CN113012767A - Desulfurization system slurry pH value online prediction method and device based on time sequence - Google Patents
Desulfurization system slurry pH value online prediction method and device based on time sequence Download PDFInfo
- Publication number
- CN113012767A CN113012767A CN202110204799.6A CN202110204799A CN113012767A CN 113012767 A CN113012767 A CN 113012767A CN 202110204799 A CN202110204799 A CN 202110204799A CN 113012767 A CN113012767 A CN 113012767A
- Authority
- CN
- China
- Prior art keywords
- data
- slurry
- value
- desulfurization system
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000002002 slurry Substances 0.000 title claims abstract description 76
- 238000006477 desulfuration reaction Methods 0.000 title claims abstract description 62
- 230000023556 desulfurization Effects 0.000 title claims abstract description 62
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000005070 sampling Methods 0.000 claims abstract description 28
- 238000004140 cleaning Methods 0.000 claims abstract description 16
- 238000003062 neural network model Methods 0.000 claims abstract description 11
- 230000003213 activating effect Effects 0.000 claims abstract description 7
- 102100033620 Calponin-1 Human genes 0.000 claims description 13
- 102100033591 Calponin-2 Human genes 0.000 claims description 13
- 101000945318 Homo sapiens Calponin-1 Proteins 0.000 claims description 13
- 101000945403 Homo sapiens Calponin-2 Proteins 0.000 claims description 13
- 238000013527 convolutional neural network Methods 0.000 claims description 11
- 230000015654 memory Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000013215 result calculation Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 2
- 239000007788 liquid Substances 0.000 claims 2
- 230000007787 long-term memory Effects 0.000 claims 2
- 230000006403 short-term memory Effects 0.000 claims 2
- 230000008569 process Effects 0.000 description 12
- 239000000243 solution Substances 0.000 description 7
- 238000012360 testing method Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000010521 absorption reaction Methods 0.000 description 4
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 2
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 description 2
- 239000010440 gypsum Substances 0.000 description 2
- 229910052602 gypsum Inorganic materials 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 1
- 235000019738 Limestone Nutrition 0.000 description 1
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 1
- 239000007864 aqueous solution Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000006028 limestone Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000377 silicon dioxide Substances 0.000 description 1
- 235000012239 silicon dioxide Nutrition 0.000 description 1
- 239000008247 solid mixture Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/90—Programming languages; Computing architectures; Database systems; Data warehousing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Fuzzy Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Treating Waste Gases (AREA)
Abstract
The invention discloses a desulfurization system slurry pH value online prediction method and device based on a time sequence, wherein the method comprises the following steps: s1, acquiring historical data of the pH value of slurry of a desulfurization system in a preset time period from a database, and sampling the historical data to obtain an original sample D; s2, carrying out data cleaning on the original sample D and carrying out data slicing to obtain classified data sets D1, D2 and D3; s3, sequentially inputting the data sets D1 and D2 into two mutually connected neural network models, splicing output results and inputting the output results as input of a full connection layer Dense1 to obtain a result A1; establishing an Autoregressive (AR) model based on the data set D3 to obtain a result A2; and S4, summing the A1 and the A2, and activating through a Sigmoid function to obtain a final pH value prediction result of the slurry of the desulfurization system. The method is low in implementation cost and high in prediction precision of disordered and frequently fluctuated data.
Description
Technical Field
The invention relates to the technical field of power station desulfurization, in particular to a desulfurization system slurry pH value online prediction method and device based on a time sequence.
Background
The pH value of the slurry of the desulfurization absorption tower is an important monitoring index for the operation of a desulfurization system. If the pH value of the slurry is too low, the sulfur dioxide absorption effect is poor, and the desulfurization efficiency is low; if the pH value is too high, the utilization rate of limestone and the purity of gypsum are reduced, which is not beneficial to the desulfurization reaction. The pH of the slurry is critical data for guiding operation adjustment, and in the actual production process, the data are often deviated and distorted.
The pH value of the slurry of the desulfurization absorption tower is generally tested by using an electrode method, the slurry of the absorption tower is a liquid-solid mixture which is different from an aqueous solution in a uniform state, and therefore the pH value test needs to be carried out in a slurry flowing state; the pH meter is directly arranged on a slurry flow pipeline in the traditional slurry pH test, and due to the fact that the slurry contains a large amount of gypsum crystals and silicon dioxide impurities, the electrode of the pH meter is seriously abraded due to overhigh slurry flow rate, the service life of the pH meter is greatly reduced, and meanwhile, the test precision is interfered.
Disclosure of Invention
The invention aims to provide a time-series-based online slurry pH value prediction method and a time-series-based online slurry pH value prediction device for a desulfurization system, and aims to realize the inspection and reconstruction of online slurry pH value measurement point data.
The invention provides a desulfurization system slurry pH value online prediction method based on a time sequence, which comprises the following steps:
s1, acquiring historical data of the pH value of slurry of a desulfurization system in a preset time period from a database, and sampling the historical data to obtain an original sample D;
s2, carrying out data cleaning on the original sample D and carrying out data slicing to obtain classified data sets D1, D2 and D3;
s3, sequentially inputting the data sets D1 and D2 into two mutually connected neural network models, splicing output results and inputting the output results as input of a full connection layer Dense1 to obtain a result A1; establishing an Autoregressive (AR) model based on the data set D3 to obtain a result A2;
s4, summing A1 and A2, and activating through a Sigmoid function to obtain a final pH value prediction result of the slurry of the desulfurization system
The invention provides a desulfurization system slurry pH value online prediction device based on a time sequence, which is characterized by comprising the following components:
a data acquisition module: the system comprises a database, a data processing module and a data processing module, wherein the data processing module is used for acquiring historical data of the pH value of the slurry of the desulfurization system in a preset time period from the database, and sampling the historical data to obtain an original sample D;
a data preprocessing module: performing data cleaning and data slicing on the original sample D to obtain classified data sets D1, D2 and D3;
a model prediction module: sequentially inputting data sets D1 and D2 into two layers of neural network models which are connected with each other, splicing output results and inputting the output results as the input of a full-connection layer Dense1 to obtain a result A1; establishing an Autoregressive (AR) model based on the data set D3 to obtain a result A2;
a result calculation module: and summing A1 and A2, and activating by a Sigmoid function to obtain a final pH value prediction result of the desulfurization system slurry.
The embodiment of the invention also provides online prediction equipment for the pH value of the slurry of the desulfurization system based on the time sequence, which comprises: the device comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the computer program is used for realizing the steps of the desulfurization system slurry pH value online prediction method based on time series when being executed by the processor.
The embodiment of the invention also provides a computer readable storage medium, wherein an implementation program for information transmission is stored on the computer readable storage medium, and the implementation program realizes the steps of the method when being executed by a processor.
The embodiment of the invention is adopted to carry out online prediction of the pH value of the slurry of the desulfurization system, complex hardware equipment is not needed, and the realization cost is low; moreover, the online prediction method for the pH value of the slurry of the desulfurization system, which is disclosed by the invention, is integrated with multiple algorithms, has high prediction precision and higher adaptability to disordered and frequently fluctuating data.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of the method for online prediction of pH value of slurry in desulfurization system based on time series in accordance with the embodiment of the present invention;
FIG. 2 is a schematic diagram of the online prediction process of the pH value of the slurry of the desulfurization system based on time series according to the embodiment of the invention;
FIG. 3 is a graph illustrating a pH portion of raw data for a slurry in a desulfurization system in accordance with an embodiment of the present invention;
FIG. 4 is a schematic diagram showing the comparison between the predicted pH value of the slurry in the desulfurization system and the actual pH value measured by the slurry pH measuring point according to the embodiment of the present invention;
FIG. 5 is a schematic diagram of an integrated power consumption increase prediction apparatus with high-frequency influence factors integrated according to a first embodiment of the present invention;
fig. 6 is a schematic diagram of an integrated power consumption increase prediction device incorporating high-frequency influencing factors according to a first embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", and the like, indicate orientations and positional relationships based on those shown in the drawings, and are used only for convenience of description and simplicity of description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be considered as limiting the present invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise. Furthermore, the terms "mounted," "connected," and "connected" are to be construed broadly and may, for example, be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Method embodiment
According to an embodiment of the present invention, a time-series-based online prediction method for pH value of desulfurization system slurry is provided, fig. 1 is a flowchart of the time-series-based online prediction method for pH value of desulfurization system slurry according to the embodiment of the present invention, and as shown in fig. 1, the time-series-based online prediction method for pH value of desulfurization system slurry according to the embodiment of the present invention specifically includes:
s1, acquiring historical data of the pH value of slurry of a desulfurization system in a preset time period from a database, and sampling the historical data to obtain an original sample D;
specifically, historical data of the pH value of the slurry in the desulfurization system in the previous week may be obtained from the database, the historical data is counted at intervals of 1min, and the obtained data is used as the original sample D.
S2, carrying out data cleaning on the original sample D and carrying out data slicing to obtain classified data sets D1, D2 and D3;
specifically, the data cleaning process is to filter outliers in the original sample, note the cleaned data as CD, and slice the data CD to obtain classified data sets D1, D2, and D3, and the specific process of slicing the data is as follows:
d1 ═ CDi (T-T-1 ≦ i ≦ T-1) for the time step T and the slurry pH P (T) to be predicted;
setting a skip step skip for D2, wherein D2 is { CDi } (i is T-1-m skip, and 0 is not more than m and T);
setting a sampling step length T1< T, D3 ═ CDi (T-T1-1 ≦ i ≦ T-1) for D3;
wherein m represents the number of sampling periods and t represents the sampling time;
s3, sequentially inputting the data sets D1 and D2 into two mutually connected neural network models, splicing output results and inputting the output results as input of a full connection layer Dense1 to obtain a result A1; establishing an Autoregressive (AR) model based on the data set D3 to obtain a result A2;
in step S3, the specific process of obtaining result a1 is:
inputting the data set D1 into a convolutional neural network CNN1, and outputting a result C1; inputting the data D2 into a convolutional neural network CNN2, and outputting a result C2; inputting C1 and C2 into long-short term memory sequences LSTM1 and LSTM2 respectively, and outputting results which are L1 and L2 respectively; splicing the output results L1 and L2 to be used as the input of a full connection layer Dense1, and obtaining an output result A1;
the CNN1 and the CNN2 adopt the same structural parameters, namely, the CNN1 and the CNN2 have the same filter number, convolution kernel number and moving step length; the LSTM1 and the LSTM2 adopt the same number of hidden layers; the splicing is to perform matrix splicing on L1 and L2, and non-corresponding elements are added;
in step S3, the building of the autoregressive model AR is implemented by using a full connection layer;
s4, summing A1 and A2, and activating through a Sigmoid function to obtain a final pH value prediction result of the slurry of the desulfurization system;
specifically, the method for summing a1 and a2 is as follows: the corresponding elements of a1 and a2 are added.
Taking a certain 660MW coal-fired power generating unit as an example, the field DCS sampling data is stored in a database of a plant-level monitoring information system (SIS), historical data of the pH value of the slurry of the desulfurization system is obtained according to the flow shown in FIG. 1, and a slurry pH value prediction model is established:
taking historical data between 3 days 00:00 in 1 month and 10 days 00:00 in 1 month in 2020, taking the data at an interval of 1min, the obtained slurry pH value sequence is shown in FIG. 3. And preprocessing the data, cleaning coarse error values, dividing the data into data sets according to a ratio of 7:1, wherein the former part is used as a training set of a model, and the latter half part is used as a test set, so that the pH value of the slurry on the next day can be predicted by using the data of the previous week. Further, the training set and the test set are respectively subjected to data slicing to form three data sets D1, D2 and D3, and the data slicing process is as follows: for the time step T and the pH value p (T) to be predicted, D1 ═ CDi (T-1 ≦ i ≦ T-1); setting a skip step skip for D2, wherein D2 is { CDi } (i is T-1-m skip, and 0 is not more than m and T); the sampling step T1< T, D3 { CDi } (T-T1-1 ≦ i ≦ T-1) is set for D3.
The training data was used to train the constructed predictive model, the parameters of which are shown in table 1:
TABLE 1
And (3) predicting the training error of the model in real time in the training process of the model, and stopping training when the error is not reduced any more. The parameters of the prediction model, i.e. the time step T and the skip step skip used for constructing the data and the sampling step T1 are arranged by combining a plurality of times to obtain relatively better values.
FIG. 4 shows the comparison of the predicted pH value of the desulfurization system with the actual measured point data over a period of time (10: 00/10/1/2020 to 00/11/1/2020). The Root Mean Square Error (RMSE) of the model predictions was 0.02217, the mean relative error (MAE) was 0.01914, and the absolute value of the relative percent error (MAPE) was 0.34637 for the entire test set. As can be seen, the model prediction error is very small, and the requirements in practical engineering are met. Meanwhile, the measured slurry pH value has obvious drift, and the model prediction result can well avoid the error value, so that the online slurry pH value prediction method for the desulfurization system successfully solves the problem that the measured pH value data of the on-site slurry pH meter fluctuates greatly in the washing process.
In conclusion, the online prediction of the pH value of the slurry of the desulfurization system is carried out by adopting the embodiment of the invention, no complex hardware equipment is needed, and the realization cost is low; moreover, the online prediction method for the pH value of the slurry of the desulfurization system, which is disclosed by the invention, is integrated with multiple algorithms, has high prediction precision and higher adaptability to disordered and frequently fluctuating data.
Device embodiment
According to an embodiment of the present invention, there is provided a time-series based online predicting device for pH value of desulfurization system slurry, fig. 5 is a schematic diagram of the time-series based online predicting device for pH value of desulfurization system slurry according to the embodiment of the present invention, and as shown in fig. 5, the time-series based online predicting device for pH value of desulfurization system slurry according to the embodiment of the present invention specifically includes:
the data acquisition module 50: the system comprises a database, a data processing module and a data processing module, wherein the data processing module is used for acquiring historical data of the pH value of the slurry of the desulfurization system in a preset time period from the database, and sampling the historical data to obtain an original sample D;
the data preprocessing module 52: the data cleaning and slicing are carried out on the original sample D, and classified data sets D1, D2 and D3 are obtained;
the data preprocessing module is specifically configured to: performing data slicing on a data CD obtained by performing data cleaning on an original sample to obtain classified data sets D1, D2 and D3, specifically:
d1 ═ CDi (T-T-1 ≦ i ≦ T-1) for the time step T and the slurry pH P (T) to be predicted;
setting a skip step skip for D2, wherein D2 is { CDi } (i is T-1-m skip, and 0 is not more than m and T);
setting a sampling step length T1< T, D3 ═ CDi (T-T1-1 ≦ i ≦ T-1) for D3;
wherein m represents the number of sampling periods and t represents the sampling time;
the model prediction module 54: the method is used for sequentially inputting data sets D1 and D2 into two layers of neural network models which are connected with each other, splicing output results and inputting the output results as a full connection layer Dense1 to obtain a result A1; establishing an Autoregressive (AR) model based on the data set D3 to obtain a result A2;
the model prediction module is specifically configured to: inputting the data set D1 into a convolutional neural network CNN1, and outputting a result C1; inputting the data D2 into a convolutional neural network CNN2, and outputting a result C2; inputting C1 and C2 into long-short term memory sequences LSTM1 and LSTM2 respectively, and outputting results which are L1 and L2 respectively; splicing the output results L1 and L2 to be used as the input of a full connection layer Dense1 to obtain an output result A1; establishing an autoregressive model AR by using a data set D3 to obtain a result A2;
the result calculation module 56: the method is used for summing A1 and A2, and obtaining a final desulfurization system slurry pH value prediction result after activation is carried out through a Sigmoid function;
the result calculation module is specifically configured to: add a1 to the corresponding element of a 2.
The embodiment of the present invention is a system embodiment corresponding to the above method embodiment, and specific operations of each module may be understood with reference to the description of the method embodiment, which is not described herein again.
Apparatus embodiment one
The embodiment of the invention provides online prediction equipment for the pH value of slurry of a desulfurization system based on a time sequence, as shown in fig. 6, comprising: a memory 60, a processor 62 and a computer program stored on the memory 60 and executable on the processor 62, which computer program, when executed by the processor 62, carries out the following method steps:
s1, acquiring historical data of the pH value of slurry of a desulfurization system in a preset time period from a database, and sampling the historical data to obtain an original sample D;
specifically, historical data of the pH value of the slurry in the desulfurization system in the previous week may be obtained from the database, the historical data is counted at intervals of 1min, and the obtained data is used as the original sample D.
S2, carrying out data cleaning on the original sample D and carrying out data slicing to obtain classified data sets D1, D2 and D3;
specifically, the data cleaning process is to filter outliers in the original sample, note the cleaned data as CD, and slice the data CD to obtain classified data sets D1, D2, and D3, and the specific process of slicing the data is as follows:
d1 ═ CDi (T-T-1 ≦ i ≦ T-1) for the time step T and the slurry pH P (T) to be predicted;
setting a skip step skip for D2, wherein D2 is { CDi } (i is T-1-m skip, and 0 is not more than m and T);
setting a sampling step length T1< T, D3 ═ CDi (T-T1-1 ≦ i ≦ T-1) for D3;
wherein m represents the number of sampling periods and t represents the sampling time;
s3, sequentially inputting the data sets D1 and D2 into two mutually connected neural network models, splicing output results and inputting the output results as input of a full connection layer Dense1 to obtain a result A1; establishing an Autoregressive (AR) model based on the data set D3 to obtain a result A2;
in step S3, the specific process of obtaining result a1 is:
inputting the data set D1 into a convolutional neural network CNN1, and outputting a result C1; inputting the data D2 into a convolutional neural network CNN2, and outputting a result C2; inputting C1 and C2 into long-short term memory sequences LSTM1 and LSTM2 respectively, and outputting results which are L1 and L2 respectively; splicing the output results L1 and L2 to be used as the input of a full connection layer Dense1, and obtaining an output result A1;
the CNN1 and the CNN2 adopt the same structural parameters, namely, the CNN1 and the CNN2 have the same filter number, convolution kernel number and moving step length; the LSTM1 and the LSTM2 adopt the same number of hidden layers; the splicing is to perform matrix splicing on L1 and L2, and non-corresponding elements are added;
in step S3, the building of the autoregressive model AR is implemented by using a full connection layer;
s4, summing A1 and A2, and activating through a Sigmoid function to obtain a final pH value prediction result of the slurry of the desulfurization system;
specifically, the method for summing a1 and a2 is as follows: the corresponding elements of a1 and a2 are added.
Device embodiment II
The embodiment of the present invention provides a computer-readable storage medium, on which an implementation program for information transmission is stored, and when being executed by a processor 62, the implementation program implements the following method steps:
s1, acquiring historical data of the pH value of slurry of a desulfurization system in a preset time period from a database, and sampling the historical data to obtain an original sample D;
specifically, historical data of the pH value of the slurry in the desulfurization system in the previous week may be obtained from the database, the historical data is counted at intervals of 1min, and the obtained data is used as the original sample D.
S2, carrying out data cleaning on the original sample D and carrying out data slicing to obtain classified data sets D1, D2 and D3;
specifically, the data cleaning process is to filter outliers in the original sample, note the cleaned data as CD, and slice the data CD to obtain classified data sets D1, D2, and D3, and the specific process of slicing the data is as follows:
d1 ═ CDi (T-T-1 ≦ i ≦ T-1) for the time step T and the slurry pH P (T) to be predicted;
setting a skip step skip for D2, wherein D2 is { CDi } (i is T-1-m skip, and 0 is not more than m and T);
setting a sampling step length T1< T, D3 ═ CDi (T-T1-1 ≦ i ≦ T-1) for D3;
wherein m represents the number of sampling periods and t represents the sampling time;
s3, sequentially inputting the data sets D1 and D2 into two mutually connected neural network models, splicing output results and inputting the output results as input of a full connection layer Dense1 to obtain a result A1; establishing an Autoregressive (AR) model based on the data set D3 to obtain a result A2;
in step S3, the specific process of obtaining result a1 is:
inputting the data set D1 into a convolutional neural network CNN1, and outputting a result C1; inputting the data D2 into a convolutional neural network CNN2, and outputting a result C2; inputting C1 and C2 into long-short term memory sequences LSTM1 and LSTM2 respectively, and outputting results which are L1 and L2 respectively; splicing the output results L1 and L2 to be used as the input of a full connection layer Dense1, and obtaining an output result A1;
the CNN1 and the CNN2 adopt the same structural parameters, namely, the CNN1 and the CNN2 have the same filter number, convolution kernel number and moving step length; the LSTM1 and the LSTM2 adopt the same number of hidden layers; the splicing is to perform matrix splicing on L1 and L2, and non-corresponding elements are added;
in step S3, the building of the autoregressive model AR is implemented by using a full connection layer;
s4, summing A1 and A2, and activating through a Sigmoid function to obtain a final pH value prediction result of the slurry of the desulfurization system;
specifically, the method for summing a1 and a2 is as follows: the corresponding elements of a1 and a2 are added.
The computer-readable storage medium of this embodiment includes, but is not limited to: ROM, RAM, magnetic or optical disks, and the like.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The online prediction method for the pH value of the slurry of the desulfurization system based on the time series is characterized by comprising the following steps of:
s1, acquiring historical data of the pH value of slurry of a desulfurization system in a preset time period from a database, and sampling the historical data to obtain an original sample D;
s2, carrying out data cleaning on the original sample D and carrying out data slicing to obtain classified data sets D1, D2 and D3;
s3, sequentially inputting the data sets D1 and D2 into two mutually connected neural network models, splicing output results and inputting the output results as input of a full connection layer Dense1 to obtain a result A1; establishing an Autoregressive (AR) model based on the data set D3 to obtain a result A2;
and S4, summing the A1 and the A2, and activating through a Sigmoid function to obtain a final pH value prediction result of the slurry of the desulfurization system.
2. The method according to claim 1, wherein the step S2 of slicing data to obtain the classified data sets D1, D2 and D3 specifically comprises:
the data set is divided by adopting the following modes for the samples after the novel data cleaning:
D1={CDi}(t-T-1≤i≤t-1);
D2={CDi}(i=t-1-m*skip,0≤m<T);
D3={CDi}(t-T1-1≤i≤t-1);
wherein T is a time step, skip is a skip step, T1 is a sampling step, T1< T, m represents the number of sampling periods, and T represents the sampling time.
3. The method according to claim 1, wherein step S3 specifically comprises:
respectively inputting data sets D1 and D2 into convolutional neural network models CNN1 and CNN2, respectively inputting output first output results into long-term and short-term memory neural network models LSTM1 and LSTM2, performing matrix splicing on output second output results and inputting the output second output results as full connection layers Dense1 to obtain a result A1, and establishing an autoregressive model AR on the full connection layers based on the data sets D3 to obtain a result A2, wherein the convolutional neural network models CNN1 and CNN2 have the same structural parameters, namely the number of the possessed filters, the number of convolutional kernels and the number of the mobile cores are the same; the long-short term memory networks LSTM1 and LSTM2 use the same number of hidden layers.
4. The method of claim 1, wherein summing a1 with a2 specifically comprises: corresponding elements of a1, a2 are added.
5. The utility model provides a desulfurization system thick liquid pH value on-line prediction device based on time series which characterized in that includes:
a data acquisition module: the system comprises a database, a data processing module and a data processing module, wherein the data processing module is used for acquiring historical data of the pH value of the slurry of the desulfurization system in a preset time period from the database, and sampling the historical data to obtain an original sample D;
a data preprocessing module: the data cleaning and slicing are carried out on the original sample D, and classified data sets D1, D2 and D3 are obtained;
a model prediction module: the method is used for sequentially inputting data sets D1 and D2 into two layers of neural network models which are connected with each other, splicing output results and inputting the output results as a full connection layer Dense1 to obtain a result A1; establishing an Autoregressive (AR) model based on the data set D3 to obtain a result A2;
a result calculation module: the method is used for summing A1 and A2 and obtaining a final desulfurization system slurry pH value prediction result after activation through a Sigmoid function.
6. The online predicting device for the pH value of the slurry in the desulfurization system based on the time series as claimed in claim 5, wherein the data preprocessing module is specifically configured to perform data slicing on the sample CD to obtain the classified data sets D1, D2 and D3, and specifically includes:
the data set is divided by adopting the following modes for the samples after the novel data cleaning:
D1={CDi}(t-T-1≤i≤t-1);
D2={CDi}(i=t-1-m*skip,0≤m<T);
D3={CDi}(t-T1-1≤i≤t-1);
wherein T is the time step, P (T) is the slurry pH value to be predicted, skip is the skip step, T1 is the sampling step, and T1< T.
7. The online prediction device for the pH value of the slurry of the desulfurization system based on the time series as claimed in claim 5, wherein the model prediction module is specifically configured to:
after data sets D1 and D2 are respectively input into convolutional neural network models CNN1 and CNN2, output first output results are respectively input into long-term and short-term memory neural network models LSTM1 and LSTM2, output second output results are subjected to matrix splicing and serve as input of a full connection layer Dense1 to obtain a result A1, and an autoregressive model AR is established in the full connection layer based on the data set D3 to obtain a result A2.
8. The online predicting device for the pH value of the slurry of the desulfurization system based on the time series as claimed in claim 5, wherein the result calculating module is specifically configured to: corresponding elements of a1, a2 are added.
9. The utility model provides a desulfurization system thick liquid pH value on-line prediction equipment based on time series which characterized in that includes: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program when executed by the processor implementing the steps of the time series based online prediction method of pH value of desulfurization system slurry according to any one of claims 1 to 4.
10. A computer-readable storage medium, wherein the computer-readable storage medium stores thereon a program for implementing information transmission, and when the program is executed by a processor, the program implements the steps of the online prediction method for pH value of desulfurization system slurry based on time series according to any one of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110204799.6A CN113012767A (en) | 2021-02-24 | 2021-02-24 | Desulfurization system slurry pH value online prediction method and device based on time sequence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110204799.6A CN113012767A (en) | 2021-02-24 | 2021-02-24 | Desulfurization system slurry pH value online prediction method and device based on time sequence |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113012767A true CN113012767A (en) | 2021-06-22 |
Family
ID=76408927
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110204799.6A Pending CN113012767A (en) | 2021-02-24 | 2021-02-24 | Desulfurization system slurry pH value online prediction method and device based on time sequence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113012767A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113379166A (en) * | 2021-07-27 | 2021-09-10 | 成都佳华物链云科技有限公司 | Method and device for predicting process parameters, electronic equipment and storage medium |
CN115684276A (en) * | 2022-12-28 | 2023-02-03 | 北京华科仪科技股份有限公司 | Desulfurization system pH value prediction method and system based on integrated fusion model |
CN115729184A (en) * | 2022-11-14 | 2023-03-03 | 青芥一合碳汇(武汉)科技有限公司 | Desulfurization optimization operation method and device based on big data analysis and edge control |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109101552A (en) * | 2018-07-10 | 2018-12-28 | 东南大学 | A kind of fishing website URL detection method based on deep learning |
CN109508812A (en) * | 2018-10-09 | 2019-03-22 | 南京航空航天大学 | A kind of aircraft Trajectory Prediction method based on profound memory network |
CN110909508A (en) * | 2019-10-29 | 2020-03-24 | 中国石油化工股份有限公司 | Heating furnace temperature field real-time prediction method based on convolution long and short term memory network |
AU2020101405A4 (en) * | 2020-07-18 | 2020-08-20 | Guizhou Minzu University | An Efficient Distributed Method for Real-Time Traffic Flow Prediction |
CN111695730A (en) * | 2020-06-09 | 2020-09-22 | 浙江大学 | ARIMA and RNN-based vertical mill vibration prediction method and device |
CN111797122A (en) * | 2020-05-28 | 2020-10-20 | 浙江大学 | Method and device for predicting change trend of high-dimensional reappearance concept drift stream data |
CN111913156A (en) * | 2020-08-05 | 2020-11-10 | 电子科技大学 | Radar radiation source individual identification method based on deep learning model and feature combination |
-
2021
- 2021-02-24 CN CN202110204799.6A patent/CN113012767A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109101552A (en) * | 2018-07-10 | 2018-12-28 | 东南大学 | A kind of fishing website URL detection method based on deep learning |
CN109508812A (en) * | 2018-10-09 | 2019-03-22 | 南京航空航天大学 | A kind of aircraft Trajectory Prediction method based on profound memory network |
CN110909508A (en) * | 2019-10-29 | 2020-03-24 | 中国石油化工股份有限公司 | Heating furnace temperature field real-time prediction method based on convolution long and short term memory network |
CN111797122A (en) * | 2020-05-28 | 2020-10-20 | 浙江大学 | Method and device for predicting change trend of high-dimensional reappearance concept drift stream data |
CN111695730A (en) * | 2020-06-09 | 2020-09-22 | 浙江大学 | ARIMA and RNN-based vertical mill vibration prediction method and device |
AU2020101405A4 (en) * | 2020-07-18 | 2020-08-20 | Guizhou Minzu University | An Efficient Distributed Method for Real-Time Traffic Flow Prediction |
CN111913156A (en) * | 2020-08-05 | 2020-11-10 | 电子科技大学 | Radar radiation source individual identification method based on deep learning model and feature combination |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113379166A (en) * | 2021-07-27 | 2021-09-10 | 成都佳华物链云科技有限公司 | Method and device for predicting process parameters, electronic equipment and storage medium |
CN113379166B (en) * | 2021-07-27 | 2023-05-26 | 成都佳华物链云科技有限公司 | Technological parameter prediction method and device, electronic equipment and storage medium |
CN115729184A (en) * | 2022-11-14 | 2023-03-03 | 青芥一合碳汇(武汉)科技有限公司 | Desulfurization optimization operation method and device based on big data analysis and edge control |
CN115684276A (en) * | 2022-12-28 | 2023-02-03 | 北京华科仪科技股份有限公司 | Desulfurization system pH value prediction method and system based on integrated fusion model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113012767A (en) | Desulfurization system slurry pH value online prediction method and device based on time sequence | |
CN111832222B (en) | Pollutant concentration prediction model training method, pollutant concentration prediction method and pollutant concentration prediction device | |
CN111310981B (en) | Reservoir water level trend prediction method based on time series | |
CN105956734A (en) | Method and system for dynamically setting performance index threshold of IT equipment | |
CN110378044A (en) | Multiple Time Scales convolutional neural networks flexible measurement method based on attention mechanism | |
CN111768038A (en) | Pollutant monitoring method and device, terminal equipment and storage medium | |
CN117218118B (en) | Slump monitoring method and device based on image sequence and readable medium | |
CN113723002A (en) | Method and system for establishing slurry pH value prediction model of desulfurization system under all working conditions | |
CN109461067A (en) | A kind of detection method of foreign exchange quotation abnormal data, apparatus and system | |
CN112787878B (en) | Network index prediction method and electronic equipment | |
CN117313957A (en) | Intelligent prediction method for production flow task amount based on big data analysis | |
CN110135114B (en) | Method and device for determining minimum navigation water level of river design | |
CN114648060A (en) | Fault signal standardization processing and classification method based on machine learning | |
CN112700050B (en) | Method and system for predicting ultra-short-term 1 st point power of photovoltaic power station | |
CN114239990A (en) | Time series data prediction method based on time series decomposition and LSTM | |
CN117195083A (en) | Slump prediction method and device based on current curve and readable medium | |
CN112472052A (en) | Weight prediction method, device and equipment based on personal motor function index (PAI) | |
CN112348236A (en) | Abnormal daily load demand prediction system and method for intelligent power consumption monitoring terminal | |
CN117035155A (en) | Water quality prediction method | |
CN110969238A (en) | Method and device for calibrating electricity consumption data | |
CN115169731A (en) | Smart campus energy consumption prediction method, device, equipment and medium | |
Ragozin et al. | State Prediction in Compound Control Systems via Time Series: Neural Network Approach | |
CN111462818A (en) | Sequencing yield prediction method and device for establishing sequencing yield prediction model | |
TWI632522B (en) | Network traffic prediction method and computer program product thereof | |
CN116933949B (en) | Water quality prediction method and system integrating hydrodynamic model and numerical model |
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 |