CN117196883A - Sewage treatment decision optimization method and system based on artificial intelligence - Google Patents
Sewage treatment decision optimization method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN117196883A CN117196883A CN202311104855.4A CN202311104855A CN117196883A CN 117196883 A CN117196883 A CN 117196883A CN 202311104855 A CN202311104855 A CN 202311104855A CN 117196883 A CN117196883 A CN 117196883A
- Authority
- CN
- China
- Prior art keywords
- sewage
- treatment
- data
- sewage treatment
- artificial intelligence
- 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
- 239000010865 sewage Substances 0.000 title claims abstract description 168
- 238000011282 treatment Methods 0.000 title claims abstract description 139
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 20
- 238000005457 optimization Methods 0.000 title claims abstract description 20
- 239000000126 substance Substances 0.000 claims abstract description 30
- 239000000463 material Substances 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims description 46
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 15
- 229910001385 heavy metal Inorganic materials 0.000 claims description 13
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 12
- 230000001580 bacterial effect Effects 0.000 claims description 12
- 229910052760 oxygen Inorganic materials 0.000 claims description 12
- 239000001301 oxygen Substances 0.000 claims description 12
- 239000007787 solid Substances 0.000 claims description 10
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 9
- 230000014509 gene expression Effects 0.000 claims description 9
- 229910052698 phosphorus Inorganic materials 0.000 claims description 9
- 239000011574 phosphorus Substances 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 6
- 229910052757 nitrogen Inorganic materials 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 4
- 239000007850 fluorescent dye Substances 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 10
- 238000012546 transfer Methods 0.000 description 8
- 239000003344 environmental pollutant Substances 0.000 description 6
- 231100000719 pollutant Toxicity 0.000 description 6
- 238000012549 training Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000011221 initial treatment Methods 0.000 description 2
- 238000004659 sterilization and disinfection Methods 0.000 description 2
- 241000894006 Bacteria Species 0.000 description 1
- 230000002378 acidificating effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- -1 physical indexes Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002351 wastewater Substances 0.000 description 1
- 238000003911 water pollution Methods 0.000 description 1
Landscapes
- Activated Sludge Processes (AREA)
Abstract
The application relates to the technical field of sewage treatment, and discloses a sewage treatment decision optimization method and system based on artificial intelligence, and relates to the field of sewage treatment, wherein the method comprises the following steps: constructing a prediction model of each treatment step according to the historical sewage data and the historical sewage treatment related data; when sewage flows into a sewage plant, calculating a pollution index of the sewage and a treatment urgency index of each step, determining a treatment pool of which step to enter according to the urgency index, collecting the content of substances to be removed in the treatment step again after entering the treatment pool, and obtaining predicted treatment time and the number of materials by a prediction model; after the treatment is finished, carrying out data acquisition on the sewage again, and judging whether the sewage at the moment reaches the discharge standard or not; if the urgency of all steps is less than a threshold, the process is terminated.
Description
Technical Field
The application relates to the technical field of sewage treatment decision making, in particular to an artificial intelligence-based sewage treatment decision optimizing method and system.
Background
Along with the increasing aggravation of water resource shortage and water pollution problems, sewage treatment plants play an increasingly important role in the construction and operation of modern cities, but most of the existing sewage treatment plants depend on manual experience and follow fixed steps in the aspects of treatment and decision making, and the problems of over high energy consumption, over high operation and maintenance costs and the like can be caused because proper and accurate decisions cannot be made according to the specific conditions of sewage.
Along with the gradual strictness of sewage discharge standards, the combination of sewage treatment decision and artificial intelligence technology has become the research focus in the current sewage treatment field, and the artificial intelligence can well solve the uncertainty caused by artificial treatment, so the application provides an artificial intelligence-based sewage treatment decision optimization method and system.
Disclosure of Invention
(one) solving the technical problems
In order to solve the problem of low treatment efficiency caused by uncertain treatment time and material amount required by treatment by using the existing sewage treatment system, the error can be reduced by using a computer to control the automatic treatment of a machine, and the pressure of people is reduced.
(II) technical scheme
The application provides an artificial intelligence-based sewage treatment decision optimization method and system, which comprise the following steps:
step S1: collecting historical sewage data and historical sewage treatment related data;
step S2: establishing a prediction model according to the collected historical sewage data and the collected historical sewage treatment related data, wherein the model can carry out self-correction according to each result;
step S3: collecting real-time sewage data according to sensors inside each treatment tank whenever sewage flows into a sewage plant;
step S4: determining which treatment step the sewage enters through calculation;
step S5: the computer compares the received real-time data with the established model to obtain predicted sewage treatment related data;
step S6: corresponding treatment is carried out on each pool according to the related data of sewage treatment obtained in the previous step, such as how long to treat and how much material is put in; after the same material number as the predicted value is put in and the predicted processing time is reached, if the content of a certain substance in the processing pool still exceeds the emission index, the new data is compared with the model again, the processing operation is carried out again, and the step is permitted to be ended until the content of the substance corresponding to the processing in the processing pool is lower than the emission index.
Further, the history data is obtained from the sewage information database, and the computer can put new data into the database after receiving the new sewage data.
Specifically, the sewage data includes: sewage volume (V), solids content (TS), chemical Oxygen Demand (COD), biochemical Oxygen Demand (BOD), total Nitrogen (TN), total Phosphorus (TP), pH, heavy metal content, and bacterial count; the sewage treatment related data includes: the processing time per step and the amount of material required per step.
Further, the prediction model is a model capable of predicting sewage treatment time and required material number according to the sewage internal data, and four different models are respectively built according to four steps of sewage treatment.
Further, the various sensors are respectively placed in the processing pools of the corresponding processing modules, and the inlet and the outlet of each processing pool are provided with the same sensor.
Specifically, the sewage volume is obtained through height calculation; the solid content is measured by a suspended matter detector; the BOD and the COD are measured by a vacuum ultraviolet spectrophotometer BOD/COD detector; TN and TP are measured by a total nitrogen/total phosphorus on-line monitor; the pH is measured by a sensor-type pH meter; the heavy metal content is measured by an electrochemical heavy metal detector; the bacterial count is measured by a fluorescent probe-based bacterial detection instrument.
Further, the pollution index c of the sewage is calculated according to the measured data by recording the solid content ts, the pH value pH, the chemical oxygen demand cod, the biochemical oxygen demand bod, the total nitrogen tn, the total phosphorus tp, the heavy metal content zj and the bacterial count xj, and the pollution index c of the sewage is increased due to the fact that the pH value is too high or too low, when the pH value pH of the sewage is more than 5, the expression of the pollution index c of the sewage is as follows:
c＝α 1 ts+α 2 ph+α 3 cod+α 4 bod+α 5 tn+α 6 tp+α 7 zj+α 8 xj
when the pH value pH of the sewage is less than 5, the sewage pollution index c is expressed as follows:
wherein alpha is 1 To alpha 8 Respectively the preset proportional coefficients of the corresponding object mass, and alpha 1 ，…，α 8 >0,α 1 +……+α 8 ＝1。
Further, the influence degree c of the substances treated in each treatment step on the sewage is calculated respectively 1 、c 2 、c 3 And c 4 The calculation expressions are respectively: c 2 ＝α 3 cod+α 4 bod+α 5 tn+α 6 tp、c 3 ＝α 7 zj、c 4 ＝α 8 xj, when ph>5, c 1 ＝α 1 ts+α 2 ph; when ph<At the time of 5 a,
further, dividing the calculated influence levels by the sewage pollution index to obtain the treatment urgency lambda of each step i The calculation expressions are respectively:
further, lambda is set i Ordered in order of increasing size, maximum lambda i The corresponding steps are preferentially carried out, and sewage flows into the corresponding sewage treatment tanks.
If in a certain calculation, all lambda i Less than 0.05, the whole process flow is ended.
Further, an artificial intelligence-based sewage treatment decision optimization system is characterized by comprising:
the prediction unit is used for collecting historical sewage data and historical sewage treatment related data, establishing a prediction model according to the collected historical sewage data and the collected historical sewage treatment related data, and performing self-correction according to each result;
the monitoring unit is used for collecting real-time sewage data according to the sensors in each treatment tank when sewage flows into the sewage plant, and determining the treatment step to which the sewage is to enter through calculation;
the data processing unit is used for comparing the received real-time data with the established model to obtain predicted sewage treatment related data;
and the processing unit is used for carrying out corresponding processing on each pool according to the obtained related data of sewage treatment, after the materials with the same predicted value are put in and reach the predicted processing time, if the content of a certain substance in the processing pool still exceeds the emission index, the new data are compared with the model again and the processing operation is carried out again until the content of the substance which is correspondingly processed in the processing pool is lower than the emission index.
(III) beneficial effects
The application provides an artificial intelligence-based sewage treatment decision optimization method and system, which have the following beneficial effects:
and collecting historical data and establishing a prediction model, so that the sewage treatment related data can be predicted through new sewage data. When sewage enters a sewage plant, the sewage firstly enters a buffer pool, the treatment urgency of each pollutant in the sewage at the moment is calculated, and the entering of the sewage into which treatment pool is firstly determined according to the treatment urgency. After entering the sewage pool, a sensor of the water inlet transmits the measured pollution index to a computer and substitutes the pollution index into a prediction model to obtain predicted processing time and processed material quantity, and the machine automatically processes according to the result; and after the treatment time is over, detecting whether the pollutant content reaches the emission index again at the water outlet. After the processing is finished, returning to the buffer pool again for selecting the next processing step.
Compared with the traditional sewage treatment, the sewage treatment provided by the application is added with the buffer pool for judging the treatment steps, and if pollutants which do not need to be treated exist, the corresponding treatment steps can be skipped, so that the treatment time is saved; in the processing process, the water outlet and the water inlet are provided with the same sensor, and the water outlet and the water inlet are used for collecting data, so that predicted processing time and processing required material quantity are obtained, and compared with traditional manual experience, the processing time and the processing required material quantity are more accurate, and the processing efficiency is improved.
Drawings
FIG. 1 is a schematic flow chart of a decision optimization method for sewage treatment according to the application;
FIG. 2 is a schematic diagram of a sewage treatment decision optimization system architecture according to the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The normal sewage treatment is carried out sequentially according to the determined treatment sequence, but if the content of certain pollutants does not exceed the emission index, the corresponding treatment is not needed; and the time of each step of sewage treatment and the amount of materials to be put in can produce certain errors because of manual operation, so that the sewage treatment efficiency can be low, and the treatment cost can be high. The application carries out decision-making optimization based on four steps of normal sewage treatment to improve the sewage treatment efficiency, reduce the sewage treatment cost,
referring to fig. 1, the application relates to an artificial intelligence-based sewage treatment decision optimization method, which comprises the following steps:
1. and collecting historical data, searching a sewage treatment database, and collecting historical sewage information data and treatment information data, wherein the historical data is used for building a prediction model.
The sewage information data refer to the content of each substance in sewage, including physical indexes, chemical indexes and biological indexes. The physical indexes comprise sewage volume (V), solid content (TS) and the like; the chemical index comprises Chemical Oxygen Demand (COD), biochemical Oxygen Demand (BOD), total Nitrogen (TN), total Phosphorus (TP), pH value, heavy metal content and the like; the biological index comprises: bacterial count, etc. The treatment information data refer to various parameters of sewage during treatment, specifically time t used in a certain step, material quantity m consumed in a certain step and the like, and the data are used for evaluating the working efficiency of each flow and are also important bases for optimizing sewage decision.
2. And (3) establishing a prediction model: establishing a prediction model according to the collected historical data, wherein the model can be realized: when sewage data is input, simulation calculation can be performed according to the model, so that the time required by ideal treatment of each flow and the ideal consumed energy and material quantity are obtained.
And selecting the content of each substance in the sewage in the last 150 times of sewage in the historical data, and correspondingly the time, the energy consumption and the material consumption of each step.
According to the collected data, cleaning and preprocessing the data, specifically:
deleting duplicate values: deleting the repeated data value in the data, and only reserving the first piece of data of the repeated data;
missing value processing: the original data may have missing data values, which affect the result during data analysis and require the missing data values to be complemented;
and (3) carrying out unification treatment: when the standard of the data of a certain data column is inconsistent or the naming rule is inconsistent in the data set, splitting the data value in the inconsistent data column by using a column splitting function;
outlier processing: the outlier is corrected based on the average of the two observations.
The purpose of this step is to remove the error values and noise in the data, making the data more accurate. The processed data totaled 100 groups.
The collected historical data are divided into four types according to four steps of sewage treatment, and the four types of the collected historical data are respectively classified into four modules:
the primary processing module: including solids content and pH data, and the time and materials consumed for the corresponding primary treatment.
Biological treatment module: including BOD content, COD content, TN content, and TP content, and the time and materials consumed for the corresponding biological treatment.
And the depth processing module is used for: including heavy metal content, and the time and materials consumed for the corresponding advanced treatment.
And a disinfection treatment module: including the number of bacteria, and the time and materials consumed for the corresponding disinfection process.
The data of each module is divided into a training set and a testing set according to the proportion of 8:2, and the training set and the testing set are used for training the model and verifying the accuracy of the model.
A predictive model is built for each of these four modules, which predictive model requires the prediction of the time required for the respective treatment and the consumption of the substance in accordance with the content of the substance. In particular, after predicting the time and the amount of material consumption required for the treatment of each material in the primary treatment module and the biological treatment module, several results are combined to obtain the total time and the total amount of material consumption required for the treatment in this step. Therefore, the deep neural network model is selected, the method is suitable for large-scale data and complex problems, the training set is used for training the neural network model, errors are calculated according to the prediction result, and weights among neurons are adjusted, so that the errors are minimized.
The performance of the neural network model is optimized through the means of cross validation, learning rate adjustment, regularization and the like.
And testing the trained neural network model by using a test set, predicting the relation between the content of substances in sewage and the treatment time and the consumption of the substances, and evaluating the accuracy of the model.
The model can realize self-optimization through an error back propagation algorithm, and after the model calculates an output result through forward transmission, the output result is compared with a target value to obtain an error value. The error values are then back propagated to the network, the contribution of each layer to the error is calculated, and the parameter values are updated according to the magnitude of each parameter contribution to the error.
3. Acquisition and transfer of real-time data: before sewage enters a sewage plant for receiving treatment, the sewage needs to enter a buffer pool, and various sensors and measuring instruments are arranged in the buffer pool to measure the substance components in the sewage in real time.
Each detecting instrument and each sensor are respectively arranged at the water inlet and the water outlet of the corresponding processing pool, the purpose of arranging the detecting instrument and the sensor at the water inlet is to collect data, and the data are substituted into the prediction model to obtain predicted processing information; the purpose of the outlet placement detection instrument and sensor is to determine whether the material currently being processed in the processing cell meets the emission standards.
The solid content is measured by a suspended matter detector; the BOD and the COD are measured by a vacuum ultraviolet spectrophotometer BOD/COD detector; TN and TP are measured by a total nitrogen/total phosphorus on-line monitor; the pH is measured by a sensor-type pH meter; the heavy metal content is measured by an electrochemical heavy metal detector; the bacterial count is measured by a fluorescent probe-based bacterial detection instrument.
Because of more data types, the system adopts a transfer station mode to transmit data.
Firstly, proper transfer station equipment needs to be selected, and the router is selected as the transfer station equipment, so that the router has the advantages of high stability, high transmission speed, long transmission distance, easiness in installation and configuration, good compatibility and the like.
The sensor is linked to the collector and the controller by adopting a standard communication interface and a standard connection mode. The collector and the controller can automatically identify the transfer station equipment and upload data to the transfer station.
The transfer station needs to process the received data, including data item compression, format conversion, data screening, etc., so that the efficiency of data transmission is higher and more reliable.
The transfer station can transmit data to the computer in a 5G mode so as to facilitate the processing and analysis of the data.
4. Sewage treatment decision: after receiving the real-time sewage data, the computer calculates the pollution index of the sewage according to the formula. Recording the solid content ts, the pH value pH, the chemical oxygen demand cod, the biochemical oxygen demand bod, the total nitrogen tn, the total phosphorus tp, the heavy metal content zj and the bacterial number xj, and calculating the pollution index c of the sewage according to the measured data, wherein the pollution index of the sewage is increased due to the fact that the pH value is too high or too low, the pH threshold value is set to be 5, and when the pH value is larger than 5, the alkaline influence of the sewage is considered; when the pH value is less than 5, the acidic influence of the sewage is considered. So when pH of sewage >5, the expression of sewage pollution index c is:
c＝α 1 ts+α 2 ph+α 3 cod+α 4 bod+α 5 tn+α 6 tp+α 7 zj+α 8 xj
when the pH value pH of the sewage is less than 5, the sewage pollution index c is expressed as follows:
wherein alpha is 1 To alpha 8 Respectively the preset proportional coefficients of the corresponding object mass, and alpha 1 ，…，α 8 >0,α 1 +……+α 8 ＝1。
The influence degree c of the substances treated by each treatment step on the sewage is calculated respectively 1 、c 2 、c 3 And c 4 The calculation expressions are respectively: c 2 ＝α 3 cod+α 4 bod+α 5 tn+α 6 tp、c 3 ＝α 7 zj、c 4 ＝α 8 xj, when ph>5, c 1 ＝α 1 ts+α 2 ph; when ph<At the time of 5 a,
dividing the calculated influence degree by the sewage pollution index to obtain the treatment urgency lambda of each step i The calculation expressions are respectively:
lambda is set to i Ordered in order of increasing size, maximum lambda i The corresponding steps are preferentially carried out, and sewage flows into the corresponding sewage treatment tanks.
5. And (3) sewage treatment: after sewage flows into the treatment pool, all substances in the sewage can be measured in real time through the sensor and the detection equipment at the inlet and are transmitted to the data processing unit through the router, and the computer in the data processing unit substitutes the received data into the prediction model to obtain the predicted values of the treatment time and the material quantity required by treatment.
The computer communicates this predicted value to various machines, which operate accordingly based on the predicted value. After these operations are completed, the sensors and detection devices at the outlet monitor the data of the substances in the sewage and transmit them to the computer, which compares them with the emission standards, and if there are substances exceeding the emission standards, substitutes them again into the model and transmits the predicted values to the various machines. This step is cycled until every substance in the treatment step does not exceed the discharge criteria, allowing the wastewater to leave the treatment area.
The separated sewage is returned to the buffer tank, and the pollution index c of the sewage and the measured treatment urgency lambda of each step are carried out again i Is selected again to the maximum lambda i And carrying out corresponding processing steps. If in a certain calculation, all lambda i Less than 0.05, the whole process flow is ended.
The application changes the traditional sewage treatment flow, determines the current treatment step by calculating the treatment urgency of each pollutant, avoids carrying out the corresponding treatment step when the content of certain pollutants is too small, and reduces the sewage treatment time; the system calculates the processing time and the material consumption of each processing step according to the prediction model and informs the machine to perform corresponding operation, thereby reducing errors caused by manual operation and greatly increasing the sewage treatment efficiency.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application.
Claims (9)
1. The sewage treatment decision optimization method based on artificial intelligence is characterized by comprising the following steps of:
collecting historical sewage data and historical sewage treatment related data; establishing a prediction model according to the collected historical sewage data and the collected historical sewage treatment related data, and performing self-correction according to each result by the prediction model;
collecting real-time sewage data according to sensors inside each treatment tank whenever sewage flows into a sewage plant; determining which treatment step the sewage enters through calculation; the computer compares the received real-time data with the established model to obtain predicted sewage treatment related data;
and (3) carrying out corresponding treatment on each pool according to the obtained related data of sewage treatment, putting materials with the same predicted value into the pool, and after reaching the predicted treatment time, if the content of a certain substance in the treatment pool still exceeds the emission index, comparing the new data with the model again, and carrying out treatment operation again until the content of the corresponding treated substance in the treatment pool is lower than the emission index, and ending the step.
2. The artificial intelligence based sewage treatment decision optimization method of claim 1, wherein the historical sewage data is obtained from a sewage information database, and the computer subsequently receives new sewage data and then places the new data in the database.
3. The artificial intelligence based sewage treatment decision optimization method of claim 1, wherein the sewage data comprises: sewage volume (V), solids content (TS), chemical Oxygen Demand (COD), biochemical Oxygen Demand (BOD), total Nitrogen (TN), total Phosphorus (TP), pH, heavy metal content, and bacterial count; the sewage treatment related data includes: the processing time per step and the amount of material required per step.
4. The artificial intelligence-based sewage treatment decision optimization method according to claim 1, wherein corresponding prediction models are respectively established according to the sewage treatment steps; by placing the various sensors into the corresponding treatment tanks, the inlet and outlet of the treatment tanks are provided with the same sensor.
5. The artificial intelligence based sewage treatment decision optimization method according to claim 4, wherein the solid content is measured by a suspended matter detector; the BOD and the COD are measured by a vacuum ultraviolet spectrophotometer BOD/COD detector; TN and TP are measured by a total nitrogen/total phosphorus on-line monitor; the pH is measured by a sensor-type pH meter; the heavy metal content is measured by an electrochemical heavy metal detector; the bacterial count is measured by a fluorescent probe-based bacterial detection instrument.
6. The artificial intelligence based sewage treatment decision optimization method according to claim 1, wherein the method for the treatment flow decision is as follows:
recording the solid content ts, the pH value pH, the chemical oxygen demand cod, the biochemical oxygen demand bod, the total nitrogen tn, the total phosphorus tp, the heavy metal content zj and the bacterial number xj, calculating the pollution index c of the sewage according to the measured data, and when the pH value pH of the sewage is more than 5, the expression of the pollution index c of the sewage is as follows:
c＝α 1 ts+α 2 ph+α 3 cod+α 4 bod+α 5 tn+α 6 tp+α 7 zj+α 8 xj
when the pH value pH of the sewage is less than 5, the sewage pollution index c is expressed as follows:
wherein alpha is 1 To alpha 8 Respectively corresponding substancesA preset proportionality coefficient of the quantity, and alpha 1 ，…，α 8 >0,α 1 +……+α 8 ＝1。
7. The artificial intelligence based sewage treatment decision optimizing method of claim 6, wherein the influence degree c of each treatment step on the sewage is calculated based on the treated matters 1 、c 2 、c 3 And c 4 The calculation expressions are respectively: c 2 ＝α 3 cod+α 4 bod+α 5 tn+α 6 tp、c 3 ＝α 7 zj、c 4 ＝α 8 xj, when ph>5, c 1 ＝α 1 ts+α 2 ph; when ph<At the time of 5 a,
8. the artificial intelligence-based sewage treatment decision optimization method according to claim 7, wherein,
dividing the calculated influence degree by the sewage pollution index to obtain the treatment urgency lambda of each step i The calculation expressions are respectively:
lambda is set to i Ordered in order of increasing size, maximum lambda i The corresponding steps are preferentially carried out, and sewage flows into the corresponding sewage treatment tanks; if in a certain calculation, all lambda i All are smaller than 0.05, and the whole process flow is finished.
9. An artificial intelligence-based sewage treatment decision optimization system, comprising:
the prediction unit is used for collecting historical sewage data and historical sewage treatment related data, establishing a prediction model according to the collected historical sewage data and the collected historical sewage treatment related data, and performing self-correction according to each result;
the monitoring unit is used for collecting real-time sewage data according to the sensors in each treatment tank when sewage flows into the sewage plant, and determining the treatment step to which the sewage is to enter through calculation;
the data processing unit is used for comparing the received real-time data with the established model to obtain predicted sewage treatment related data;
and the processing unit is used for carrying out corresponding processing on each pool according to the obtained related data of sewage treatment, after the materials with the same predicted value are put in and reach the predicted processing time, if the content of a certain substance in the processing pool still exceeds the emission index, the new data are compared with the model again and the processing operation is carried out again until the content of the substance which is correspondingly processed in the processing pool is lower than the emission index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311104855.4A CN117196883A (en) | 2023-08-29 | 2023-08-29 | Sewage treatment decision optimization method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311104855.4A CN117196883A (en) | 2023-08-29 | 2023-08-29 | Sewage treatment decision optimization method and system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117196883A true CN117196883A (en) | 2023-12-08 |
Family
ID=88984281
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311104855.4A Pending CN117196883A (en) | 2023-08-29 | 2023-08-29 | Sewage treatment decision optimization method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117196883A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117964024A (en) * | 2024-04-02 | 2024-05-03 | 车泊喜智能科技(山东)有限公司 | Car washing wastewater purification treatment control system based on artificial intelligence |
-
2023
- 2023-08-29 CN CN202311104855.4A patent/CN117196883A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117964024A (en) * | 2024-04-02 | 2024-05-03 | 车泊喜智能科技(山东)有限公司 | Car washing wastewater purification treatment control system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109408774B (en) | Method for predicting sewage effluent index based on random forest and gradient lifting tree | |
| US20220082545A1 (en) | Total Nitrogen Intelligent Detection Method Based on Multi-objective Optimized Fuzzy Neural Network | |
| CN110824915B (en) | GA-DBN network-based intelligent monitoring method and system for wastewater treatment | |
| CN109828089B (en) | DBN-BP-based water quality parameter nitrous acid nitrogen online prediction method | |
| CN107402586A (en) | Dissolved Oxygen concentration Control method and system based on deep neural network | |
| CN111414694A (en) | Sewage monitoring system based on FCM and BP algorithm and establishment method thereof | |
| CN110889085A (en) | Intelligent wastewater monitoring method and system based on complex network multiple online regression | |
| CN104376380A (en) | Ammonia concentration predicting method based on recursion self-organization neural network | |
| CN108562709A (en) | A kind of sewage disposal system water quality monitoring method for early warning based on convolution self-encoding encoder extreme learning machine | |
| CN117196883A (en) | Sewage treatment decision optimization method and system based on artificial intelligence | |
| CN113011661A (en) | Aeration control system for river ecological restoration and control method thereof | |
| CN114037163A (en) | Sewage treatment effluent quality early warning method based on dynamic weight PSO (particle swarm optimization) optimization BP (Back propagation) neural network | |
| CN111693667A (en) | Water quality detection system and method based on gated recursive array | |
| CN106706491B (en) | Intelligent detection method for membrane bioreactor-MBR water permeability | |
| CN114169242A (en) | Intelligent control algorithm for analyzing ecological oxygenation of river channel based on parameter uncertainty | |
| CN115396981A (en) | Intelligent monitoring system based on big data technology | |
| CN114858207A (en) | Soft measurement-based gridding source tracing investigation method for drain outlet of river channel | |
| CN110057410B (en) | Method and device for measuring and calculating pollutant production of daily domestic sewage of per capita | |
| CN111125907A (en) | Sewage treatment ammonia nitrogen soft measurement method based on hybrid intelligent model | |
| CN114119277A (en) | Artificial intelligent neural network-based flocculation dosing decision analysis method | |
| CN105372995A (en) | Measurement and control method for sewage disposal system | |
| CN106769748B (en) | Intelligent detection system for water permeability of membrane bioreactor-MBR (Membrane bioreactor) | |
| CN117170221A (en) | Artificial intelligence control system for sewage treatment | |
| CN117057668A (en) | Industrial pollutant emission prediction method based on deep learning model | |
| CN112070317A (en) | Hotel air conditioner energy consumption prediction method |
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 |