater outlet steam temperature, reheater attemperation water temperature, horizontal reheater outlet (inlet) flue gas temperature, reheat steam pressure, reheat steam temperature, and the like, and historical action characteristics a" such as reheater attemperation water regulating valve position and reheater flue gas baffle, the initial LSTM network model is trained to obtain a reheat steam temperature change dynamic characteristic model, as shown in fig. 3.
It is understood that the reheat steam temperature variation dynamics model can be used for the state-action feature pairs for the past t moments (s { (s)) " 1 ,a” 1 ),(s” 2 ,a” 2 ),...,(s” t ,a” t ) Processing, and outputting state feature S at the next moment " t+1 That is, the superheated steam temperature change dynamic characteristic model can be obtained through a mathematical modelAnd (3) is represented by the following formula.
The formula (3) is:
s” t+1 ＝f m1 ((s”,a”) 1～t ) (3)
wherein, ((s ", a") 1～t ) Is a state-action feature pair of the past t moments(s) " 1 ,a” 1 ),(s” 2 ,a” 2 ),...,(s” t ,a” t )}。
It should be noted that the training process of the reheat steam temperature variation dynamic characteristic model is the same as the training process of the superheat steam temperature variation dynamic characteristic model, and the training processes can be referred to each other.
Superheated steam temperature change dynamic characteristic model s 'shown based on the embodiment of the invention' t+1 ＝f m1 ((s',a') 1～t ) And reheat steam temperature variation dynamic characteristic model s' t+1 ＝f m1 ((s”,a”) 1～t ) It can be determined that the steam temperature control system comprehensive dynamic characteristic model can be represented by formula (4).
Formula (4):
s t+1 ＝f m (s t ,a t ) (4)
wherein s is t+1 Characteristic of the state at time t +1, s t Characteristic of the state at time t, a t Is the behavior characteristic at the time t.
With reference to fig. 3, a final steam temperature control optimization model is established based on the steam temperature control behavior strategy model, the superheated steam temperature change dynamic characteristic model and the reheated steam temperature change dynamic characteristic model which are established in the above embodiments.
Wherein, the steam temperature control optimization model can be expressed by formulas (5), (6) and (7).
Formula (5):
wherein r is t (s t ,a t ) Refers to the comprehensive optimization of the objective function, s t Is a characteristic of the state at time t, a t Is tBehavioral characteristics of time of day, a 0 H-1 represents a 0 ,a 1 ,...,a H-1 An action sequence from time 0 to time H-1.
Equation (5) is used to solve the maximum value of the jackpot value from time 0 to time H-1 in the action sequence.
Optionally, in order to maintain the ideal stable state of the superheated steam temperature and the reheated steam temperature and the stability of the change of the model output steam temperature control strategy, a comprehensive optimization objective function may be determined based on a cost function of the change fluctuation of the superheated steam temperature, and a cost function of the fluctuation of the motion.
Specifically, the specific process of determining the comprehensive optimization objective function based on the cost function of the fluctuation of the superheated steam temperature, the cost function of the fluctuation of the superheated steam temperature and the cost function of the fluctuation of the motion includes:
firstly, the temperature T of the superheated steam 1 Rated superheated steam temperature value G 1 Constant g 1 And (5) substituting the formula (8) to determine a cost function of the change fluctuation of the superheated steam temperature.
Formula (8):
wherein the content of the first and second substances,
as a cost function of fluctuations in superheated steam temperature, T 1 For the temperature of superheated steam G 1 Is a rated superheated steam temperature value g 1 Given a constant, G 1 ±g 1 For the permissible range of the superheated steam temperature fluctuation, k 1 ,k 2 Is a constant number k 2 >k 1 >0。
Then, the reheated steam temperature T is firstly measured 2 Rated reheat steam temperature value G 2 Constant g 2 And (4) substituting the formula (9) to determine a cost function of the reheat steam temperature variation fluctuation.
Formula (9):
wherein the content of the first and second substances,
is a cost function of the change fluctuation of the reheated steam temperature, and is T 2 Is the reheat steam temperature G 2 Is the rated reheat steam temperature value, g 2 Given a constant, G 2 ±g 2 To the allowable reheat steam temperature fluctuation range, k 1 ,k 2 Is a constant number, k 2 >k 1 >0。
Then, in order to make the recommended action smoother, a cost function of the volatility of the recommended action needs to be incorporated. The action characteristic a at the time t t And the action characteristic a at the time t-1 t-1 And substituting the formula (10) to determine a cost function of the volatility of the recommended action.
Equation (10):
wherein, cost a Cost function of volatility of recommended actions, a t Is the motion characteristic at time t, a t-1 Is the action characteristic at the moment t-1.
Finally, the cost function of the change fluctuation of the superheated steam temperature is obtained based on the formula (8)
The cost function of the reheat steam temperature variation fluctuation obtained by the formula (9)
And the cost function cost of the volatility of the recommended action obtained by the formula (10) a Substituting into formula (11) to define the comprehensive optimization objective function r t 。
Formula (11):
wherein α, β, γ are given constants. Equation (5) considers the jackpot value over a finite time domain H, i.e. r over a finite time domain t Is the overall optimization objective.
Continuing with equation (6):
subject to s t+1 ＝f m (s t ,a t ) (6)
wherein s is t+1 The state characteristic at the t +1 moment is required to satisfy the comprehensive dynamic characteristic model, s, of the steam temperature control system t Is a characteristic of the state at time t, a t Is the behavior characteristic at the moment t.
Continuing with equation (7):
s 0 ＝s init ,s t ∈S,a t ∈A (7)
wherein s is 0 As a characteristic of the state at the present moment, s init The method refers to the state characteristic (initial state characteristic) of the system at the known current moment (0 moment), S is the overall state characteristic space of the steam temperature control system, and A is the corresponding overall action characteristic space.
S203: and controlling the steam temperature control system to execute the action corresponding to the steam temperature control recommended value based on the steam temperature control recommended value.
In the process of implementing step S203 specifically, the steam temperature control system is controlled to execute the first control action in the optimal target action sequence, that is, the first control action in the optimal target action sequence
The optimal control value of the steam temperature system recommended at the current moment is obtained.
In the embodiment of the invention, a steam temperature control behavior strategy model and a steam temperature control system comprehensive dynamic characteristic model are firstly established, and then a steam temperature control optimization model established by utilizing the steam temperature control behavior strategy model and the steam temperature control system comprehensive dynamic characteristic model is utilized. And then, the detection data is processed by using a steam temperature control optimization model so as to obtain a steam temperature control recommended value, and the steam temperature control is carried out by the above method, so that the steam temperature of the boiler can be accurately controlled.
Based on the steam temperature control method shown in the embodiment of the present invention, in the process of processing the detection data based on the steam temperature control optimization model in the specific implementation step S202 to obtain the steam temperature control recommended value, as shown in fig. 4, the method includes the following steps:
s401: and processing the detection data by utilizing a steam temperature control behavior strategy model and a steam temperature control system comprehensive dynamic characteristic model to obtain a behavior action sequence.
Specific contents of S401: the state feature s at 0, which is the starting point of the state feature in the detection data 0 Characterization of the state s 0 Inputting a steam temperature control behavior strategy model, namely calculating the action characteristic a at the 0 moment in the formula (1) 0 Is recorded as
(ii) a Then the state feature s 0 And action characteristics a 0 Inputting the state characteristic s of the steam temperature control system into a comprehensive dynamic characteristic model, namely a formula (4), and calculating the state characteristic s of the next moment 1 The state feature s of the next time obtained by calculation is calculated in the same way 1 Inputting a steam temperature control behavior strategy model, namely calculating the action characteristic a at the moment 1 in the formula (1) 1 Is marked as
(ii) a And the like until the H-1 moment is calculated, thereby obtaining a behavior action sequence
S402: and sampling the action series to obtain a target action sequence.
In step S402, the number of target motion sequences is plural.
Specific contents of S402: will act on the sequence
Inputting equation (12), i.e. Gaussian distribution corresponding to action sequence
And sampling to obtain a target action sequence.
Equation (12):
wherein M belongs to { 0.,. Multidot.M }, M is the preset iteration number,
is the average of the motion samples at time t,
is the variance of the motion sample at time t, A i And marking an action sequence for the ith item, and performing co-sampling to obtain N action sequences with the length of H.
The target action sequence is a sampled action sequence, and the number of the target action sequences is N.
The preset iteration times are the preset maximum iteration times.
S403: and calculating based on the comprehensive optimization objective function aiming at each target action sequence to obtain the accumulated reward value corresponding to each group of target action sequences.
