A method for rapid mixing of replenishment disinfectant

Abstract

The application discloses a kind of supplementary disinfectant quick mixing method, comprising: step 1: establishing stirring time prediction model;Step 2: control based on stirring time prediction model;After the residual chlorine concentration of tap water in water tank is lower than the set value and disinfectant is added, the stirring time prediction model is used to predict the stirring time and the corresponding stirring speed required for stirring to reach the standard residual chlorine concentration, then the stirrer is controlled to stir according to the predicted stirring time and stirring speed;Step 3: iterative update;The input data and output data of stirring time prediction model each time are compared with training sample library as new data set, update training sample library, and repeat step S3 to optimize the model.The method establishes a prediction model based on stirring time, which can quantitatively predict the stirring time required to speed up the mixing speed of disinfectant, and solves the technical problem that supplementary disinfectant cannot be quickly and uniformly mixed with tap water and affects the safety of residents' water use.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of secondary water supply, in particular to a rapid mixing method of supplementing disinfectant. BACKGROUND

[0002] Secondary water supply refers to a water supply mode that supplies users or self-uses through pipelines via storage and pressurization facilities when the requirements of domestic and industrial building life drinking water on water pressure and water quantity exceed the capacity of urban public water supply or self-built water supply pipeline network. At present, the secondary water supply usually adopts a water supply mode of municipal water supply -> water storage equipment (hereinafter referred to as water tank) -> secondary pressurization water supply equipment -> user water. Among them, when the tap water of the municipal pipeline network enters the water tank, the tap water will stay in the water tank for a period of time due to various reasons. If the staying time is too long, the residual chlorine content in the tap water will be greatly reduced, which will result in poor sensory properties of the secondary water supply, easy breeding and invasion of bacteria, and thus affect the safety of residents' water use.

[0003] In order to solve the above technical problems, the prior art has proposed the following related technologies:

[0004] For example, the patent document with publication number CN111410279A discloses a method for supplementing chlorine in secondary water supply water storage equipment. The method uses a dilution device composed of two small dilution tanks to quantitatively dilute high-concentration sodium hypochlorite stock solution to a concentration range allowed by regulations, and then add it to the water tank to increase the residual chlorine concentration of the tap water in the water tank, which can effectively ensure the safety of residents' water use.

[0005] For example, the patent document with publication number CN113233557A discloses an intelligent chlorine supplementing and disinfecting control system for secondary water supply with precise control. The control system includes a secondary water supply tank, a residual chlorine real-time sampling and detection system, a distributed circulating dosing system, a chlorine supplementing system, and an artificial intelligence controller. The system uses a high-precision residual chlorine sensor to accurately detect the residual chlorine value in the water tank, making the dosing amount of the chlorine supplementing system more safe and accurate. The distributed circulating dosing system is used to make the disinfectant uniformly diffuse to all parts of the water tank, so that the disinfectant is quickly and uniformly mixed in the water tank, ensuring that the detection data of the residual chlorine real-time sampling and detection system is accurate and reliable.

[0006] The above-mentioned patents in actual application are all through the water pump to add disinfectant to the water tank and mix with tap water to increase the residual chlorine concentration. However, due to the small fluctuation range of tap water in the water tank, it is difficult for the disinfectant to be quickly and uniformly mixed with the tap water. Especially during holidays, due to the reasons such as residents going out for tourism, etc., there is a lot of water left in the water tank. If the disinfectant is added, it may take more than 1 hour to mix uniformly with the tap water. During this period, the residual chlorine concentration of the tap water in the water tank is not up to standard, and if the residents use water during this period, it will affect their health.

[0007] In addition, the prior art also discloses a means of setting a stirrer in the water tank to accelerate the mixing speed of the disinfectant and tap water, but it has the problem that the start-stop time and stirring speed of the stirrer are difficult to control; for example, if the stirring time is too short and / or the stirring speed is too low, the disinfectant is still difficult to be quickly and effectively mixed in the tap water, and if the stirring time is too long and / or the stirring speed is too fast, it will increase energy consumption.

