CN112906967A - Desulfurization system slurry circulating pump performance prediction method and device - Google Patents
Desulfurization system slurry circulating pump performance prediction method and device Download PDFInfo
- Publication number
- CN112906967A CN112906967A CN202110205956.5A CN202110205956A CN112906967A CN 112906967 A CN112906967 A CN 112906967A CN 202110205956 A CN202110205956 A CN 202110205956A CN 112906967 A CN112906967 A CN 112906967A
- Authority
- CN
- China
- Prior art keywords
- slurry
- circulating pump
- data
- desulfurization system
- slurry circulating
- 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 175
- 238000006477 desulfuration reaction Methods 0.000 title claims abstract description 86
- 230000023556 desulfurization Effects 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 44
- 239000007788 liquid Substances 0.000 claims description 43
- 238000010521 absorption reaction Methods 0.000 claims description 42
- 238000012216 screening Methods 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 22
- 238000004140 cleaning Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 241001123248 Arma Species 0.000 claims description 10
- 238000000354 decomposition reaction Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000010977 unit operation Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 9
- 230000008859 change Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003009 desulfurizing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 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
- 238000005070 sampling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Abstract
The invention provides a method and a device for predicting the performance of a slurry circulating pump of a desulfurization system, electronic equipment and a storage medium, and relates to the technical field of power station desulfurization.
Description
Technical Field
The invention relates to the technical field of power station desulfurization, in particular to a method and a device for predicting the performance of a slurry circulating pump of a desulfurization system, electronic equipment and a storage medium.
Background
The desulfurization slurry circulating pump is an important composition content of a desulfurization system of a thermal power plant and is also an important device for maximizing environmental benefits of the power plant. However, in the practical application process, the slurry circulating pump of the desulfurization system often breaks down, so that the frequency of the faults is high, and the types of the faults are various, thereby seriously reducing the operation reliability of the desulfurization system of the thermal power plant.
Accordingly, a method for predicting the performance of a slurry circulating pump of a desulfurization system is needed to improve the operational reliability of the desulfurization system of a thermal power plant.
Disclosure of Invention
The invention aims to provide a method and a device for predicting the performance of a slurry circulating pump of a desulfurization system, electronic equipment and a storage medium.
In a first aspect, one or more embodiments of the present invention provide a method for predicting the performance of a slurry circulation pump of a desulfurization system, the method comprising:
acquiring historical operating data of relevant parameters of a desulfurization system in a unit SIS database, and processing the historical operating data to obtain a data sample set { FDi };
training the data sample set { FDi } by adopting an LSSVM algorithm to obtain an LSSVM model set { M }iThe model input is the slurry density of the desulfurization system, the liquid level of the absorption tower and the front pressure of a slurry circulating pump, and the model output is the current of the slurry circulating pump;
inputting the density of the slurry of the desulfurization system, the liquid level of the absorption tower and the pressure before the slurry circulating pump under the standard working condition into the LSSVM model set, and outputting a current time sequence data set { GD (generalized regression) of the slurry circulating pumpi}(1≤i≤m);
(ii) the slurry circulation pump current timing data set { GDiPerforming wavelet decomposition to obtain a trend component and a detail component, respectively utilizing a GM (1,1) model and an ARMA model to perform modeling prediction on the trend component and the detail component to obtain output results, and overlapping the output results to obtain a slurry circulation pump current prediction data set (HD)jJ is more than or equal to 1 and less than or equal to n, and n is the predicted time interval number.
Optionally, obtaining historical operating data of relevant parameters of the desulfurization system in the unit SIS database and processing the historical operating data to obtain a data sample set { FDi } includes:
acquiring historical operating data of relevant parameters of a desulfurization system in a unit SIS database to obtain an original data sample D;
carrying out data cleaning on an original data sample D, and recording the cleaned sample as a CD;
with unit load and inlet SO of desulfurization system2Performing steady-state screening on the sample CD under the condition that the concentration is steady-state judgment to obtain a steady-state operation data sample set SD;
screening the unit operation conditions by taking the slurry density, the absorption tower liquid level and the slurry circulating pump front pressure as indexes, and setting the variation ranges of the slurry density, the absorption tower liquid level and the slurry circulating pump front pressure to obtain a sample FD meeting the set requirements;
dividing the screened sample FD into m time period sample sets { FD } according to the time labelsi}(1≤i≤m)。
Optionally, the relevant parameters of the desulfurization system are: unit load, desulfurization system inlet SO2Concentration, slurry density, absorption tower liquid level, slurry circulating pump pre-pump pressure and slurry circulating pump current.
Optionally, the data cleaning process is to filter samples containing a dead value and an outlier in the original sample D, wherein the dead value is caused by a unit shutdown or a data transmission channel failure, and the outlier occurs due to an equipment failure or a sensor failure.
Optionally, the determination conditions in the steady-state screening are: the unit load fluctuation range does not exceed 10MW in 10min, and the SO at the inlet of the desulfurization system2The concentration fluctuation amplitude is not more than 25mg/m3。
Optionally, the data generation period is divided into periods spanning one month, and the performance of the slurry circulation pump is not considered to change greatly within one month.
Optionally, screening the unit operation conditions by using the slurry density, the liquid level of the absorption tower and the pressure before the slurry circulating pump as indexes comprises:
screening the operation conditions of the unit by taking the slurry density, the liquid level of the absorption tower and the pump front pressure of a slurry circulating pump as indexes, wherein the slurry taking density is [1050-]kg/m3A sample of (1); the liquid level of the absorption tower is taken to be [7.5-9 ]]m between samples; the pressure of the slurry taking circulating pump is positioned between 40 and 70]kPa samples, and data samples meeting the three screening conditions are obtained.
In a second aspect, one or more embodiments of the present invention provide a prediction apparatus for performance of a slurry circulation pump of a desulfurization system, the prediction apparatus comprising:
the data processing module is used for acquiring historical operating data of relevant parameters of the desulfurization system in the unit SIS database and processing the historical operating data to obtain a data sample set { FDi };
the LSSVM model training module trains a data sample set { FDi } by adopting an LSSVM algorithm to obtain an LSSVM model set { M }iThe model input is the slurry density of the desulfurization system, the liquid level of the absorption tower and the front pressure of a slurry circulating pump, and the model output is the current of the slurry circulating pump;
a time sequence data set acquisition module for inputting the density of the desulfurization system slurry, the liquid level of the absorption tower and the pressure before the slurry circulating pump under the standard working condition into the LSSVM model set and outputting a current time sequence data set { GD of the slurry circulating pumpi}(1≤i≤m);
A calculation module for fitting the slurry circulation pump current timing data set { GDiPerforming wavelet decomposition into a trend component and a detail component, respectively usingThe GM (1,1) model and the ARMA model and predict the trend component and the detail component to obtain output results, and the output results are superposed to obtain a slurry circulating pump current prediction data set { HDjJ is more than or equal to 1 and less than or equal to n, and n is the predicted time interval number.
In a third aspect, one or more embodiments of the present invention provide an electronic device, including:
a processor, a memory for storing processor-executable instructions;
wherein the processor implements the above method by executing the executable instructions.
In a fourth aspect, one or more embodiments of the invention provide a computer-readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the steps of the above-described method.
Has the advantages that:
the invention provides a method and a device for predicting the performance of a slurry circulating pump of a desulfurization system, electronic equipment and a storage medium, wherein the prediction method obtains and processes historical operating data of relevant parameters of the desulfurization system in a unit SIS database to obtain a data sample set { FDi }; training the data sample set { FDi } by adopting an LSSVM algorithm to obtain an LSSVM model set { M }iThe model input is the slurry density of the desulfurization system, the liquid level of the absorption tower and the front pressure of a slurry circulating pump, and the model output is the current of the slurry circulating pump; inputting the density of the slurry of the desulfurization system, the liquid level of the absorption tower and the pressure before the slurry circulating pump under the standard working condition into the LSSVM model set, and outputting a current time sequence data set { GD (generalized regression) of the slurry circulating pumpiI is more than or equal to 1 and less than or equal to m; (ii) the slurry circulation pump current timing data set { GDiPerforming wavelet decomposition to obtain a trend component and a detail component, respectively utilizing a GM (1,1) model and an ARMA model to perform modeling prediction on the trend component and the detail component to obtain output results, and overlapping the output results to obtain a slurry circulation pump current prediction data set (HD)jJ is more than or equal to 1 and less than or equal to n, and n is the predicted time interval number; through effective data processing and mining tools, stable and accurate acquisition is performed from current operation data of complex and disordered mass slurry circulating pumpsThe time sequence variation trend of the slurry circulating pump is obtained by tracking and modeling the operating current of the slurry circulating pump, and the operating reliability of the desulfurization system of the thermal power plant is improved.
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 diagram illustrating a method for predicting the performance of a desulfurization system slurry circulation pump in accordance with one or more embodiments of the present invention;
FIG. 2 is a flowchart illustrating a method for obtaining historical operating data of parameters associated with a desulfurization system in a crew SIS database and processing the historical operating data to obtain a data sample set { FDi }, in accordance with one or more embodiments of the present invention;
FIG. 3 is a flow chart illustrating a method for predicting the performance of a desulfurization system slurry circulation pump, according to one embodiment of the present invention;
FIG. 4 is a time sequence variation of the current of the slurry circulating pump under the same condition as the embodiment of FIG. 3;
FIG. 5 shows the current timing prediction of the slurry circulation pump under the same condition as the embodiment shown in FIG. 3;
FIG. 6 is a block diagram illustrating a device for predicting the performance of a slurry circulation pump of a desulfurization system in accordance with one or more embodiments of the present invention;
FIG. 7 is a block diagram of the structure of the data processing module of FIG. 6;
fig. 8 is a block diagram illustrating an electronic device according to an 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.
The invention aims to provide a method for predicting the performance of a slurry circulating pump of a desulfurization system, which is used for acquiring a stable and accurate time sequence change trend from complex and disordered massive current operation data of the slurry circulating pump through an effective data processing and mining tool, namely acquiring the performance change trend of the slurry circulating pump through tracking and modeling the operation current of the slurry circulating pump so as to improve the operation reliability of the desulfurization system of a thermal power plant.
Fig. 1 is a flow chart illustrating a method for predicting the performance of a slurry circulation pump of a desulfurization system according to an embodiment of the present invention, as shown in fig. 1, the method comprising:
s20, acquiring historical operating data of relevant parameters of the desulfurization system in the unit SIS database, and processing the historical operating data to obtain a data sample set { FDi };
s40, training the data sample set { FDi } by adopting an LSSVM algorithm to obtain an LSSVM model set { M }iThe model input is the slurry density of the desulfurization system, the liquid level of the absorption tower and the front pressure of a slurry circulating pump, and the model output is the current of the slurry circulating pump;
s60, inputting the density of the desulfurization system slurry, the liquid level of the absorption tower and the pressure before the slurry circulating pump under the standard working condition into the LSSVM model set, and outputting a current time sequence data set { GD (generalized minimum support vector machine) of the slurry circulating pumpi}(1≤i≤m);
S80, setting the current time sequence data set { GD of the slurry circulating pumpiPerforming wavelet decomposition to obtain a trend component and a detail component, respectively utilizing a GM (1,1) model and an ARMA model to perform modeling prediction on the trend component and the detail component to obtain output results, and overlapping the output results to obtain a slurry circulation pump current prediction data set (HD)jJ is more than or equal to 1 and less than or equal to n, and n is the predicted time interval number.
In the prediction method, a data sample set { FDi } is obtained by acquiring and processing historical operating data of relevant parameters of a desulfurization system in a unit SIS database; making a data sample set by using LSSVM algorithmFDi is trained to obtain an LSSVM model set { M }iThe model input is the slurry density of the desulfurization system, the liquid level of the absorption tower and the front pressure of a slurry circulating pump, and the model output is the current of the slurry circulating pump; inputting the density of the slurry of the desulfurization system, the liquid level of the absorption tower and the pressure before the slurry circulating pump under the standard working condition into the LSSVM model set, and outputting a current time sequence data set { GD (generalized regression) of the slurry circulating pumpiI is more than or equal to 1 and less than or equal to m; (ii) the slurry circulation pump current timing data set { GDiPerforming wavelet decomposition to obtain a trend component and a detail component, respectively utilizing a GM (1,1) model and an ARMA model to perform modeling prediction on the trend component and the detail component to obtain output results, and overlapping the output results to obtain a slurry circulation pump current prediction data set (HD)jJ is more than or equal to 1 and less than or equal to n, and n is the predicted time interval number; through effective data processing and an excavating tool, a stable and accurate time sequence change trend is obtained from the current operation data of the complicated and disordered mass slurry circulating pump, namely the performance change trend of the slurry circulating pump is obtained through tracking and modeling of the operation current of the slurry circulating pump, and the operation reliability of the desulfurization system of the thermal power plant is improved.
Specifically, as shown in fig. 2, obtaining and processing historical operating data of relevant parameters of the desulfurization system in the unit SIS database to obtain a data sample set { FDi } includes:
s201, obtaining historical operation data of relevant parameters of a desulfurization system in a unit SIS database to obtain an original data sample D;
s202, carrying out data cleaning on an original data sample D, and recording the cleaned sample as a CD;
s203, according to the unit load and the inlet SO of the desulfurization system2Performing steady-state screening on the sample CD under the condition that the concentration is steady-state judgment to obtain a steady-state operation data sample set SD;
s204, screening the operation working conditions of the unit by taking the slurry density, the liquid level of the absorption tower and the pressure in front of a slurry circulating pump as indexes, and setting the variation ranges of the slurry density, the liquid level of the absorption tower and the pressure in front of the slurry circulating pump to obtain a sample FD meeting the set requirements;
s205, dividing the screened sample FD into m time slots according to the time labelsSegment sample set { FDi}(1≤i≤m)。
Specifically, the relevant parameters of the desulfurization system are as follows: unit load, desulfurization system inlet SO2Concentration, slurry density, absorption tower liquid level, slurry circulating pump pre-pump pressure and slurry circulating pump current.
It should be noted that the data cleaning process is to filter samples, which include a dead value and an outlier, in the original sample D, where the dead value is caused by a unit shutdown or a data transmission channel failure, and the outlier occurs due to an equipment failure or a sensor failure.
In some embodiments, the decision conditions at steady state screening are: the unit load fluctuation range does not exceed 10MW in 10min, and the SO at the inlet of the desulfurization system2The concentration fluctuation amplitude is not more than 25mg/m3。
In some embodiments, the data progression interval spans a month, and the slurry circulation pump performance is considered to vary little within a month.
In some embodiments, screening the unit operation conditions by taking the slurry density, the absorption tower liquid level and the pressure before the slurry circulating pump as indexes comprises the following steps:
screening the operation conditions of the unit by taking the slurry density, the liquid level of the absorption tower and the pump front pressure of a slurry circulating pump as indexes, wherein the slurry taking density is [1050-]kg/m3A sample of (1); the liquid level of the absorption tower is taken to be [7.5-9 ]]m between samples; the pressure of the slurry taking circulating pump is positioned between 40 and 70]kPa samples, and data samples meeting the three screening conditions are obtained.
The beneficial effects of the method for predicting the performance of the slurry circulating pump of the desulfurization system according to the present invention are described in the following preferred embodiment:
the framework of the invention mainly comprises the core steps of historical data sampling, data cleaning, steady state screening, working condition screening, time section division, LSSVM model training, standard working condition testing, slurry circulating pump current trend prediction and the like, and the detailed flow is shown in figure 3. Taking a desulfurization system of a certain coal-fired unit as an example, the method comprises the following specific operation steps:
1. raw data acquisition
Collecting unit load and desulfurization system inlet SO from 4 months in 2019 to 9 months in 2020 in SIS historical database2The data of concentration, slurry density, liquid level of the absorption tower, pressure before a slurry circulating pump and current of the slurry circulating pump are obtained at the interval of 1 min.
2. Data cleansing
And (4) carrying out data cleaning on the original operation data, and removing dead values and outlier data to obtain sample data after cleaning.
3. Steady state screening
The unit load fluctuation range does not exceed 10MW within 10 minutes, and the SO of the desulfurization system2The concentration fluctuation amplitude is not more than 25mg/m3And (3) as a steady state judgment condition, performing steady state screening on the cleaned data, and taking the arithmetic mean of 10 groups of screened data within 10 minutes of a steady state process as a group of data in order to further remove the influence of data fluctuation and unsteady state.
4. Working condition screening
In the slurry density (kg/m)3) The liquid level (m) of the absorption tower and the pressure (kPa) before a slurry circulating pump are taken as indexes to screen the operation working conditions of the unit, and the density of the slurry taking liquid is positioned in [1050-]A sample of (1); the liquid level of the absorption tower is taken to be [7.5-9 ]]A sample of (1); the pressure of the slurry taking circulating pump is positioned between 40 and 70]And obtaining data samples meeting the three screening conditions.
5. Time segment partitioning
And 4, dividing the screened data samples obtained in the step 4 into 18 time interval sample sets by taking a month as a unit.
6. LSSVM-based current model training of slurry circulation pump
And (4) respectively training by utilizing the 18 time period sample sets obtained in the step (5) to obtain 18 LSSVM-based slurry circulation pump current models.
(7) Test of standard working conditions
Determining the slurry density at 1100kg/m3Inputting the current models of the 18 LSSVM-based slurry circulating pumps obtained in the step 6 by taking the liquid level of the absorption tower of 8.2m and the pump front pressure of the slurry circulating pump of 62kPa as standard working conditionsAnd obtaining 18 current outputs under the standard working condition, and arranging the current outputs according to time sequence, as shown in figure 4.
(8) Slurry circulation pump current prediction
And (3) performing wavelet decomposition by taking the first 15 of the 18 currents obtained in the step (7) as input to decompose the currents into a trend component and a detail component, respectively performing modeling prediction on the trend component and the detail component by utilizing a GM (1,1) model and an ARMA model to obtain a prediction result of the last three months, wherein as shown in FIG. 5, predicted values of the currents in 7 months, 8 months and 9 months in 2020 are closer to actual values, and errors are smaller, so that the method can well predict the current trend of the slurry circulating pump, and can clearly judge the performance change trend of the slurry circulating pump.
Based on the same inventive concept, the embodiment of the present invention further provides a device for predicting the performance of a slurry circulation pump of a desulfurization system, which can be used for implementing the method described in the above embodiment, as described in the following embodiment. Because the principle of solving the problems of the desulfurization system slurry circulating pump performance prediction device is similar to a desulfurization system slurry circulating pump performance prediction method, the implementation of the desulfurization system slurry circulating pump performance prediction device can refer to the implementation of the desulfurization system slurry circulating pump performance prediction method, and repeated parts are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the system described in the following embodiments is preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated, and in particular, as shown in fig. 6, the desulfurization system slurry circulation pump performance prediction apparatus includes:
the data processing module 20 is configured to obtain historical operating data of relevant parameters of the desulfurization system in the unit SIS database, and process the historical operating data to obtain a data sample set { FDi };
the LSSVM model training module 40 trains the data sample set { FDi } by using the LSSVM algorithm to obtain an LSSVM model set { M }iThe model input is the slurry density of the desulfurization system, the liquid level of the absorption tower and the front pressure of a slurry circulating pump, and the model output is the current of the slurry circulating pump;
a time sequence data set acquisition module 60, configured to input the desulfurization system slurry density, the absorption tower liquid level, and the slurry circulation pump front pressure in the standard working condition into the LSSVM model set, and output a slurry circulation pump current time sequence data set { GDi}(1≤i≤m);
A calculation module 80 for fitting the slurry circulation pump current timing data set { GDiPerforming wavelet decomposition to obtain a trend component and a detail component, respectively utilizing a GM (1,1) model and an ARMA model to perform modeling prediction on the trend component and the detail component to obtain output results, and overlapping the output results to obtain a slurry circulation pump current prediction data set (HD)jJ is more than or equal to 1 and less than or equal to n, and n is the predicted time interval number.
In the prediction device of this embodiment, historical operating data of relevant parameters of a desulfurization system in a unit SIS database is obtained through a data processing module 20 and processed to obtain a data sample set { FDi }; the LSSVM model training module 40 trains the data sample set { FDi } by using an LSSVM algorithm to obtain an LSSVM model set { M }iThe model input is the slurry density of the desulfurization system, the liquid level of the absorption tower and the front pressure of a slurry circulating pump, and the model output is the current of the slurry circulating pump; the time sequence data set acquisition module 60 inputs the desulfurization system slurry density, the absorption tower liquid level and the slurry circulating pump front pressure under the standard working condition into the LSSVM model set and outputs a slurry circulating pump current time sequence data set { GDiI is more than or equal to 1 and less than or equal to m; calculation module 80 sets the slurry circulation pump current timing data set { GDiPerforming wavelet decomposition to obtain a trend component and a detail component, respectively utilizing a GM (1,1) model and an ARMA model to perform modeling prediction on the trend component and the detail component to obtain output results, and overlapping the output results to obtain a slurry circulation pump current prediction data set (HD)jJ is more than or equal to 1 and less than or equal to n, and n is the predicted time interval number; through effective data processing and an excavating tool, a stable and accurate time sequence change trend is obtained from the current operation data of the complicated and disordered mass slurry circulating pump, namely the performance change trend of the slurry circulating pump is obtained through tracking and modeling of the operation current of the slurry circulating pump, and the operation reliability of the desulfurization system of the thermal power plant is improved.
Specifically, as shown in fig. 7, the data processing module 20 includes:
the data acquisition unit 201 is used for acquiring historical operating data of relevant parameters of the desulfurization system in the unit SIS database to obtain an original data sample D;
the data cleaning unit 202 is used for performing data cleaning on an original data sample D, and the cleaned sample is marked as CD;
a first screening unit 203 for loading the unit and desulfurizing the system inlet SO2Performing steady-state screening on the sample CD under the condition that the concentration is steady-state judgment to obtain a steady-state operation data sample set SD;
the second screening unit 204 is used for screening the operation conditions of the unit by taking the slurry density, the liquid level of the absorption tower and the pump front pressure of the slurry circulating pump as indexes, setting the variation ranges of the slurry density, the liquid level of the absorption tower and the pump front pressure of the slurry circulating pump, and obtaining a sample FD meeting the set requirements;
a sample dividing unit 205 for dividing the filtered sample FD into m time interval sample sets { FDi}(1≤i≤m)。
An electronic device is also provided in an embodiment of the present invention, and fig. 8 shows a schematic structural diagram of an electronic device to which an embodiment of the present invention can be applied, and as shown in fig. 8, the computer electronic device includes a Central Processing Unit (CPU)801 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)802 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 803. In the RAM803, various programs and data necessary for system operation are also stored. The CPU 801, ROM 802, and RAM803 are connected to each other via a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.
The following components are connected to the I/O interface 805: an input portion 806 including a keyboard, a mouse, and the like; an output section 807 including a signal such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 808 including a hard disk and the like; and a communication section 809 including a network interface card such as a LAN card, a modem, or the like. The communication section 809 performs communication processing via a network such as the internet. A drive 810 is also connected to the I/O interface 805 as necessary. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 810 as necessary, so that a computer program read out therefrom is mounted on the storage section 808 as necessary.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The invention also provides a computer readable storage medium, which can be the computer readable storage medium contained in the device for predicting the performance of the slurry circulating pump of the desulfurization system in the embodiment; or it may be a computer-readable storage medium that exists separately and is not built into the electronic device. The computer readable storage medium stores one or more programs for use by one or more processors in performing a method for predicting the performance of a desulfurization system slurry circulation pump as described herein.
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. A method for predicting the performance of a slurry circulating pump of a desulfurization system is characterized by comprising the following steps:
acquiring historical operating data of relevant parameters of a desulfurization system in a unit SIS database, and processing the historical operating data to obtain a data sample set { FDi };
training the data sample set { FDi } by adopting an LSSVM algorithm to obtain an LSSVM model set { M }iThe model input is the slurry density of the desulfurization system, the liquid level of the absorption tower and the front pressure of a slurry circulating pump, and the model output is the current of the slurry circulating pump;
inputting the density of the slurry of the desulfurization system, the liquid level of the absorption tower and the pressure before the slurry circulating pump under the standard working condition into the LSSVM model set, and outputting a current time sequence data set { GD (generalized regression) of the slurry circulating pumpi}(1≤i≤m);
(ii) the slurry circulation pump current timing data set { GDiPerforming wavelet decomposition to obtain a trend component and a detail component, respectively utilizing a GM (1,1) model and an ARMA model to perform modeling prediction on the trend component and the detail component to obtain output results, and overlapping the output results to obtain a slurry circulation pump current prediction data set (HD)jJ is more than or equal to 1 and less than or equal to n, and n is the predicted time interval number.
2. The prediction method of claim 1, wherein obtaining historical operating data of relevant parameters of the desulfurization system in the unit SIS database and processing the historical operating data to obtain a data sample set { FDi } comprises:
acquiring historical operating data of relevant parameters of a desulfurization system in a unit SIS database to obtain an original data sample D;
carrying out data cleaning on an original data sample D, and recording the cleaned sample as a CD;
by unit loadAnd desulfurization system inlet SO2Performing steady-state screening on the sample CD under the condition that the concentration is steady-state judgment to obtain a steady-state operation data sample set SD;
screening the unit operation conditions by taking the slurry density, the absorption tower liquid level and the slurry circulating pump front pressure as indexes, and setting the variation ranges of the slurry density, the absorption tower liquid level and the slurry circulating pump front pressure to obtain a sample FD meeting the set requirements;
dividing the screened sample FD into m time period sample sets { FD } according to the time labelsi}(1≤i≤m)。
3. The prediction method according to claim 2, wherein the desulfurization system-related parameters are: unit load, desulfurization system inlet SO2Concentration, slurry density, absorption tower liquid level, slurry circulating pump pre-pump pressure and slurry circulating pump current.
4. The prediction method according to claim 2, wherein the data cleaning process is to filter samples containing a dead value and an outlier in the original samples D, wherein the dead value is caused by a unit shutdown or a data transmission channel failure, and the outlier is caused by an equipment failure or a sensor failure.
5. The prediction method according to claim 1, wherein the determination conditions in the steady-state screening are: the unit load fluctuation range does not exceed 10MW in 10min, and the SO at the inlet of the desulfurization system2The concentration fluctuation amplitude is not more than 25mg/m3。
6. The prediction method of claim 1, wherein the data is divided into time segments spanning a month, and the slurry circulation pump performance is considered to be less variable within a month.
7. The prediction method of claim 1, wherein the screening of the unit operation conditions by using the slurry density, the absorption tower liquid level and the slurry circulating pump front pressure as indexes comprises the following steps:
screening the operation conditions of the unit by taking the slurry density, the liquid level of the absorption tower and the pump front pressure of a slurry circulating pump as indexes, wherein the slurry taking density is [1050-]kg/m3A sample of (1); the liquid level of the absorption tower is taken to be [7.5-9 ]]m between samples; the pressure of the slurry taking circulating pump is positioned between 40 and 70]kPa samples, and data samples meeting the three screening conditions are obtained.
8. A desulfurization system slurry circulation pump performance prediction apparatus, characterized in that the prediction apparatus comprises:
the data processing module is used for acquiring historical operating data of relevant parameters of the desulfurization system in the unit SIS database and processing the historical operating data to obtain a data sample set { FDi };
the LSSVM model training module trains a data sample set { FDi } by adopting an LSSVM algorithm to obtain an LSSVM model set { M }iThe model input is the slurry density of the desulfurization system, the liquid level of the absorption tower and the front pressure of a slurry circulating pump, and the model output is the current of the slurry circulating pump;
a time sequence data set acquisition module for inputting the density of the desulfurization system slurry, the liquid level of the absorption tower and the pressure before the slurry circulating pump under the standard working condition into the LSSVM model set and outputting a current time sequence data set { GD of the slurry circulating pumpi}(1≤i≤m);
A calculation module for fitting the slurry circulation pump current timing data set { GDiPerforming wavelet decomposition to obtain a trend component and a detail component, respectively utilizing a GM (1,1) model and an ARMA model to perform modeling prediction on the trend component and the detail component to obtain output results, and overlapping the output results to obtain a slurry circulation pump current prediction data set (HD)jJ is more than or equal to 1 and less than or equal to n, and n is the predicted time interval number.
9. An electronic device, comprising:
a processor, a memory for storing processor-executable instructions;
wherein the processor implements the method of any one of claims 1-8 by executing the executable instructions.
10. A computer readable storage medium having stored thereon computer instructions which, when executed by a processor, carry out the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110205956.5A CN112906967A (en) | 2021-02-24 | 2021-02-24 | Desulfurization system slurry circulating pump performance prediction method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110205956.5A CN112906967A (en) | 2021-02-24 | 2021-02-24 | Desulfurization system slurry circulating pump performance prediction method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112906967A true CN112906967A (en) | 2021-06-04 |
Family
ID=76106774
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110205956.5A Pending CN112906967A (en) | 2021-02-24 | 2021-02-24 | Desulfurization system slurry circulating pump performance prediction method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112906967A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113392912A (en) * | 2021-06-18 | 2021-09-14 | 大唐环境产业集团股份有限公司 | Multi-mode operation fault diagnosis and early warning method, system and equipment for slurry circulating pump |
CN115025599A (en) * | 2022-03-11 | 2022-09-09 | 华能(浙江)能源开发有限公司玉环分公司 | Method for realizing energy conservation and consumption reduction of desulfurization slurry circulating pump by using desulfurization additive |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015176565A1 (en) * | 2014-05-22 | 2015-11-26 | 袁志贤 | Method for predicting faults in electrical equipment based on multi-dimension time series |
CN109961186A (en) * | 2019-03-22 | 2019-07-02 | 大唐环境产业集团股份有限公司 | Desulphurization system operating parameter prediction technique based on decision tree and BP neural network |
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 |
CN111222680A (en) * | 2019-10-28 | 2020-06-02 | 同济大学 | Wind power station output ultra-short-term prediction method based on least square support vector machine |
US20200201282A1 (en) * | 2017-06-26 | 2020-06-25 | Jiangnan University | Energy consumption prediction system and method based on the decision tree for CNC lathe turning |
CN111766179A (en) * | 2020-07-08 | 2020-10-13 | 大唐环境产业集团股份有限公司 | Limestone slurry density measurement method, system and equipment based on LSSVM |
CN112070321A (en) * | 2020-09-22 | 2020-12-11 | 大唐环境产业集团股份有限公司 | Limestone slurry supply control method, equipment and medium based on GA-LSSVM |
AU2020103422A4 (en) * | 2020-11-13 | 2021-01-28 | Xi’an University of Technology | A precipitation prediction method based on gravity wave potential energy |
CN112365065A (en) * | 2020-11-16 | 2021-02-12 | 大唐环境产业集团股份有限公司 | WFGD self-adaptive online optimization scheduling method |
AU2020104000A4 (en) * | 2020-12-10 | 2021-02-18 | Guangxi University | Short-term Load Forecasting Method Based on TCN and IPSO-LSSVM Combined Model |
-
2021
- 2021-02-24 CN CN202110205956.5A patent/CN112906967A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015176565A1 (en) * | 2014-05-22 | 2015-11-26 | 袁志贤 | Method for predicting faults in electrical equipment based on multi-dimension time series |
US20200201282A1 (en) * | 2017-06-26 | 2020-06-25 | Jiangnan University | Energy consumption prediction system and method based on the decision tree for CNC lathe turning |
CN109961186A (en) * | 2019-03-22 | 2019-07-02 | 大唐环境产业集团股份有限公司 | Desulphurization system operating parameter prediction technique based on decision tree and BP neural network |
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 |
CN111222680A (en) * | 2019-10-28 | 2020-06-02 | 同济大学 | Wind power station output ultra-short-term prediction method based on least square support vector machine |
CN111766179A (en) * | 2020-07-08 | 2020-10-13 | 大唐环境产业集团股份有限公司 | Limestone slurry density measurement method, system and equipment based on LSSVM |
CN112070321A (en) * | 2020-09-22 | 2020-12-11 | 大唐环境产业集团股份有限公司 | Limestone slurry supply control method, equipment and medium based on GA-LSSVM |
AU2020103422A4 (en) * | 2020-11-13 | 2021-01-28 | Xi’an University of Technology | A precipitation prediction method based on gravity wave potential energy |
CN112365065A (en) * | 2020-11-16 | 2021-02-12 | 大唐环境产业集团股份有限公司 | WFGD self-adaptive online optimization scheduling method |
AU2020104000A4 (en) * | 2020-12-10 | 2021-02-18 | Guangxi University | Short-term Load Forecasting Method Based on TCN and IPSO-LSSVM Combined Model |
Non-Patent Citations (1)
Title |
---|
魏建鹏等: "基于LSSVM的石灰石制浆控制参数寻优方法", 《电力科学与工程》, vol. 35, no. 4, pages 64 - 68 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113392912A (en) * | 2021-06-18 | 2021-09-14 | 大唐环境产业集团股份有限公司 | Multi-mode operation fault diagnosis and early warning method, system and equipment for slurry circulating pump |
CN115025599A (en) * | 2022-03-11 | 2022-09-09 | 华能(浙江)能源开发有限公司玉环分公司 | Method for realizing energy conservation and consumption reduction of desulfurization slurry circulating pump by using desulfurization additive |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106294120B (en) | Method, apparatus and computer program product for testing code | |
CN112906967A (en) | Desulfurization system slurry circulating pump performance prediction method and device | |
CN112181758B (en) | Fault root cause positioning method based on network topology and real-time alarm | |
CN103235759A (en) | Method and device for generating test cases | |
CN109299530B (en) | Simulation test case generation method, system, storage medium and terminal | |
CN114757587A (en) | Product quality control system and method based on big data | |
CN115453356B (en) | Power equipment operation state monitoring and analyzing method, system, terminal and medium | |
CN112529036A (en) | Fault early warning method, device, equipment and storage medium | |
CN116256631A (en) | DCS data-based data processing method and device for generator set online diagnosis system | |
CN112686291A (en) | Water quality prediction method, device, system and computer readable storage medium | |
CN116362428A (en) | Short-term load prediction method based on VMD-PCF-ARIMA | |
CN114244681B (en) | Equipment connection fault early warning method and device, storage medium and electronic equipment | |
CN107748711B (en) | Method for automatically optimizing Storm parallelism, terminal equipment and storage medium | |
CN113536042B (en) | Time series abnormity detection method, device and equipment | |
CN113468813B (en) | Desulfurization system inlet SO2Concentration prediction method and device and electronic equipment | |
CN111984624B (en) | Method and system for data migration through correction migration model | |
CN114764532A (en) | Distribution network terminal reliability prediction method and system | |
CN114881112A (en) | System anomaly detection method, device, equipment and medium | |
CN112803428A (en) | Receiving-end main network frame dynamic reactive power supply configuration node selection method and terminal | |
CN105809304A (en) | Method for analyzing correlation of production and operation parameters of power plant and pollution treatment facility | |
CN111799849A (en) | Wind power plant reactive voltage sensitivity calculation method and device | |
CN109298999B (en) | Core software testing method and device based on data distribution characteristics | |
CN115290798B (en) | Stability performance monitoring method and terminal of transformer oil chromatographic online monitoring device | |
CN116244283A (en) | Machine learning sample screening method and device for artificial intelligent system of generator set | |
CN113780579B (en) | Natural gas purification foaming early warning model training method, device and equipment |
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 |