Intelligent water quality monitoring system for water plant

Abstract

The invention discloses an intelligent water quality monitoring system for a water plant, relates to the technical field of water treatment, and solves the problems that in the prior art, the adding proportion of a pollutant treatment agent is calculated according to a monitoring state, the pollutant treatment agent is not considered to be influenced by the environment, so that the treatment result cannot achieve an expected effect, time consumption is increased, and the cost is reduced. The technical problem that the water production efficiency is relatively low is solved. A pollution coefficient is generated according to water quality data of a water source detection area, and an alarm signal is generated according to the pollution coefficient; according to the water quality data and the environmental data of the water source treatment area, generating the putting amount of a pollutant treatment agent; an alarm signal is generated according to water quality data after putting, water quality detection during water source introduction is added, environmental data are considered in factors affecting the putting amount of the pollutant treatment agent, whether the putting effect reaches the standard or not is detected, time consumption caused by serious water source pollution and poor putting effect of the pollutant treatment agent is reduced, and the water quality detection efficiency is improved. And the water production efficiency of a water production plant is further improved.

Description

Technical Field

[0001] The present application belongs to the field of water treatment technology, and specifically is an intelligent water quality monitoring system for a water treatment plant. Background Art

[0002] Water plants play an important role in protecting public health and sanitation, promoting economic development, and maintaining the ecological environment. Through the treatment and operation of water supply systems in water plants, the daily needs of the public can be met, public health and urban development can be guaranteed. With the development of industrial automation and information technology, intelligent water quality monitoring systems have gradually become an important means for water plants to improve management levels and ensure water quality safety. However, existing water quality monitoring systems often lack comprehensiveness and intelligence, and it is difficult to meet the high requirements of water plants for water quality monitoring.

[0003] The prior art (invention patent application with publication number CN118084098A) discloses a water treatment system and method for a smart water plant, comprising the following steps: real-time monitoring of water quality of the smart water plant through sensors, water pollution change gradient analysis of the smart water plant, identification of harmful compound components, and calculation of component content floating increments for pollution change rate quantification data to obtain component content floating fitting data; calculation of the floating dosage ratio of sewage treatment agents based on the component content floating fitting data, chemical reaction simulation of harmful compound component data, and reaction degree data screening to obtain sewage reaction degree screening data; construction of a sewage reaction model for the sewage reaction degree screening data, and learning of sewage treatment intelligent control strategies to generate sewage treatment intelligent control strategies.

[0004] The above scheme realizes intelligent sewage treatment by monitoring and analyzing water quality and calculating the dosage ratio of pollutant treatment agent. The dosage ratio of pollutant treatment agent is calculated according to the monitoring status, but the lack of consideration of the influence of the environment on the pollutant treatment agent may cause the treatment result to fail to achieve the expected effect, increase time consumption, and thus lead to low water production efficiency. Therefore, the intelligent water quality monitoring system for water treatment plants still needs to be further improved. Summary of the invention

[0005] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes an intelligent water quality monitoring system for a water treatment plant, which is used to solve the technical problem that the prior art calculates the dosage ratio of the pollutant treatment agent based on the monitoring status, but fails to consider that the pollutant treatment agent is affected by the environment, which may cause the treatment result to fail to achieve the expected effect, increase time consumption, and thus lead to low water production efficiency.

[0006] To achieve the above-mentioned purpose, the first aspect of the present application provides a water quality intelligent monitoring system for a water treatment plant, comprising: a data acquisition module, a data analysis module, an early warning module and a database;

[0007] The data acquisition module: acquires water quality data of the water source detection area, water quality data and environmental data of each water source treatment area through data acquisition equipment; the water quality data includes several detection items and their corresponding detection data;

[0008] The data analysis module generates a pollution coefficient according to the water quality data of the water source detection area, and generates an alarm signal according to the pollution coefficient; and

[0009] Generate the amount of pollutant treatment agent to be added based on the water quality data and environmental data of each water source treatment area and its corresponding characteristic project data; generate an alarm signal based on the water quality data after addition;

[0010] The early warning module makes corresponding prompts according to the alarm signal and sends the alarm signal to relevant management personnel.

[0011] The present application obtains water quality data of a water source detection area, water quality data and environmental data of each water source treatment area; generates a pollution coefficient based on the water quality data of the water source detection area, and generates an alarm signal based on the pollution coefficient; and generates a pollutant treatment agent dosage based on the water quality data and environmental data of each water source treatment area, as well as its corresponding characteristic item data; generates an alarm signal based on the water quality data after dosage; makes corresponding prompts based on the alarm signal, and sends the alarm signal to relevant management personnel, thereby increasing water quality testing when water sources are introduced, taking environmental data into consideration as factors affecting the pollutant treatment agent dosage, and detecting whether the dosage is up to standard, reducing time consumption due to severe water source pollution and poor pollutant treatment agent dosage, and thereby improving the water production efficiency of the water plant.

[0012] Furthermore, generating a pollution coefficient according to water quality data of a water source detection area includes:

[0013] Obtaining several test items and corresponding test data from water quality data within the water source test area, as well as their corresponding standard safety ranges;

[0014] The test items are divided into water quality data group 1 and water quality data group 2 according to the standard safety range; the standard safety range in the water quality data group 1 is the test items with only upper limit values ​​or lower limit values; the standard safety range in the water quality data group 2 is the test items with both upper limit values ​​and lower limit values;

[0015] Generate a pollution coefficient WX1 according to the test data corresponding to several test items in the water quality data group 1;

[0016] Generate pollution coefficient 2 WX2 according to the test data corresponding to several test items in water quality data group 2;

[0017] The pollution coefficient WX of the water source detection area is calculated based on the pollution coefficient WX1 and the pollution coefficient WX2. The specific formula is as follows: WX=WX1+WX2.

[0018] Furthermore, the generation of a pollution coefficient WX1 according to the test data corresponding to a plurality of test items in the water quality data group 1 includes:

[0019] Extract the test data JSi corresponding to several test items in the water quality data group 1, and the upper limit value or lower limit value DXZi in the corresponding standard safety range;

[0020] Determine in turn whether each test data is within its corresponding standard safety range;

[0021] If yes, the contamination coefficient of the detection data is set to "0", that is, WXi=0;

[0022] If not, the item pollution coefficient WXi of the test data is calculated by the formula WXi=ki×arctan((|JSi-DXZi| / DXi)^βi); wherein ki is the proportional coefficient, ki∈(0,2 / π); βi is the exponential coefficient, βi∈(0,1); DXi is the unit data corresponding to the i-th test item in the set water quality data group 1;

[0023] The pollution coefficient WX1 is calculated by the formula: WX1=∑(WXi); wherein i represents the number corresponding to a number of test items in the water quality data set 1, and i=1, 2,…, M; M is the total number of test items in the water quality data set 1.

[0024] Furthermore, the generation of the second pollution coefficient WX2 according to the test data corresponding to the plurality of test items in the second water quality data group includes:

[0025] Extract the test data JSj corresponding to several test items in the water quality data group 2, as well as the upper and lower limits of the corresponding standard safety range; generate the standard safety intermediate value BAZj and the floating deviation FPj according to the upper and lower limits of the standard safety range;

[0026] Determine in turn whether each test data is within its corresponding standard safety range;

[0027] If yes, the contamination coefficient of the detection data WXj=0;

[0028] If not, the item pollution coefficient WXj of the test data is calculated by the formula WXj=kj×arctan(((|JSj-BAZj|-FPj) / DXj)^βj); wherein kj is the proportional coefficient, kj∈(0,2 / π); βj is the exponential coefficient, βj∈(0,1); DXj is the unit data corresponding to the jth test item in the set water quality data group 2;

[0029] The pollution coefficient WX2 of the water quality data group two is calculated by the formula: WX2=∑WXj; wherein j represents the number of each test item in the water quality data group two, j=1, 2, ..., N; N is the total number of test items in the water quality data group two.

[0030] Furthermore, the generating of the standard safety intermediate value BAZj and the floating deviation FPj according to the upper limit value and the lower limit value of the standard safety range includes:

[0031] The upper limit value in the standard safety range corresponding to the test item numbered j is marked as BAFDj, and the lower limit value is marked as BAFXj;

[0032] Calculate the standard safety intermediate value BAZj of several test data through the formula;

[0033] BAZj=(BAFDj+BAFXj) / 2;

[0034] Calculate the floating deviation FPj of several test data through the formula;

[0035] FPj=(BAFDj-BAFXj) / 2.

[0036] Further, generating an alarm signal according to the pollution coefficient includes:

[0037] Obtain the pollution coefficient of the water source detection area and the project pollution coefficients corresponding to several detection items in the water source detection area;

[0038] Determine whether the pollution coefficient of the water source detection area is greater than the overall pollution threshold; if so, generate an overall exceeding-the-standard danger alarm signal;

[0039] No, when there is a detection item corresponding to a project pollution coefficient greater than its corresponding project pollution threshold; then a project exceeding the standard danger alarm signal corresponding to the detection item is generated.

[0040] Furthermore, the pollutant treatment agent dosage is generated according to the water quality data and environmental data of each water source treatment area and its corresponding characteristic project data, including:

[0041] Extract the treatment items in the feature item data and the corresponding impact items; mark the test data corresponding to the test items that are the same as the treatment items in the water quality data as treatment test data; mark the test data corresponding to the test items that are the same as the impact items as impact test data; input the treatment test data, impact test data and environmental data into the treatment agent dosage prediction model to obtain the unit treatment agent dosage DCT;

[0042] The pollutant treatment agent dosage CTL is calculated by the formula CTL=DCT×SV; SV is the water volume.

[0043] Furthermore, the treatment agent dosage prediction model is constructed by an artificial intelligence model, including:

[0044] Acquire from the database a number of treatment detection data, impact detection data and environmental data corresponding to each characteristic item data, as well as the corresponding unit treatment agent dosage; the environmental data includes temperature;

[0045] Dividing a number of treatment detection data, impact detection data, environmental data and unit treatment agent dosage into training data, verification data and test data; performing data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set;

[0046] Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model;

[0047] By verifying the pre-trained model on the test set, we finally obtained a treatment agent dosage prediction model whose input is treatment detection data, impact detection data and environmental data, and whose output is the corresponding unit treatment agent dosage; the artificial intelligence model includes BP neural network model and RBF neural network model.

[0048] Furthermore, the data preprocessing includes data cleaning and data standardization.

[0049] Furthermore, the generating of an alarm signal according to the water quality data after the pollutant treatment agent is added includes:

[0050] Obtain the reaction time after the pollutant treatment agent is placed in the water source treatment area;

[0051] When there is a reaction duration greater than its corresponding duration threshold:

[0052] Obtain the processing and testing data from the water quality data in the corresponding water source treatment area and its corresponding standard safety range;

[0053] Determine whether the processed test data is within the corresponding standard safety range;

[0054] Yes, do nothing;

[0055] No, an abnormal alarm signal is generated.

[0056] Compared with the prior art, the beneficial effects of this application are:

[0057] 1. The present application obtains water quality data of a water source detection area, water quality data and environmental data of each water source treatment area; generates a pollution coefficient based on the water quality data of the water source detection area, and generates an alarm signal based on the pollution coefficient; and generates a pollutant treatment agent dosage based on the water quality data and environmental data of each water source treatment area, as well as its corresponding characteristic item data; generates an alarm signal based on the water quality data after dosage; makes corresponding prompts based on the alarm signal, and sends the alarm signal to relevant management personnel, thereby increasing water quality testing when water sources are introduced, taking environmental data into consideration as factors affecting the amount of pollutant treatment agents added, and detecting whether the dosage is up to standard, thereby reducing time consumption due to severe water source pollution and poor effect of pollutant treatment agent dosage, and thereby improving the water production efficiency of the water treatment plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0059] Figure 1 This is a schematic diagram of the principle of an intelligent water quality monitoring system for a water treatment plant used in this application;

[0060] Figure 2 This is a flow chart of an intelligent water quality monitoring system for a water treatment plant used in the present application. DETAILED DESCRIPTION

[0061] The technical solution of the present application will be described clearly and completely in conjunction with the embodiments below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0062] See also Figure 1-Figure 2 , the first aspect of the present application provides a water quality intelligent monitoring system for a water treatment plant, including: a data acquisition module, a data analysis module, an early warning module and a database;

[0063] Data acquisition module: The water quality data of the water source detection area, the water quality data of each water source treatment area and the environmental data are obtained through the data acquisition equipment; the water quality data includes several test items and their corresponding test data; the test items are several items that need to be measured and tested in the water source set in advance, and the test data are the content or concentration of the corresponding test items; the water source detection area is the area corresponding to the water source introduced by the water treatment plant; the water source treatment area is the area where the water source is treated in various ways after the water source is introduced by the water treatment plant; the data acquisition equipment is the detection equipment for each test data; the test data includes heavy metal content, pH value and turbidity, etc.

[0064] Data analysis module: Generate pollution coefficient according to water quality data of water source detection area, and generate alarm signal according to pollution coefficient; pollution coefficient refers to the degree of water source pollution, which is used to judge whether the corresponding water source can reach the water quality standard for normal water use by residents through treatment; generate pollutant treatment agent dosage according to water quality data and environmental data of each water source treatment area, as well as its corresponding characteristic project data; generate alarm signal according to water quality data after dosage; environmental data includes water body temperature; because temperature will affect the treatment efficiency and intensity of treatment agent; therefore, when obtaining pollutant treatment agent dosage, temperature is taken into account to improve the accuracy of treatment agent dosage setting;

[0065] Early warning module: Give corresponding prompts according to the alarm signals and send the alarm signals to relevant managers; the alarm signals include overall exceeding danger alarm signals, project exceeding danger alarm signals and abnormal alarm signals.

[0066] This embodiment obtains water quality data of a water source detection area, water quality data and environmental data of each water source treatment area; generates a pollution coefficient based on the water quality data of the water source detection area, and generates an alarm signal based on the pollution coefficient; and generates a pollutant treatment agent dosage based on the water quality data and environmental data of each water source treatment area, as well as its corresponding characteristic item data; generates an alarm signal based on the water quality data after dosage; makes corresponding prompts based on the alarm signal, and sends the alarm signal to relevant management personnel, thereby increasing water quality testing when water sources are introduced, taking environmental data into consideration as factors affecting the pollutant treatment agent dosage, and detecting whether the dosage effect meets the standards, thereby reducing time consumption due to severe water source pollution and poor pollutant treatment agent dosage effect, and thereby improving the water production efficiency of the water plant.

[0067] Generate pollution coefficients based on water quality data from the water source detection area, including:

[0068] Obtain several test items and corresponding test data in the water quality data within the water source detection area, as well as their corresponding standard safety ranges; the test data are the data corresponding to each set test item that affects water quality safety; the standard safety range is the range of each test data that determines that the water quality meets safety requirements;

[0069] The test items are divided into water quality data group 1 and water quality data group 2 according to the standard safety range; the standard safety range in water quality data group 1 is the test items with only upper limit or lower limit; the standard safety range in water quality data group 2 is the test items with both upper limit and lower limit; for example, the standard safety range of pH value is between 6.5 and 9.5, which has upper limit and lower limit, so it is divided into water quality data group 2; the standard safety range of turbidity is less than 1 degree, which has upper limit, so it is divided into water quality data group 1;

[0070] Generate a pollution coefficient WX1 according to the test data corresponding to several test items in the water quality data group 1; the pollution coefficient WX1 refers to the degree of deviation of each test data in the water quality data group 1 from its corresponding standard safety range;

[0071] Generate a pollution coefficient 2 WX2 according to the test data corresponding to several test items in the water quality data group 2; the pollution coefficient 2 WX2 refers to the degree of deviation between each test data in the water quality data group 2 and its corresponding standard safety range;

[0072] The pollution coefficient WX of the water source detection area is calculated based on the pollution coefficient one WX1 and the pollution coefficient two WX2. The specific formula is as follows: WX=WX1+WX2; as the pollution coefficients of water quality data group one and water quality data group two increase, the pollution coefficient of the water source detection area will also increase accordingly.

[0073] Generate a pollution coefficient WX1 based on the test data corresponding to several test items in the water quality data group 1, including:

[0074] Extract the test data JSi corresponding to several test items in the water quality data group 1, and the upper limit value or lower limit value DXZi in the corresponding standard safety range;

[0075] Determine in turn whether each test data is within its corresponding standard safety range;

[0076] If yes, the pollution coefficient of the corresponding test data in the water quality data group 1 is set to "0", that is, WXi = 0;

[0077] If not, the project pollution coefficient WXi of the test data is calculated by the formula WXi=ki×arctan((|JSi-DXZi| / DXi)^βi); wherein, ki is the proportional coefficient, ki∈(0,2 / π), and the setting of ki is to make WXi∈(0,1), and the specific value is set according to experience; βi is the exponential coefficient, βi∈(0,1), and the specific value is set according to experience; DXi is the unit data corresponding to the i-th test item in the set water quality data group 1; as the difference between each test data in the water quality data group 1 and its corresponding standard safety range increases, the corresponding deviation degree increases, which further indicates that the pollution degree of each test data increases, and therefore the project pollution coefficient of each test data will also increase accordingly;

[0078] The pollution coefficient WX1 is calculated by the formula: WX1 = ∑(WXi); wherein, i represents the numbers corresponding to several test items in the water quality data group one, and i = 1, 2, ..., M; M is the total number of test items in the water quality data group one; as the pollution coefficients of the items of each test data in the water quality data group one increase, the pollution coefficient of the water quality data group one will also increase accordingly.

[0079] Generate pollution coefficient 2 WX2 based on the test data corresponding to several test items in water quality data group 2, including:

[0080] Extract the test data JSj corresponding to several test items in the water quality data group 2, as well as the upper and lower limits of the corresponding standard safety range; generate the standard safety intermediate value BAZj and the floating deviation FPj according to the upper and lower limits of the standard safety range;

[0081] Determine in turn whether each test data is within its corresponding standard safety range;

[0082] If yes, the pollution coefficient of the corresponding test data in the water quality data group 2 is set to "0", WXj = 0;

[0083] If not, the project pollution coefficient WXj of the test data is calculated by the formula WXj=kj×arctan(((|JSj-BAZj|-FPj) / DXj)^βj); wherein, kj is the proportional coefficient, kj∈(0,2 / π), and the setting of kj is to make WXj∈(0,1), and the specific value is set according to experience; βj is the exponential coefficient, βj∈(0,1), and the specific value is set according to experience; DXj is the unit data corresponding to the jth test item in the set water quality data group 2; as the various test data in the water quality data group 2 deviate more and more from the standard safety range, it means that the pollution degree of each test data is getting bigger and bigger, so the project pollution coefficient of each test data will also increase accordingly;

[0084] The pollution coefficient WX2 of the water quality data group two is calculated by the formula: WX2=∑WXj; wherein j represents the number of each test item in the water quality data group two, j=1, 2,…, N; N is the total number of test items in the water quality data group two; as the pollution coefficient of each test data item in the water quality data group two increases, the pollution coefficient of the water quality data group two will also increase accordingly.

[0085] According to the standard safety range of several test data in the water quality data group 2, the corresponding standard safety intermediate value BAZj and floating deviation FPj are generated, including:

[0086] Obtain the standard safety ranges corresponding to the several test data in the water quality data group 2, as well as the corresponding maximum value BAFDj of the standard safety range and the minimum value BAFXj of the standard safety range;

[0087] Calculate the standard safety intermediate value BAZj corresponding to several test data through the formula;

[0088] BAZj=(BAFDj+BAFXj) / 2; As the maximum value of the standard safety range and the minimum value of the standard safety range corresponding to a number of test data increase, the corresponding standard safety intermediate value will also increase;

[0089] The floating deviation FPj corresponding to a number of test data is calculated by the formula; the floating deviation refers to the distance between the standard safety range and the standard safety middle value;

[0090] FPj=(BAFDj-BAFXj) / 2; as the standard safety range corresponding to a number of test data becomes larger and larger, the distance between the corresponding maximum value of the standard safety range and the minimum value of the standard safety range will increase, and therefore the floating deviation corresponding to a number of test data will also increase accordingly.

[0091] Generates alarm signals based on contamination factors, including:

[0092] Obtain the pollution coefficient of the water source detection area and the pollution coefficients corresponding to several detection data in the water source detection area;

[0093] Determine whether the pollution coefficient of the water source detection area is greater than the overall pollution threshold; if so, generate an overall exceeding-standard danger alarm signal; the overall pollution threshold is set based on experience;

[0094] No, when there is a project pollution coefficient corresponding to the detection item that is greater than its corresponding project pollution threshold, the project pollution threshold is set based on experience; then a project exceeding the standard danger alarm signal corresponding to the detection item is generated.

[0095] Based on the water quality data and environmental data of each water source treatment area and its corresponding characteristic project data, the pollutant treatment agent dosage is generated, including:

[0096] Extract the treatment items in the feature item data and the corresponding several influencing items; the treatment items are the treatment items corresponding to the water source treatment area, such as in the process of removing suspended solids, the items related to the removal of suspended solids can be set as treatment items; when the influencing items are the treatment items corresponding to the water source treatment, there will be other detection items that affect the treatment results, such as the pH value in the process of treating suspended solids that affects the treatment results; the detection data corresponding to the detection items in the water quality data that are the same as the treatment items are marked as treatment detection data; the detection data corresponding to the detection items that are the same as the influencing items are marked as influencing detection data; the processing detection data, the influencing detection data and the environmental data are input into the treatment agent dosage prediction model to obtain the unit treatment agent dosage DCT;

[0097] The pollutant treatment agent dosage CTL is calculated by the formula CTL=DCT×SV; SV is the water volume, and the basic unit of the water volume is consistent with the unit treatment agent dosage. For example, if the basic unit of the unit treatment agent dosage is "volume / liter", then the unit of the water volume should be "liter"; as the water volume increases and the unit treatment agent dosage increases, more treatment agents are needed to make the water quality reach the standard safety range, so the pollutant treatment agent dosage will also increase accordingly.

[0098] The treatment agent dosage prediction model is constructed through an artificial intelligence model, including:

[0099] Obtaining from the database a number of treatment test data, impact test data and environmental data corresponding to each characteristic item data, as well as the corresponding unit treatment agent dosage; the environmental data includes temperature;

[0100] Divide a number of treatment test data, impact test data, environmental data and unit treatment agent dosage into training data, verification data and test data; perform data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set; the ratio between the training set, the test set and the verification set is 7:2:1;

[0101] Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model;

[0102] By verifying the pre-trained model on the test set, we finally obtained a treatment agent dosage prediction model whose input is treatment detection data, impact detection data and environmental data, and whose output is the corresponding unit treatment agent dosage; the artificial intelligence model includes BP neural network model and RBF neural network model.

[0103] Data preprocessing includes data cleaning and data standardization;

[0104] Data cleaning: directly remove the missing values ​​in the treatment test data, impact test data and environmental data corresponding to each feature item data, as well as the corresponding unit treatment agent dosage, to obtain normal data;

[0105] Data normalization: Normalize normal data using the maximum and minimum normalization method to obtain a number of treatment test data, impact test data and environmental data corresponding to each characteristic item data after preprocessing, as well as the corresponding unit treatment agent dosage.

[0106] Generate alarm signals based on water quality data after the pollutant treatment agent is placed, including:

[0107] Obtain the reaction time after the pollutant treatment agent is placed in the water source treatment area;

[0108] When there is a reaction duration that is longer than its corresponding duration threshold: the duration threshold is set based on experience;

[0109] Obtain the processing and testing data from the water quality data in the corresponding water source treatment area and its corresponding standard safety range;

[0110] Determine whether the processed test data is within the corresponding standard safety range;

[0111] If yes, do nothing; if no, generate an abnormal alarm signal; if the turbidity in the water quality data in the water source treatment area is detected to be 1.5 degrees after the reaction time, and the standard safety range of turbidity is less than 1 degree, it is determined that the treatment result of the corresponding water source treatment area does not meet the standard, and the turbidity after treatment is not within the standard safety range, then generate an abnormal alarm signal.

[0112] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0113] The working principle of the present application is as follows: by obtaining water quality data of the water source detection area, water quality data and environmental data of each water source treatment area; generating a pollution coefficient according to the water quality data of the water source detection area, and generating an alarm signal according to the pollution coefficient; and, generating the amount of pollutant treatment agent according to the water quality data and environmental data of each water source treatment area, as well as its corresponding characteristic project data; generating an alarm signal according to the water quality data after the release; making corresponding prompts according to the alarm signal, and sending the alarm signal to relevant management personnel, increasing the water quality detection when the water source is introduced, taking environmental data into consideration as factors affecting the amount of pollutant treatment agent released, and detecting whether the release effect meets the standard, reducing the time consumption caused by serious water source pollution and poor effect of pollutant treatment agent release, thereby improving the water production efficiency of the water plant, and avoiding the prior art of calculating the release ratio of pollutant treatment agents based on the monitoring status, and lacking consideration of the impact of the environment on the pollutant treatment agent, which may cause the treatment results to fail to achieve the expected effect, increase time consumption, and thus lead to low water production efficiency.

[0114] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.

Claims

1. An intelligent water quality monitoring system for a water treatment plant, characterized in that: include: Data collection module, data analysis module, early warning module and database; The data acquisition module: acquires water quality data of the water source detection area, water quality data and environmental data of each water source treatment area through data acquisition equipment; the water quality data includes several detection items and their corresponding detection data; The data analysis module generates a pollution coefficient according to the water quality data of the water source detection area, and generates an alarm signal according to the pollution coefficient; and Generate the amount of pollutant treatment agent to be added based on the water quality data and environmental data of each water source treatment area and its corresponding characteristic project data; generate an alarm signal based on the water quality data after addition; The early warning module makes corresponding prompts according to the alarm signal and sends the alarm signal to relevant management personnel.

2. The water quality intelligent monitoring system for water treatment plants according to claim 1 is characterized in that: The generating of the pollution coefficient according to the water quality data of the water source detection area includes: Obtaining several test items and corresponding test data from water quality data within the water source test area, as well as their corresponding standard safety ranges; The test items are divided into water quality data group 1 and water quality data group 2 according to the standard safety range; the standard safety range in the water quality data group 1 is the test items with only upper limit values ​​or lower limit values; the standard safety range in the water quality data group 2 is the test items with both upper limit values ​​and lower limit values; Generate a pollution coefficient WX1 according to the test data corresponding to several test items in the water quality data group 1; Generate pollution coefficient 2 WX2 according to the test data corresponding to several test items in water quality data group 2; The pollution coefficient WX of the water source detection area is calculated based on the pollution coefficient WX1 and the pollution coefficient WX2. The specific formula is as follows: WX=WX1+WX2.

3. The water quality intelligent monitoring system for water treatment plants according to claim 2 is characterized in that: The method of generating a pollution coefficient WX1 according to the test data corresponding to a plurality of test items in the water quality data group 1 includes: Extract the test data JSi corresponding to several test items in the water quality data group 1, and the upper limit value or lower limit value DXZi in the corresponding standard safety range; Determine in turn whether each test data is within its corresponding standard safety range; If yes, the contamination coefficient of the detection data is set to "0", that is, WXi=0; If not, the item pollution coefficient WXi of the test data is calculated by the formula WXi=ki×arctan((|JSi-DXZi| / DXi)^βi); wherein ki is the proportional coefficient, ki∈(0,2 / π); βi is the exponential coefficient, βi∈(0,1); DXi is the unit data corresponding to the i-th test item in the set water quality data group 1; The pollution coefficient WX1 is calculated by the formula: WX1=∑(WXi); wherein i represents the number corresponding to a number of test items in the water quality data set 1, and i=1, 2,…, M; M is the total number of test items in the water quality data set 1.

4. The water quality intelligent monitoring system for water treatment plants according to claim 2 is characterized in that: The method of generating a second pollution coefficient WX2 according to the test data corresponding to a plurality of test items in the second water quality data group includes: Extract the test data JSj corresponding to several test items in the water quality data group 2, as well as the upper and lower limits of the corresponding standard safety range; generate the standard safety intermediate value BAZj and the floating deviation FPj according to the upper and lower limits of the standard safety range; Determine in turn whether each test data is within its corresponding standard safety range; If yes, the contamination coefficient of the detection data WXj=0; If not, the item pollution coefficient WXj of the test data is calculated by the formula WXj=kj×arctan(((|JSj-BAZj|-FPj) / DXj)^βj); wherein kj is the proportional coefficient, kj∈(0,2 / π); βj is the exponential coefficient, βj∈(0,1); DXj is the unit data corresponding to the jth test item in the set water quality data group 2; The pollution coefficient WX2 of the water quality data group two is calculated by the formula: WX2=∑WXj; wherein j represents the number of each test item in the water quality data group two, j=1, 2, ..., N; N is the total number of test items in the water quality data group two.

5. The water quality intelligent monitoring system for water treatment plants according to claim 4 is characterized in that: The step of generating a standard safety intermediate value BAZj and a floating deviation FPj according to the upper limit value and the lower limit value of the standard safety range includes: The upper limit value in the standard safety range corresponding to the test item numbered j is marked as BAFDj, and the lower limit value is marked as BAFXj; Calculate the standard safety intermediate value BAZj of several test data through the formula; BAZj=(BAFDj+BAFXj) / 2; Calculate the floating deviation FPj of several test data through the formula; FPj=(BAFDj-BAFXj) / 2.

6. The water quality intelligent monitoring system for water treatment plants according to claim 1 is characterized in that: The step of generating an alarm signal according to the pollution coefficient comprises: Obtain the pollution coefficient of the water source detection area and the project pollution coefficients corresponding to several detection items in the water source detection area; Determine whether the pollution coefficient of the water source detection area is greater than the overall pollution threshold; if so, generate an overall exceeding-the-standard danger alarm signal; No, when there is a detection item corresponding to a project pollution coefficient greater than its corresponding project pollution threshold; then a project exceeding the standard danger alarm signal corresponding to the detection item is generated.

7. The water quality intelligent monitoring system for water treatment plants according to claim 1 is characterized in that: The pollutant treatment agent dosage is generated according to the water quality data and environmental data of each water source treatment area and its corresponding characteristic project data, including: Extract the treatment items in the feature item data and the corresponding impact items; mark the test data corresponding to the test items that are the same as the treatment items in the water quality data as treatment test data; mark the test data corresponding to the test items that are the same as the impact items as impact test data; input the treatment test data, impact test data and environmental data into the treatment agent dosage prediction model to obtain the unit treatment agent dosage DCT; The pollutant treatment agent dosage CTL is calculated by the formula CTL=DCT×SV; SV is the water volume.

8. The water quality intelligent monitoring system for water treatment plants according to claim 7 is characterized in that: The treatment agent dosage prediction model is constructed by an artificial intelligence model, including: Acquire from the database a number of treatment detection data, impact detection data and environmental data corresponding to each characteristic item data, as well as the corresponding unit treatment agent dosage; the environmental data includes temperature; Dividing a number of treatment detection data, impact detection data, environmental data and unit treatment agent dosage into training data, verification data and test data; performing data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set; Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally obtained a treatment agent dosage prediction model whose input is treatment detection data, impact detection data and environmental data, and whose output is the corresponding unit treatment agent dosage; the artificial intelligence model includes BP neural network model and RBF neural network model.

9. The water quality intelligent monitoring system for water treatment plants according to claim 1 is characterized in that: The generating of an alarm signal according to the water quality data after the pollutant treatment agent is added includes: Obtain the reaction time after the pollutant treatment agent is placed in the water source treatment area; When there is a reaction duration greater than its corresponding duration threshold: Obtain the processing and testing data from the water quality data in the corresponding water source treatment area and its corresponding standard safety range; Determine whether the processed test data is within the corresponding standard safety range; If yes, no action is taken; if no, an abnormal alarm signal is generated.

Images