Dosing control method, device, product and plant in water treatment processes

Abstract

The present disclosure relates to the technical field of water treatment, and provides a dosing control method, device, product and equipment in a water treatment process. The method comprises: obtaining a current characteristic value of a dosing amount prediction characteristic in the water treatment process; obtaining a first dosing amount prediction grade and a first dosing amount prediction value based on a dosing amount classification prediction model and a dosing amount regression prediction model in a preset dosing amount prediction model according to the current characteristic value; determining a current dosing amount prediction value based on the first dosing amount prediction grade and the first dosing amount prediction value; determining a first difference value between the current dosing amount prediction value and a current dosing amount value of a dosing pump; updating a current operating frequency of the dosing pump according to the first difference value, the first dosing amount grade to which the current dosing amount prediction value belongs, and a second dosing amount grade to which the current dosing amount value of the dosing pump belongs; and controlling the dosing pump to perform a dosing operation according to the current operating frequency. The present scheme can prolong the service life of the dosing pump.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of water treatment, and in particular, to a dosing control method in a water treatment process, a dosing control device in the water treatment process, a computer program product and an electronic device. BACKGROUND

[0002] In the water treatment process, the dosing amount in the water treatment process can be controlled by the running frequency of the dosing pump.

[0003] In the related art, as soon as the predicted dosing amount value changes, the running frequency of the dosing pump is adjusted to put the dosing amount corresponding to the predicted dosing amount value into the water to be treated, but frequent running frequency adjustment will increase the mechanical wear of the dosing pump, reduce the service life of the dosing pump, and cause the dosing amount to fluctuate back and forth, affecting the water treatment effect.

[0004] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present disclosure, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0005] The purpose of the present disclosure is to provide a dosing control method in a water treatment process, a dosing control device in the water treatment process, a computer program product and an electronic device, thereby at least prolonging the service life of the dosing pump to some extent.

[0006] Other characteristics and advantages of the present disclosure will become apparent from the following detailed description, or will be learned by practice of the present disclosure.

[0007] According to a first aspect of the present disclosure, a dosing control method in a water treatment process is provided, comprising: obtaining a current feature value of a dosing amount prediction feature in a water treatment process, the dosing amount prediction feature comprising a floc feature, an inlet water parameter feature and an outlet water parameter feature; obtaining a first dosing amount prediction level and a first dosing amount prediction value based on a dosing amount classification prediction model and a dosing amount regression prediction model in a preset dosing amount prediction model, respectively, according to the current feature value of the dosing amount prediction feature; determining a current dosing amount prediction value based on an overlapping relationship between the first dosing amount prediction level and the first dosing amount prediction value; determining a first difference value between the current dosing amount prediction value and a current dosing amount value of the dosing pump, updating a current running frequency of the dosing pump according to the first difference value, a first dosing amount level to which the current dosing amount prediction value belongs and a second dosing amount level to which the current dosing amount value of the dosing pump belongs, and controlling the dosing pump to perform a dosing operation in the water treatment process according to the current running frequency.

[0008] According to a second aspect of the present disclosure, a dosing control device in a water treatment process is provided, comprising: a current characteristic value acquisition module configured to acquire a current characteristic value of a dosing amount prediction characteristic in the water treatment process, the dosing amount prediction characteristic comprising a floc characteristic, an influent parameter characteristic, and an effluent parameter characteristic; a prediction module configured to obtain a first dosing amount prediction level and a first dosing amount prediction value based on a dosing amount classification prediction model and a dosing amount regression prediction model in a preset dosing amount prediction model, respectively, according to the current characteristic value of the dosing amount prediction characteristic; a current dosing amount prediction value determination module configured to determine a current dosing amount prediction value based on an overlapping relationship between the first dosing amount prediction level and the first dosing amount prediction value; and a dosing pump control module configured to determine a first difference value between the current dosing amount prediction value and a current dosing amount value of a dosing pump, update a current operating frequency of the dosing pump according to the first difference value, a first dosing amount level to which the current dosing amount prediction value belongs, and a second dosing amount level to which the current dosing amount value of the dosing pump belongs, and control the dosing pump to perform a dosing operation in the water treatment process according to the current operating frequency.

[0009] According to a third aspect of the present disclosure, a computer program product containing instructions which, when executed on a computer, cause the computer to perform the steps of the dosing control method in a water treatment process according to the first aspect is provided.

[0010] According to a fourth aspect of the present disclosure, a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the dosing control method in a water treatment process according to the first aspect of the above-mentioned embodiments is provided.

[0011] According to a fifth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the dosing control method in a water treatment process according to the first aspect of the above-mentioned embodiments.

[0012] According to the above technical solutions, the dosing control device in a water treatment process, the dosing control device in a water treatment process, and the computer program product and electronic device implementing the dosing control method in a water treatment process according to the exemplary embodiments of the present disclosure at least have the following advantages and positive effects:

[0013] In the technical solution provided by some embodiments of the present disclosure, a dosing amount prediction grade is obtained according to a dosing amount classification prediction model, a dosing amount prediction value is obtained according to a dosing amount regression prediction model, and then a current dosing amount prediction value is determined according to the dosing amount prediction grade and the dosing amount prediction value. Then, the current running frequency of the dosing pump is updated according to a first difference value between the current dosing amount prediction value and an actual dosing amount value of the dosing pump, and a relationship between a first dosing amount grade to which the current dosing amount prediction value belongs and a second dosing amount grade to which the actual dosing amount value of the dosing pump belongs. The dosing amount in the water treatment process is controlled according to the updated current running frequency. Compared with the related art, on the one hand, the present disclosure constrains the dosing amount prediction value by the dosing amount prediction grade, thereby improving the prediction accuracy of the dosing amount prediction value. On the other hand, the present disclosure updates the current running frequency of the dosing pump according to the first difference value and the relationship between the first dosing amount grade and the second dosing amount grade, thereby avoiding frequent adjustment of the dosing pump while ensuring dosing accuracy, which is conducive to prolonging the service life of the dosing pump.

[0014] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and are not limiting to the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0015] The accompanying drawings, which are incorporated into and form part of the specification, illustrate an embodiment consistent with the present disclosure and, together with the specification, serve to explain the principles of the present disclosure. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0016] Figure 1 A flowchart of a dosing control method in a water treatment process in an exemplary embodiment of the present disclosure is shown;

[0017] Figure 2 A schematic diagram of a water treatment system in an exemplary embodiment of the present disclosure is shown;

[0018] Figure 3 A flowchart of a method for determining a preset dosing amount prediction model in an exemplary embodiment of the present disclosure is shown;

[0019] Figure 4 A flowchart of a method for updating the current running frequency of the dosing pump in an exemplary embodiment of the present disclosure is shown;

[0020] Figure 5 A flowchart of a method for updating the current running frequency of the first dosing pump and the second dosing pump in an exemplary embodiment of the present disclosure is shown;

[0021] Figure 6 Fig. 2 shows a flow diagram illustrating another method of updating the current operating frequency of the first dosing pump and the second dosing pump in an exemplary embodiment of the present disclosure;

[0022] Figure 7 Fig. 3 shows a block diagram illustrating a composition of a dosing control device in a water treatment process in an exemplary embodiment of the present disclosure;

[0023] Figure 8 Fig. 4 shows a block diagram illustrating a structure of an electronic device in an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] