Water quality prediction method, system and equipment and readable storage medium

Abstract

The invention provides a water quality prediction method, system and device and a readable storage medium. The water quality prediction method comprises the steps of obtaining initial water quality data; inputting the initial water quality data into a sewage treatment model; and performing rolling calculation on the initial water quality data based on the sewage treatment model to obtain water quality prediction data. According to the method, the effluent quality of the sewage plant can be simulated in advance according to the water quality prediction data, so that the effluent quality of the sewage plant is pre-warned in advance, relevant measures are taken in time, the effluent of the sewage plant is ensured to stably reach the standard, and the possibility that the environment is polluted by the effluent discharged by the sewage plant is reduced.

Description

Technical Field

[0001] The present application belongs to the technical field of water quality prediction, and relates to a water quality prediction method, and in particular to a water quality prediction method, system, device and readable storage medium. Background Art

[0002] In the current sewage treatment process, due to environmental factors, improper addition of drugs and chemicals, improper operation and management, etc., the effluent quality of the sewage treatment plant is not up to standard, which poses a great threat to rivers, soil, and people's health and life. Therefore, how to predict the effluent quality after sewage treatment has become one of the technical problems that need to be solved urgently. Summary of the invention

[0003] The present application provides a water quality prediction method, system, device and readable storage medium for predicting the effluent quality of a sewage treatment plant in advance.

[0004] In a first aspect, an embodiment of the present application provides a water quality prediction method, the method comprising: obtaining initial water quality data; inputting the initial water quality data into a sewage treatment model; and performing a rolling calculation on the initial water quality data based on the sewage treatment model to obtain water quality prediction data.

[0005] In an implementation of the first aspect, inputting the initial water quality data into the sewage treatment model includes: acquiring first water quality source data; performing a preprocessing operation on the first water quality source data to obtain second water quality source data; sending the second water quality source data to a water quality database; establishing a connection between the water quality database and the sewage treatment model; extracting a set of the second water quality source data from the water quality database as the initial water quality data, and inputting the initial water quality data into the sewage treatment model.

[0006] In an implementation of the first aspect, the rolling calculation of the initial water quality data based on the sewage treatment model to obtain the water quality prediction data includes: determining the duration information, frequency information and output step information of the rolling calculation; and performing a rolling calculation on the initial water quality data based on the sewage treatment model according to the duration information, the frequency information and the output step information to obtain the water quality prediction data.

[0007] In an implementation of the first aspect, the rolling calculation of the initial water quality data based on the sewage treatment model includes: inputting the initial water quality data into the sewage treatment model to obtain the first water quality prediction data; inputting the first water quality data in the previous water quality prediction data into the sewage treatment model to obtain the current water quality prediction data, and repeating this step until the termination condition is met, the first water quality data being the static indicator data in the water quality prediction data.

[0008] In an implementation of the first aspect, the second water quality data in the water quality prediction data is used to predict the effluent water quality of the sewage treatment plant corresponding to the sewage treatment model within a preset time.

[0009] In an implementation of the first aspect, the water quality prediction method also includes: if the second water quality data is less than or equal to a water quality threshold, determining that the effluent water quality of the sewage treatment plant within the preset time is normal water quality; if the second water quality data is greater than the water quality threshold, determining that the effluent water quality of the sewage treatment plant within the preset time is abnormal water quality.

[0010] In an implementation of the first aspect, the method for constructing the sewage treatment model includes: constructing an initial water quality model; correcting the initial water quality model based on historical water quality data to obtain a corrected water quality model; and verifying the corrected water quality model based on real-time water quality data to obtain the sewage treatment model.

[0011] The water quality prediction method provided in the embodiment of the present application can perform rolling calculations on the initial water quality data according to the sewage treatment model to obtain water quality prediction data, and in this way, the effluent quality of the sewage treatment plant can be simulated in advance. The staff can make appropriate adjustments to the sewage treatment link of the sewage treatment plant in a timely manner according to the water quality prediction data to ensure that the effluent quality of the sewage treatment plant is normal and reduce the possibility of water discharged from the sewage treatment plant polluting the environment.

[0012] In a second aspect, an embodiment of the present application provides a water quality prediction system, which includes: a water quality data acquisition module for acquiring initial water quality data; a water quality data input module for inputting the initial water quality data into a sewage treatment model; and a water quality data prediction module for performing a rolling calculation on the initial water quality data based on the sewage treatment model to obtain water quality prediction data.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement a water quality prediction method as described in any one of the first aspects of the embodiments of the present application when executing the computer program.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the water quality prediction method described in any one of the first aspects of the embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1A Shown is a schematic diagram of an application scenario of a water quality prediction method provided in one embodiment of the present application.

[0016] Figure 1B Shown is a flow chart of a water quality prediction method in one embodiment of the present application.

[0017] Figure 2 Shown is a flow chart of inputting initial water quality data into a sewage treatment model in one embodiment of the present application.

[0018] Figure 3 Shown is a flow chart for determining water quality prediction data in one embodiment of the present application.

[0019] Figure 4 Shown is a flow chart of rolling calculation of initial water quality data based on a sewage treatment model in one embodiment of the present application.

[0020] Figure 5 Shown is a flow chart of constructing a sewage treatment model in one embodiment of the present application.

[0021] Figure 6 Shown is a schematic diagram of a sewage treatment model in one embodiment of the present application.

[0022] Figure 7 Shown is another flowchart of rolling calculation of initial water quality data based on a sewage treatment model in one embodiment of the present application.

[0023] Figure 8 Shown is a schematic diagram of a water quality prediction system in one embodiment of the present application.

[0024] Fig. 9 Shown is a schematic diagram of the structure of an electronic device in an embodiment of the present application.