[0008] Therefore, it is necessary to develop a new technology that can effectively accelerate the mixing of disinfectant. SUMMARY

[0009] The present application aims to overcome the above-mentioned problems in the prior art and provides a rapid mixing method for supplementing disinfectant, which establishes a prediction model based on stirring time, which can quantitatively predict the time needed for stirring to accelerate the mixing speed of disinfectant, solving the technical problem of uniform mixing of supplement disinfectant with tap water and affecting the safety of residents' water.

[0010] To achieve the above-mentioned purposes, the technical solutions adopted by the present application are as follows:

[0011] A rapid mixing method for supplementing disinfectant, comprising the following steps:

[0012] Step 1: Establishing a stirring time prediction model

[0013] The method for establishing the stirring time prediction model is as follows:

[0014] S1: Each time the residual chlorine concentration of tap water in the water tank is lower than the set value, the current residual water volume and current residual chlorine concentration of tap water in the water tank are obtained; after adding disinfectant to the water tank, the stirrer is used for stirring, and the disinfectant dosage, real-time residual chlorine concentration, stirring speed and stirring time required to reach the standard residual chlorine concentration are obtained;

[0015] S2: Based on the results of S1, a plurality of data groups of water tank volume-residual water volume-current residual chlorine concentration-disinfectant dosage-real-time residual chlorine concentration-stirring speed-stirring time are established, and the data groups are divided into training sample library and verification sample library respectively;

[0016] S3: First, train the convolutional neural network based on the training sample library to obtain the trained stirring time prediction model; then verify the stirring time prediction model based on the verification sample library until the stirring time prediction model that meets the requirements is obtained;

[0017] Step 2: Control based on the stirring time prediction model

[0018] After the residual chlorine concentration of tap water in the water tank is lower than a set value and the disinfectant is added, the stirring time prediction model is used to predict the stirring time and the corresponding stirring speed required for stirring to reach the standard residual chlorine concentration, and then the stirrer is controlled to stir according to the predicted stirring time and stirring speed.

[0019] Step 3: Iterative updating

[0020] The input data and output data of the stirring time prediction model each time are compared with the training sample library as a new data set, the training sample library is updated, and step S3 is repeated to optimize the model through repeated dynamic training.

[0021] The current residual water volume, the current residual chlorine concentration, the disinfectant addition amount, the real-time residual chlorine concentration, the stirring speed and the stirring time in step S1 are obtained based on water tanks of different volumes.

[0022] The stirring speed in step S1 is increased according to the increase of the current residual water volume.

[0023] The number of data sets in step S2 is not less than 200.

[0024] The ratio of the training sample library to the verification sample library in the data set in step S2 is 5:1.

[0025] In step 1, the current residual water volume is obtained by measuring the water level meter arranged in the water tank, the current residual chlorine concentration and the real-time residual chlorine concentration are obtained by measuring the residual chlorine instrument arranged in the water tank, and the stirring speed and the stirring time are obtained by measuring the sensor and the timer, respectively.

[0026] The advantages of the present application are as follows:

[0027] 1. The rapid mixing method comprises three steps of establishing a stirring time prediction model, controlling based on the stirring time prediction model and iterative updating, wherein the stirring time prediction model can be established according to a preset test water tank or pre-established according to a water tank in use, and in actual use, the stirring time prediction model can predict the required stirring time and the corresponding stirring speed according to the current water tank volume, the residual water volume, the current residual chlorine concentration, the disinfectant addition amount and the real-time residual chlorine concentration in advance, so as to control the stirrer to stir according to the corresponding time and speed, thereby achieving the purpose of accelerating the mixing speed of the disinfectant.

[0028] In summary, the present application can quantitatively predict the required stirring time to accelerate the mixing speed of the disinfectant, and solve the technical problem that the added disinfectant cannot be quickly and uniformly mixed with tap water and affect the safety of residents' water use.

[0029] 2、The present application can improve the prediction accuracy of the stirring time prediction model through iterative updating, which not only realizes accurate control of the stirrer, but also is conducive to achieving the effect of effective mixing and reducing energy consumption.

[0030] 3、The present application establishes the residual water volume, the current residual chlorine concentration, the disinfectant dosage, the real-time residual chlorine concentration, the stirring speed and the stirring time of the stirring time prediction model based on different volume water tanks, which makes the stirring time prediction model ensure the accuracy of the prediction results under different working conditions.

[0031] 4、The present application adopts the method that the stirring speed increases with the increase of the current residual water volume, which can use a higher stirring speed for mixing when the current residual water volume is large, thereby achieving the effect of rapid mixing.

[0032] 5、The present application sets the number of data groups to not less than 200, and makes the ratio of the training sample library to the validation sample library in the data group 5:1, which uses more data for training test, which is conducive to improving the prediction accuracy of the stirring time prediction model. BRIEF DESCRIPTION OF DRAWINGS

[0033] Figure 1 The flowchart of the present application. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application will be further described below in combination with the drawings and examples, and the implementation of the present application includes but is not limited to the following examples. Based on the examples in the present application, all other examples obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0035] The present application provides a rapid mixing method for supplementing disinfectant, as shown in Figure 1 The method specifically comprises the following steps:

[0036] Step 1: Establishing a stirring time prediction model

[0037] The data required for establishing the stirring time prediction model can be obtained on the basis of the patent document with publication number CN111410279A, and based on this, the specific establishment method of the stirring time prediction model is as follows:

[0038] S1: Each time when the residual chlorine concentration of tap water in the water tank is lower than the set value, the current residual water volume and the current residual chlorine concentration of tap water in the water tank are obtained; after adding disinfectant to the water tank, the stirrer is used for stirring, and the disinfectant dosage, real-time residual chlorine concentration, stirring speed and stirring time required to reach the standard residual chlorine concentration are obtained.

[0039] The current remaining water amount, the current residual chlorine concentration, the disinfectant dosage, the real-time residual chlorine concentration, the stirring speed and the stirring time are obtained based on water tanks with different volumes, the current remaining water amount is obtained by measuring the water level in the water tank by a water level gauge, the current residual chlorine concentration and the real-time residual chlorine concentration are both obtained by measuring the residual chlorine in the water tank by a residual chlorine meter, and the stirring speed and the stirring time are both obtained by measuring by a sensor and a timer respectively.

[0040] To improve the accuracy of the stirring time prediction model, the above data can be obtained by presetting water tanks with different volumes, by water tanks with different volumes that are actually in use, or by a combination of the two. It should be noted that the implementation of the present application requires a stirrer, so whether it is a preset water tank or a water tank in use, a stirrer needs to be provided in the water tank when obtaining the above data.

[0041] In addition, the stirring speed of the stirrer increases with the increase of the current remaining water amount, that is, the stirring speed is proportional to the current remaining water amount. When the current remaining water amount in the water tank is small, low-speed stirring can be used; when the current remaining water amount in the water tank is large, high-speed stirring can be used to achieve the best stirring and mixing effect.

[0042] S2: Based on the results of S1, a plurality of water tank volume-remaining water amount-current residual chlorine concentration-disinfectant dosage-real-time residual chlorine concentration-stirring speed-stirring time data sets are established, and the data sets are divided into training sample library and verification sample library respectively.

[0043] Preferably, the number of data sets in this step is not less than 200, and the ratio of the training sample library to the verification sample library in the data set is 5:1, so as to ensure that the stirring time prediction model obtained in S3 has higher accuracy.

[0044] S3: First, train the convolutional neural network based on the training sample library, and obtain the trained stirring time prediction model after the training is completed; then, verify the stirring time prediction model based on the verification sample library, and obtain the stirring time prediction model that meets the requirements and has high reliability after the verification is completed.

[0045] Step 2: Control based on the stirring time prediction model

[0046] After the residual chlorine concentration of tap water in the water tank is lower than the set value and the disinfectant is added, the stirring time prediction model is used to predict the stirring time and the corresponding stirring speed required for stirring to reach the standard residual chlorine concentration according to the current water tank volume, the remaining water amount, the current residual chlorine concentration, the disinfectant dosage and the real-time residual chlorine concentration, and then the stirrer is controlled to stir at the predicted stirring time and stirring speed, so that the disinfectant can be quickly and uniformly mixed with tap water.

[0047] Step 3: Iterative update

[0048] The input data and output data of the stirring time prediction model each time are compared with the training sample library as a new data set, the training sample library is updated, and the step S3 is repeated to optimize the model through repeated dynamic training, and the accuracy of the stirring time prediction model is further improved.

[0049] The method can pre-establish a stirring time prediction model, quantitatively predict the stirring time required in actual application according to the prediction model, and make the stirrer stir according to the predicted time, which not only effectively speeds up the mixing speed of the disinfectant, but also reduces the running time of the stirrer, and guarantees the water safety of the residents.

[0050] The above is only a specific embodiment of the present application, any feature disclosed in the specification can be replaced by other equivalent or similar purpose replacement features unless specifically described, and all features disclosed or all steps in the method or process can be combined in any way except for mutually exclusive features and / or steps.

Claims

1. A method of rapid mixing of make-up disinfectant solution, characterised in that, The method comprises the following steps: Step 1: establishing a stirring time prediction model The method for establishing the stirring time prediction model is as follows: S1: each time when the residual chlorine concentration of tap water in the water tank is lower than a set value, the current residual water volume and the current residual chlorine concentration of the tap water in the water tank are obtained; each time after adding disinfectant to the water tank, the stirring is carried out using a stirrer, and the disinfectant addition amount, the real-time residual chlorine concentration, the stirring speed and the stirring time required to reach the standard residual chlorine concentration are obtained; S2: based on the results of S1, a plurality of data groups of water tank volume-residual water volume-current residual chlorine concentration-disinfectant addition amount-real-time residual chlorine concentration-stirring speed-stirring time are established, and the data groups are divided into a training sample library and a verification sample library respectively; S3: first, the convolutional neural network is trained based on the training sample library to obtain a trained stirring time prediction model; then, the stirring time prediction model is verified based on the verification sample library until a stirring time prediction model meeting the requirements is obtained; Step 2: control based on the stirring time prediction model After the residual chlorine concentration of tap water in the water tank is lower than the set value and the disinfectant is added, the stirring time prediction model is used to predict the stirring time required to reach the standard residual chlorine concentration and the corresponding stirring speed, and then the stirrer is controlled to stir at the predicted stirring time and stirring speed; Step 3: iterative update The input data and output data of the stirring time prediction model each time are compared with the training sample library as new data groups, the training sample library is updated, and step S3 is repeated to optimize the model through repeated dynamic training.

2. The method of claim 1, wherein: The current residual water volume, the current residual chlorine concentration, the disinfectant addition amount, the real-time residual chlorine concentration, the stirring speed and the stirring time in step S1 are obtained based on water tanks of different volumes.

3. The method of claim 1, wherein: The stirring speed in step S1 increases according to the increase of the current residual water volume.

4. The method of claim 1, wherein: The number of data groups in step S2 is not less than 200.

5. A method of rapidly mixing a replenishment sterilizing solution as defined in claim 4, wherein: In the data groups in step S2, the ratio of the number of data groups in the training sample library to the number of data groups in the verification sample library is 5:

1.

6. The method of claim 1, wherein: In step 1, the current residual water volume is obtained by measuring the water level meter arranged in the water tank, the current residual chlorine concentration and the real-time residual chlorine concentration are obtained by measuring the residual chlorine instrument arranged in the water tank, and the stirring speed and the stirring time are obtained by measuring the sensor and the timer respectively.

Images