In step S403, the comprehensive optimization objective function is calculated based on a target action sequence and a state feature sequence corresponding to the target action sequence output by the steam temperature control system comprehensive dynamic characteristic model.
Specific contents of S403: for any action sequence a 0 ,a 1 ,...,a H-1 Based on the above process of step S402, it is determined to calculate the action sequence of the comprehensive optimization objective function, but it is also required to know the corresponding state sequence. Therefore, it is necessary to set a in the operation sequence 0 And status characteristics s 0 Input steam temperature control system synthesisThe dynamic characteristics model, equation (6), calculates the state characteristics s at the next time 1 The state feature s at the next time obtained by calculation is calculated in the same way 1 And action sequence a 1 Inputting the state characteristic s of the steam temperature control system into a comprehensive dynamic characteristic model, namely a formula (6), and calculating the state characteristic s at the next moment 2 And the like, thereby obtaining a state characteristic sequence { s) corresponding to the target action sequence 0 ,s 1 ,...,s H-1 }。
Wherein the state characteristic s 0 Is obtained by inputting the state characteristics in the detection data into equation (7).
Finally, the action sequence { a } 0 ,a 1 ,...,a H-1 And a sequence of state features s corresponding to the target sequence of actions 0 ,s 1 ,...,s H-1 The input to equation (5) is calculated to determine the cumulative prize value R for the sequence of actions i 。
Note that the jackpot value R i It can also be expressed by the formula (13).
Formula (13):
wherein r is t For comprehensive optimization of the objective function, i is the index of the sequence.
In addition, the jackpot value { R corresponding to the N action sequences having the length H is determined based on the step S403 1 ,R 2 ,...,R N }。
S404: ordering the sequence of target actions based on the magnitude of the jackpot value.
S405: and selecting a set of target action sequences to be optimized based on the sequencing sequence corresponding to the target action sequences.
In the process of implementing steps S404 and S405 specifically, action sequence A i Substituting into equation (14) to sort the target action sequence by the magnitude of the jackpot value, i.e., sort in descending order, according to what is being achievedAnd the target action sequences with the accumulated reward values ranked from high to low take J target action sequences with the ranking orders as a set of target action sequences to be optimized through the ranking of the target action sequences from high to low.
Equation (14):
A elites ＝sort(A i )[-J：] (14)
wherein A is i Is a target action sequence, J is the J action sequence with the highest accumulated reward value, namely the J action sequence with the highest accumulated reward value, the value of J is a positive integer which is more than or equal to 0, A elites A set of action sequences is marked for the selected J entry.
S406: and performing iterative optimization on the set of the target action sequences to be optimized until the optimization times are equal to the preset iteration times, and determining the current target action sequence as a steam temperature control recommended value.
Specific contents of S406: first, use A elites For those in formula (12)
And
carry out optimization, namely A elites All sequences in t time step move
Mean of (A) elites ) t Substituting into equation (15) to optimize
And A is elites All sequences in t time step move
Variance of (A) var (A) elites ) t Substituting into equation (16) to optimize
Equation (15):
wherein mean (A) elites ) t Is A elites In all sequences t time steps
δ is a constant.
Equation (16):
wherein, var (A) elites ) t Is A elites All sequences in t time step move
δ is a constant.
In the embodiment of the invention, when m =0, the iteration is the first time, and the time is the first time
Is composed of
Namely the behavior calculated in step S401;
is composed of
I.e., the initialization sample variance is given, so that steps S402 to S406 are performed. After S406 is executed, the first iteration is completed, and m updates m, i.e., m is incremented by one (m = 1), and the updated m is calculated by equations (15) and (16)
And
and returns to perform steps S402 to S406. And repeating the steps until M times of iterative calculation are finished, namely obtaining the finally needed optimal action sequence, namely the steam temperature control recommended value when the iterative times reach the maximum M.
In the embodiment of the invention, a steam temperature control behavior strategy model and a steam temperature control system comprehensive dynamic characteristic model are utilized to process detection data to obtain a behavior action sequence; sampling the action series to obtain a target action sequence; calculating each target action sequence based on a comprehensive optimization objective function to obtain a cumulative reward value corresponding to each group of target action sequences; and sequencing the target action sequences based on the size of the accumulated reward value, and selecting a set of target action sequences to be optimized based on the sequencing sequence corresponding to the target action sequences. And performing iterative optimization on the set of target action sequences to be optimized until the optimization times are equal to the preset iteration times, and determining the current target action sequence as a steam temperature control recommended value. By means of the method, the steam temperature can be controlled accurately.
Corresponding to the steam temperature control method shown in the above embodiment of the present invention, the embodiment of the present invention also discloses a steam temperature control device, as shown in fig. 5, which is a schematic structural diagram of the steam temperature control device shown in the embodiment of the present invention, and the steam temperature control device includes:
the acquiring unit 501 is configured to acquire detection data of the steam temperature control system, where the detection data refers to a current state characteristic and an action characteristic.
And the steam temperature control optimization model 502 is used for inputting the detection data into a pre-established steam temperature control optimization model, and processing the detection data based on the steam temperature control optimization model to obtain a steam temperature control recommended value.
It should be noted that the pre-established steam temperature control optimization model is constructed by a steam temperature control behavior strategy model and a steam temperature control system comprehensive dynamic characteristic model, and both the steam temperature control behavior strategy model and the steam temperature control system comprehensive dynamic characteristic model are constructed based on the construction unit 504.
An executing unit 503, configured to control the steam temperature control system to execute an action corresponding to the steam temperature control recommended value based on the steam temperature control recommended value.
It should be noted that, the specific principle and the implementation process of each unit in the steam temperature control device disclosed in the embodiment of the present invention are the same as the steam temperature control method disclosed in the embodiment of the present invention, and reference may be made to the corresponding parts in the steam temperature control method disclosed in the embodiment of the present invention, which are not described herein again.
In the embodiment of the invention, the steam temperature control optimization model constructed by the steam temperature control behavior strategy model and the steam temperature control system comprehensive dynamic characteristic model is used for processing the detection data so as to obtain the steam temperature control recommended value, and the steam temperature control is carried out by the above method, so that the steam temperature of the boiler can be accurately controlled.
Optionally, based on the steam temperature control device shown in the above embodiment of the present invention, the steam temperature control optimization model 502 is specifically configured to:
processing the detection data by utilizing a steam temperature control behavior strategy model and a steam temperature control system comprehensive dynamic characteristic model to obtain a behavior action sequence; sampling the action series to obtain a target action sequence; calculating each target action sequence based on a comprehensive optimization objective function to obtain a cumulative reward value corresponding to each group of target action sequences; ordering the sequence of target actions based on the magnitude of the jackpot value; and selecting a set of target action sequences to be optimized based on the sequencing sequence corresponding to the target action sequences, performing iterative optimization on the set of target action sequences to be optimized until the optimization times are equal to the preset iteration times, and determining the current target action sequence as a steam temperature control recommended value.
It should be noted that the comprehensive optimization objective function is obtained by calculating based on a target action sequence and a state feature sequence corresponding to the target action sequence output by the comprehensive dynamic characteristic model of the steam temperature control system. The number of the target action sequences is multiple.
In the embodiment of the invention, a steam temperature control behavior strategy model and a steam temperature control system comprehensive dynamic characteristic model are utilized to process detection data to obtain a behavior action sequence; sampling the action series to obtain a target action sequence; calculating based on a comprehensive optimization objective function aiming at each target action sequence to obtain an accumulated reward value corresponding to each group of target action sequences; and sequencing the target action sequences based on the size of the accumulated reward value, and selecting a set of target action sequences to be optimized based on the sequencing sequence corresponding to the target action sequences. And performing iterative optimization on the set of target action sequences to be optimized until the optimization times are equal to the preset iteration times, and determining the current target action sequence as a steam temperature control recommended value. By means of the method, the steam temperature can be controlled accurately.
Optionally, based on the steam temperature control device shown in the embodiment of the present invention, the unit 504 is configured to acquire a model of the comprehensive dynamic characteristics of the operation of the thermal power generating unit and the steam temperature control system; processing the historical data to obtain a steam temperature control offline data set; and training a deep neural network model based on the state characteristics in the steam temperature control offline data set to obtain a steam temperature control behavior strategy model.
Optionally, the constructing unit 504 is further configured to: determining an initial LSTM network model; training the initial LSTM network model based on the state characteristics and the action characteristics related to the superheated steam temperature change in the steam temperature control offline data set to obtain a superheated steam temperature change dynamic characteristic model; and training the initial LSTM network model based on the state characteristics and action characteristics related to the reheat steam temperature change in the steam temperature control offline data set to obtain a reheat steam temperature change dynamic characteristic model.
In the embodiment of the invention, a steam temperature control behavior strategy model and a steam temperature control system comprehensive dynamic characteristic model are firstly constructed, and then a steam temperature control optimization model is constructed by utilizing the steam temperature control behavior strategy model and the steam temperature control system comprehensive dynamic characteristic model. And then, the detection data is processed by utilizing the steam temperature control optimization model, so that a steam temperature control recommended value is obtained, and the steam temperature control is carried out in the above way, so that the steam temperature of the boiler can be accurately controlled.
The embodiment of the invention also discloses electronic equipment which is used for operating the database storage process, wherein the steam temperature control method disclosed by the figure 2 and the figure 4 is executed when the database storage process is operated.
The embodiment of the invention also discloses a computer storage medium which comprises a storage database storage process, wherein when the storage database storage process runs, the equipment where the storage medium is located is controlled to execute the steam temperature control method disclosed by the figure 2 and the figure 4.
In the context of this disclosure, a computer storage medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
All the embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, the system or system embodiments, which are substantially similar to the method embodiments, are described in a relatively simple manner, and reference may be made to some descriptions of the method embodiments for relevant points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. A steam temperature control method, characterized in that the method comprises:
acquiring detection data of a steam temperature control system;
inputting the detection data into a pre-established steam temperature control optimization model, and processing the detection data based on the steam temperature control optimization model to obtain a steam temperature control recommended value, wherein the pre-established steam temperature control optimization model is constructed by a steam temperature control behavior strategy model and a steam temperature control system comprehensive dynamic characteristic model, and the steam temperature control behavior strategy model and the steam temperature control system comprehensive dynamic characteristic model are obtained based on historical data training;
controlling the steam temperature control system to execute an action corresponding to the steam temperature control recommended value based on the steam temperature control recommended value;
the actions corresponding to the steam temperature control recommended value are as follows: processing the detection data by utilizing a steam temperature control behavior strategy model and a steam temperature control system comprehensive dynamic characteristic model to obtain a behavior action sequence;
sampling the action series to obtain a plurality of target action sequences, and controlling the steam temperature control system to execute a first control action in the optimal target action sequence;
the detection data refers to the state characteristics of the steam temperature control system at the current moment;
aiming at each target action sequence, calculating based on a comprehensive optimization objective function to obtain an accumulated reward value corresponding to each group of target action sequences, wherein the comprehensive optimization objective function is obtained by calculating based on the target action sequences and state characteristic sequences which are output by the comprehensive dynamic characteristic model of the steam temperature control system and correspond to the target action sequences;
sorting the sequence of target actions based on the magnitude of the jackpot value;
selecting a set of target action sequences to be optimized based on the sequencing sequence corresponding to the target action sequences;
performing iterative optimization on the set of the target action sequences to be optimized until the optimization times are equal to the preset iteration times, and determining the current target action sequence as a steam temperature control recommended value;
collecting historical data of the operation of the thermal power generating unit;
processing the historical data to obtain a steam temperature control offline data set;
training a deep neural network model based on the state characteristics and the action characteristics in the steam temperature control offline data set to obtain a steam temperature control behavior strategy model;
the action characteristics refer to the related quantity which can be operated in the steam temperature control system and is used for adjusting the superheated steam temperature and the reheated steam temperature, and the action characteristics specifically comprise data of a temperature-reducing water spray regulating valve position on the left (right) side of a primary (secondary) superheater, an overheated flue gas baffle, a reheater temperature-reducing water regulating valve position and a reheater flue gas baffle.
2. The method of claim 1, wherein the steam temperature control system comprehensive dynamic characteristic model comprises a superheated steam temperature change dynamic characteristic model and a reheated steam temperature change dynamic characteristic model, and the process of obtaining the steam temperature control system comprehensive dynamic characteristic model based on historical data training comprises:
collecting historical data of the operation of the thermal power generating unit;
processing the historical data to obtain a steam temperature control offline data set;
determining an initial LSTM network model;
training the initial LSTM network model based on state characteristics and action characteristics related to the superheated steam temperature change in the steam temperature control offline data set to obtain a superheated steam temperature change dynamic characteristic model;
and training the initial LSTM network model based on the state characteristics and action characteristics related to the reheat steam temperature change in the steam temperature control offline data set to obtain a reheat steam temperature change dynamic characteristic model.
3. A steam temperature control device, the device comprising:
the acquisition unit is used for acquiring detection data of the steam temperature control system;
the steam temperature control optimization model is used for inputting the detection data into a pre-established steam temperature control optimization model and processing the detection data based on the steam temperature control optimization model to obtain a steam temperature control recommended value, wherein the pre-established steam temperature control optimization model is constructed by a steam temperature control behavior strategy model and a steam temperature control system comprehensive dynamic characteristic model, and the steam temperature control behavior strategy model and the steam temperature control system comprehensive dynamic characteristic model are both constructed based on a construction unit;
the execution unit is used for controlling the steam temperature control system to execute the action corresponding to the steam temperature control recommended value based on the steam temperature control recommended value;
the actions corresponding to the steam temperature control recommended value are as follows: processing the detection data by utilizing the steam temperature control behavior strategy model and the steam temperature control system comprehensive dynamic characteristic model to obtain a behavior action sequence, sampling the action sequence to obtain a plurality of target action sequences, and controlling the steam temperature control system to execute a first control action in the optimal target action sequence;
the detection data refer to the state characteristics of the steam temperature control system at the current moment;
aiming at each target action sequence, calculating based on a comprehensive optimization objective function to obtain a cumulative reward value corresponding to each group of target action sequences, wherein the comprehensive optimization objective function is obtained by calculating based on the target action sequences and state characteristic sequences which are output by the comprehensive dynamic characteristic model of the steam temperature control system and correspond to the target action sequences; ordering the sequence of target actions based on the magnitude of the jackpot value; selecting a set of target action sequences to be optimized based on the sequencing sequence corresponding to the target action sequences; performing iterative optimization on the set of the target action sequences to be optimized until the optimization times are equal to the preset iteration times, and determining the current target action sequence as a steam temperature control recommended value;
the construction unit is used for acquiring historical data of the operation of the thermal power generating unit; processing the historical data to obtain a steam temperature control offline data set; training a deep neural network model based on the state characteristics and the action characteristics in the steam temperature control offline data set to obtain a steam temperature control behavior strategy model;
the action characteristics refer to the related quantity which can be operated in the steam temperature control system and is used for adjusting the superheated steam temperature and the reheated steam temperature, and the action characteristics specifically comprise data of a temperature-reducing water spray regulating valve position on the left (right) side of a primary (secondary) superheater, an overheated flue gas baffle, a reheater temperature-reducing water regulating valve position and a reheater flue gas baffle.
4. The apparatus of claim 3, wherein the build unit is further configured to: determining an initial LSTM network model; training the initial LSTM network model based on the state characteristics and the action characteristics related to the superheated steam temperature change in the steam temperature control offline data set to obtain a superheated steam temperature change dynamic characteristic model; and training the initial LSTM network model based on the state characteristics and action characteristics related to the reheat steam temperature change in the steam temperature control offline data set to obtain a reheat steam temperature change dynamic characteristic model.
5. An electronic device, characterized in that the electronic device is configured to run a program, wherein the program is configured to execute the steam temperature control method according to any one of claims 1-2 when running.