[0025] Component number description

[0026] Steps S11 to S13

[0027] Steps S21 to S25

[0028] Steps S31 to S32

[0029] Steps S41 to S42

[0030] Steps S51 to S53

[0031] Steps S701 to S712

[0032] 600 Sewage Treatment Model

[0033] 601 Influent Input Model

[0034] 602 Carbon source input model

[0035] 603 Biochemical Reactor

[0036] 604 Carbon source input model

[0037] 605 Biochemical Reactor

[0038] 606 The first sedimentation tank model

[0039] 607 Second sedimentation tank model

[0040] 608 Second sedimentation tank model

[0041] 609 Membrane Filtration Model

[0042] 610 Membrane Filtration Model

[0043] 611 Chemical Disinfection Model

[0044] 612 Output Model

[0045] 80 Water Quality Prediction System

[0046] 81 Water quality data acquisition module

[0047] 82 Water quality data input module

[0048] 83 Water quality data prediction module

[0049] 90 Electronic equipment

[0050] 91 Processor

[0051] 92 Non-volatile storage media

[0052] 93 System Bus

[0053] 94 Internal memory

[0054] 95 Network Interface DETAILED DESCRIPTION

[0055] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0056] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed at will, and the component layout may also be more complicated.

[0057] The existing technology lacks a water quality prediction method for predicting the effluent quality of a sewage treatment plant in advance.

[0058] At least for the above-mentioned problems, the embodiment of the present application provides a water quality prediction method. In the water quality prediction method, by obtaining initial water quality data, inputting the initial water quality data into a sewage treatment model, and performing rolling calculations on the initial water quality data based on the sewage treatment model, water quality prediction data is obtained, which can solve the technical problem that the prior art cannot predict the effluent water quality of a sewage treatment plant in advance.

[0059] Figure 1A A schematic diagram of an application scenario of a water quality prediction method provided by an embodiment of the present application is shown. Figure 1A As shown, the application scenario includes a data acquisition device and an electronic device, wherein the water quality database is located in the electronic device. The data acquisition device is used to collect data related to water quality prediction, including a water quality analyzer, a water quality sensor, etc.

[0060] The electronic device of the embodiment of the present application is used to transmit the initial water quality data in the water quality database to the data processing device through the network.

[0061] The data processing equipment of the embodiment of the present application includes: a water quality analyzer, a water quality sensor, etc., which are used to receive initial water quality data sent by an electronic device and simulate the process of sewage treatment in a sewage treatment plant in advance based on the initial water quality data.

[0062] The technical solutions in the embodiments of the present application will be described in detail below in conjunction with the drawings in the embodiments of the present application.

[0063] Figure 1B Shown is a flow chart of a water quality prediction method in one embodiment of the present application. Figure 1BAs shown, the water quality prediction method provided in the embodiment of the present application includes the following steps S11 to S13.

[0064] S11, obtaining initial water quality data.

[0065] Among them, the data indicators corresponding to the initial water quality data include: total suspended solids, total phosphorus, chemical oxygen demand, ammonia nitrogen and biochemical oxygen demand, pH value, etc.

[0066] Among them, the initial water quality data is the preprocessed data.

[0067] Exemplarily, the initial water quality data is extracted from a water quality database of a sewage treatment plant.

[0068] It should be noted that the above initial water quality data are the water quality data corresponding to the sewage to be treated in the sewage treatment plant.

[0069] S12, inputting the initial water quality data into a sewage treatment model.

[0070] Before inputting the initial water quality data into the sewage treatment model, the data input format of the sewage treatment model is confirmed, and according to the data input format of the sewage treatment model, the data format of the initial water quality data is modified into a format that can be input into the sewage treatment model.

[0071] Exemplarily, the data input format of the sewage treatment model may be CSV, TXT, etc.

[0072] It should be noted that the data input format of the above-mentioned sewage treatment model is only used for illustrative purposes. In practical applications, the data input format of the sewage treatment model can be reasonably set according to actual needs, and this application does not impose any restrictions on this.

[0073] Specifically, the process of inputting the initial water quality data into the sewage treatment model may include: finding the corresponding data input cells on the data input page of the sewage treatment model, and inputting the collected initial water quality data into the corresponding cells one by one.

[0074] In another specific embodiment, if the sewage treatment model is executed based on a programming language, the process of inputting the initial water quality data into the sewage treatment model may further include: inputting the initial water quality data into a programming input interface where the sewage treatment model is located.

[0075] S13, performing rolling calculation on the initial water quality data based on the sewage treatment model to obtain water quality prediction data.

[0076] Among them, the water quality prediction data is the prediction result of the water quality data corresponding to the effluent water quality after the sewage treatment plant treats sewage in the future period of time.

[0077] Exemplarily, the process of rolling calculation is, for example: input the initial water quality data into the sewage treatment model for model calculation to obtain water quality prediction data t1. Input the first water quality data t10 in the water quality prediction data t1 into the sewage treatment model for model calculation to obtain water quality prediction data t2; directly output the second water quality data t11 in the water quality prediction data t1 from the output port of the sewage treatment model to predict the effluent water quality of the sewage treatment plant. Input the first water quality data t20 in the water quality prediction data t2 into the sewage treatment model for model calculation to obtain water quality prediction data t2; directly output the second water quality data t21 in the water quality prediction data t2 from the output port of the sewage treatment model to predict the effluent water quality of the sewage treatment plant. ... Input the first water quality data tn0 in the water quality prediction data tn into the sewage treatment model for model calculation to obtain water quality prediction data tn+1; directly output the second water quality data tn1 in the water quality prediction data tn from the output port of the sewage treatment model to predict the effluent water quality of the sewage treatment plant. Repeat the above model calculation steps until the termination condition is met.

[0078] In the water quality prediction method provided in the embodiment of the present application, the acquired initial water quality data is input into the sewage treatment model, and the initial water quality is rolled over in the sewage treatment model to obtain a water quality prediction result, thereby realizing a full-process simulation of the sewage treatment plant and solving the technical problem of being unable to predict the effluent water quality after treatment in the sewage treatment plant.

[0079] Figure 2 Shown is a flow chart of inputting initial water quality data into a sewage treatment model in one embodiment of the present application. Figure 2 As shown, the process of inputting initial water quality data into the sewage treatment model in the embodiment of the present application includes the following steps S21 to S25.

[0080] S21, obtaining first water quality source data.

[0081] Among them, the first water quality source data is directly extracted from untreated sewage.

[0082] It should be noted that the data index corresponding to the first water quality source data is the same as the data index corresponding to the initial water quality data, that is, the first water quality source data includes a plurality of water quality data.

[0083] Exemplarily, the data indicators may include: total suspended solids, total phosphorus, chemical oxygen demand, ammonia nitrogen, etc. The water quality data in the first water quality source data at least includes water quality data corresponding to total suspended solids, water quality data corresponding to total phosphorus, water quality data corresponding to chemical oxygen demand, and water quality data corresponding to ammonia nitrogen.

[0084] Exemplarily, the first water quality source data in the sewage can be extracted based on a water quality analyzer, wherein the water quality analyzer can be any one of a multi-parameter water quality analyzer, a handheld spectrometer, and the like.

[0085] Exemplarily, the first water quality source data in the sewage can also be extracted based on a water quality sensor, wherein the water quality sensor can be any one of a pH sensor, a turbidity sensor, a conductivity sensor, and the like.

[0086] It should be noted that the water quality analyzer and water quality sensor used in the above-mentioned extraction of the first water quality source data in the sewage are only used for illustrative purposes. In actual applications, appropriate instruments / equipment can be selected to extract the first water quality source data in the sewage according to specific circumstances, and this application does not impose any restrictions on this.

[0087] S22, performing a preprocessing operation on the first water quality source data to obtain second water quality source data.

[0088] The preprocessing operation includes any one or a combination of the following operations: data cleaning operation, data conversion operation, data verification operation, data reduction operation, etc.

[0089] Exemplarily, if the first water quality source data extracted directly from sewage contains any one or more of missing data, duplicate data, anomaly data, etc., a data cleaning operation in the preprocessing operation can be performed on the first water quality source data. After performing the data cleaning operation on the first water quality source data, the second water quality source data can be obtained.

[0090] For example, if there is inconsistency in data formats among multiple data in the first water quality source data, the first water quality source data can be converted, the data format of the first water quality source data can be adjusted, or the first water quality source data can be normalized, etc., to obtain the second water quality source data.

[0091] Among them, data conversion includes any one or a combination of the following operations: normalization and standardization, data discretization, data encoding, etc.

[0092] It should be noted that, when performing the preprocessing operation on the first water quality source data, any one or more data operation modes in the preprocessing operation can be selected according to the actual data processing situation of the first water quality source data, and this application does not impose any restrictions on this.

[0093] S23, sending the second water quality source data to a water quality database.

[0094] Wherein, a plurality of groups of second water quality source data are stored in the water quality database.

[0095] Exemplarily, before sending the second water quality source data to the water quality database, it is necessary to establish a connection between the second water quality source data and the water quality database. After the connection is established, the second water quality source data is sent to the water quality database using an insert command of the database. After all the second water quality source data are inserted into the water quality database, the connection to the water quality database is closed.

[0096] The insert command of the water quality database may be: SQL insert statement, SQL insert default value, etc.

[0097] It should be noted that the above-mentioned water quality database insertion command is only used for illustrative purposes. In actual applications, a suitable insertion command can be selected according to the specific situation, and this application does not impose any restrictions on this.

[0098] S24, establishing a connection between the water quality database and the sewage treatment model.

[0099] Before establishing a connection between the water quality database and the sewage treatment model, the connection information of the water quality database is confirmed.

[0100] Exemplarily, the water quality database and the sewage treatment model may be connected by any one of two connection modes: direct connection and middleware connection.

[0101] Among them, direct connection is applicable to the situation where the sewage treatment model interacts directly with the water quality database.

[0102] Specifically, middleware connection refers to using middleware services to bridge the water quality database and the sewage treatment model. The middleware services may be: API services, message queue services, etc.

[0103] It should be noted that in addition to the two connection methods given in this application to connect the water quality database and the sewage treatment model, in actual applications, any other suitable connection method can be selected according to the specific situation, and this application does not impose any restrictions on this.

[0104] S25, extracting a set of the second water quality source data from the water quality database as the initial water quality data, and inputting the initial water quality data into the sewage treatment model.

[0105] Among them, a set of second water quality source data includes all data indicators.

[0106] Specifically, before the effluent water quality of the sewage treatment plant needs to be predicted, a set of second water quality source data is extracted from the water quality database in advance, and the extracted set of second water quality source data is used as the initial water quality data.

[0107] The embodiment of the present application provides a method for inputting initial water quality data into a sewage treatment model. By performing data preprocessing operations on the first water quality source data, data cleaning operations can be performed on abnormal data in the first water quality source data, or the data format of all data in the first water quality source data can be uniformly adjusted to obtain adjusted second water quality source data, which provides an accurate data basis for the subsequent input of initial water quality data into the sewage treatment model. Multiple groups of preprocessed second water quality source data are sent to the water quality database for storage, so that a group of second water quality source data can be subsequently extracted as initial water quality data to be input into the sewage treatment model. This avoids reducing the processing efficiency of the sewage treatment model due to data errors in the initial water quality data in the sewage treatment model. In the present application, the accuracy of the initial water quality data is improved through data preprocessing operations, and the processing efficiency of the subsequent rolling calculation of the initial water quality data in the sewage treatment model is improved.

[0108] Figure 3 Shown is a flow chart for determining water quality prediction data in one embodiment of the present application. Figure 3 As shown, the process of determining water quality prediction data in the embodiment of the present application includes the following steps S31 to S32.

[0109] S31, determining the duration information, frequency information and output step information of the rolling calculation.

[0110] The duration information indicates the calculation interval of the rolling calculation, the frequency information indicates the update frequency of the initial water quality data, and the output step information indicates the time interval for outputting the calculation results.

[0111] Among them, rolling calculations can be carried out in the sewage treatment model.

[0112] Specifically, the duration information, frequency information and output step information of the rolling calculation are determined before the rolling calculation.

[0113] For example, assume that the duration information of the rolling calculation is set to 30 days; the frequency information is set to 1 day, that is, within the 30-day period, the initial water quality data will be updated every day; the output step information is set to 3 days, that is, the water quality prediction results are output every 3 days.

[0114] It should be noted that the above-mentioned specific time settings for duration information, frequency information and output step information are only for illustrative purposes. In actual applications, the time corresponding to the appropriate duration information, frequency information and output step information can be selected according to the specific application scenario, and there is no limitation on this.

[0115] S32, performing rolling calculation on the initial water quality data based on the sewage treatment model according to the duration information, the frequency information and the output step information, to obtain the water quality prediction data.

[0116] Specifically, after determining the duration information, frequency information and output step information, the initial water quality data is input into the sewage treatment model, and the initial water quality data is rolled over and calculated based on the sewage treatment model to obtain water quality prediction data.

[0117] The embodiment of the present application determines the duration information, frequency information and output step information of the rolling calculation, and performs a rolling calculation on the initial water quality data based on the sewage treatment model according to the duration information, frequency information and output step information of the rolling calculation to obtain water quality prediction data. According to the water quality prediction data, the effluent water quality of the sewage treatment plant is simulated in advance to provide advance warning of the effluent water quality of the sewage treatment plant, and relevant measures are taken in time to ensure that the effluent of the sewage treatment plant is stable and meets the standards.

[0118] Figure 4 The flowchart of the rolling calculation of the initial water quality data based on the sewage treatment model in one embodiment of the present application is shown. Figure 4 As shown, in one embodiment of the present application, the process of rolling calculation of the initial water quality data based on the sewage treatment model includes the following steps S41 to S42.

[0119] S41, inputting the initial water quality data into the sewage treatment model to obtain the first water quality prediction data.

[0120] Wherein, the water quality prediction data includes first water quality data.

[0121] Specifically, according to the previously set step information, after the initial water quality data is input into the sewage treatment model for model calculation, the first water quality prediction data is output, that is, the first water quality prediction data is the water quality prediction result corresponding to the first step information.

[0122] S42, inputting the first water quality data in the previous water quality prediction data into the sewage treatment model to obtain the current water quality prediction data, and repeating this step until the termination condition is met.

[0123] The first water quality data is static indicator data in the numerical prediction data, and the static indicator data specifically includes: pH value, biochemical oxygen demand, chemical oxygen demand, hardness, alkalinity and / or dissolved oxygen, etc.

[0124] The termination condition may be duration information, and when the running time of the rolling calculation is greater than the time interval corresponding to the duration information, the rolling calculation is terminated. In addition, the termination condition may also be the number of water quality prediction data obtained or any other appropriate behavior for terminating the rolling calculation, which is not limited in this application.

[0125] The specific process of rolling calculation is as follows: during the first cycle, the initial water quality data is input into the sewage treatment model for calculation, and the output of the sewage treatment model is the prediction data obtained by the first water quality prediction, referred to as the first water quality prediction data, and the rest is similar. The first water quality data in the first water quality prediction data is input into the sewage treatment model for calculation, and the output of the sewage treatment model is the second water quality prediction data. The first water quality data in the second water quality prediction data is input into the sewage treatment model for calculation, and the output of the sewage treatment model is the third water quality prediction data, and so on, until the termination condition is met and no more training is performed.

[0126] In some embodiments, the second water quality data in the water quality prediction data is used to predict the effluent water quality of the sewage treatment plant corresponding to the sewage treatment model within a preset time. The second water quality data is weakened data.

[0127] The second water quality data represents the water quality status of the sewage treatment plant at a specific time point or time period.

[0128] The preset time may be one week, two weeks, or one month in the future.

[0129] It should be noted that the above-mentioned preset time can be reasonably determined based on the specific operating conditions of the sewage treatment plant, and this application does not impose any restrictions on this.

[0130] In some embodiments, the water quality prediction method also includes: if the second water quality data is less than or equal to a water quality threshold, determining that the effluent water quality of the sewage treatment plant within the preset time is normal water quality; if the second water quality data is greater than the water quality threshold, determining that the effluent water quality of the sewage treatment plant within the preset time is abnormal water quality.

[0131] Specifically, the specific setting of water quality thresholds must comply with the settings of environmental protection agencies or relevant laws and regulations. The specific setting of water quality thresholds can be reasonably set according to the requirements or uses in different regions and scenarios, and this application does not impose any restrictions on this.

[0132] Exemplarily, if the second water quality data is less than or equal to the water quality threshold, it is determined that the effluent water quality of the sewage treatment plant within the preset time is normal water quality. This means that the various water treatment submodules of the sewage treatment plant operate normally within the preset time, and there is no need to make any modifications to the various water treatment submodules in the sewage treatment plant. On the contrary, if the second water quality data is greater than the water quality threshold, it is determined that the effluent water quality of the sewage treatment plant within the preset time is abnormal water quality. At this time, appropriate adjustments should be made to the corresponding water treatment submodules in the sewage treatment plant. For example, if it is detected that the carbon-nitrogen ratio (C / N) in the second water quality data is greater than the carbon-nitrogen ratio (C / N) in the water quality threshold, and the carbon-phosphorus ratio (C / P) is greater than the carbon-phosphorus ratio (C / P) in the water quality threshold, then the carbon source addition amount in the carbon source addition module in the sewage treatment plant should be increased in time to promote microorganisms to better perform nitrification and denitrification and remove nitrogen and phosphorus.

[0133] In the embodiment of the present application, a method for rolling calculation of initial water quality data based on a sewage treatment model is provided, wherein the initial water quality data is input into the sewage treatment model to obtain the first water quality prediction data, and then the first water quality data in the previous water quality prediction data is input into the sewage treatment model for calculation again to obtain the current water quality prediction data, and the above steps are repeated until the termination condition is met. The whole process tracking of the effluent water quality of the sewage treatment plant is realized through rolling calculation, the effluent water quality of the sewage treatment plant is simulated in advance, and the water quality prediction data is obtained. According to the water quality prediction data, appropriate measures are taken in time for each water treatment submodule of the sewage treatment plant to ensure that the effluent of the sewage treatment plant is stable and meets the standards.

[0134] See also Figure 5 , Figure 5 Shown is a flow chart of constructing a sewage treatment model in one embodiment of the present application. Figure 5 As shown, the process of constructing a sewage treatment model in one embodiment of the present application includes the following steps S51 to S53.

[0135] S51, construct an initial water quality model.

[0136] Exemplarily, the initial water quality model is constructed based on the process line of the sewage treatment plant.

[0137] S52, correcting the initial water quality model based on historical water quality data to obtain a corrected water quality model.

[0138] Among them, historical water quality data include historical laboratory data, historical online monitoring and operation data.

[0139] Specifically, after constructing the initial water quality model, the historical water quality data is input into the initial water quality model for correction. During the correction process, the various parameters in the initial water quality model can be adjusted accordingly according to the data output of the initial water quality model, so that the initial water quality model is close to the treatment effect of the actual sewage treatment plant.

[0140] S53, verifying the corrected water quality model based on real-time water quality data to obtain the sewage treatment model.

[0141] Among them, real-time water quality data refers to the data when the sewage treatment plant actually treats sewage.

[0142] Exemplarily, the data of the actual sewage treatment at the sewage treatment plant is extracted and input into the corrected water quality model, and the output water quality data is obtained after data processing by the corrected water quality model. The sewage treatment plant outputs treated water, and the water quality data of the treated water output from the sewage treatment plant is compared with the water quality data output by the corrected water quality model. If the water quality error between the water quality data of the treated water output from the sewage treatment plant and the water quality data output by the corrected water quality model is within the allowable error range, it means that the corrected water quality model verification has passed, and the corrected water quality model is the sewage treatment model. On the contrary, if the water quality error between the water quality data of the treated water output from the sewage treatment plant and the water quality data output by the corrected water quality model is not within the allowable error range, the corrected water quality model is verified again based on the real-time water quality data until the water quality error between the water quality data of the treated water output from the sewage treatment plant and the water quality data output by the corrected water quality model is within the allowable error range.

[0143] The embodiment of the present application provides a method for constructing a sewage treatment model, which constructs an initial water quality model through the process line of a sewage treatment plant, and corrects the constructed initial water quality model based on historical water quality data and verifies the initial water quality model based on real-time water quality data to obtain a sewage treatment model, thereby ensuring the accuracy of the sewage treatment model and providing an accurate model basis for subsequent rolling calculations based on the sewage treatment model.

[0144] like Figure 6 As shown, in one embodiment, the sewage treatment model 600 of the present application includes an inlet input model 601, a carbon source addition input model 602 and 604, biochemical reactors 603 and 605, a first sedimentation tank model 606, a second sedimentation tank model 607 and 608, membrane filtration models 609 and 610, a chemical disinfection model 611, and an output model 612.

[0145] In the influent input model 601, the influent input includes urban sewage COD, urban sewage nitrogen, urban sewage phosphorus, etc.

[0146] The general composition of urban sewage COD is: ASM2d contains 9 dissolved substances (excluding S_S) and 10 particulate substances, and the dissolved and particulate substances are represented by S_* and X_* respectively. In order to explain the dominant reproduction and elimination of certain species of microorganisms in the activated sludge system, it is necessary to consider the biomass part of the influent. If the bacterial species content in the influent is high, then even in the high load state that may be eliminated, the reaction process may occur.

[0147] In order to explain the value-added and elimination phenomenon of polyphosphate bacteria and autotrophic bacteria in the system, the present application embodiment incorporates polyphosphate bacteria and autotrophic bacteria in the inlet water into the inlet water parameters. In most cases, the content of autotrophic bacteria X_AUT in the inlet water is very low, and so is the polyphosphate bacteria X_PAO. It should be noted that X_PAO does not include stored polyhydroxyalkanoic acid X_PHA, and it is generally believed that they are independent compounds. Similarly, the polyphosphate stored in the polyphosphate bacteria is also considered to be an independent component, which means that the contribution of polyphosphate bacteria to total suspended solids comes from three parts--X_PAO, X_PHA, and X_PP.

[0148] In addition, the influent component model can be divided into two types of models: component-based and component-based. Total COD, TKN and ammonia nitrogen are used as the main influent characteristic inputs, while the model components include soluble inert COD (si), easily biodegradable matrix (ss, sf or slf, etc.), particulate inert matter (xi), non-biodegradable cell decay products (xu) and biomass concentration (xbh, xba and xbp) specified by the proportion of total COD. The difference lies mainly in the determination of organic nitrogen and phosphorus components. The former uses clear static variables such as dissolved total organic nitrogen, particulate total organic nitrogen, etc., while the latter uses the component ratio of the static variable of COD to simulate organic nitrogen and phosphorus, and uses ammonia nitrogen and phosphorus in the influent as the main correction parameters to maintain the input of nitrogen and phosphorus in the model. The models of component-based analysis methods are: ASM1, Barker&Dold and UCTPHO+, and the models of component-based analysis methods are: ASM2d, ASM3, ASM3+Bio-P and TU Delft.

[0149] Add wastewater to the activated sludge system in the endogenous respiration state and measure the respiration rate until it returns to the endogenous level. Integrate the respiration rate curve over time, which is equivalent to soluble and easily degradable organic matter Ss and Xs.

[0150]

[0151] Among them, V T Represents the reactor volume, V W represents the volume of wastewater, Ss and Xs represent soluble and easily degradable organic matter, and Y Hrepresents the yield coefficient, t1 represents the time when microorganisms rapidly degrade organic matter, t2 represents the time when microorganisms slowly degrade organic matter, R1 represents the oxygen uptake rate (OUR) change curve when microorganisms rapidly degrade organic matter, R2 represents the OUR change curve when microorganisms slowly degrade organic matter, and R3 represents the OUR change curve during endogenous respiration of microorganisms.

[0152] In some implementations, the fast oxygen demand Ss can be decomposed and calculated by a material balance equation of a continuous experiment, or by an inflection point analysis of a multi-component substrate respiration rate curve.

[0153] Estimate Xs, affecting the denitrification performance of the system: Method 1: The ratio of BOD to (1-fBOD) is BCOD, where fBOD is 0.15, which is used to compensate for the non-biodegradable inert residual substances produced by biomass decay. The difference between BCOD and Ss is Xs; Method 2: The respiratory response of XS is very small, the experimental measurement is relatively long, and nitrification is superimposed. The optimal parameter estimation algorithm is used to eliminate the influence of nitrification. The formula is:

[0154]

[0155] in, Indicates the proportion of slowly degradable organic matter to COD, COD stands for chemical oxygen demand, BOD U represents the final biochemical oxygen demand, S S Indicates rapidly biodegradable organic matter.

[0156] Estimating Xi has an impact on sludge production, MLSS and sedimentation performance: The difference between COD and BOD is Si and Xi. If Si is known, Xi can be calculated using the formula:

[0157]

[0158] in, Indicates the content of inert particulate organic matter. represents the content of inert dissolved organic matter, COD represents chemical oxygen demand, S I Indicates non-biodegradable dissolved organic matter, BOD U represents the final biochemical oxygen demand, BOD5 represents the 5-day biochemical oxygen demand, f BOD Indicates BOD5 / BOD U ratio.

[0159] The main component of total nitrogen in urban sewage is reduced nitrogen, which exists in the form of ammonia nitrogen or in the form of amino compounds in organic matter. Ammonia nitrogen is the main reduced component, usually accounting for 60% to 70% of the total Kjeldahl nitrogen, mainly from urea. Urea hydrolyzes quickly, so urea is rarely found in sewage plants. In raw sewage, low concentrations of nitrates or nitrites can be found, usually in the range of 0 to 1 mg / L, mainly from infiltrated water. If the concentration is high, it may come from groundwater and industrial sewage. In the component-based model, organic nitrogen is generally divided into dissolved and particulate states. The particulate state must be converted into a dissolved state through a hydrolysis step before it can be converted into ammonia nitrogen (ASM1) through an ammoniation reaction. Ammonia nitrogen and TN are measured, nitrates and nitrites are deducted, TKN is calculated, and sTKN is calculated by assuming that ammonia nitrogen accounts for the proportion of dissolved TKN. xTKN is calculated through TKN and sTKN. In ASM2d, organic nitrogen is further accounted for using the component ratios of the static variables of COD, using ammonia nitrogen and total nitrogen (or TKN) in the influent as the main correction parameters to maintain the nitrogen input in the model.

[0160] Determine the ammonia nitrogen and TN of the influent and determine the N component:

[0161] S TKN =S NH / f rsNH

[0162] Among them, S TKN represents the dissolved Kjeldahl nitrogen concentration, S NH represents the ammonia nitrogen concentration, f rsNH It indicates the ratio of ammonia nitrogen to dissolved Kjeldahl nitrogen.

[0163] Carbon source dosing input models 602 and 604 are used to input chemical dosage or water in the wastewater treatment process, which facilitates the conversion of typical chemical components into state variables used in the wastewater treatment model.

[0164] In biochemical reactors 603 and 605, the biochemical pool is mainly used to remove organic matter and remove nitrogen and phosphorus, so the biochemical pool can be simulated by a modified version of the activated sludge model No. 2 (ASM2d). The ASM2d model adds two processes based on ASM2 to illustrate that polyphosphate bacteria (PAO) can use intracellular organic storage for denitrification. Unlike ASM2, which assumes that PAOs only grow under aerobic conditions, ASM2d includes denitrifying PAOs. ASM2d includes four main functions: carbon oxidation, nitrification, denitrification, and biological phosphorus removal.

[0165] In the first sedimentation tank model 606, common first sedimentation tank models include: one or more of a point sedimentation tank model, a volume ideal sedimentation tank model, a layered sedimentation tank model, a CFD sedimentation tank model, a reaction sedimentation tank model, and the like.

[0166] Individual discrete non-flocculated particles (of the same type, such as sand) will settle at the same rate regardless of their concentration. The settling rate of an individual particle is a function of shape, size (diameter), and density only. The settling behavior of a MLSS mixture from an activated sludge reactor is very different from that of a sand suspension, primarily due to the nature of their flocculation. Initially in an SVI or zone settling rate test, the sludge containing large and small organic flocs and inorganic particles will settle as flocs (free settling), and the settling rate will be strongly affected by the MLSS concentration.

[0167] The regional sedimentation process runs through free sedimentation, flocculation sedimentation, and layered sedimentation until there is no sludge layer with the original MLSS concentration - it settles through a transition zone into the compression zone (compression sedimentation). Compression sedimentation is significantly different from regional sedimentation - the particles support each other, and compression is achieved by squeezing water out of the sludge flocs. The sedimentation rate is no longer a function of sludge concentration, but depends on the pore pressure and the compressibility and permeability of the sludge.

[0168] In the second sedimentation tank models 607 and 608, this physicochemical process is simulated by combining the corresponding phosphorus removal unit with the filtration sedimentation model. The stoichiometric ratio is used as the basis for the sedimentation model, but the complexity of the wastewater chemistry, including the effects of pH, alkalinity and other elements, means that the stoichiometric ratio is only the maximum phosphorus removal that can be achieved in the presence of a large excess of chemicals. In practice, the removal rate achieved is much lower because all the added chemical is not available for phosphorus addition. However, the available portion, and therefore the required dosage, can be estimated or calibrated for different locations and specified in the model.

[0169] In membrane filtration models 609 and 610, the filter cloth filter uses a zero volume membrane filter model, in which the soluble state variable is not affected and the particle state variable is calculated based on the solid separation proportional factor (empirical removal efficiency) and material conservation.

[0170] In the chemical disinfection model 611, the chemical disinfection model calculates the proportion of surviving E. coli based on the residence time in the disinfection device. The state variables are not affected by this model.

[0171] In output model 612, the effluent quality index model in the effluent process of output model 612 is estimated using user-specified concentration limits and specific compound weighting coefficients.

[0172] The effluent quality index represents the effluent pollution load on the receiving water body and is estimated using the expression provided in the COST simulation benchmark:

[0173]

[0174] Where Q(t) represents the instantaneous effluent flow, n represents the number of compounds in the EQI estimation, and w i represents the weight coefficient of the compound in EQI, Si(t) represents the instantaneous concentration of the compound in EQI estimation, T represents the time period of moving average calculation, and t represents the starting time of moving average calculation.

[0175] Figure 7 Shown is another flowchart of rolling calculation of initial water quality data based on a sewage treatment model in one embodiment of the present application. Figure 7 As shown, another method for performing rolling calculation on initial water quality data based on a sewage treatment model provided in an embodiment of the present application includes the following steps S700 to S712.

[0176] S700, obtaining first water quality source data.

[0177] Among them, the first water quality source data is directly extracted from untreated sewage.

[0178] S701, obtaining second water quality source data.

[0179] Specifically, the second water quality source data can be obtained by performing a preprocessing operation on the obtained first water quality source data.

[0180] S702, sending to water quality database.

[0181] The second water quality source data is sent to a water quality database.

[0182] S703, extracting initial water quality data.

[0183] Specifically, a set of second water quality source data is extracted from the water quality database as initial water quality data.

[0184] S704, determine duration information.

[0185] S705: Determine frequency information.

[0186] S706, determine output step information.

[0187] S707, input the sewage treatment model.

[0188] Specifically, the determined duration information, frequency information and output step information are input into the sewage treatment model, and corresponding parameters of the sewage treatment model are set.

[0189] S708, performing model calculation.

[0190] Specifically, model calculations are performed on initial water quality data in a sewage treatment model.

[0191] S709, obtaining water quality prediction data.

[0192] Specifically, after the initial water quality data is modeled in the sewage treatment model, water quality prediction data is obtained.

[0193] S710, obtaining first water quality data.

[0194] Specifically, the water quality prediction data includes first water quality data and second water quality data. The first water quality data extracted from the water quality prediction data will enter the sewage treatment model again for model calculation, and the step of re-entering the first water quality data into the sewage treatment model for model calculation will be repeated until the termination condition is met.

[0195] S711, obtaining second water quality data.

[0196] S712, predict the effluent quality of sewage treatment plants.

[0197] Specifically, the effluent quality of the sewage treatment plant is predicted based on the second water quality data, and advance warning is given for the effluent, and the aeration volume is adjusted or the carbon source addition is increased in time to ensure that the effluent of the sewage treatment plant is stable and meets the standards.

[0198] It should be noted that the specific process of each step of rolling calculation of initial water quality data based on the sewage treatment model in the embodiment of the present application is the same as that in the above Figures 1B to 6 The methods or steps are similar and will not be repeated in this application.

[0199] The protection scope of the water quality prediction method of the embodiment of the present application is not limited to the execution order of the steps listed in this embodiment. All solutions implemented by adding, reducing or replacing steps in the prior art based on the principles of the present application are included in the protection scope of the present application.

[0200] The embodiment of the present application also provides a water quality prediction system, which can implement the water quality prediction method of the present application. However, the implementation system of the water quality prediction method of the present application includes but is not limited to the structure of the feature vector extraction device listed in this embodiment. All structural deformations and replacements of the prior art made according to the principles of the present application are included in the protection scope of the present application.

[0201] like Figure 8 As shown, in one embodiment, the water quality prediction system 80 of the present application includes a water quality data acquisition module 81 , a water quality data input module 82 , and a water quality data prediction module 83 .

[0202] The water quality data acquisition module 81 is used to acquire initial water quality data.

[0203] The water quality data input module 82 is used to input the initial water quality data into the sewage treatment model.

[0204] The water quality data prediction module 83 is used to perform rolling calculation on the initial water quality data based on the sewage treatment model to obtain water quality prediction data.

[0205] The structures and principles of the water quality data acquisition module 81, the water quality data input module 82, and the water quality data prediction module 83 correspond to the steps in the above-mentioned water quality prediction method, so they will not be described in detail here.

[0206] In the several embodiments provided in the present application, it should be understood that the disclosed device or method can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules / units is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules or units, which can be electrical, mechanical or other forms.

[0207] The modules / units described as separate components may or may not be physically separated, and the components displayed as modules / units may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules / units may be selected according to actual needs to achieve the purpose of the embodiments of the present application. For example, the functional modules / units in the various embodiments of the present application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0208] Those of ordinary skill in the art should further appreciate that the units and steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0209] The embodiment of the present application also provides a computer-readable storage medium. A person of ordinary skill in the art can understand that all or part of the steps in the method for implementing the above embodiment can be completed by a program to instruct the processor, and the program can be stored in a computer-readable storage medium, and the storage medium is a non-transitory medium, such as a random access memory, a read-only memory, a flash memory, a hard disk, a solid-state hard disk, a magnetic tape, a floppy disk, an optical disc, and any combination thereof. The above storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disc (DVD)), or a semiconductor medium (e.g., a solid-state disk (SSD)), etc.

[0210] An embodiment of the present application also provides an electronic device. Fig. 9 The structure diagram of the electronic device 90 in one embodiment of the present application is shown as follows: the water quality prediction method provided in the embodiment of the present application can be applied to Fig. 9 The electronic device 90 is shown, but is not limited thereto. Fig. 9 As shown, the electronic device 90 includes a processor 91 , a memory, a system bus 93 , and a network interface 95 , wherein the memory may include a non-volatile storage medium 92 and an internal memory 94 .

[0211] The non-volatile storage medium 92 can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any one of the water quality prediction methods provided in the embodiments of the present application.

[0212] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0213] The internal memory 94 provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any one of the water quality prediction methods provided in the embodiments of the present application.

[0214] The network interface 95 is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will appreciate that Figure 1A The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0215] It should be understood that the processor 91 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0216] The electronic device 90 in the embodiment of the present application may include terminal devices such as tablet computers, laptop computers, mobile phones, supercomputers, smart wearable devices, etc., and can also be applied to databases, servers, and service response systems based on terminal artificial intelligence. The embodiment of the present application does not impose any restrictions on the specific type of electronic device.

[0217] For example, the electronic device can be a station (STAION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a computer, a laptop computer, a handheld communication device, a handheld computing device, and / or other devices for communicating on wireless systems and next-generation communication systems, such as mobile terminals in 5G networks, mobile terminals in future evolved public land mobile networks (Public Land Mobile Network, PLMN) or mobile terminals in future evolved non-terrestrial networks (Non-terrestrial Network, NTN), etc.

[0218] As an example but not limitation, when the electronic device is a wearable device, the wearable device can also be a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as gloves and watches equipped with near-field communication modules. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. It is attached to the user and performs payment, authentication and other operations through a pre-bound electronic card. Wearable devices are not only hardware devices, but also powerful functions achieved through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various types of smart watches and smart bracelets with display screens.

[0219] The descriptions of the processes or structures corresponding to the above-mentioned figures have different emphases. For parts that are not described in detail in a certain process or structure, please refer to the relevant descriptions of other processes or structures.

[0220] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A water quality prediction method, characterized in that: The method comprises: Obtain initial water quality data; inputting the initial water quality data into a wastewater treatment model; The initial water quality data is subjected to rolling calculation based on the sewage treatment model to obtain water quality prediction data.

2. The water quality prediction method according to claim 1, characterized in that: The inputting the initial water quality data into the sewage treatment model comprises: Obtaining first water quality source data; Performing a preprocessing operation on the first water quality source data to obtain second water quality source data; Sending the second water quality source data to a water quality database; Establishing a connection between the water quality database and the sewage treatment model; A set of the second water quality source data is extracted from the water quality database as the initial water quality data, and the initial water quality data is input into the sewage treatment model.

3. The water quality prediction method according to claim 1, characterized in that: The rolling calculation of the initial water quality data based on the sewage treatment model to obtain water quality prediction data includes: Determining the duration information, frequency information and output step information of the rolling calculation; According to the duration information, the frequency information and the output step information, the initial water quality data is rolled over and calculated based on the sewage treatment model to obtain the water quality prediction data.

4. The water quality prediction method according to claim 1, characterized in that: The rolling calculation of the initial water quality data based on the sewage treatment model includes: Inputting the initial water quality data into the sewage treatment model to obtain the first water quality prediction data; The first water quality data in the previous water quality prediction data is input into the sewage treatment model to obtain the current water quality prediction data, and this step is repeated until the termination condition is met. The first water quality data is the static indicator data in the water quality prediction data.

5. The water quality prediction method according to claim 4, characterized in that: The second water quality data in the water quality prediction data is used to predict the effluent water quality of the sewage treatment plant corresponding to the sewage treatment model within a preset time.

6. The water quality prediction method according to claim 5, characterized in that: The water quality prediction method further comprises: If the second water quality data is less than or equal to the water quality threshold, it is determined that the effluent water quality of the sewage treatment plant within the preset time is normal water quality; If the second water quality data is greater than the water quality threshold, it is determined that the effluent water quality of the sewage treatment plant within the preset time is abnormal water quality.

7. The water quality prediction method according to claim 1, characterized in that: The method for constructing the sewage treatment model comprises: Constructing an initial water quality model; Correcting the initial water quality model based on historical water quality data to obtain a corrected water quality model; The corrected water quality model is verified based on real-time water quality data to obtain the sewage treatment model.

8. A water quality prediction system, characterized in that: The water quality prediction system comprises: A water quality data acquisition module, used to acquire initial water quality data; A water quality data input module, used for inputting the initial water quality data into the sewage treatment model; The water quality data prediction module is used to perform rolling calculations on the initial water quality data based on the sewage treatment model to obtain water quality prediction data.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor; The memory is used to store computer programs; The processor is used to execute the computer program and implement the water quality prediction method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the water quality prediction method according to any one of claims 1 to 7 is implemented.

Images