CN112365065B - WFGD self-adaptive online optimization scheduling method - Google Patents
WFGD self-adaptive online optimization scheduling method Download PDFInfo
- Publication number
- CN112365065B CN112365065B CN202011279200.7A CN202011279200A CN112365065B CN 112365065 B CN112365065 B CN 112365065B CN 202011279200 A CN202011279200 A CN 202011279200A CN 112365065 B CN112365065 B CN 112365065B
- Authority
- CN
- China
- Prior art keywords
- data
- circulating pump
- slurry circulating
- neural network
- wfgd
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000005457 optimization Methods 0.000 title claims abstract description 22
- 239000002002 slurry Substances 0.000 claims abstract description 60
- 238000006477 desulfuration reaction Methods 0.000 claims abstract description 29
- 230000023556 desulfurization Effects 0.000 claims abstract description 29
- 238000013528 artificial neural network Methods 0.000 claims abstract description 23
- 238000012216 screening Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 21
- 241000282461 Canis lupus Species 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 7
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 4
- 241000282421 Canidae Species 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 6
- 238000004458 analytical method Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 239000003245 coal Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000003344 environmental pollutant Substances 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 231100000719 pollutant Toxicity 0.000 description 2
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000003546 flue gas Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Abstract
The invention relates to the technical field of desulfurization of coal-fired power plants, and particularly discloses a WFGD self-adaptive online optimization scheduling method, which comprises the following steps: firstly, collecting historical data of measuring points from a unit, wherein the data information comprises unit load, SO2 concentration at an inlet/outlet of a desulfurization system and current parameters of a slurry circulating pump; secondly, acquiring each time node when the slurry circulating pump is started/stopped according to the current parameter of the slurry circulating pump; thirdly, performing steady-state screening on the obtained data samples; fourthly, establishing a single WFGD online optimization scheduling model based on GWO-BP neural network to form a prediction model group; fifthly, guiding the power station to optimally schedule the slurry circulating pump; and sixthly, performing model self-adaptive updating. According to the method, based on historical operation data of the unit, data samples before and after the slurry circulating pump is started and stopped are extracted, and the advantage of big data is played.
Description
Technical Field
The disclosure relates to the technical field of desulfurization of coal-fired power plants, in particular to a WFGD self-adaptive online optimization scheduling method.
Background
WFGD is a desulfurization system of a coal-fired unit, SO 2 is one of the most main pollutants of a thermal power plant, 90% of SO 2 in the atmosphere is derived from coal, and the excessive emission of the SO 2 causes great pollution to the environment, SO that the emission control of SO 2 is also more and more paid attention to the government. In order to reduce pollutant emission and purify air, no less power generation enterprises have performed ultra-low emission modification to meet the environmental protection requirement. At present, the desulfurization system of the coal-fired unit is lack of operation and operation specifications of ultralow emission, SO that in the actual operation process, operators generally control the emission concentration of SO 2 in a safe area lower than the emission limit value to a certain extent in order to ensure standard emission, which can definitely bring improvement of desulfurization energy consumption, reduce desulfurization operation economy and greatly increase desulfurization cost of a power plant.
The optimized operation technology of the desulfurization system of the coal-fired power plant has attracted a great deal of attention from researchers. The optimized operation of the prior desulfurization system mainly comprises a mechanism analysis method based on process mechanism analysis, a process object mathematical model and the like, and a neural network and support vector machine data driving method. However, as an important component of a thermal power plant, the actual operation state of a flue gas desulfurization system is affected by various external conditions, including plant load, coal quality, boiler combustion mode, and the like, and is difficult to be represented by a general mechanism model. In addition, due to the continuous change of external conditions, the desulfurization system is difficult to be in a long-term stable operation state, so that the actual operation data of the system has large fluctuation, and a reliable optimization scheme is difficult to be given based on stable target working conditions.
Disclosure of Invention
The invention aims to solve the problems of unstable operation and large fluctuation of actual operation data of the existing desulfurization system.
In order to achieve the above purpose, the basic scheme of the invention provides a WFGD self-adaptive online optimization scheduling method, which comprises the following steps:
firstly, collecting historical data of measuring points from a unit, wherein the data information comprises unit load, the concentration of SO 2 at an inlet/outlet of a desulfurization system and current parameters of a slurry circulating pump;
step two, according to the current parameters of the slurry circulating pump, acquiring each time node when the slurry circulating pump is started/stopped, and acquiring historical operation data of each parameter of 1 hour before the slurry circulating pump is started/stopped and 1 hour after the slurry circulating pump is started/stopped;
thirdly, performing steady-state screening on the obtained data samples to obtain a slurry circulating pump start/stop data sample set, and dividing the data samples into corresponding sample libraries according to the operation condition of the slurry circulating pump;
Fourthly, respectively establishing independent WFGD online optimization scheduling models based on GWO-BP neural network by taking average load of a unit before and after start/stop, average concentration of SO 2 at an inlet and concentration of SO 2 at an average outlet before start/stop as input parameters of the models and concentration variation of SO 2 at an outlet after start/stop as output parameters of the models to form a prediction model group;
Fifthly, dividing real-time operation data of the unit by the number of operation of the slurry circulating pump, entering a corresponding model, calculating the change condition of the concentration of the SO 2 at the outlet after the start/stop of the pump, obtaining the concentration of the SO 2 at the outlet after the start/stop of the pump, and guiding a power station to optimally schedule the slurry circulating pump;
And sixthly, acquiring start/stop data of the slurry circulating pump from the real-time data, dividing the data according to the running condition of the slurry circulating pump, and storing the data in a corresponding model sample library to achieve the purpose of self-adaptive updating of the model.
Further, the first step specifically comprises: historical data of time spans required by all measuring points are collected from SIS data sources of the unit, and data including unit load, SO 2 concentration at inlet/outlet of a desulfurization system, slurry circulating pump current and the like are taken at intervals of 1 min. The data to be taken is arranged in chronological order, wherein the time span and the taking interval of the data are customizable.
Further, in the second step, a time at which the current of the single slurry circulation pump is changed or reduced from 0 to 0 is recorded, and the current is changed only once within 1 hour before and after the time, and historical operation data of relevant parameters are recorded for each hour before and after the time.
Further, the conditions for steady-state screening in the third step are: the average load of the unit is changed to 13-15MW and the average concentration of SO 2 at the inlet is changed to 30-50mg/m 3 before and after the slurry circulating pump is started and stopped.
Further, the construction of the GWO-BP neural network model in the fourth step comprises the following specific steps:
Step one, determining input and output parameters of a BP neural network, and carrying out normalization processing on input and output data;
Step two, carrying out population initialization by GWO algorithm, randomly initializing the position X j (j=1, 2, …, n) of the gray wolf population, wherein each gray wolf individual comprises a group of weights alpha i, wherein alpha 1+α2+…+αi =i, i is the number of corresponding input parameters, and initializing parameters a, a and C;
Constructing a fitness function, multiplying each normalized input parameter by a corresponding weight alpha i to serve as a new input parameter, training a BP neural network, and predicting output y i and expected output by using a trained model Constructing a fitness function by R 2 of (2);
In the above Representation ofSum of squares with y i;
Step four, performing BP neural network training in the step three on each of the wolf individuals in the population, calculating the fitness value of each of the wolf individuals through a fitness function, and selecting 3 wolves with the highest fitness value from the fitness values as a current optimal solution X α, a suboptimal solution X β and a third optimal solution X δ;
Step five, updating the positions of other omega wolf individuals, updating parameters a, A and C, reconstructing a new BP neural network according to the step three, training the network, recalculating the fitness value of each gray wolf individual, and updating X α、Xβ and X δ;
Step six, judging whether GWO algorithm reaches the initial iteration III, if so, stopping iteration, and outputting an optimal result X α; otherwise, repeatedly executing the third step to the fifth step until the maximum iteration times are reached;
And step seven, training the BP neural network again by using the weight alpha i of the optimal input parameter obtained by GWO algorithm, and obtaining the final BP neural network model with highest training precision.
Further, the sixth step specifically includes: acquiring start-stop data of the liquid circulation pump from the real-time data of the second step and the third step, dividing the data according to the operation condition of the slurry circulation pump, storing the data in a corresponding model sample library, and carrying out training update on the GWO-BP model again according to the construction of the GWO-BP neural network model in the fourth step.
The principle and effect of the invention are as follows:
1. Compared with the prior art, on the premise of ensuring that the outlet emission concentration of the desulfurization system reaches the standard, the method provided by the invention divides the operation working conditions of the desulfurization system by taking the operation condition of the slurry circulating pump as a condition, and respectively establishes independent WFGD on-line optimization scheduling models based on GWO-BP neural networks to form a model group, thereby solving the problems of unstable operation and large fluctuation of actual operation data of the existing desulfurization system.
2. The influence of the start/stop of a single slurry circulating pump on the concentration change of an outlet SO 2 of the desulfurization system is predicted through the established model group, SO that the online dispatching of the slurry circulating pump is realized, the purpose of reducing the running cost of the desulfurization system is achieved, meanwhile, the start/stop data of the slurry circulating pump are continuously obtained from real-time data of a unit, and the online self-adaptive updating of the model is realized.
3. According to the method, based on historical operation data of the unit, data samples before and after the slurry circulating pump is started and stopped are extracted, and the advantage of big data is played.
4. The GWO-BP modeling method is provided, an artificial neural network is combined with an optimization algorithm, and meanwhile, a modeling method of multi-model fusion is adopted aiming at the problem of multiple target working conditions, so that the prediction accuracy of a model is improved.
5. The machine set real-time operation data is utilized to realize the self-adaptive update of the model, and the method is more suitable for practical engineering application.
6. The method can better predict the variation of the concentration of SO 2 at the outlet of the desulfurization system after the slurry circulating pump is started and stopped, and provides a guiding basis for the online optimization scheduling of the slurry circulating pump. Meanwhile, the self-adaptive updating of the model can be realized by utilizing the start-stop samples of the slurry circulating pump in the real-time data. Meets the engineering requirement, and fully plays the advantage of big data of the unit. The method aims to optimize the operation cost of the desulfurization system and improve the economic benefit of the power plant.
Drawings
FIG. 1 is a flow chart of a WFGD adaptive online optimization scheduling method in accordance with an embodiment of the present invention.
Detailed Description
The following is a further detailed description of the embodiments:
examples:
A WFGD self-adaptive online optimization scheduling method comprises the following steps:
data after long blowing or major repair in the SIS system is collected, and the collection interval is 15min (according to the situation). The frame of the invention mainly comprises core modules of data acquisition, data preprocessing, data processing, model construction, monitoring analysis, pollution positioning and the like, and a detailed flow chart is shown in figure 1:
First, collecting historical data of measuring points. Historical data of time spans required by all measuring points are collected from SIS data sources of the unit, and data including loads, SO 2 concentration at inlets of a desulfurization system and the like are taken at intervals of 1 min. The data to be taken is arranged in chronological order, wherein the time span and the taking interval of the data are customizable.
And secondly, acquiring each time node when the slurry circulating pump is started/stopped according to the current parameter of the slurry circulating pump, recording the time when the current of a single slurry circulating pump is changed or reduced to 0 from 0, changing the current within 1 hour before and after the time only once, and recording the historical operation data of the relevant parameters within each hour before and after the time.
Thirdly, steady-state screening is carried out on the obtained data samples, wherein the conditions of the steady-state screening are as follows: and the average load change of the unit before and after the start/stop of the slurry circulating pump is not more than 15MW, and the average concentration change of SO 2 at the inlet is not more than 50mg/m 3, SO as to obtain a slurry circulating pump start/stop data sample set. Dividing the data samples into corresponding sample libraries according to the operation condition of the slurry circulating pump.
And fourthly, taking the average load of the unit before and after the start/stop of the slurry circulating pump, the average concentration of SO 2 at the inlet and the concentration of SO 2 at the average outlet before the start/stop of the slurry circulating pump as input parameters of a model, taking the concentration variation of SO 2 at the outlet after the start/stop of the slurry circulating pump as output parameters of the model, and carrying out normalization processing on input and output data. Multiplying each normalized input parameter by a corresponding weight alpha i to serve as a new input parameter, training the BP neural network, and predicting output y k and expected output by using a trained modelIs used to construct the fitness function. And searching the weight alpha i with the highest training precision of the BP algorithm by utilizing the GWO algorithm, and retraining the BP model to obtain a final BP neural network model with the highest training precision. Establishing independent WFGD online optimization scheduling models based on GWO-BP neural networks by the method respectively to form a prediction model group;
the construction of GWO-BP neural network model comprises the following specific steps:
Step one, determining input and output parameters of a BP neural network, and carrying out normalization processing on input and output data;
Step two, carrying out population initialization by GWO algorithm, randomly initializing a gray wolf population position X j (j=1, 2, …, n), wherein n is the number of samples, each gray wolf individual comprises a group of weights alpha i, wherein alpha 1+α2+…+αi =i, i is the number of corresponding input parameters, and initializing parameters a, A and C;
Constructing a fitness function, multiplying each normalized input parameter by a corresponding weight alpha i to serve as a new input parameter, training a BP neural network, and predicting output y i and expected output by using a trained model Constructing a fitness function by R 2 of (2);
In the above Representation ofSum of squares with y i;
Step four, performing BP neural network training in the step three on each of the wolf individuals in the population, calculating the fitness value of each of the wolf individuals through a fitness function, and selecting 3 wolves with the highest fitness value from the fitness values as a current optimal solution X α, a suboptimal solution X β and a third optimal solution X δ;
Step five, updating the positions of other omega wolf individuals, updating parameters a, A and C, reconstructing a new BP neural network according to the step three, training the network, recalculating the fitness value of each gray wolf individual, and updating X α、Xβ and X δ;
Step six, judging whether GWO algorithm reaches the initial iteration III, if so, stopping iteration, and outputting an optimal result X α; otherwise, repeatedly executing the third step to the fifth step until the maximum iteration times are reached;
And step seven, training the BP neural network again by using the weight alpha i of the optimal input parameter obtained by GWO algorithm, and obtaining the final BP neural network model with highest training precision.
Fifthly, dividing real-time operation data of the unit by the number of operation of the slurry circulating pump, entering a corresponding model, and calculating the change condition of the concentration of the outlet SO 2 after starting and stopping the pump to obtain the concentration of the outlet SO 2 after starting and stopping the pump. If the concentration of SO 2 at the outlet of the desulfurization system obtained through model calculation after the slurry circulating pump is started/stopped meets the national emission standard, the desulfurization system of the power station can be guided to run in a pump-reducing mode.
And sixthly, acquiring start-stop data of the liquid circulation pump from the real-time data of the second step and the third step, dividing the data according to the running condition of the slurry circulation pump, storing the data into a corresponding model sample library, and training and updating the GWO-BP model again according to the construction of the GWO-BP neural network model in the fourth step.
The method can better predict the variation of the concentration of SO 2 at the outlet of the desulfurization system after the slurry circulating pump is started and stopped, and provides a guiding basis for the online optimization scheduling of the slurry circulating pump. Meanwhile, the self-adaptive updating of the model can be realized by utilizing the start-stop samples of the slurry circulating pump in the real-time data. Meets the engineering requirement, and fully plays the advantage of big data of the unit. The method aims to optimize the operation cost of the desulfurization system and improve the economic benefit of the power plant.
The foregoing is merely exemplary embodiments of the present application, and specific structures and features that are well known in the art are not described in detail herein. It should be noted that modifications and improvements can be made by those skilled in the art without departing from the structure of the present application, and these should also be considered as the scope of the present application, which does not affect the effect of the implementation of the present application and the utility of the patent. The protection scope of the present application is subject to the content of the claims, and the description of the specific embodiments and the like in the specification can be used for explaining the content of the claims.
Claims (6)
1. The WFGD self-adaptive online optimization scheduling method is characterized by comprising the following steps:
firstly, collecting historical data of measuring points from a unit, wherein the data information comprises unit load, the concentration of SO 2 at an inlet/outlet of a desulfurization system and current parameters of a slurry circulating pump;
step two, according to the current parameters of the slurry circulating pump, acquiring each time node when the slurry circulating pump is started/stopped, and acquiring historical operation data of each parameter of 1 hour before the slurry circulating pump is started/stopped and 1 hour after the slurry circulating pump is started/stopped;
thirdly, performing steady-state screening on the obtained data samples to obtain a slurry circulating pump start/stop data sample set, and dividing the data samples into corresponding sample libraries according to the operation condition of the slurry circulating pump;
Fourthly, respectively establishing independent WFGD online optimization scheduling models based on GWO-BP neural network by taking average load of a unit before and after start/stop, average concentration of SO 2 at an inlet and concentration of SO 2 at an average outlet before start/stop as input parameters of the models and concentration variation of SO 2 at an outlet after start/stop as output parameters of the models to form a prediction model group;
Fifthly, dividing real-time operation data of the unit by the number of operation of the slurry circulating pump, entering a corresponding model, calculating the change condition of the concentration of the SO 2 at the outlet after the start/stop of the pump, obtaining the concentration of the SO 2 at the outlet after the start/stop of the pump, and guiding a power station to optimally schedule the slurry circulating pump;
And sixthly, acquiring start/stop data of the slurry circulating pump from the real-time data, dividing the data according to the running condition of the slurry circulating pump, and storing the data in a corresponding model sample library to achieve the purpose of self-adaptive updating of the model.
2. The WFGD adaptive online optimization scheduling method according to claim 1, wherein: the first step specifically comprises the following steps: historical data of time spans required by all measuring points are collected from SIS data sources of the unit, the time spans and the collecting intervals of the data can be customized by adopting the parameters including unit load, SO 2 concentration at the inlet/outlet of a desulfurization system and current parameters of a slurry circulating pump at intervals of 1min and arranging the adopted data in time sequence.
3. The WFGD adaptive online optimization scheduling method according to claim 1 or 2, wherein: in the second step, a time point when the current of a single slurry circulating pump is changed or reduced from 0 to 0 is recorded, and the current is changed only once within 1 hour before and after the time point, and historical operation data of relevant parameters in each hour before and after the time point are recorded.
4. The WFGD adaptive online optimization scheduling method according to claim 3, wherein: the conditions for steady-state screening in the third step are as follows: the average load of the unit is changed to 13-15MW and the average concentration of SO 2 at the inlet is changed to 30-50mg/m 3 before and after the slurry circulating pump is started and stopped.
5. The WFGD adaptive online optimization scheduling method according to claim 4, wherein: the construction of the GWO-BP neural network model in the fourth step comprises the following specific steps:
Step one, determining input and output parameters of a BP neural network, and carrying out normalization processing on input and output data;
Step two, carrying out population initialization by GWO algorithm, randomly initializing the position X j of the gray wolf population (j=1, 2, …, n, wherein n is the number of samples), wherein each gray wolf individual comprises a group of weights alpha i, wherein alpha 1+α2+…+αi =i, i is the number of corresponding input parameters, and initializing the parameters a, A and C;
Constructing a fitness function, multiplying each normalized input parameter by a corresponding weight alpha i to serve as a new input parameter, training a BP neural network, and predicting output y i and expected output by using a trained model Constructing a fitness function by R 2 of (2);
In the above Representation ofSum of squares with y i;
Step four, performing the BP neural network training of the step three on each of the wolf individuals in the population, calculating the fitness value of each of the wolf individuals through a fitness function, and selecting 3 wolves with the highest fitness value from the fitness values as a current optimal solution X α, a suboptimal solution X β and a third optimal solution X δ;
Updating the positions of other omega wolf individuals, updating parameters a, A and C, reconstructing a new BP neural network according to the third step, training the network, recalculating the fitness value of each gray wolf individual, and updating X α、Xβ and X δ;
Step six, judging whether GWO algorithm reaches the initial iteration III, if so, stopping iteration, and outputting an optimal result X α; otherwise, repeatedly executing the third step to the fifth step until the maximum iteration times are reached;
And step seven, training the BP neural network again by using the weight alpha i of the optimal input parameter obtained by GWO algorithm, and obtaining the final BP neural network model with highest training precision.
6. The WFGD adaptive online optimization scheduling method according to claim 5, wherein: the sixth step is specifically: and obtaining the start and stop data of the slurry circulating pump from the historical operation data of the second step and the start and stop data sample set of the slurry circulating pump of the third step, dividing the data according to the operation condition of the slurry circulating pump, storing the data into a corresponding model sample library, and training and updating the GWO-BP model again according to the construction of the GWO-BP neural network model in the fourth step.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011279200.7A CN112365065B (en) | 2020-11-16 | WFGD self-adaptive online optimization scheduling method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011279200.7A CN112365065B (en) | 2020-11-16 | WFGD self-adaptive online optimization scheduling method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112365065A CN112365065A (en) | 2021-02-12 |
| CN112365065B true CN112365065B (en) | 2024-07-02 |
Family
ID=
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948869A (en) * | 2019-04-22 | 2019-06-28 | 东南大学 | Desulphurization system SO based on orderly cluster discretization2Exit concentration prediction technique |
| CN109978048A (en) * | 2019-03-22 | 2019-07-05 | 大唐环境产业集团股份有限公司 | A kind of Desulfurization tower slurry circulating pump malfunction analysis and problem shpoting method |
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109978048A (en) * | 2019-03-22 | 2019-07-05 | 大唐环境产业集团股份有限公司 | A kind of Desulfurization tower slurry circulating pump malfunction analysis and problem shpoting method |
| CN109948869A (en) * | 2019-04-22 | 2019-06-28 | 东南大学 | Desulphurization system SO based on orderly cluster discretization2Exit concentration prediction technique |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110263395A (en) | The power plant's denitration running optimizatin method and system analyzed based on numerical simulation and data | |
| CN112580250A (en) | Thermal power generating unit denitration system based on deep learning and optimization control method | |
| CN111804146A (en) | Intelligent ammonia injection control method and intelligent ammonia injection control device | |
| CN112396220B (en) | Optimized scheduling method for wind power-containing and demand side resources based on scene reduction | |
| CN114191953A (en) | Flue gas desulfurization and denitrification control method based on convolutional neural network and XGboost | |
| CN102073785A (en) | Daily gas load combination prediction method based on generalized dynamic fuzzy neural network | |
| CN114225662B (en) | Hysteresis model-based flue gas desulfurization and denitrification optimal control method | |
| CN104715142B (en) | A kind of station boiler NOxDischarge dynamic soft-measuring method | |
| CN112465239B (en) | Desulfurization system operation optimization method based on improved PSO-FCM algorithm | |
| CN110188383A (en) | A kind of power station SCR denitration modeling method based on selective ensemble model | |
| CN113094988A (en) | Data-driven slurry circulating pump operation optimization method and system | |
| CN109242136A (en) | A kind of micro-capacitance sensor wind power Chaos-Genetic-BP neural network prediction technique | |
| CN112132379B (en) | Economic-considered new energy cross-region consumption evaluation method and storage medium | |
| CN112364562A (en) | Cooperative control method and system for flue gas environmental protection island | |
| CN113440990A (en) | EMD-LSTM based outlet SO2Concentration prediction method | |
| CN114119273A (en) | Park comprehensive energy system non-invasive load decomposition method and system | |
| CN111815039A (en) | Weekly scale wind power probability prediction method and system based on weather classification | |
| Hao et al. | Prediction of nitrogen oxide emission concentration in cement production process: a method of deep belief network with clustering and time series | |
| CN112365065B (en) | WFGD self-adaptive online optimization scheduling method | |
| CN114239292A (en) | Comprehensive evaluation method and system for low-carbon economic operation-oriented multifunctional demand park | |
| CN117634678A (en) | Low-carbon park carbon emission prediction method based on actual operation scene | |
| CN109766666A (en) | Boiler smoke based on low nitrogen burning and SNCR-SCR Collaborative Control discharges NOxConcentration prediction method | |
| CN113947013A (en) | Boiler short-term NO based on hybrid deep neural network modelingxEmission prediction method | |
| CN113595798A (en) | Network flow prediction method and system for improving lightning connection process optimization algorithm | |
| CN113095534A (en) | Wind power prediction method combining ARIMA and improved Elman neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |