CN115903548B - Optimization method, device and equipment for coal mill unit controller and storage medium - Google Patents
Optimization method, device and equipment for coal mill unit controller and storage medium Download PDFInfo
- Publication number
- CN115903548B CN115903548B CN202211685468.XA CN202211685468A CN115903548B CN 115903548 B CN115903548 B CN 115903548B CN 202211685468 A CN202211685468 A CN 202211685468A CN 115903548 B CN115903548 B CN 115903548B
- Authority
- CN
- China
- Prior art keywords
- coal mill
- mill unit
- control
- state information
- simulation system
- 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
- 239000003245 coal Substances 0.000 title claims abstract description 232
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000005457 optimization Methods 0.000 title claims abstract description 30
- 238000004088 simulation Methods 0.000 claims abstract description 78
- 239000000843 powder Substances 0.000 claims description 69
- 239000003570 air Substances 0.000 claims description 40
- 230000006870 function Effects 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 16
- 239000012080 ambient air Substances 0.000 claims description 4
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Disintegrating Or Milling (AREA)
Abstract
The invention discloses an optimization method, device and equipment for a coal mill unit controller and a storage medium. The method comprises the following steps: acquiring state information of a coal mill unit simulation system, and determining a control feature set according to the state information; inputting the control feature set into a coal mill unit controller to obtain a group of control instructions generated by the coal mill unit controller; inputting a plurality of groups of control instructions into a coal mill unit simulation system to obtain a state prediction track output by the coal mill unit simulation system; the network parameters of the coal mill set controller are adjusted according to the reward value of the state prediction track, so that the optimization of the coal mill set controller is realized, the problems of uncoordinated, unstable, large control deviation and the like of the existing coal mill set controller are solved, and the control stability and accuracy of the coal mill set controller are optimized.
Description
Technical Field
The invention relates to the technical field of automatic control, in particular to an optimization method, device and equipment of a coal mill unit controller and a storage medium.
Background
The coal mill unit is an important component of a large-scale coal-fired boiler, and how to work can directly determine the combustion efficiency and safety inside the boiler. The coal mill unit mainly comprises a grinding bowl system and a primary air system, wherein the grinding bowl system is responsible for grinding entered coal blocks into high-precision coal powder, and the primary air system is required to generate strong air with proper temperature and speed to blow the coal powder into a boiler burner through an air outlet. The cooperation of the two systems to produce the proper wind-powder flow is the most important control objective.
At present, the control of the system is mainly completed by PID controllers, and two independent PID controllers are respectively responsible for tracking the temperature and the speed of wind powder to achieve a set value, and both PID controllers can control the cold air baffle plate and the hot air baffle plate to achieve the control targets. Because the same control point (the cold air baffle and the hot air baffle) is simultaneously operated by two controllers, the problem that the opening of the baffle oscillates due to the fact that the control directions are opposite is unavoidable. On the other hand, the influence of the baffle action on the temperature and the speed of wind powder is nonlinear and is also coupled, so that the problems of uncoordinated, unstable, large control deviation and the like of the PID controller of the conventional coal mill unit are caused.
Disclosure of Invention
The invention provides an optimization method, device, equipment and storage medium of a coal mill unit controller, which are used for solving the problems of uncoordinated, unstable, large control deviation and the like of the existing coal mill unit controller and optimizing the control stability and accuracy of the coal mill unit controller.
According to an aspect of the present invention, there is provided a method of optimizing a coal mill unit controller, comprising:
acquiring state information of a coal mill unit simulation system, and determining a control feature set according to the state information;
inputting the control feature set into a coal mill unit controller to obtain a group of control instructions generated by the coal mill unit controller;
inputting a plurality of groups of control instructions and corresponding control feature sets into the coal mill unit simulation system to obtain a state prediction track output by the coal mill unit simulation system;
and adjusting network parameters of the coal mill unit controller according to the reward value of the state prediction track.
Further, acquiring state information of a coal mill unit simulation system, and determining a control feature set according to the state information, wherein the method comprises the following steps:
acquiring current state information and historical state information of a coal mill unit simulation system;
and determining a control feature set according to the current state information and the historical state information.
Further, inputting a plurality of groups of control instructions and corresponding control feature sets into the coal mill unit simulation system to obtain a state prediction track output by the coal mill unit simulation system, wherein the method comprises the following steps:
inputting a group of control instructions and corresponding control feature sets into the coal mill unit simulation system to obtain a prediction state output by the coal mill unit simulation system;
and forming a state prediction track according to the control instructions at different moments and the prediction states determined by the corresponding control feature sets.
