CN115826509A - Control method, control device, electronic equipment and storage medium - Google Patents
Control method, control device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115826509A CN115826509A CN202211177193.9A CN202211177193A CN115826509A CN 115826509 A CN115826509 A CN 115826509A CN 202211177193 A CN202211177193 A CN 202211177193A CN 115826509 A CN115826509 A CN 115826509A
- Authority
- CN
- China
- Prior art keywords
- index
- discharge
- sewage discharge
- data
- target
- 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
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)
Abstract
The application discloses a control method, a control device, electronic equipment and a storage medium, relates to the technical field of sewage treatment, and comprises the following steps: acquiring a first effluent index of a target upstream sewage discharge point; inputting the first water outlet index into a pre-established neural network prediction model to predict the water quality index of a downstream water inlet of a sewage treatment plant; the operation of the sewage treatment plant is controlled based on the water quality index, the water quality impact which possibly occurs in the downstream can be predicted in advance according to the water quality index, the condition that the upstream sewage discharge point exceeds the standard for sewage discharge can be predicted according to the random forest model, and the operation load of the sewage treatment plant can be controlled to deal with the upstream sewage discharge condition.
Description
Technical Field
The application relates to the technical field of sewage treatment, in particular to a control method, a control device, electronic equipment and a storage medium.
Background
The domestic sewage treatment plant is generally lack of sewage source supervision, operation management is mainly based on experience, technological parameters cannot be optimized and adjusted in time according to the fluctuation of inlet water quality and water quantity, the load impact level of pollutants is weak, and intelligent diagnosis cannot be carried out on operation conditions. When the pollutants generate large impact, the water quality of the effluent at the downstream of the sewage system may not reach the discharge index.
Disclosure of Invention
In view of the above problems, the present application provides a control method, an apparatus, an electronic device, and a storage medium, which can realize prediction of downstream sewage impact through a neural network prediction model after acquiring upstream sewage data, and control operation of a sewage treatment plant, thereby improving an intelligent treatment level of sewage.
In a first aspect, an embodiment of the present application provides a control method, including: acquiring a first effluent index of a target upstream sewage discharge point; inputting the first water outlet index into a pre-established neural network prediction model to predict the water quality index of a downstream water inlet of a sewage treatment plant; and controlling the operation of the sewage treatment plant based on the water quality index.
In a second aspect, an embodiment of the present application provides a control apparatus, including: the acquisition module is used for acquiring a first effluent index of a target upstream sewage discharge point. And the prediction module is used for inputting the first water outlet index into a pre-established neural network prediction model so as to predict the water quality index of a downstream water inlet of a sewage treatment plant. And the control module is used for controlling the operation of the sewage treatment plant based on the water quality index.
In a third aspect, an embodiment of the present application provides an electronic device, including: at least one processor and memory; the processor is configured to execute the computer program stored in the memory to implement the control method as described in any one of the embodiments of the first aspect.
In a fourth aspect, an embodiment of the present application provides a computer storage medium, where one or more programs are stored, and the one or more programs are executable by the electronic device described in the third aspect to implement the control method described in any one of the embodiments of the first aspect.
According to the control method, the control device, the electronic equipment and the storage medium, the first effluent index of the target upstream sewage discharge point is obtained and input into the pre-established neural network model to predict the water quality index of the downstream water inlet of the sewage treatment plant, so that sewage impact is rapidly diagnosed, finally, the operation of the sewage treatment plant is controlled based on the water quality index, so that the downstream impact can be effectively predicted according to the upstream pollutant inflow, and the operation of the sewage treatment plant can be scheduled in advance.
It should be understood that the statements in this section are not intended to identify key or critical features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become apparent from the following description.
Drawings
The present application will be described in more detail below on the basis of embodiments and with reference to the accompanying drawings.
Fig. 1 shows a schematic flow chart of a control method proposed in an embodiment of the present application;
fig. 2 shows a schematic flow chart of another control method proposed in an embodiment of the present application;
fig. 3 shows a flow chart of a control method step S250 proposed in an embodiment of the present application;
FIG. 4 is a schematic view showing a discharge map of salt-containing wastewater according to an embodiment of the present application;
FIG. 5 is a diagram illustrating a neural network layer in a neural network prediction model according to an embodiment of the present application;
FIG. 6 is a schematic diagram illustrating the predicted and measured values of the pH of the saline pipe network proposed in an embodiment of the present application;
fig. 7 is a block diagram showing a configuration of a control apparatus proposed in an embodiment of the present application;
fig. 8 shows a block diagram of an electronic device proposed in an embodiment of the present application for executing a control method according to an embodiment of the present application;
fig. 9 illustrates a computer-readable storage medium proposed in an embodiment of the present application for storing or carrying a program for implementing a control method according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
In the correlation technique, considering that the sources of pollutants in an industrial sewage system are complex and various, and the types of pollutants mostly depend on the attributes of production raw materials, standardized management and control are difficult to perform from the sources. Based on the particularity of the industrial sewage system and multivariable and complex influence relations in the sewage system, the traditional hydrodynamic force mathematical model is difficult to process complex nonlinear multivariable relations and to quickly diagnose the incoming water impact.
In view of the above problems, the applicant proposes a control method, an apparatus, an electronic device and a storage medium according to embodiments of the present application, and by using a neural network technology, after a first effluent index of a target upstream sewage discharge point is obtained, a water quality index of a downstream water inlet of a sewage treatment plant is quickly predicted, and a prediction of water quality impact that may occur in a downstream may be performed in advance according to the water quality index, and the operation of the sewage treatment plant may be controlled to cope with an upstream sewage discharge situation. The control method is explained in detail in the following embodiments.
The following is introduced for an application scenario of the control method provided in the embodiment of the present application:
referring to fig. 1, fig. 1 is a schematic flow chart of a control method provided in an embodiment of the present application, in the embodiment, the control method may be applied to a control apparatus 800 shown in fig. 8 and an electronic device 200 (fig. 9), where the electronic device may be an intelligent terminal such as a desktop computer, a tablet computer, a smartphone, and the like, where the electronic device may include one or more electronic devices, information may be transmitted between the plurality of electronic devices in a wireless and/or wired manner, the plurality of electronic devices may cooperatively complete the control method, exemplarily, data is collected and interacted between upstream and downstream, and a flow of the control method is completed according to the collected data, and the electronic device may further include a server and a cloud server, and the like to store and process data obtained from upstream and downstream so as to provide data for analysis and prediction of a sewage treatment plant, where a water quality test analysis may be entered into an LIMS system, and reading of the data may be completed by the LIMS system. The control method may include steps S110 to S130.
Step S110: and acquiring a first effluent index of a target upstream sewage discharge point.
In the embodiment of the application, in the process of obtaining the first effluent index, the electronic device may collect detailed parameters such as process parameters of each upstream sewage discharge point and sewage discharge control indexes. Illustratively, the collection of the sewage discharge amount, the liquid level and the like of each oil-containing sewage discharge point can be included. Meanwhile, the first effluent indexes of all the sewage discharge points can be analyzed, and as a mode, the target upstream sewage discharge point can be confirmed through collected detailed information such as process parameters, sewage discharge control indexes and the like.
It should be noted that the first effluent index may include effluent indexes such as COD, petroleum, PH, and the like, where COD refers to chemical oxygen demand, that is, the amount of reducing substances to be oxidized in the water sample is measured.
Step S120: and inputting the first water outlet index into a pre-established neural network prediction model so as to predict the water quality index of a downstream water inlet of the sewage treatment plant.
In the embodiment of the application, a neural network prediction model is pre-established, after upstream related data are collected at each target upstream sewage discharge point, the data can be input into the neural network prediction model through electronic equipment to obtain a predicted value corresponding to a water quality index of a downstream water inlet, wherein the collected upstream sewage discharge point data can be directly collected by measurement equipment and then transmitted into the electronic equipment in real time, or after being processed by the measurement equipment, the collected upstream sewage discharge point data can be input into the electronic equipment according to a key water quality index screened and confirmed by a user to obtain a predicted value required by the user and a prediction function.
Step S130: and controlling the operation of the sewage treatment plant based on the water quality index.
In the embodiment of the application, after the water quality index number is obtained, the treatment standard of the sewage treatment plant can be adjusted and controlled by combining the water quality index to ensure that the effluent reaches the required index.
In the embodiment, considering the influence of the upstream sewage discharge point on the water quality of the downstream treatment field in the sewage treatment process, and combining the characteristic that the sewage discharge has hysteresis, the obtained first water outlet index of the target upstream sewage discharge point is input into the neural network prediction model to predict the water quality index of the downstream water inlet in advance, so as to provide support and basis for managing the sewage treatment plant in advance, and when large sewage impact is generated upstream, the sewage treatment plant is adjusted and controlled in time to ensure the downstream water quality index.
Referring to fig. 2, fig. 2 is another schematic flow chart of a control method provided in the present embodiment, and the method is applied to an electronic device and may include steps S210 to S270.
Step S210: acquiring a discharge map, first sewage discharge data of an upstream sewage discharge point and second sewage discharge data of a downstream water inlet;
in this application embodiment, the discharge map of the oily and saline sewage may be formed by obtaining the discharge map according to the upstream and downstream production operation characteristics of the sewage, the discharge trend and the discharge rule of the oily and saline sewage, referring to fig. 4, fig. 4 is a schematic diagram of the discharge map of the saline sewage in this application embodiment, and the connection relationship between the saline and oily sewage pipe network and the upstream sewage treatment plant is formed by each node of the upstream sewage discharge point and each node of the downstream sewage discharge point. The first sewage discharge data of the upstream sewage discharge point and the second sewage discharge data of the downstream water inlet can be acquired or stored data values in real time based on each upstream acquisition device and each downstream acquisition device.
As an embodiment, the discharge map of the oil-containing and salt-containing wastewater may be drawn based on the upstream discharge point, the upstream discharge information of the oil-containing and salt-containing wastewater, and based on the discharge flow direction, for example, the number of sampling points of the water quality index of the oil-containing and salt-containing wastewater may be counted, respectively, for example, the number of COD water quality analyses, the number of petroleum water quality analyses, the number of PH value water quality analyses, and other parameters may be counted.
Step S220: an upstream sewage discharge point and a downstream water inlet are identified based on the discharge map.
In the embodiment of the application, the discharge information of the upstream oil-containing and salt-containing sewage discharge points can be counted according to the discharge map so as to confirm the number of sampling points of the upstream sewage discharge points and the number of the downstream water inlets.
Step S230: and determining the association relationship between the upstream sewage discharge point and the downstream water inlet based on the upstream sewage discharge point, the downstream water inlet, the first sewage discharge data and the second sewage discharge data.
In this application embodiment, the incidence relation between the upstream sewage discharge point and the downstream sewage discharge point can be confirmed according to the collected first sewage discharge data and the second sewage discharge data, that is, the upstream sewage discharge point is connected with the downstream sewage discharge point correspondingly, the sewage treatment capacity is equal, and the downstream sewage discharge point corresponds to the upstream sewage discharge points in quantity.
Step S240: based on the correlation, a target upstream sewage discharge point is determined from the upstream sewage discharge points.
In the embodiment of the application, after the association relationship is confirmed, the upstream sewage discharge points are screened to determine the main target upstream sewage discharge points affecting the corresponding downstream water inlets, so as to reduce the data calculation amount.
Step S250: an association between a discharge index of the target upstream sewage discharge point and a discharge index of the downstream water inlet is determined based on the first sewage discharge data and the second sewage discharge data.
In the embodiment of the application, after the target upstream sewage discharge point is confirmed, the discharge index of the target upstream sewage discharge point and the corresponding discharge index of the downstream water inlet are determined, and the appropriate discharge index requirement is obtained according to the corresponding discharge indexes of the upstream and the downstream.
Step S260: the target emission index is confirmed based on the correlation.
Step S270: and determining a neural network prediction model based on third sewage discharge data corresponding to a target discharge index of a target upstream sewage discharge point and fourth sewage discharge data corresponding to a water quality index of a downstream water inlet, wherein the target discharge index is a water outlet index.
In the embodiment of the application, the neural network prediction model is confirmed by the screened and correlated third sewage discharge data of the upstream sewage discharge point and the fourth sewage discharge data of the downstream water inlet, so that interference data are reduced, and the model is ensured to have more accurate recognition degree.
In the embodiment, the constructed discharge map and the incidence relation between the upstream discharge point and the downstream water inlet are obtained to screen the sewage discharge point, the incidence is constructed, the map is constructed for the whole data to be visually analyzed, inquired and explored, the water quality index analysis frequency is arranged, the integrity and the accuracy of the data are checked, the target discharge data of the target upstream discharge point and the target discharge data of the downstream water outlet are ensured to confirm the neural network prediction model, and the accuracy of the neural network prediction model is ensured.
The embodiments of the present application are further limited in consideration of the problem that the upstream sewage discharge point has an excessive risk.
In some embodiments, the control method provided in the embodiment of the present application may further include step S112 to step S114.
Step S112: and selecting a target evaluation index in the first effluent indexes, wherein the target evaluation index is an index influencing the pollution of the oil-containing and/or salt-containing water quality of the upstream sewage discharge point.
In the embodiment of the application, a target evaluation index can be selected according to the sewage discharge condition and the actual condition on site, wherein the target evaluation index can comprise the constructed water quantity/day, the discharge time, the discharge frequency, the water quality exceeding time, the water quality exceeding frequency, the discharge point pollution discharge equivalent, the water quality fault tolerance rate and the like. As an evaluation index for tracing the pollution situation.
In some embodiments, all upstream sewage discharge points can be used as tracing high-risk pollution source nodes according to the target evaluation index, and the situation can be analyzed and the data situation can be obtained through actual sampling.
It should be noted that the target evaluation index determined to participate in the tracing may include a water quality analysis index, where the water quality analysis index may include COD, petroleum, ammonia nitrogen, and the like.
In the embodiment of the application, the average index of each upstream sewage discharge point and the qualified or standard exceeding conditions of the water quality of the water inlets containing the oil and salt sewage can be counted through the real-time database and LIMS sampling analysis data of each upstream sewage discharge point
Step S114: and predicting target upstream sewage discharge points corresponding to the high-risk pollution sources based on the random forest algorithm model, and determining the sequence of the target upstream sewage discharge points corresponding to the high-risk pollution sources.
In the embodiment of the application, the water quantity/day, the discharge time, the discharge times, the water quality exceeding time, the water quality exceeding times, the discharge point pollution discharge equivalent, the water quality fault tolerance and the like can be input into a random forest algorithm model to respectively analyze the influence of the parameters on the effluent water quality indexes of the oil-containing and salt-containing sewage pipe networks. The high-risk pollution source node information when the water quality of the water inlet of the sewage treatment plant exceeds the standard can be confirmed, and the high-risk pollution conditions can be sequenced to determine corresponding discharge points and pollution severity.
Illustratively, the COD exceeding influence factors of the salt-containing sewage pipe network outlet are ranked as follows: the water volume/day of the No. 1 oil separation tank, the COD pollution discharge equivalent of the No. 1 oil separation tank, the WT019 flow length, the WT019 water volume/day, the WT019 intermittent discharge times, the 3# sewage stripping COD superscalar times, the WT005 petroleum overproof times, the WT005COD and the like. Based on the above, the list of the high-risk pollution source nodes when the COD of the salt-containing pipe network outlet exceeds the standard can be determined through a principal component analysis method and sequenced.
In the embodiment, the change trend of key indexes of a water inlet of a sewage treatment plant is predicted and evaluated through a random forest algorithm model, high-risk pollution source nodes are analyzed, and under the condition that the upstream sewage discharge points exceed the standard risk, which discharge point is specifically caused can be determined, the troubleshooting efficiency is improved, the risk is found in time, and the standard exceeding pollution discharge is sent by the high-risk pollution source.
Referring to fig. 3, fig. 3 is a flowchart illustrating a step S250 of the control method according to the embodiment of the present application. Applied to the electronic device, determining the correlation between the discharge index of the target upstream sewage discharge point and the discharge index of the downstream water inlet based on the first sewage discharge data and the second sewage discharge data may include steps S310 to S320.
Step S310: and preprocessing the first sewage discharge data and the second sewage discharge data to obtain intermediate data.
In the embodiment of the application, for the condition that the first sewage discharge data and the second sewage discharge data collected by the collection equipment have data loss, intermediate data are obtained by preprocessing the collected data, so that the influence of the loss of subsequent input data on the establishment of a prediction model is avoided.
For example, for preprocessing the first and second wastewater discharge data, the data may be preprocessed based on field production operation experience and expert opinions, and may be preprocessed by a method of sliding mean missing value supplement, missing value data supplement of KNN proximity value algorithm, data filtering, and the like. After the data are processed, through data exploration and cleaning, the LIMS system data are mostly subjected to assay analysis with week granularity, so that the LIMS data are used as a reference, the LIMS system data are associated with real-time database data to form a plurality of groups of data which are integrated into a wide table and used as the basis for subsequent data screening and modeling.
In some embodiments, pre-processing the first wastewater discharge data and the second wastewater discharge data to obtain intermediate data may include the steps of:
acquiring Euclidean distances between each data point and each prediction point of missing data corresponding to first sewage discharge data and second sewage discharge data;
wherein, the Euclidean distance calculation formula is as follows:
wherein d (x, y) is the distance from the calculation predicted point (point to be classified, missing value) to each other sample (data point), d is the coordinate of the predicted value (missing value), and x and y are the coordinates of the samples.
And sequencing the Euclidean distances to confirm the prediction point with the minimum distance, namely the minimum K points.
And comparing the categories of the predicted points (K points) with the minimum distance to confirm that the predicted points are the first category with the highest ratio in the points with the minimum distance.
Classifying the missing data into a first category to populate the first and second wastewater discharge data to obtain intermediate data.
Step S320: an association between a discharge index of the target upstream sewage discharge point and a discharge index of the downstream water intake is determined based on the intermediate data.
In the embodiment, the collected data are preprocessed to ensure the establishment of a subsequent neural network prediction model, and meanwhile, the relevance between an upstream sewage discharge point and a downstream water inlet is established for the preprocessed intermediate data, so that the accuracy of the neural network prediction model is further improved.
For example, real-time database data of preliminarily screened effluent discharge point flow, liquid level, and partial water quality analysis data may be correlated with LIMS system data. The data of the real-time database can be selected from the average value of the corresponding hour, and the average value corresponds to the LIMS data to form a plurality of groups of data taking the LIMS system data as the reference.
In some embodiments, determining a correlation between the discharge index of the target upstream sewage discharge point and the discharge index of the downstream water intake based on the intermediate data comprises:
and determining the relevance between the discharge index of the target upstream sewage discharge point and the discharge index of the downstream water inlet by adopting a preset algorithm based on the intermediate data, wherein the preset algorithm comprises at least one of the following steps: a correlation analysis algorithm, a principal component analysis algorithm.
In the embodiment, relevance and influence of discharge indexes of various upstream sewage discharge points on discharge indexes of water outlets of downstream sewage treatment plants are analyzed and evaluated through various algorithms such as correlation analysis, principal component analysis and the like.
In some embodiments, determining the neural network prediction model based on third sewage discharge data corresponding to a target discharge index of the target upstream sewage discharge point and fourth sewage discharge data corresponding to a target discharge index of the downstream water inlet, wherein the target discharge index is a water outlet index comprises: .
And carrying out normalization processing on third sewage discharge data corresponding to a target discharge index of a target upstream sewage discharge point and fourth sewage discharge data corresponding to a target discharge index of a downstream water inlet.
In the embodiment of the application, the sewage discharge points with higher water quality relevance degree and higher weight with the water inlet of the downstream sewage treatment plant and the corresponding water quality analysis data thereof are screened based on the relevance analysis result, and the water quality analysis indexes participating in modeling are determined based on the screened sewage discharge points.
Illustratively, according to the treatment, and according to the water quality analysis statistical number and the field expert experience, the COD, the petroleum and the PH value of the water quality analysis index participating in the neural network algorithm modeling are finally screened, wherein the prediction index of the random forest algorithm is the COD, the petroleum and the ammonia nitrogen.
And confirming the neural network prediction model based on the data after the normalization processing.
In the embodiment of the application, the associated real-time database data and LIMS system data are subjected to deep processing and mining, and all parameters participating in model calculation are subjected to normalization processing. The normalization processing formula is as follows:
where x represents the input data x per dimension k Normalized value, x min And x max The minimum and maximum values in each dimension of data. After normalization processing, the range result of each dimension of data is 0-1.
In the present embodiment, y = k 1 x 1 +k 2 x 2 +k 3 x 3 +…+k n x n And establishing a multi-parameter linear function in the model for the basic formula. Where k is the weight coefficient of each parameter. Assigning the y value obtained by the linear function to a Sigmoid activation function of the neural network
Adding a nonlinear factor into a conventional linear relation function, and taking the output of the Sigmoid activation function as the input of a new neural network layer. And according to the layer number of the neural network, performing circular calculation in the neural network, and outputting a final prediction result.
In some embodiments, validating the neural network predictive model based on the normalized data comprises:
and dividing the data after the normalization processing into a test set and a training set.
An intermediate neural network model is determined based on the training set.
And inputting the test set into the intermediate neural network model to determine a predicted value.
In some embodiments, when the neural network layer is for predicting the COD of saline wastewater, the neural network layer is set to two layers.
An average absolute error value is determined based on the predicted values and the true values in the test set.
In this embodiment, the calculation formula of the average absolute error value is:
wherein the content of the first and second substances,
the predicted value at the time t is, and y (t) is the true value.
And determining the intermediate neural network model as the neural network prediction model under the condition that the average absolute error value meets an error threshold value.
In some embodiments, under the condition that the average absolute error value does not meet the error threshold, the optimal solution of the neural network model is found by adopting grid search, and the model is optimized based on the optimal demodulation whole model parameters, iteration times, the number of layers of the neural network and the like, so that the model accuracy is improved.
In the embodiment of the application, a neural network prediction model is utilized on the basis of a normalized data set to build a water quality analysis index prediction and model of an upstream sewage discharge point to a downstream sewage treatment field water inlet, and the fitting degree and the model applicability of the model are analyzed.
Illustratively, referring to fig. 5, in the embodiment of the present application, the saline sewage COD neural network layer is, based on the parameters participating in the modeling neural network prediction model, it can be seen that the weight coefficient k values of the parameters are 0.05, -0.611,0.188, -0.91,0.57, -0.616,0.429, -1.799, -1.495, -0.417,0.875,1.544,1.841, -0.781, -2.792,0.752,1.598,1.698, -0.246 in this order. And (3) adjusting model parameters such as model parameters, iteration times and neural network hidden layers by adjusting the optimal parameters in the model, analyzing the predicted value and the actual value by using an average absolute error method, outputting a model result if the error reaches an expected value, and continuously changing the number of layers of the neural network and the corresponding model parameters if the error does not reach the expected value to finally obtain the optimized model.
Please refer to the schematic diagram of the predicted value and the measured value of the PH value of the saline pipe network shown in fig. 5, wherein for the COD index prediction of saline sewage in the present application as an example, the network layer in the neural network prediction model is finally determined to be two layers.
Referring to fig. 6, fig. 6 is a schematic diagram of a predicted value and a measured value of the PH value of the saline pipe network shown in the present application, and it can be seen from the diagram that the PH value of the saline pipe network is closer to the predicted value obtained by the neural network prediction model, that is, in the present application, the prediction model obtained by the above-mentioned implementation has higher prediction accuracy.
TABLE 1
In addition, as shown in table 1, the prediction result of the PH value of the saline pipe network is shown in table 1, and the obtained absolute error result is 5.445%, which is superior to the average absolute error result of three layers of the neural network in the conventional technology, of 9.1%, so that the neural network prediction model is further verified to have better prediction accuracy.
In the embodiment of the application, for each pollutant node, a random forest algorithm is utilized to analyze the influence of each evaluation index of an upstream sewage discharge point on COD (chemical oxygen demand), petroleum and ammonia nitrogen exceeding of a water inlet of a downstream oil-containing and salt-containing sewage treatment plant, 80% of data can be selected for modeling, and 20% of data can be used as test data to improve the accuracy of the model.
In conclusion, according to the control method provided by the application, relevance and influence on the water inlet index of a downstream sewage treatment field can be determined through the discharge condition of each upstream sewage discharge point according to the sewage discharge characteristics, the key index of the water inlet of the sewage treatment field can be predicted and evaluated in advance according to relevance analysis and a neural network model, in addition, a target evaluation index is established, the sequencing of the target evaluation index is analyzed through a random forest algorithm model, high-risk pollution nodes are sequenced through principal component analysis, the positioning of a pollution source is confirmed under the condition that the water inlet key index of the sewage treatment field exceeds the standard, the sewage treatment impact prediction is realized, the excessive pollution discharge of high-risk pollutants is prevented, the sewage impact is reduced, and the stable operation and the discharge standard of a sewage treatment system are ensured.
Referring to fig. 7, fig. 7 is a block diagram of a control device according to the present application, where the control device 700 includes: an obtaining module 710, a predicting module 720, and a controlling module 730, wherein:
the obtaining module 710 is configured to obtain a first effluent index of a target upstream sewage discharge point.
And the predicting module 720 is used for inputting the first water outlet index into a pre-established neural network predicting model so as to predict the water quality index of the downstream water inlet of the sewage treatment plant.
And the control module 730 is used for controlling the operation of the sewage treatment plant based on the water quality index.
In some embodiments, the control device 700 further comprises: the system comprises a sub-acquisition module, a first confirmation module, a second confirmation module, a third confirmation module, a fourth confirmation module, a fifth confirmation module and a sixth confirmation module, wherein:
and the sub-acquisition module is used for acquiring a discharge map, first sewage discharge data of an upstream sewage discharge point and second sewage discharge data of the downstream water inlet.
A first confirmation module to confirm an upstream sewage discharge point and a downstream water intake based on the discharge map.
And the second confirmation module is used for determining the incidence relation between the upstream sewage discharge point and the downstream water inlet based on the upstream sewage discharge point, the downstream water inlet, the first sewage discharge data and the second sewage discharge data.
And the third confirming module is used for determining a target upstream sewage discharge point from the upstream sewage discharge points based on the association relation.
A fourth confirmation module to determine a correlation between the discharge index of the target upstream sewage discharge point and the discharge index of the downstream water inlet based on the first sewage discharge data and the second sewage discharge data.
A fifth validation module to validate a target emission metric based on the correlation.
A sixth determining module, configured to determine the neural network prediction model based on third sewage discharge data corresponding to a target discharge index of the target upstream sewage discharge point and fourth sewage discharge data corresponding to a target discharge index of the downstream water inlet, where the target discharge index is a water outlet index.
In some embodiments, the control device 700 further comprises: evaluation index module and pollution sequencing module, wherein:
and the evaluation index module is used for selecting a target evaluation index in the first effluent index, wherein the target evaluation index is an index influencing the oil-containing and/or salt-containing water quality pollution of an upstream sewage discharge point.
And the pollution sequencing module is used for predicting target upstream sewage discharge points corresponding to the high-risk pollution sources based on the random forest algorithm model and determining sequencing of the target upstream sewage discharge points corresponding to the high-risk pollution sources.
In some embodiments, the fourth confirmation module further comprises: a preprocessing module and an association module, wherein:
and the preprocessing module is used for preprocessing the first sewage discharge data and the second sewage discharge data to obtain intermediate data.
And the correlation module is used for determining the correlation between the discharge index of the target upstream sewage discharge point and the discharge index of the downstream water inlet based on the intermediate data.
In some embodiments, the association module further comprises: a pre-processing module, wherein:
the preset processing module is used for determining the relevance between the discharge index of the target upstream sewage discharge point and the discharge index of the downstream water inlet by adopting a preset algorithm based on the intermediate data, wherein the preset algorithm comprises at least one of the following steps: a correlation analysis algorithm, a principal component analysis algorithm.
In some embodiments, the sixth confirmation module further comprises: sub-processing module and sub-confirmation module, wherein:
and the sub-processing module is used for carrying out normalization processing on third sewage discharge data corresponding to a target discharge index of the target upstream sewage discharge point and fourth sewage discharge data corresponding to a target discharge index of the downstream water inlet.
And the sub-confirmation module is used for confirming the neural network prediction model based on the data after the normalization processing.
In some embodiments, the sub-processing module is further configured to divide the normalized data into a test set and a training set; determining an intermediate neural network model based on the training set; inputting the test set into the intermediate neural network model to determine a predicted value; determining an average absolute error value based on the predicted values and real values in the test set; determining the intermediate neural network model as a neural network prediction model if the mean absolute error value satisfies an error threshold.
In some embodiments, the pre-processing module further comprises: distance acquisition module, distance confirmation module, category confirmation module and fill module, wherein:
and the distance acquisition module is used for acquiring Euclidean distances between each data point and each prediction point of the missing data corresponding to the first sewage discharge data and the second sewage discharge data.
And the distance confirmation module is used for sequencing the Euclidean distances so as to confirm the predicted point with the minimum distance.
And the category confirmation module is used for comparing the categories of the predicted points with the minimum distance so as to confirm that the predicted points are the first category with the highest ratio in the points with the minimum distance.
A filling module for classifying the missing data into a first category to fill the first sewage discharge data and the second sewage discharge data to obtain intermediate data.
It should be noted that the device embodiment in the present application corresponds to the foregoing method embodiment, and specific principles in the device embodiment may refer to the contents in the foregoing method embodiment, which is not described herein again.
In several embodiments provided in this embodiment, the coupling between the modules may be electrical, mechanical or other type of coupling.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing module, or each module may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
Referring to fig. 8, fig. 8 is a block diagram of an electronic device 200 capable of executing the control method according to an embodiment of the present disclosure, where the electronic device 200 may be a smart phone, a tablet computer, a computer, or a portable computer.
The electronic device 200 also includes a processor 202 and a memory 204. The memory 204 stores programs that can execute the content of the foregoing embodiments, and the processor 202 can execute the programs stored in the memory 204.
The Memory 204 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). The memory 204 may be used to store instructions, programs, code sets, or instruction sets. Memory 204 may include a program storage area and a data storage area, where the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (e.g., instructions for a user to obtain a random number), instructions for implementing the various method embodiments described below, and the like. The stored data area may also store data (e.g., random numbers) created by the terminal in use, and the like.
The electronic device 200 may further include a network module for receiving and transmitting electromagnetic waves, and implementing interconversion between the electromagnetic waves and the electrical signals, so as to communicate with a communication network or other devices, for example, an audio playing device. The network module may include various existing circuit elements for performing these functions, such as an antenna, a radio frequency transceiver, a digital signal processor, an encryption/decryption chip, a Subscriber Identity Module (SIM) card, memory, and so forth. The network module may communicate with various networks such as the internet, an intranet, a wireless network, or with other devices via a wireless network. The wireless network may comprise a cellular telephone network, a wireless local area network, or a metropolitan area network. The screen can display the interface content and perform data interaction.
Referring to fig. 9, a block diagram of a computer-readable storage medium according to an embodiment of the present application is shown. The computer-readable storage medium 900 has program code 910 stored therein, and the program code 910 can be called by the processor to execute the method described in the above method embodiments.
The computer-readable storage medium 900 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. Alternatively, the computer-readable storage medium includes a non-volatile computer-readable storage medium. The computer readable storage medium 900 has storage space for program code 910 to perform any of the method steps of the method described above. The program code 910 can be read from or written to one or more computer program products. The program code 910 may be compressed, for example, in a suitable form.
Embodiments of the present application also provide a computer program product or computer program comprising computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the control method described in the above-mentioned various alternative implementations.
The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (11)
1. A control method, characterized in that the method comprises:
acquiring a first effluent index of a target upstream sewage discharge point;
inputting the first water outlet index into a pre-established neural network prediction model to predict the water quality index of a downstream water inlet of a sewage treatment plant;
and controlling the operation of the sewage treatment plant based on the water quality index.
2. The method of claim 1, further comprising:
acquiring a discharge map, first sewage discharge data of an upstream sewage discharge point and second sewage discharge data of a downstream water inlet;
identifying an upstream sewage discharge point and a downstream water inlet based on the discharge map;
determining an association relation between the upstream sewage discharge point and the downstream water inlet based on the upstream sewage discharge point, the downstream water inlet, the first sewage discharge data and the second sewage discharge data;
determining a target upstream sewage discharge point from the upstream sewage discharge points based on the correlation;
determining a correlation between a discharge index of the target upstream sewage discharge point and a discharge index of a downstream water inlet based on the first sewage discharge data and the second sewage discharge data;
identifying a target emission indicator based on the correlation;
and determining the neural network prediction model based on third sewage discharge data corresponding to a target discharge index of the target upstream sewage discharge point and fourth sewage discharge data corresponding to a water quality index of the downstream water inlet, wherein the target discharge index is a water outlet index.
3. The method of claim 1, further comprising:
selecting a target evaluation index in the first effluent indexes, wherein the target evaluation index is an index influencing the pollution of oil-containing and/or salt-containing water at an upstream sewage discharge point;
and predicting target upstream sewage discharge points corresponding to the high-risk pollution sources generated by the target evaluation indexes based on a random forest algorithm model, and determining the sequence of the target upstream sewage discharge points corresponding to the high-risk pollution sources.
4. The method of claim 2, wherein the determining a correlation between the discharge indicator of the target upstream sewage discharge point and the discharge indicator of the downstream water inlet based on the first sewage discharge data and the second sewage discharge data comprises:
preprocessing the first sewage discharge data and the second sewage discharge data to obtain intermediate data;
a correlation between a discharge index of the target upstream sewage discharge point and a discharge index of the downstream water inlet is determined based on the intermediate data.
5. The method of claim 4, wherein determining a correlation between a discharge index of a target upstream sewage discharge point and a discharge index of a downstream water inlet based on the intermediate data comprises:
determining a correlation between a discharge index of a target upstream sewage discharge point and a discharge index of a downstream water inlet by using a preset algorithm based on the intermediate data, wherein the preset algorithm comprises at least one of the following: a correlation analysis algorithm, a principal component analysis algorithm.
6. The method of claim 2, wherein determining the neural network predictive model based on third wastewater discharge data corresponding to a target discharge index of the target upstream wastewater discharge point and fourth wastewater discharge data corresponding to a target discharge index of the downstream water inlet, wherein the target discharge index is a water outlet index comprises:
carrying out normalization treatment on third sewage discharge data corresponding to a target discharge index of the target upstream sewage discharge point and fourth sewage discharge data corresponding to a target discharge index of the downstream water inlet;
and confirming the neural network prediction model based on the data after the normalization processing.
7. The method of claim 6, wherein validating the neural network predictive model based on the normalized data comprises:
dividing the data after normalization into a test set and a training set;
determining an intermediate neural network model based on the training set;
inputting the test set into the intermediate neural network model to determine a predicted value;
determining an average absolute error value based on the predicted value and the real value in the test set;
determining the intermediate neural network model as a neural network prediction model if the mean absolute error value satisfies an error threshold.
8. The method of claim 4, wherein said pre-processing said first wastewater discharge data and said second wastewater discharge data to obtain intermediate data comprises:
acquiring Euclidean distances between each data point and each prediction point of missing data corresponding to first sewage discharge data and second sewage discharge data;
sequencing the Euclidean distances to confirm a predicted point with the minimum distance;
comparing the categories of the predicted points with the minimum distance to confirm that the predicted points are the first category which accounts for the highest of the points with the minimum distance;
classifying the missing data into a first category to populate the first and second wastewater discharge data to obtain intermediate data.
9. A control device, characterized in that the device comprises:
the acquisition module is used for acquiring a first effluent index of a target upstream sewage discharge point;
the prediction module is used for inputting the first water outlet index into a pre-established neural network prediction model so as to predict the water quality index of a downstream water inlet of a sewage treatment plant;
and the control module is used for controlling the operation of the sewage treatment plant based on the water quality index.
10. An electronic device, comprising:
one or more processors;
a memory;
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the control method of any of claims 1-8.
11. A computer-readable storage medium, characterized in that the computer-readable storage medium stores program code that is invokable by one or more processors to perform a control method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211177193.9A CN115826509A (en) | 2022-09-26 | 2022-09-26 | Control method, control device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211177193.9A CN115826509A (en) | 2022-09-26 | 2022-09-26 | Control method, control device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115826509A true CN115826509A (en) | 2023-03-21 |
Family
ID=85524014
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211177193.9A Pending CN115826509A (en) | 2022-09-26 | 2022-09-26 | Control method, control device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115826509A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117164103A (en) * | 2023-07-03 | 2023-12-05 | 广西智碧达智慧环境科技有限公司 | Intelligent control method, terminal and system of domestic sewage treatment system |
| CN117195135A (en) * | 2023-11-01 | 2023-12-08 | 潍坊德瑞生物科技有限公司 | Water pollution anomaly traceability detection method and system |
-
2022
- 2022-09-26 CN CN202211177193.9A patent/CN115826509A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117164103A (en) * | 2023-07-03 | 2023-12-05 | 广西智碧达智慧环境科技有限公司 | Intelligent control method, terminal and system of domestic sewage treatment system |
| CN117195135A (en) * | 2023-11-01 | 2023-12-08 | 潍坊德瑞生物科技有限公司 | Water pollution anomaly traceability detection method and system |
| CN117195135B (en) * | 2023-11-01 | 2024-02-27 | 潍坊德瑞生物科技有限公司 | Water pollution anomaly traceability detection method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115826509A (en) | Control method, control device, electronic equipment and storage medium | |
| Liu et al. | A systematic approach to optimizing value for fuzzy linear regression with symmetric triangular fuzzy numbers | |
| CN115222303B (en) | Industry risk data analysis method and system based on big data and storage medium | |
| CN111652661B (en) | Mobile phone client user loss early warning processing method | |
| CN116596095B (en) | Training method and device of carbon emission prediction model based on machine learning | |
| CN115237804A (en) | Performance bottleneck assessment method, performance bottleneck assessment device, electronic equipment, medium and program product | |
| CN114418189A (en) | Water quality grade prediction method, system, terminal device and storage medium | |
| CN111404835B (en) | Flow control method, device, equipment and storage medium | |
| CN117195083A (en) | Slump prediction method and device based on current curve and readable medium | |
| CN113988676B (en) | Safety management method and system for water treatment equipment | |
| CN114417830A (en) | Risk evaluation method, device, equipment and computer readable storage medium | |
| CN113052422A (en) | Wind control model training method and user credit evaluation method | |
| CN110087230A (en) | Data processing method, device, storage medium and electronic equipment | |
| CN117131999B (en) | Digital twin-based rail transit passenger flow prediction system and method thereof | |
| CN113239026B (en) | Cloud server and cloud data processing method based on same | |
| Gobeyn et al. | A variable length chromosome genetic algorithm approach to identify species distribution models useful for freshwater ecosystem management | |
| CN117171446B (en) | Technical transaction recommendation method and recommendation system based on big data analysis | |
| CN114581249B (en) | Financial product recommendation method and system based on investment risk bearing capacity assessment | |
| CN112714062B (en) | Multi-path routing method and device for ultra-computation user experience quality | |
| CN117217901A (en) | Risk test method and device, storage medium and electronic device | |
| CN114297027A (en) | Log inspection method and device based on machine learning and electronic equipment | |
| Yang et al. | Estimating the water quality index based on interpretable machine learning models | |
| CN117787700A (en) | Post-loan risk prediction method based on dynamic graph sequence | |
| Fulford et al. | Eco-decisional well-being networks as a tool for community decision support | |
| CN117454281A (en) | Method, device and equipment for generating SOAR script and readable storage medium |
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 |