6. A computer storage medium, characterized in that the storage medium comprises a stored program, wherein when the program runs, the device on which the storage medium is located is controlled to execute the steam temperature control method according to any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111220384.4A CN113885607B (en) | 2021-10-20 | 2021-10-20 | Steam temperature control method and device, electronic equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111220384.4A CN113885607B (en) | 2021-10-20 | 2021-10-20 | Steam temperature control method and device, electronic equipment and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113885607A CN113885607A (en) | 2022-01-04 |
| CN113885607B true CN113885607B (en) | 2022-12-27 |
Family
ID=79003911
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111220384.4A Active CN113885607B (en) | 2021-10-20 | 2021-10-20 | Steam temperature control method and device, electronic equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113885607B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114625091A (en) * | 2022-03-21 | 2022-06-14 | 京东城市(北京)数字科技有限公司 | Optimization control method and device, storage medium and electronic equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101221415A (en) * | 2007-01-10 | 2008-07-16 | 株式会社日立制作所 | Plant control apparatus |
| CN110941186A (en) * | 2019-12-26 | 2020-03-31 | 华润电力技术研究院有限公司 | Steam temperature control optimization method based on neural network and universal gravitation search algorithm |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5277064B2 (en) * | 2009-04-22 | 2013-08-28 | 株式会社日立製作所 | Plant control device, thermal power plant control device, and thermal power plant |
| US9932907B2 (en) * | 2015-03-03 | 2018-04-03 | General Electric Company | Methods and systems for enhancing control of power plant generating units |
| CN109190327B (en) * | 2018-11-23 | 2022-11-22 | 华北电力大学（保定） | Method, device and equipment for analyzing and optimizing organic Rankine cycle system |
-
2021
- 2021-10-20 CN CN202111220384.4A patent/CN113885607B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101221415A (en) * | 2007-01-10 | 2008-07-16 | 株式会社日立制作所 | Plant control apparatus |
| CN110941186A (en) * | 2019-12-26 | 2020-03-31 | 华润电力技术研究院有限公司 | Steam temperature control optimization method based on neural network and universal gravitation search algorithm |
Non-Patent Citations (7)
| Title |
|---|
| 主蒸汽隔离阀驱动装置动作性能优化方法研究;邢璐辉等;《机电信息》;20200415(第11期);全文 * |
| 再热汽温神经网络预测模型的构建及仿真;张韵辉等;《电力系统及其自动化学报》;20060225(第01期);全文 * |
| 基于有限元模型校正及降阶的温控系统设计;王晓娜等;《系统仿真学报》;20180608(第06期);全文 * |
| 基于遗传算法的MFA控制在主汽温系统中的仿真研究;宁薇薇;《电力职业技术学刊》;20101215(第04期);全文 * |
| 智能混合模型预测技术在火电厂节能减排中的应用;符岳全;《热力发电》;20091015(第10期);全文 * |
| 符岳全.智能混合模型预测技术在火电厂节能减排中的应用.《热力发电》.2009,(第10期), * |
| 超超临界锅炉闭环燃烧优化控制方法及应用!;周慎学等;《自动化仪表》;20181020(第10期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113885607A (en) | 2022-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1698956B1 (en) | Method for optimizing combined cycle/combined process facilities | |
| CN105955026B (en) | Fuzzy PID control method, device and system | |
| CN107168392B (en) | Method for setting PID (proportion integration differentiation) parameter of boiler drum water level | |
| CN107515598A (en) | Fired power generating unit distributed and coordinated control system based on multi-parameter dynamic matrix control | |
| CN108509752A (en) | A kind of superheater mechanism model dynamic parameter setting method of combination field data | |
| CN110285403A (en) | Main Steam Temperature Control method based on controlled parameter prediction | |
| CN102889598A (en) | Control method for assisting stable combustion of garbage by predicting garbage calorific value | |
| WO2015035134A1 (en) | Combined cycle power generation optimization system | |
| Draganescu et al. | Generalized predictive control for superheated steam temperature regulation in a supercritical coal-fired power plant | |
| CN102608911A (en) | Fossil power plant coordination control method based on multi-parameter prediction | |
| CN113885607B (en) | Steam temperature control method and device, electronic equipment and computer storage medium | |
| CN103744294A (en) | Multi-target soot blowing optimization method based on fuzzy control, server and system | |
| CN113031565B (en) | Method and system for predicting primary frequency modulation power response performance of thermal power generating unit | |
| CN107065556A (en) | A kind of automatic search method of reactor core unit Variable power optimization of operation strategy scheme | |
| CN108762086B (en) | Secondary reheat steam temperature control device and control system based on model predictive control | |
| Elshafei et al. | Boilers optimal control for maximum load change rate | |
| Halihal | Modeling and Control of Water Level in Boiler Drum for Nassiriyah Thermal Power Plant. | |
| JPH11242503A (en) | Plant operation control support system | |
| CN110610276B (en) | Comprehensive energy system scheduling method and system containing generalized predictive control | |
| CN114562713A (en) | Main steam temperature control method and system for power generation boiler | |
| Tang et al. | Data analytics based dual-optimized adaptive model predictive control for the power plant boiler | |
| Gordillo et al. | Genetic design of a fuzzy logic controller for a solar power plant | |
| Valsalam et al. | Boiler modelling and optimal control of steam temperature in power plants | |
| CN112348696A (en) | Heat supply unit peak regulation upper limit evaluation method and system based on BP neural network | |
| CN112381296A (en) | Neural network model for predicting wall temperature of high-temperature superheater of coal-fired unit |
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 |