Furthermore, the coal mill unit simulation system takes exogenous variables and control variables as input variables, and takes endogenous inertial variables and endogenous non-inertial variables as output variables;
wherein the exogenous variables include: ambient air temperature, preheated air temperature and instantaneous coal quantity; the control variables include: cold baffle opening and hot baffle opening; the endogenous inertial variables include: pressure difference between upper and lower sides of the grinding bowl, outlet air powder temperature and outlet air powder speed; the endogenous non-inertial variables include: inlet air volume and mixed air temperature.
Further, the state prediction track includes: a wind powder temperature prediction track and a wind powder speed prediction track; and adjusting network parameters of the coal mill unit controller according to the reward value of the state prediction track, wherein the adjustment comprises the following steps:
determining a wind powder temperature rewarding value according to the wind powder temperature prediction track and a wind powder temperature control rewarding function;
determining a wind powder speed rewarding value according to the wind powder speed predicting track and a wind powder speed control rewarding function;
determining the sum of the wind powder temperature rewarding value and the wind powder speed rewarding value as the rewarding value of the state prediction track;
and adjusting network parameters of the coal mill unit controller according to the reward value.
According to another aspect of the present invention, there is provided a control method of a coal mill unit, including:
acquiring historical state information and current state information of a coal mill unit, and determining a control feature set according to the historical state information and the current state information;
inputting the control feature set into a coal mill unit controller determined by adopting an optimization method of the coal mill unit controller, and obtaining a target control instruction generated by the coal mill unit controller;
and controlling the coal mill unit based on the target control instruction.
According to another aspect of the present invention, there is provided an optimizing apparatus of a coal mill unit controller, comprising:
the state information acquisition module is used for acquiring state information of the coal mill unit simulation system and determining a control feature set according to the state information;
the command generation module is used for inputting the control feature set into the coal mill unit controller to obtain a group of control commands generated by the coal mill unit controller;
the state track prediction module is used for inputting a plurality of groups of control instructions and corresponding control feature sets into the coal mill unit simulation system to obtain a state prediction track output by the coal mill unit simulation system;
and the parameter adjustment module is used for adjusting the network parameters of the coal mill unit controller according to the reward value of the state prediction track.
According to another aspect of the present invention, there is provided a coal pulverizer set controller comprising:
the state information acquisition module is used for acquiring historical state information and current state information of the coal mill unit and determining a control feature set according to the historical state information and the current state information;
the command generation module is used for inputting the control characteristic set into the coal mill unit controller determined by the optimization method of the coal mill unit controller according to any one of claims 1-5, and obtaining a target control command generated by the coal mill unit controller;
and the control module is used for controlling the coal mill unit based on the target control instruction.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of optimizing a coal pulverizer set controller of any one of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to execute the optimization method of the coal pulverizer set controller of any one of the embodiments of the present invention.
According to the technical scheme, state information of a coal mill unit simulation system is obtained, and a control feature set is determined according to the state information; inputting the control feature set into a coal mill unit controller to obtain a group of control instructions generated by the coal mill unit controller; inputting a plurality of groups of control instructions into a coal mill unit simulation system to obtain a state prediction track output by the coal mill unit simulation system; the network parameters of the coal mill set controller are adjusted according to the reward value of the state prediction track, so that the optimization of the coal mill set controller is realized, the problems of uncoordinated, unstable, large control deviation and the like of the existing coal mill set controller are solved, and the control stability and accuracy of the coal mill set controller are optimized.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for optimizing a coal pulverizer set controller according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for controlling a coal pulverizer set according to a second embodiment of the present invention;
FIG. 3 is a schematic structural view of an optimizing apparatus for a coal pulverizer set controller according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a coal mill unit controller according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural view of an electronic device for implementing the optimization method of the coal mill unit controller according to the embodiment of the invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It is noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of the present invention and in the foregoing figures, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a method for optimizing a coal mill unit controller according to an embodiment of the present invention, where the method may be performed by an optimizing device of the coal mill unit controller, and the optimizing device of the coal mill unit controller may be implemented in hardware and/or software, and the optimizing device of the coal mill unit controller may be configured in an electronic device. As shown in fig. 1, the method includes:
s110, acquiring state information of a coal mill unit simulation system, and determining a control feature set according to the state information.
Wherein the coal mill unit simulation system describes a mathematical model between the coal mill unit control instructions and the status information. The status information may be understood as information for reflecting the status of the coal mill set, and may include: current state information and historical state information. Examples include: inlet air temperature, inlet wind speed, induced draft fan frequency, pressure difference between upper and lower sides of grinding bowl, instantaneous coal quantity, opening of cold baffle, opening of hot baffle, outlet air temperature, outlet wind speed and the like. The control feature set is a set formed by features for determining control instructions and is used for describing the environmental state of the coal mill unit, and based on the control feature set, the coal mill unit controller can better judge the current dynamic process of the coal mill unit.
Specifically, a coal mill unit simulation system is constructed, state information of the coal mill unit simulation system is obtained, and state representation design is carried out on the state information to determine a control feature set. Illustratively, the control feature set may include: instantaneous value, sequence average value and sequence difference value corresponding to each state information.
In the field of industrial control, simulation systems take on an extremely important role. The method has the advantages that the stable and reliable coal mill unit simulation system is built, and the method has a key effect on building a control model of a reliable and efficient coal mill unit controller and verifying the safety and effectiveness of the control model.
Considering that the process industry is a large hysteresis system, each control instruction can generate long-term influence on the target state, so that a simulation system suitable for the scene has a steady track deduction capability instead of a point deduction capability, thereby realizing accurate judgment on the influence generated by each control instruction. Classical supervised learning theory treats sample points in a dataset in isolation, considers them all independently co-distributed, and optimizes the objective to pursue the best approximation at each sample point:
wherein pi E (|s) is the distribution of possible system responses of the physical system of the actual coal mill train for a given state s; pi (|s) is the distribution of possible system responses of the coal mill train simulation system for a given state s, D KL (. Cndot. ) represents calculating the KL divergence between two distributions.Represented is a decision maker pi according to the physical system of the actual coal mill set E And controlling the obtained state distribution. />Representing the status distribution->Is a mathematical expectation of (a). The optimization objective is to find a strategy that minimizes the mathematical expectation of KL divergence between the two distributions.
This approximation to the sample points ignores the timing characteristics exhibited on the trajectory curves, and the resulting simulation environment lacks sequence stability. To overcome this disadvantage, the present invention may employ the generation of an anti-mimetic learning theory as a basis theory for simulation system construction. Under this theory, a complete learning algorithm is composed of a generator model and a discriminant model. Specifically, the generator model is responsible for generating a target track based on random seeds, and the discriminant model is responsible for effectively distinguishing virtually generated tracks from tracks that have been actually generated in history. The optimization objective of this algorithm is:
where D (s, a) is a arbiter that can make a determination of a state-response trajectory, identifying whether the trajectory is extracted from historical data. If so, a 1 will tend to be output, otherwise a 0 will tend to be output. ρ π ,Respectively representing the track sets generated by the generator and track sets in the history data. The first optimization objective is to adjust the parameters of the discriminant D to increase its discrimination of true versus generated trajectories, and the second optimization objective is to adjust the parameters of the generator pi to reduce the likelihood that the trajectory generated by the generator will be recognized by the discriminant. The discriminator strives to improve the recognition capability and the generator strives to improve the forgery capability, and the discriminator and the generator fight against each other to finally obtain a generator which can be spurious. This generator is a simulation model of the actual physical system that generates a state-response trajectory having the same structural characteristics as the trajectory derived from the actual physical system.
Under the guidance of the target, the track of the performance deduced by the constructed simulation model can keep the structural characteristics of the real track, and is more suitable for the process industry scene. In particular to a problem of building a simulation system of a coal mill unit, the invention uses the ambient air temperature, the preheated air temperature and the instantaneous coal quantity as exogenous variables of the coal mill unit, uses the opening of a cold baffle and the opening of a hot baffle as control variables, uses the inlet air quantity and the mixed air temperature as endogenous non-inertial variables, uses the up-down pressure difference of a grinding bowl, the outlet air powder temperature and the outlet air powder speed as endogenous inertial variables, and uses a generated countermeasure simulation learning algorithm to build the simulation system of the coal mill unit. The coal mill unit simulation system takes exogenous variables and control variables as inputs and takes endogenous inertial variables and endogenous non-inertial variables as outputs.
S120, inputting the control feature set into the coal mill set controller to obtain a set of control instructions generated by the coal mill set controller.
The coal mill unit controller is a controller constructed based on a neural network technology and is used for generating control instructions capable of controlling the coal mill unit.
Illustratively, a coal mill set controller is noted pi, which may be based on the control feature set s t Calculate a group of control instructions a t I.e.
a t ＝π(s t )。
S130, inputting a plurality of groups of control instructions and corresponding control feature sets into the coal mill unit simulation system to obtain a state prediction track output by the coal mill unit simulation system.
The state prediction track is a track composed of a plurality of predicted states obtained at different times, and the state prediction track is understood as a time series composed of the predicted states.
Specifically, a control instruction and a control feature set generated by the coal mill unit controller are input into the coal mill unit simulation system, a predicted state is obtained through forward pushing calculation of the coal mill unit simulation system, and steps S110-S130 are repeatedly executed to obtain a state prediction track formed by a plurality of predicted states corresponding to different moments.
Exemplary, the coal mill set simulation system is denoted as F to control the feature set s t And control instruction a t As input, the new round of control feature sets is output, namely:
s t+1 ＝F(s t ,a t )；
and forming a strip-shaped prediction track according to the control characteristic sets output by the simulation systems of the coal mill units at a plurality of moments.
And S140, adjusting network parameters of the coal mill unit controller according to the reward value of the state prediction track.
Specifically, a reward value corresponding to the state prediction track is calculated according to the reward function, and based on a near-end strategy optimal PPO algorithm, the back propagation of an error value between the reward value and a preset value is carried out, so that the network parameters of the coal mill unit controller are adjusted.
According to the technical scheme, the state information of the coal mill unit simulation system is obtained, and the control feature set is determined according to the state information; inputting the control feature set into a coal mill unit controller to obtain a group of control instructions generated by the coal mill unit controller; inputting a plurality of groups of control instructions into a coal mill unit simulation system to obtain a state prediction track output by the coal mill unit simulation system; the network parameters of the coal mill set controller are adjusted according to the reward value of the state prediction track, so that the optimization of the coal mill set controller is realized, the problems of uncoordinated, unstable, large control deviation and the like of the existing coal mill set controller are solved, and the control stability and accuracy of the coal mill set controller are optimized. The optimization method of the coal mill set provided by the invention mainly utilizes two components of the simulator and the controller, has the advantages of previewability, testability, analyzability, learning and the like, can be adaptively deployed on the coal mill sets of various coal-fired boilers, and has low development cost and high development speed.
Optionally, acquiring state information of the coal mill unit simulation system, determining a control feature set according to the state information, and including:
acquiring current state information and historical state information of a coal mill unit simulation system;
and determining a control feature set according to the current state information and the historical state information.
Specifically, to assist the coal mill unit controller in achieving stable and efficient control, features input into the coal mill unit controller need to include not only current state information of the current time of the coal mill unit simulation system, but also historical state information within a specific time period. And determining a control feature set according to the current state information and the historical state information.
Illustratively, status information for three control cycles of a controller coal pulverizer set simulation system is collected, a status average value, a status differential value, and a marker variable of a control target is determined according to the status information for the three control cycles.
Optionally, inputting a plurality of groups of control instructions and corresponding control feature sets into the coal mill unit simulation system to obtain a state prediction track output by the coal mill unit simulation system, including:
inputting a group of control instructions and corresponding control feature sets into the coal mill unit simulation system to obtain a prediction state output by the coal mill unit simulation system;
and forming a state prediction track according to the control instructions at different moments and the prediction states determined by the corresponding control feature sets.
Specifically, each generated control instruction and corresponding control feature set are used as input of the coal mill unit simulation system, and the prediction state of the coal mill unit simulation system can be obtained through calculation of the neural network parameters in the coal mill unit simulation system. And sequentially inputting a plurality of control instructions and corresponding control feature sets generated at different moments into a coal mill unit simulation system, so that a prediction state at the corresponding moment can be obtained. The predicted states at a plurality of times may constitute a state prediction trajectory having a time sequence.
Optionally, the state prediction track includes: a wind powder temperature prediction track and a wind powder speed prediction track; and adjusting network parameters of the coal mill unit controller according to the reward value of the state prediction track, wherein the adjustment comprises the following steps:
determining a wind powder temperature rewarding value according to the wind powder temperature prediction track and a wind powder temperature control rewarding function;
determining a wind powder speed rewarding value according to the wind powder speed predicting track and a wind powder speed control rewarding function;
determining the sum of the wind powder temperature rewarding value and the wind powder speed rewarding value as the rewarding value of the state prediction track;
and adjusting network parameters of the coal mill unit controller according to the reward value.
The main control parameters of the coal mill unit controller comprise: outlet air powder temperature and outlet air powder speed. Thus, the coal mill train controller's reward function may be comprised of two parts, a wind-powder temperature control reward function and a wind-powder speed control reward function.
For example, the goal of the air powder temperature control bonus function may be that the outlet air powder temperature is equal to the outlet air powder temperature set point, and the bonus value may be calculated by squaring the deviation between the outlet air powder temperature and the set point. The goal of the wind powder speed control reward function may be that the outlet wind powder speed is in the interval of 25-35 m/s, the reward value may be that the outlet wind powder speed is between 28 and 32 m/s, then the reward value is 6; the outlet air powder speed is between 26 and 28 meters/second or between 32 and 34 meters/second, and the rewarding value is 2; the outlet air speed is below 26 m/s or above 34 m/s, then the prize value is-2.
Exemplary, the wind powder temperature prize value may be expressed in terms of wind powder temperature control accuracy, denoted Score 1 The calculation method is as follows:
wherein s is 1,i The temperature of the wind powder at the moment i is represented. The wind speed rewarding value can be expressed by wind speed control accuracy and is marked as Score 2 The calculation method is as follows:
wherein s is 2,i The wind powder speed at the moment i is represented, II represents an indication function, and if the operation result of the subscript of the indication function is True, the indication function result is 1; if the operation result of the index of the indicating function is True, the indicating function result is 0.
The total Score was:
Score＝Score 1 +Score 2 。
example two
Fig. 2 is a flowchart of a control method of a coal mill unit according to a second embodiment of the present invention, where the present embodiment is applicable to a case of controlling a coal mill unit based on a coal mill unit controller, the method may be performed by the coal mill unit controller, and the coal mill unit controller may be implemented in a form of hardware and/or software. As shown in fig. 2, the method includes:
s210, acquiring historical state information and current state information of the coal mill unit, and determining a control feature set according to the historical state information and the current state information.
Specifically, in the process of controlling the coal mill unit by adopting the coal mill unit controller, current state information of the coal mill unit is collected in real time, and a control feature set is determined according to the current state information and historical state information collected at the past moment.
S220, inputting the control feature set into the coal mill set controller determined by the optimization method of the coal mill set controller, and obtaining a target control instruction generated by the coal mill set controller.
Specifically, the control feature set is input into the coal mill unit controller optimized by the optimization method of the coal mill unit control provided in the first embodiment, and the target control command is generated by the coal mill unit controller according to the control feature set.
S230, controlling the coal mill unit based on the target control instruction.
Specifically, the running state of the mill unit is controlled according to a target control instruction generated by the coal mill unit controller.
According to the technical scheme, the historical state information and the current state information of the coal mill unit are obtained, and the control feature set is determined according to the historical state information and the current state information; inputting the control feature set into a coal mill unit controller determined by adopting an optimization method of the coal mill unit controller, and obtaining a target control instruction generated by the coal mill unit controller; based on the target control instruction control the coal mill unit, the cold baffle and the hot baffle can be adjusted through the optimized coal mill unit controller, and the accurate tracking of the outlet air powder temperature setting and the outlet air powder speed setting is realized.
Example III
Fig. 3 is a schematic structural diagram of an optimizing apparatus for a coal mill unit controller according to a third embodiment of the present invention. As shown in fig. 3, the apparatus includes:
a state information obtaining module 310, configured to obtain state information of a coal mill unit simulation system, and determine a control feature set according to the state information;
the instruction generation module 320 is configured to input the control feature set into a coal mill unit controller, and obtain a set of control instructions generated by the coal mill unit controller;
the state track prediction module 330 is configured to input a plurality of groups of control instructions and corresponding control feature sets into the coal mill unit simulation system, so as to obtain a state prediction track output by the coal mill unit simulation system;
and the parameter adjustment module 340 is configured to adjust network parameters of the coal mill unit controller according to the reward value of the state prediction track.
Optionally, the status information obtaining module is specifically configured to:
acquiring current state information and historical state information of a coal mill unit simulation system;
and determining a control feature set according to the current state information and the historical state information.
Optionally, the state track prediction module is specifically configured to:
inputting a group of control instructions and corresponding control feature sets into the coal mill unit simulation system to obtain a prediction state output by the coal mill unit simulation system;
and forming a state prediction track according to the control instructions at different moments and the prediction states determined by the corresponding control feature sets.
Optionally, the coal mill unit simulation system uses exogenous variables and control variables as input variables, and uses endogenous inertial variables and endogenous non-inertial variables as output variables;
wherein the exogenous variables include: ambient air temperature, preheated air temperature and instantaneous coal quantity; the control variables include: cold baffle opening and hot baffle opening; the endogenous inertial variables include: pressure difference between upper and lower sides of the grinding bowl, outlet air powder temperature and outlet air powder speed; the endogenous non-inertial variables include: inlet air volume and mixed air temperature.
Optionally, the parameter adjustment module is specifically configured to:
determining a wind powder temperature rewarding value according to the wind powder temperature prediction track and a wind powder temperature control rewarding function;
determining a wind powder speed rewarding value according to the wind powder speed predicting track and a wind powder speed control rewarding function;
determining the sum of the wind powder temperature rewarding value and the wind powder speed rewarding value as the rewarding value of the state prediction track;
and adjusting network parameters of the coal mill unit controller according to the reward value.
The optimization device of the coal mill unit controller provided by the embodiment of the invention can execute the optimization method of the coal mill unit controller provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example IV
Fig. 4 is a schematic structural diagram of a coal mill unit controller according to a third embodiment of the present invention. As shown in fig. 4, the coal mill unit controller includes:
a state information acquisition module 410, configured to acquire historical state information and current state information of a coal mill unit, and determine a control feature set according to the historical state information and the current state information;
a command generating module 420, configured to input the control feature set into a coal mill unit controller determined by using the optimization method of the coal mill unit controller according to any one of claims 1 to 5, and obtain a target control command generated by the coal mill unit controller;
a control module 430 for controlling the coal mill unit based on the target control command.
The coal mill unit controller provided by the embodiment of the invention can execute the control method of the coal mill unit provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example five
Fig. 5 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the optimization method of the coal mill train controller.
In some embodiments, the optimization method of the coal mill train controller can be implemented as a computer program, which is tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the above-described optimization method of the coal mill unit controller may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the optimization method of the coal mill train controller in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage 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. Alternatively, the computer readable storage medium may be a machine readable signal medium. 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 portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (9)
1. An optimization method of a coal mill unit controller is characterized by comprising the following steps:
acquiring state information of a coal mill unit simulation system, and determining a control feature set according to the state information;
inputting the control feature set into a coal mill unit controller to obtain a group of control instructions generated by the coal mill unit controller;
inputting a plurality of groups of control instructions and corresponding control feature sets into the coal mill unit simulation system to obtain a state prediction track output by the coal mill unit simulation system;
adjusting network parameters of the coal mill unit controller according to the reward value of the state prediction track;
inputting a plurality of groups of control instructions and corresponding control feature sets into the coal mill unit simulation system to obtain a state prediction track output by the coal mill unit simulation system, wherein the method comprises the following steps of:
inputting a group of control instructions and corresponding control feature sets into the coal mill unit simulation system to obtain a prediction state output by the coal mill unit simulation system;
and forming a state prediction track according to the control instructions at different moments and the prediction states determined by the corresponding control feature sets.
2. The method of claim 1, wherein obtaining status information of a coal mill train simulation system, determining a set of control features based on the status information, comprises:
acquiring current state information and historical state information of a coal mill unit simulation system;
and determining a control feature set according to the current state information and the historical state information.
3. The method of claim 1, wherein the coal mill train simulation system uses exogenous variables and control variables as input variables and endogenous inertial variables and endogenous non-inertial variables as output variables;
wherein the exogenous variables include: ambient air temperature, preheated air temperature and instantaneous coal quantity; the control variables include: cold baffle opening and hot baffle opening; the endogenous inertial variables include: pressure difference between upper and lower sides of the grinding bowl, outlet air powder temperature and outlet air powder speed; the endogenous non-inertial variables include: inlet air volume and mixed air temperature.
4. The method of claim 1, wherein the state prediction trajectory comprises: a wind powder temperature prediction track and a wind powder speed prediction track; and adjusting network parameters of the coal mill unit controller according to the reward value of the state prediction track, wherein the adjustment comprises the following steps:
determining a wind powder temperature rewarding value according to the wind powder temperature prediction track and a wind powder temperature control rewarding function;
determining a wind powder speed rewarding value according to the wind powder speed predicting track and a wind powder speed control rewarding function;
determining the sum of the wind powder temperature rewarding value and the wind powder speed rewarding value as the rewarding value of the state prediction track;
and adjusting network parameters of the coal mill unit controller according to the reward value.
5. The control method of the coal mill unit is characterized by comprising the following steps of:
acquiring historical state information and current state information of a coal mill unit, and determining a control feature set according to the historical state information and the current state information;
inputting the control feature set into a coal mill unit controller determined by the optimization method of the coal mill unit controller according to any one of claims 1-4, and obtaining a target control instruction generated by the coal mill unit controller;
and controlling the coal mill unit based on the target control instruction.
6. An optimizing apparatus of a coal mill unit controller, comprising:
the state information acquisition module is used for acquiring state information of the coal mill unit simulation system and determining a control feature set according to the state information;
the command generation module is used for inputting the control feature set into the coal mill unit controller to obtain a group of control commands generated by the coal mill unit controller;
the state track prediction module is used for inputting a plurality of groups of control instructions and corresponding control feature sets into the coal mill unit simulation system to obtain a state prediction track output by the coal mill unit simulation system;
the parameter adjustment module is used for adjusting network parameters of the coal mill unit controller according to the reward value of the state prediction track;
the state track prediction module is specifically configured to:
inputting a group of control instructions and corresponding control feature sets into the coal mill unit simulation system to obtain a prediction state output by the coal mill unit simulation system;
and forming a state prediction track according to the control instructions at different moments and the prediction states determined by the corresponding control feature sets.
7. A coal pulverizer set controller, comprising:
the state information acquisition module is used for acquiring historical state information and current state information of the coal mill unit and determining a control feature set according to the historical state information and the current state information;
the command generation module is used for inputting the control characteristic set into the coal mill unit controller determined by the optimization method of the coal mill unit controller according to any one of claims 1-4, and obtaining a target control command generated by the coal mill unit controller;
and the control module is used for controlling the coal mill unit based on the target control instruction.
8. An electronic device, the electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of optimizing the coal pulverizer set controller of any one of claims 1-5.
9. A computer readable storage medium storing computer instructions for causing a processor to execute the method of optimizing the coal pulverizer set controller of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211685468.XA CN115903548B (en) | 2022-12-27 | 2022-12-27 | Optimization method, device and equipment for coal mill unit controller and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211685468.XA CN115903548B (en) | 2022-12-27 | 2022-12-27 | Optimization method, device and equipment for coal mill unit controller and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115903548A CN115903548A (en) | 2023-04-04 |
| CN115903548B true CN115903548B (en) | 2024-03-08 |
Family
ID=86489612
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211685468.XA Active CN115903548B (en) | 2022-12-27 | 2022-12-27 | Optimization method, device and equipment for coal mill unit controller and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115903548B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101770209A (en) * | 2010-03-09 | 2010-07-07 | 浙江大学 | Method for performing scattering predictive control on multi-time-scale complex huge system |
| CN110346160A (en) * | 2019-06-24 | 2019-10-18 | 浙江大学 | A kind of coal-grinding engine efficiency abnormality detection and diagnostic method based on SVR |
| CN110673478A (en) * | 2019-09-29 | 2020-01-10 | 京东城市(北京)数字科技有限公司 | Control method, device and system of coal mill and storage medium |
| CN111222284A (en) * | 2019-12-27 | 2020-06-02 | 中国大唐集团科学技术研究院有限公司西北电力试验研究院 | Overall soft measurement method for primary air volume at inlet of medium-speed coal mill unit |
| CN112130538A (en) * | 2020-09-22 | 2020-12-25 | 京东城市(北京)数字科技有限公司 | Method, device, equipment and medium for control optimization and model training of coal mill |
| CN114721345A (en) * | 2022-06-10 | 2022-07-08 | 南栖仙策(南京)科技有限公司 | Industrial control method, device and system based on reinforcement learning and electronic equipment |
| CN114924684A (en) * | 2022-04-24 | 2022-08-19 | 南栖仙策(南京)科技有限公司 | Environmental modeling method and device based on decision flow graph and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7850104B2 (en) * | 2007-03-21 | 2010-12-14 | Honeywell International Inc. | Inferential pulverized fuel flow sensing and manipulation within a coal mill |
-
2022
- 2022-12-27 CN CN202211685468.XA patent/CN115903548B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101770209A (en) * | 2010-03-09 | 2010-07-07 | 浙江大学 | Method for performing scattering predictive control on multi-time-scale complex huge system |
| CN110346160A (en) * | 2019-06-24 | 2019-10-18 | 浙江大学 | A kind of coal-grinding engine efficiency abnormality detection and diagnostic method based on SVR |
| CN110673478A (en) * | 2019-09-29 | 2020-01-10 | 京东城市(北京)数字科技有限公司 | Control method, device and system of coal mill and storage medium |
| CN111222284A (en) * | 2019-12-27 | 2020-06-02 | 中国大唐集团科学技术研究院有限公司西北电力试验研究院 | Overall soft measurement method for primary air volume at inlet of medium-speed coal mill unit |
| CN112130538A (en) * | 2020-09-22 | 2020-12-25 | 京东城市(北京)数字科技有限公司 | Method, device, equipment and medium for control optimization and model training of coal mill |
| CN114924684A (en) * | 2022-04-24 | 2022-08-19 | 南栖仙策(南京)科技有限公司 | Environmental modeling method and device based on decision flow graph and electronic equipment |
| CN114721345A (en) * | 2022-06-10 | 2022-07-08 | 南栖仙策(南京)科技有限公司 | Industrial control method, device and system based on reinforcement learning and electronic equipment |
Non-Patent Citations (5)
| Title |
|---|
| Optimization of Power Station Boiler Coal Mill Output Based on the Particle Swarm Algorithm;Yanjun Fang, Xiaojie Qin, Yuan Fang;Proceedings of the 2012 IEEE IEEM;1-5 * |
| 双进双出磨煤机优化控制系统;孙德利, 等;工业控制与应用;第34卷(第1期);22-25 * |
| 基于动态RBF网络的预测控制在 中速磨煤机优化控制的应用;张柯，等;化工自动化及仪表(第1期);58-61 * |
| 基于自适应神经网络模糊PID的磨煤机控制研究;郭佳跃，韦根原;热能动力工程;第37卷(第2期);148-154 * |
| 磨煤机料位自寻优控制系统设计;蒋恒，李波;重庆电力高等专科学校学报;第18卷(第2期);58-61 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115903548A (en) | 2023-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bajpai et al. | Fuzzy adaptive particle swarm optimization for bidding strategy in uniform price spot market | |
| CN108551167A (en) | A kind of electric power system transient stability method of discrimination based on XGBoost algorithms | |
| CN105864797B (en) | Real-time prediction system and method for boiler entering heat value of circulating fluidized bed household garbage incineration boiler | |
| WO2018200845A1 (en) | Integrating machine learning into control systems | |
| Perninge et al. | Importance sampling of injected powers for electric power system security analysis | |
| CN102840571B (en) | Firepower power station boiler based on Subspace Identification exports the forecasting procedure of superheated steam | |
| CN104539601B (en) | Dynamic network attack process analysis method for reliability and system | |
| CN102799151B (en) | Statistical-classification-based method for real-time balance adjustment of metallurgical gas system | |
| CN115795992A (en) | Park energy Internet online scheduling method based on virtual deduction of operation situation | |
| CN115903548B (en) | Optimization method, device and equipment for coal mill unit controller and storage medium | |
| CN114912697A (en) | Boiler slagging degree prediction method based on PSO algorithm and related device | |
| CN116562156B (en) | Training method, device, equipment and storage medium for control decision model | |
| Sun et al. | Scheduling model of power system based on forecasting error of wind power plant output | |
| CN115597872A (en) | Load shedding test method, device, equipment and medium for pumped storage unit | |
| CN115388586A (en) | Refrigeration control model, device, electronic equipment and storage medium | |
| CN112134275B (en) | Method and system for calculating reliability of power system including wind power plant | |
| CN109670636B (en) | Optimization method and device of energy scheduling model for universal energy station | |
| Chang | Application of Hopfield Neural Network to the optimal chilled water supply temperature calculation of air-conditioning systems for saving energy | |
| Li et al. | The research on electric load forecasting based on nonlinear gray bernoulli model optimized by cosine operator and particle swarm optimization | |
| Liu et al. | Active power dynamic interval control based on operation data mining for wind farms to improve regulation performance in AGC | |
| US20240183337A1 (en) | Method of controlling a wind farm using a reinforcement learning method | |
| Wang et al. | Cost Prediction Research for Commissioning Projects of Thermal Power Plants Based on a Hybrid Algorithm | |
| Chen et al. | Construction method of core backbone grid based on improved fireworks algorithm and risk theory | |
| Tang et al. | A novel self-adaptive nonlinear discrete grey model based on non-homogeneous index sequence and its application | |
| Qin et al. | Research on forecasting the cost of residential construction based on PCA and LS-SVM |
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 | ||
| CB02 | Change of applicant information |
Address after: 210000 building C4, Hongfeng Science Park, Nanjing Economic and Technological Development Zone, Nanjing City, Jiangsu Province Applicant after: NANQI XIANCE (NANJING) TECHNOLOGY Co.,Ltd. Address before: 210000 floor 17, building 32, headquarters base, Jiangning District, Nanjing, Jiangsu Province Applicant before: NANQI XIANCE (NANJING) TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |