CN115809749A - Establishment method of sewage treatment comprehensive online prediction model and prediction early warning method - Google Patents
Establishment method of sewage treatment comprehensive online prediction model and prediction early warning method Download PDFInfo
- Publication number
- CN115809749A CN115809749A CN202310086581.4A CN202310086581A CN115809749A CN 115809749 A CN115809749 A CN 115809749A CN 202310086581 A CN202310086581 A CN 202310086581A CN 115809749 A CN115809749 A CN 115809749A
- Authority
- CN
- China
- Prior art keywords
- data
- sewage treatment
- prediction model
- online prediction
- inspection data
- 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.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Landscapes
- Activated Sludge Processes (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a method for establishing a comprehensive online prediction model for sewage treatment and a prediction early warning method, wherein firstly, in the modeling process, an offline model is established and calibrated by using historical data and supplementary experiment data of a sewage treatment facility; communicating data between the offline model and the sewage treatment information platform to enable the offline model to become an online prediction model connected with the sewage treatment information platform, wherein the sewage treatment information platform acquires first-class data including operating parameters of a sewage treatment facility and the quality of sewage inlet water; the second class data containing effluent quality is obtained through online prediction model prediction and is compared with the third class data containing actual effluent quality, the online prediction model is corrected, and the model accuracy is verified.
Description
Technical Field
The invention relates to the field of sewage treatment, in particular to a method for establishing a comprehensive online prediction model for sewage treatment and a prediction early warning method.
Background
The simulation and prediction of the biochemical sewage treatment process by computer modeling is a popular direction for the research in the field of sewage treatment in recent years.
The invention patent application with publication number CN 11239137A discloses a prediction model and a prediction method for the change rule of the concentration of organic micropollutants in sewage, wherein the prediction model is an ASM-OMPs offline model based on a water synergistic Activated Sludge Model (ASM), and is mainly used for predicting the change of the concentration of the Organic Micropollutants (OMPs) in the sewage, inputting the actually measured concentration of the organic micropollutants in the sewage into the offline model, and describing the growth and the growth of microorganisms by using Monod dynamics
The method is used for simulating, calculating and predicting the concentration of the organic micro-pollutants by metabolizing the organic micro-pollutants, the kinetic and stoichiometric parameters of the method are only used as influence factors for predicting the concentration of the organic micro-pollutants, and typical default values of the kinetic and stoichiometric parameters proposed by the international water protocol are only input into the offline model, so that the concentration of the organic micro-pollutants in the sewage can be predicted only, and the method has certain limitation.
In addition, the invention patent application with publication number CN112415911A discloses a parameter automatic calibration method based on sensitivity analysis and differential evolution algorithm, which is basically characterized in that a group of offline models based on an international water-assisted Activated Sludge Model (ASM) is established, water quality parameters and operating parameters of a sewage treatment facility are calculated and output through offline model simulation, and relevant parameters obtained through the simulation calculation are used as future predictions of the sewage treatment facility and the sewage quality and are compared with measured values, and parameter correction is continuously performed after a simulation deviation is found, so as to improve the accuracy of the offline model prediction.
In both of the above two patent documents, an offline model is established based on an ASM activated sludge model, and the past operating conditions of the sewage treatment facility are simulated and reproduced on the offline model in combination with the operating parameters of the sewage treatment facility and the historical data of the sewage quality, and for various data such as the operating parameters of the sewage treatment facility, the component concentration in the influent water, the kinetic parameters and the like of the activated sludge treatment section, different data sources thereof cannot be fully considered and utilized, and the use of the various data directly influences the accuracy of the prediction of the future operation and the future sewage quality conditions of the sewage treatment facility by the offline model.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a method for establishing a comprehensive online prediction model for sewage treatment and a prediction early warning method, wherein the model for sewage treatment is established, and on the basis, the model is communicated with data of a sewage treatment information platform in the existing sewage treatment facility (including a sewage treatment plant and other facilities related to sewage treatment), and quantitative analysis is carried out according to the model and different types of data so as to assist technicians and managers of the sewage treatment facility to better guide the actual operation of sewage treatment.
In order to realize the purpose, the invention adopts the following technical scheme:
on one hand, the invention provides a method for establishing a comprehensive online prediction model for sewage treatment, which comprises the following steps:
s1, establishing an accurate offline model of a sewage treatment facility and a sewage treatment process by using operating parameters of the sewage treatment facility, historical data of sewage quality and data collected by a supplementary experiment;
s2, communicating data between the offline model and the sewage treatment information platform to enable the offline model to become an online prediction model connected with the sewage treatment information platform, wherein the sewage treatment information platform acquires first-class data including operation parameters of a sewage treatment facility and sewage inlet water quality;
and S3, simulating and calculating the first type of data by using an online prediction model, generating second type of data including calculation results and prediction information, and sharing and displaying the second type of data to a sewage treatment informatization platform.
In the step S2, the first type data is defined to include first machine inspection data collected by the sewage treatment facility on line and first human inspection data collected and detected by human each day;
the first machine inspection data comprises data automatically acquired by equipment instruments such as various instruments and meters, sensors and monitoring facilities in the sewage treatment facility and communicated with the sewage treatment information platform, wherein the data comprises water quality data and flow data such as COD (chemical oxygen demand) data, NH3-N (NH 3-N) data, TP (TP), TN (TN) data and TSS (total suspended solids) data of a sewage inlet, and data such as temperature and dissolved oxygen concentration of a biochemical reaction tank, wherein the COD is chemical oxygen demand and is used for defining the concentration of organic pollutants in a water sample; NH3-N refers to the concentration of ammonia nitrogen in a water sample; TN refers to the total nitrogen concentration in the water sample; TP indicates the total phosphorus concentration in a water sample; PO4-Ps refers to orthophosphate in a water sample; TSS refers to the total suspended solids concentration in a water sample.
The first human inspection data are data which are manually detected and recorded, and comprise data obtained by manually reading data of various detection instruments, data obtained by a sample experiment at a sewage inlet, data read by manually reading operation parameters of a sewage treatment facility and the like, wherein the data comprise indexes of water quality indexes such as COD, TN, NH3-N, TP, PO4-P, TSS and the like, and operation parameter data such as sludge reflux flow, mixed liquid reflux flow, sludge discharge amount and the like which are adjusted and manually recorded according to daily operation needs; the report forms are uploaded to the sewage treatment information platform manually through the first person inspection data.
Therefore, the first machine detection data and the first person detection data have more repeated detection items, can be used for rechecking the data, and are convenient for finding the abnormity of the detection item indexes in time.
In addition, in step S2, the sewage treatment information platform further obtains third-class data including operating parameters of the sewage treatment facility and COD, TN, NH3-N, TP, TSS, and the like of the effluent quality, wherein the third-class data includes third machine inspection data acquired by the sewage treatment facility on line and third human inspection data acquired and detected by a manual work every day according to different data sources.
The third kind of data comprises information such as MLSS and MLVSS, and information such as COD, TN, NH3-N, TP and TSS of effluent, wherein MLSS refers to the total suspended solid particle concentration of the mixed solution, and MLVSS refers to the volatile suspended solid particle concentration of the mixed solution; and uploading the third people inspection data to the information platform in a report form.
On the other hand, the invention also provides a prediction and early warning method adopting the sewage treatment comprehensive online prediction model, which comprises the following substeps:
s3-0, steady state calculation: performing steady-state calculation by using an online prediction model to simulate and calculate the mean value of the first person inspection data in the past several days;
s3-1, dynamic calculation: and (3) performing simulation calculation on first inspection data in the past hours by using an online prediction model, and performing simulation calculation on second type data in the future hours.
Specifically, the step S3-0 further includes:
s3-0-0, comparing the second type of data output by steady state calculation with the average value of third people inspection data in the past several days, and judging whether the second type of data is consistent with the average value;
s3-0-1, if the online prediction model is effective, carrying out the next step of dynamic calculation;
if not, the online model is calibrated for the first time: correcting the parameter input value of the online prediction model according to the average value of the first personal inspection data in the past several days so as to enable the comparison result to be consistent;
in some preferred embodiments, step S3-1 is followed by:
and S3-2, performing dynamic calculation simulation calculation in the step S3-1, outputting the output value of the second class data in a plurality of hours in the future and third machine inspection data in a plurality of hours in the future, judging whether the output value is consistent with the third machine inspection data, and verifying the validity of the online prediction model again.
Preferably, when judging whether the third machine inspection data in the next several hours in the step S3-2 is consistent with the output value of the second type data in the next several hours after the simulation calculation of the online prediction model and the output;
if yes, the online prediction model is valid;
if not, the following steps are carried out: s3-2-0, comparing the first machine inspection data with the first person inspection data, and verifying the validity of the first machine inspection data;
in addition, in some preferred embodiments, in step S3-2-0, if the first inspection data and the first human inspection data do not match, the sewage treatment facility for collecting the first inspection data is maintained with reference to the first human inspection data;
if the first machine inspection data and the first person inspection data are consistent, and the second type of data which is simulated and calculated by the online prediction model through dynamic calculation in the past days is not consistent with the first type of data, professional personnel are required to correct the parameters of the online prediction model.
In the above implementation steps, when steady state calculation is performed, steady state calculation is performed once a day in the online prediction model, and in step S3-0, the online prediction model is used for simulating first human inspection data within a period of time since the current day, specifically, considering that the sludge retention time for healthy operation of most sewage treatment facilities is 15 days to 20 days, in step S3-0, it is reasonable to simulate the first human inspection data within the past 30 days since the current day in the online prediction model.
In addition, in the daily steady-state calculation and dynamic calculation in the above-described steps S3-0 to S3-1, the result of the simulation calculation of the daily steady-state calculation is taken as the initial value of the first dynamic calculation in the present day, and the result of the last dynamic calculation is taken as the initial value in each of the remaining dynamic calculations.
Compared with the prior art, the invention has the following beneficial effects:
(1) In the prediction model and the prediction early warning method, the operation parameters of the sewage treatment facility and the historical data of the sewage quality are firstly adopted for modeling, and the data intercommunication between the offline model and the sewage treatment informatization platform in the existing sewage treatment plant is realized to form the online prediction model, so that the timeliness and the convenience of the online prediction model for acquiring the first type of data are greatly improved, and meanwhile, the simulation calculation result and the prediction information can be timely and effectively displayed and early warned on the sewage treatment informatization platform.
(2) In addition, in order to ensure the effectiveness of the online model, the implementation steps of the method comprise the steps of establishing and calibrating an offline model, performing steady-state calculation in online operation and performing dynamic calculation in online operation, and the names and the functions of various data required by model calibration are defined and distinguished, the first data acquired by the sewage treatment information platform are divided into first inspection data and first personal inspection data, and the purposes of the various data in the steps of establishing and operating the model are clearly divided;
(3) In addition, in the step of the prediction early warning scheme, a plurality of sub-steps are set to realize comparison between machine inspection data and human inspection data and determine the validity of an input value calculated by an online prediction model; and the substep is set to realize the comparison of the predicted value of the online model and the measured value of the third type of data, and the effectiveness of the online prediction model is determined.
Drawings
FIG. 1 is a block flow diagram of a method for establishing a comprehensive online prediction model for sewage treatment according to an embodiment of the present invention;
FIG. 2 is a first flowchart of a prediction and early warning method of a comprehensive online prediction model for sewage treatment according to an embodiment of the present invention;
fig. 3 is a block diagram of a flow chart of a prediction and early warning method of a sewage treatment comprehensive online prediction model in an embodiment of the present invention.
Detailed Description
The invention is further illustrated by the following examples in conjunction with the accompanying drawings:
the specific implementation mode of the invention is divided into two parts, namely the establishment method of the comprehensive online prediction model for sewage treatment and the prediction method of the comprehensive online prediction model for sewage treatment.
The first embodiment is as follows:
referring to fig. 1, the embodiment discloses a method for establishing a comprehensive online prediction model for sewage treatment, which comprises the following steps:
s1, establishing an accurate offline model of a sewage treatment facility and a sewage treatment process by using operating parameters of the sewage treatment facility, historical data of sewage quality and supplementary experiment data; in the step, the established offline model can be based on activated sludge models such as ASM1, ASM2d and ASM3 released by International Water Association, or on models developed secondarily by the activated sludge models, or on other types of commercial models or independently developed models on the market, in short, the offline model in the step can be established on various existing activated sludge models;
in the step, historical data including operating parameters of the sewage treatment facility, the quality of inlet water, the operating state, the quality of outlet water and the like in the past year can be collected for the historical data of the operating parameters and the quality of the sewage; in addition, for supplementary experiment data, a supplementary experiment plan with a period of two weeks can be executed during off-line modeling, and the components of the wastewater inlet water quality are determined by using the supplementary experiment data;
in addition, it is easy to understand that the offline model is used for simulating and reproducing the historical conditions of the sewage treatment facility and the sewage quality, and does not have a direct prediction function for the future conditions, so after the offline model is established, the offline model needs to be calibrated by using the real data of the sewage treatment facility and the sewage quality, so that the real operating condition and the real sewage quality condition of the sewage treatment facility can be simulated and reproduced by the offline model;
s2, communicating data between the offline model and the sewage treatment information platform to enable the offline model to become an online prediction model connected with the sewage treatment information platform; in this step, the sewage treatment information platform refers to a system platform already provided in the existing sewage treatment facility, such as a sewage treatment real-time monitoring system platform in a sewage treatment plant and various intelligent water affair information system platforms, and the sewage treatment information platform has perfect functions of monitoring the operation parameter condition and the water quality condition of the sewage treatment facility;
the calibrated offline model is embedded into the sewage treatment information platform in an interface, wireless transceiving mode or directly, so that data intercommunication between the offline model and the sewage treatment information platform can be realized, and online deployment of the offline model is further realized.
In addition, since the acquired data of the existing sewage treatment information platform includes information such as state parameters of sewage treatment facilities and sewage quality at sewage inlet/outlet, in order to identify the use occasion and usage of the data information, the following definitions are made for the data in the present invention:
the first type of data comprises operating parameters of the sewage treatment facility and sewage quality information sampled at a sewage inlet, and is divided into first inspection data acquired by the sewage treatment facility on line and first person inspection data acquired and detected by manpower every day according to different sampling modes.
The second type of data is an output value obtained by performing simulation calculation on the online prediction model using the first type of data as an input value.
And the third type data comprises sewage quality information sampled at a sewage outlet, wherein the third type data is divided into third machine inspection data acquired by a sewage treatment facility on line and third personnel inspection data acquired and detected by manpower every day according to different sampling modes.
S3, performing simulation calculation on the first type of data by using an online prediction model, generating second type of data including calculation results and prediction information, and displaying the second type of data through a sewage treatment informatization platform; in the step, the online prediction model acquires the first type of data, performs simulation calculation, and sends the generated calculation result and prediction information to the sewage treatment information platform, so that the function establishment of the online prediction model is completed.
In above-mentioned step S1 to S3, data that equipment instruments that first machine examined data and third machine examined data and had communicate with sewage treatment information platform such as all kinds of instruments and meters in the sewage treatment facility, sensor and control facility are automatic to be acquireed on line, like the quality of water data such as COD, ammonia nitrogen, total phosphorus of acquireing into water and water, flow and dissolved oxygen concentration etc. data, specifically say:
the first mechanical inspection data comprise water quality data and flow data of COD, NH3-N, TP and the like at the sewage inlet, and data of temperature, dissolved oxygen concentration and the like of the biochemical reaction tank.
COD is chemical oxygen demand and is used for defining the concentration of organic pollutants in a water sample;
TP refers to the total phosphorus concentration in the water sample;
TN refers to the total nitrogen concentration in the water sample;
TSS refers to the total suspended solids concentration in a water sample.
In addition, the third machine inspection data comprises COD, TN, NH3-N, TP, TSS and other data at the effluent, and the individual sewage plant also comprises NO3-N and NH3-N measured at a certain position along the process of the biochemical reaction tank;
NH3-N refers to the concentration of ammonia nitrogen in a water sample;
NO3-N refers to the nitrate nitrogen (i.e., nitrate nitrogen) concentration in a water sample.
In the steps S1 to S3, the first human test data and the third human test data are data obtained by a manual test experiment and a manual record, and include data of various types of test instruments read manually, data obtained by a sewage sample experiment, and data of operating parameters of sewage treatment facilities read manually, specifically including inflow water quality indexes COD, TN, NH3-N, TP, PO4-P, TSS, and the like, and MLSS and MLVSS in the biochemical reaction tank, where MLSS refers to the total suspended solid particle concentration of the mixed solution; MLVSS refers to the concentration of volatile suspended solid particles in the mixed liquor. And the operation parameter data information such as the sludge reflux flow, the mixed liquid reflux flow, the sludge discharge amount and the like is adjusted and manually recorded according to the daily operation requirement. The first person examines data and the third person examines data and uploads the input to the sewage treatment information platform through the manual work.
In conclusion, no matter the sewage inlet or the sewage outlet are provided with two data forms of human inspection data and machine inspection data, the data is convenient to recheck, and the abnormity of the detection item index is convenient to find in time.
In addition, because first person examines data and third person and examines data and adopt artifical detection experiment to obtain, generally, the used water sample of artifical detection is mostly 24 hours of a complete day mixed water sample, compare in the mode that first person examines data and third person and examines data and pass through the online acquisition of instrument, it is more comprehensive that artifical detection has sewage sample range, the more accurate advantage of quality of water index, and examine the promptness that data all have the data source with the machine, therefore, first person examines data and third person and examines data more suitable steady state calculation.
Example two:
referring to fig. 2 to 3, as a second part of the present invention, the present invention provides a prediction and early warning method using the sewage treatment comprehensive online prediction model as described in the first embodiment, wherein the prediction and early warning method comprises the following sub-steps:
s3-0, steady state calculation: performing steady-state calculation by using an online prediction model to simulate and calculate the mean value of the first person detection data in the past several days;
s3-1, dynamic calculation: and (3) performing simulation calculation on the first inspection data in the past hours by using an online prediction model, and performing simulation calculation and outputting second type data in the future hours.
Next, the steady state calculation section in step S3-0 will be described.
In step S3-0, the result of the steady state calculation generally reflects the state and treatment effect of the sewage treatment facility and the sewage quality after a period of time, the purpose of the steady state calculation is to anchor the average value of the existing states of the sewage treatment facility and the sewage quality condition by using relatively reliable water quality data, the first human inspection data uses relatively reliable manual inspection (report) data, and therefore, the output value obtained by performing the steady state calculation by using the first human inspection data is closer to the average state of the actual sewage treatment facility and the sewage quality than data obtained by any other inspection mode, and is a more reasonable initial input value for dynamic calculation, so it is necessary to use the average value of the first human inspection data after a period of time as the input value for performing the steady state calculation by using an online prediction model.
At present, in the existing sewage treatment facilities, considering that the sludge retention time for healthy operation is about 15 days to 20 days, it is necessary to select a time period not less than the sludge retention time as the time day for steady state calculation.
Therefore, referring to fig. 2, in one embodiment, the average value of the first human test data in the past 30 days is selected as the input value of the steady state calculation, and the steady state calculation is performed once a day, and it should be noted that the input value of the daily steady state calculation refers to the average value of the first human test data in the past 30 days of the current day of the cut-off steady state calculation.
In addition, referring to fig. 2, in order to make the work of the online prediction model more intelligent and facilitate the staff to intuitively obtain the working state of the current online prediction model, in one embodiment, before performing daily steady-state calculation, a data inspection step is further added in the prediction and early warning method, and integrity inspection can be performed on the first human inspection data acquired by the online prediction model within the past 30 days; that is, for the average value of the first human examination data in the past 30 days required for the steady state calculation, before the steady state calculation, it is first checked whether the parameters and index data of the first human examination data in the past 30 days required for the past are sound, and there are the following possible cases:
for the case of complete absence of data, a warning i (a): "the first human exam data in the past 30 days is completely missing, the system will use the last steady state calculation as the initial value for the next dynamic calculation. ", i.e., the system may use the last steady state calculation result in the last 30 days as the initial value of the dynamic calculation in step S3-1, and may use the steady state calculation result in the last day as the initial value of the dynamic calculation in the current day if the first human examination data in the last 30 days cannot be acquired by the steady state calculation in the current day.
For the case of partial absence of data, a warning I (b) may be generated and executed that "detect data incomplete, please upload first human test data, the system will use the average of the first human test data uploaded over the past 30 days as the input to the steady state calculation. "at this point, since only the first human data for several days over the last 30 days is complete, such as only 15 or 20 days, the system will use the average of these 15 or 20 days as the input for the steady state calculation.
Due to the data intercommunication between the online prediction model and the sewage treatment information platform, the warning I (a), the warning I (b) and other warning information described later can be displayed in the sewage treatment information platform, so that workers can conveniently acquire information and perform maintenance operation.
And after the data inspection step is passed, performing steady state calculation.
In addition, referring to fig. 2, in an embodiment, after the steady state calculation is completed and before the dynamic calculation, a checking and correcting step of the steady state calculation result is further introduced into the online prediction model, namely, the step S3-0 further includes:
s3-0-0, comparing the result of steady state calculation by using the average value of the first personal inspection data in the last 30 days (namely the second type of data calculated by the online prediction model) with the average value of the third personal inspection data in the last 30 days, and judging whether the data are consistent; ( It should be noted that: the judgment standard of whether the two data are in accordance is that whether the difference of the average values of all detection indexes in the two data exceeds 20%, for example, whether the difference of the MLSS index predicted in the second data and the MSLL index in the third human inspection data exceeds 20%, if the difference exceeds 20%, the two data are not in accordance. )
And S3-0-1, if the result is positive, the online prediction model is valid, and the step S3-1 is carried out, otherwise, the input parameters of the online prediction model are wrong, and parameter correction is carried out on the online prediction model according to the average value of the first personal inspection data in the last 30 days until the comparison results of the two are consistent.
Referring to fig. 2, in step S3-0-0, when the average value of the third human test data in the past 30 days is introduced, it is necessary to determine whether the data is sound, and if not, a warning ii is generated and executed: "the third person in the past 30 days examines the data is not sound, can't carry on the check of the steady state calculated result of the day, the steady state calculated result at present will be used in the dynamic calculation directly. ", namely, when warning II is prompted, because the online prediction model carries out steady state calculation once every day, the online prediction model directly defaults that the current steady state calculation result is effective in consideration of small difference of two adjacent steady state calculations, and directly enters the next step of dynamic calculation.
Next, the dynamic calculation section will be described.
After the steady-state calculation is completed, the online prediction model already obtains the average value of the sewage treatment facility and the existing state of the sewage quality, and can be used for predicting the future water outlet situation, so in the dynamic calculation of the step 3-1, the average value of the first machine inspection data in the past hours is selected as an input value of the dynamic calculation, and the water outlet change in hours caused by the future water outlet quantity of the sewage, the water quality and the fluctuation of the operation condition can be reflected through the calculation of the online prediction model.
In addition, in dynamic calculation, the first machine inspection data is derived from the sewage treatment facility on-line sampling at regular time, and the water quality input value of the on-line prediction model is detected, so that the frequency of the sewage treatment facility on-line sampling detection is limited by the detection method in the current industry, generally, the longest detection step comprises sampling, resolution and analysis, and can be as long as 2 hours, and therefore, in one embodiment, the average value of the first machine inspection data of the past 2 hours is selected and extracted.
After extracting the average value of the first inspection data of the past 2 hours, before dynamic calculation, checking whether the first inspection data of the past 2 hours is sound, entering the dynamic detection step after confirming that the data is sound, and if the data is not sound, generating and executing a warning IV: "the first inspection data of the past 2 hours is not sound, and the dynamic calculation is terminated. ", when the dynamic calculation is terminated, wait for the next first inspection data after 2 hours.
In dynamic calculation, the online prediction model calculates and predicts the second class data within 2 hours in the future according to the average value of the first inspection data in the past 2 hours as an input value.
Therefore, after the dynamic calculation in step S3-1, a step S3-2 is further provided to compare the dynamically calculated output value (the average value of the second kind of data in the future 2 hours) with the average value of the third machine inspection data obtained at the effluent 2 hours later, specifically:
referring to fig. 3, which is a continuation chart of the dynamic calculation subsequent flow in fig. 2, in step 3-2, the online prediction model performs analog calculation according to the average value of the first machine inspection data in the past 2 hours and outputs the second type of data as an output value, and the output value is compared with the third machine inspection data obtained in the next water outlet to determine whether the values are consistent; it should be noted that, because the current environmental protection monitoring unit can set up the structure such as the water detection sensing probe at the sewage outlet, the data that it obtained are generally comparatively accurate, consequently, the source of the data can be that the environmental protection monitoring unit can set up water detection sensing probe etc. at sewage outlet for the third machine.
In the steps S3-0 to S3-2, the dynamic calculation predicts the effluent quality of the sewage in the future for several hours, so that the prediction of the effluent quality of the sewage in the future for a long time can be predicted and early warned through continuous dynamic calculation; in addition to the warning procedure caused by the above data incompleteness, normally, the output value of the steady state calculation performed every day is used as the initial value of the first dynamic calculation in the current day, and the input value of each dynamic calculation in the rest of the current day is used as the output value of the last dynamic calculation, so that the continuous prediction of the future operation condition of the sewage treatment facility and the sewage quality condition can be realized.
Referring to fig. 3, it is disclosed whether the third machine inspection data (i.e., the third machine inspection data obtained in the next water discharge in the present embodiment) in the future several hours in the determination step S3-2 matches the output value of the second type data in the future several hours, which is calculated and output by the online prediction model simulation;
if yes, the online prediction model is proved to be effective, the online prediction model and the dynamic calculation are proved to be effective, and the next dynamic calculation can be directly executed;
if not, the following step S3-2-0 is carried out:
s3-2-0, comparing the first machine inspection data with the first person inspection data, and verifying the validity of the first machine inspection data; if the first machine inspection data is not consistent with the first person inspection data, taking the first person inspection data as a reference, and maintaining the sewage treatment facility and the related probes for acquiring the first machine inspection data; if the first machine inspection data and the first person inspection data are consistent, and the second type of data which is simulated and calculated by the online prediction model through dynamic calculation in the past days is not consistent with the third machine inspection data, the dynamic calculation is invalid, and the next dynamic calculation is carried out after the parameters of the online prediction model are corrected by a professional, specifically:
referring to FIG. 3, in one embodiment, in step S3-2-0, it is first determined whether the online predictive model can obtain the first human survey data of the previous day, and if not, a warning VI is generated: "the error due to the dynamic calculation result is checked, the first person data of yesterday is lost, and the current data comparison cannot be carried out. ", and directly proceed to the next dynamic calculation.
In step S3-2-0, if the online prediction model can obtain the sound first person inspection data of the previous day, the first person inspection data of the previous day is compared with the first machine inspection data, and it is determined whether the difference between the values of the first person inspection data and the first machine inspection data exceeds 20%, for example, whether the content of common indexes such as MSLL, COD, TN, TP, TDS and the like differs by 20%.
If the difference between the first person inspection data of the previous day and the first machine inspection data exceeds 20%, generating and executing a warning V: the first person inspection data and the first machine inspection data have too large difference, so that the result of the output value of the dynamic calculation is inconsistent with the result of the third machine inspection data, and the next round of dynamic calculation is directly carried out.
If the difference between the first person inspection data and the first machine inspection data in the previous day is not more than 20%, further judging whether 40% of dynamic calculation output values in a plurality of dynamic calculations in the past 5 days are consistent with the result of the third machine inspection data, and if so, directly entering the next dynamic calculation; if not, generating a warning VII: the first person inspection data is consistent with the first machine inspection data, but the dynamic calculation result is not consistent with the third machine inspection data for multiple days, and the online prediction model needs to be maintained. And entering the next dynamic calculation after the maintenance is finished.
In the whole logic flow of the online prediction model, the step of carrying out model validity check for multiple times is carried out, the validity of the online prediction model is judged, the model maintenance is timely reminded, the phenomenon that the model enters a once-for-all technical error area after online deployment is prevented, eight different warning contents are given according to different conditions, and the model state and the data state are effectively prompted; and on the premise of effective data and effective model, the dynamic operation effect in the sewage treatment facility is predicted and early warned, so that technical management personnel of the sewage treatment facility can judge the overproof risk and the actual operation state, and can take preventive measures before problems occur.
In addition, in the logic flow, the soundness judgment of manual detection of water inlet data, operation data, sewage treatment facility operation parameter data, on-line monitoring data and the like is involved, the condition that the validity of the data is not checked during data collection is prevented, and real effective data resources are accumulated for the sewage treatment process.
The above examples are only used to illustrate the technical solutions of the present invention, and do not limit the scope of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from these embodiments without inventive step, are within the scope of the present invention. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art may still make various combinations, additions, deletions or other modifications of the features of the embodiments of the present invention according to the situation without conflict, so as to obtain different technical solutions without substantially departing from the spirit of the present invention, and these technical solutions also fall within the protection scope of the present invention.
Claims (10)
1. The method for establishing the sewage treatment comprehensive online prediction model is characterized by comprising the following steps of:
s1, establishing an accurate off-line model in the sewage treatment facility and the sewage treatment process;
s2, communicating data between the offline model and the sewage treatment information platform to form an online prediction model connected with the sewage treatment information platform, wherein the sewage treatment information platform acquires first-class data including operation parameters of a sewage treatment facility and the quality of sewage inlet water; the first type of data comprises first machine inspection data acquired by a sewage treatment facility on line and first personal inspection data acquired and detected by manpower every day;
and S3, performing simulation calculation on the first type of data by using an online prediction model, generating second type of data including a calculation result and prediction early warning information, and sharing the second type of data to a sewage treatment informatization platform.
2. The method for establishing the sewage treatment comprehensive online prediction model according to claim 1, characterized in that: in step S2, the sewage treatment information platform further obtains a third type of data including the quality of the sewage effluent, wherein the third type of data includes third machine inspection data acquired by the sewage treatment facility on line and third human inspection data acquired and detected by using manual work every day.
3. A prediction and early warning method using the sewage treatment comprehensive online prediction model according to claim 2, characterized by comprising the following substeps:
s3-0, steady state calculation: the online prediction model simulates and calculates the average value of the first person detection data in the past days to perform steady-state calculation;
s3-1, dynamic calculation: and (3) performing simulation calculation on the first inspection data in the past hours by using an online prediction model, and performing simulation calculation and outputting second type data in the future hours.
4. The prediction and early warning method of the sewage treatment comprehensive online prediction model according to claim 3, wherein the step S3-0 comprises:
s3-0-0, comparing the second type of data output by steady state calculation with the average value of the third personal inspection data in the past several days, and judging whether the second type of data is consistent with the third personal inspection data;
s3-0-1, if the online prediction model is effective, carrying out the next step of dynamic calculation;
if not, the online model is calibrated for the first time: and correcting the parameter input value of the online prediction model according to the average value of the first personal inspection data in the past several days so as to enable the comparison result to be consistent.
5. The prediction and early warning method of the sewage treatment comprehensive online prediction model according to claim 3 or 4, characterized in that: the step S3-1 is followed by the following steps:
and S3-2, performing dynamic calculation simulation calculation in the step S3-1, outputting the output value of the second class data in a plurality of hours in the future and third machine inspection data in a plurality of hours in the future, judging whether the output value is consistent with the third machine inspection data, and verifying the validity of the online prediction model again.
6. The prediction and early warning method of the sewage treatment comprehensive online prediction model according to claim 5, characterized in that: when the third machine inspection data of a plurality of hours in the future in the step S3-2 and the output value of the second type data of a plurality of hours in the future are judged to be consistent or not through simulation calculation of the online prediction model;
if yes, the online prediction model is valid;
if not, the following steps are carried out:
and S3-2-0, comparing the first machine inspection data with the first person inspection data, and verifying the validity of the first machine inspection data.
7. The prediction and early warning method of the sewage treatment comprehensive online prediction model according to claim 6, characterized in that: in step S3-2-0:
if the first machine inspection data is not consistent with the first person inspection data, taking the first person inspection data as a reference, and maintaining the sewage treatment facility for collecting the first machine inspection data;
if the first machine inspection data and the first person inspection data are consistent, and the second type of data which is simulated and calculated by the online prediction model through dynamic calculation in the past days is not consistent with the first type of data, professional personnel are required to correct the parameters of the online prediction model.
8. The prediction and early warning method of the sewage treatment comprehensive online prediction model according to claim 3, characterized in that: in the online prediction model, steady state calculations are performed once a day, and in step S3-0, the steady state calculations for each day are each used to simulate first person examination data for a period of time past the current day using the online prediction model.
9. The prediction and early warning method of the sewage treatment comprehensive online prediction model according to claim 8, characterized in that: in the daily steady-state calculation and dynamic calculation in steps S3-0 to S3-1, the result of the simulation calculation of the daily steady-state calculation is used as the input value of the first dynamic calculation in the day, and the result of the last dynamic calculation in each of the remaining dynamic calculations is used as the input value of the starting point.
10. The prediction and early warning method of the sewage treatment comprehensive online prediction model according to claim 8, characterized in that: in the daily steady state calculation of step S3-0, the first human test data within the past 30 days of the current day is simulated using the online prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310086581.4A CN115809749B (en) | 2023-02-09 | 2023-02-09 | Method for establishing comprehensive online prediction model of sewage treatment and prediction and early warning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310086581.4A CN115809749B (en) | 2023-02-09 | 2023-02-09 | Method for establishing comprehensive online prediction model of sewage treatment and prediction and early warning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115809749A true CN115809749A (en) | 2023-03-17 |
| CN115809749B CN115809749B (en) | 2023-09-12 |
Family
ID=85487705
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310086581.4A Active CN115809749B (en) | 2023-02-09 | 2023-02-09 | Method for establishing comprehensive online prediction model of sewage treatment and prediction and early warning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115809749B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117808216A (en) * | 2024-03-01 | 2024-04-02 | 四川省铁路建设有限公司 | Energy saving and emission reduction effect evaluation method for sewage treatment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110470810A (en) * | 2019-07-09 | 2019-11-19 | 中电建水环境治理技术有限公司 | Monitoring water quality method and apparatus |
| CN111125964A (en) * | 2019-12-27 | 2020-05-08 | 华东理工大学 | Sewage treatment process proxy model construction method based on kriging interpolation method |
| CN111487950A (en) * | 2020-04-24 | 2020-08-04 | 西安交通大学 | 'prediction-verification-feedback-optimization' closed-loop system for online early warning and offline diagnosis |
| CN111639881A (en) * | 2020-06-10 | 2020-09-08 | 浙江和达科技股份有限公司 | Sewage discharge treatment method and system |
| CN113033092A (en) * | 2021-03-24 | 2021-06-25 | 石化盈科信息技术有限责任公司 | Sewage treatment data processing method and device, computer equipment and storage medium |
| CN113947034A (en) * | 2021-08-26 | 2022-01-18 | 深圳市广汇源环境水务有限公司 | Smart city wading link overall process coupling simulation method |
-
2023
- 2023-02-09 CN CN202310086581.4A patent/CN115809749B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110470810A (en) * | 2019-07-09 | 2019-11-19 | 中电建水环境治理技术有限公司 | Monitoring water quality method and apparatus |
| CN111125964A (en) * | 2019-12-27 | 2020-05-08 | 华东理工大学 | Sewage treatment process proxy model construction method based on kriging interpolation method |
| CN111487950A (en) * | 2020-04-24 | 2020-08-04 | 西安交通大学 | 'prediction-verification-feedback-optimization' closed-loop system for online early warning and offline diagnosis |
| CN111639881A (en) * | 2020-06-10 | 2020-09-08 | 浙江和达科技股份有限公司 | Sewage discharge treatment method and system |
| CN113033092A (en) * | 2021-03-24 | 2021-06-25 | 石化盈科信息技术有限责任公司 | Sewage treatment data processing method and device, computer equipment and storage medium |
| CN113947034A (en) * | 2021-08-26 | 2022-01-18 | 深圳市广汇源环境水务有限公司 | Smart city wading link overall process coupling simulation method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117808216A (en) * | 2024-03-01 | 2024-04-02 | 四川省铁路建设有限公司 | Energy saving and emission reduction effect evaluation method for sewage treatment |
| CN117808216B (en) * | 2024-03-01 | 2024-05-07 | 四川省铁路建设有限公司 | Energy saving and emission reduction effect evaluation method for sewage treatment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115809749B (en) | 2023-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rieger et al. | Data Reconciliation for Wastewater Treatment Plant Simulation Studies—Planning for High‐Quality Data and Typical Sources of Errors | |
| Langergraber et al. | A guideline for simulation studies of wastewater treatment plants | |
| Rieger et al. | Progress in sensor technology-progress in process control? Part I: Sensor property investigation and classification | |
| CN110110466B (en) | Sewage treatment target parameter prediction method for machine learning and process simulation | |
| EP1801682B1 (en) | Information analysis system for water distribution and pipelines | |
| CN101261145A (en) | Water pollutant discharging gross amount intelligentized measurement method | |
| CN100514060C (en) | On-line virtual monitoring method for water chemical oxygen demand | |
| CN101839817A (en) | Experimental method for intelligent detection of poisonous and harmful gas alarm equipment and device thereof | |
| CN110186505B (en) | Method for predicting standard reaching condition of rural domestic sewage treatment facility effluent based on support vector machine | |
| CN115809749B (en) | Method for establishing comprehensive online prediction model of sewage treatment and prediction and early warning method | |
| CN110132629B (en) | Method for predicting operation effectiveness of rural domestic sewage treatment facility by using support vector machine | |
| CN117195135B (en) | Water pollution anomaly traceability detection method and system | |
| CN115470702A (en) | Sewage treatment water quality prediction method and system based on machine learning | |
| CN201680985U (en) | Intelligent detecting and testing device for poisonous and harmful gas alarm | |
| CN114531618A (en) | Data acquisition method and system for water meter collector, storage medium and intelligent terminal | |
| CN117170221A (en) | Artificial intelligence control system for sewage treatment | |
| CN115685792A (en) | Wastewater intermittent drain outlet flow triggering method and device based on flow threshold | |
| CN113533672B (en) | Water quality on-line monitoring method and device | |
| CN108760664B (en) | Water quality multi-parameter automatic detection and analysis method | |
| Pan et al. | A new approach to estimating oxygen off-gas fraction and dynamic alpha factor in aeration systems using hybrid machine learning and mechanistic models | |
| CN104502560B (en) | The chemical examination chamber system checked and accepted for Coal Quality | |
| JP2008112428A (en) | Method and apparatus for statistically predicting quality of inflow water in water disposal facility | |
| CN116187596B (en) | Method and device for predicting biochemical oxygen demand based on online data correction | |
| CN117234156A (en) | Ore dressing plant inspection system and inspection method | |
| CN109933031A (en) | A kind of system and method automatically correcting soft measuring instrument according to analysis data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |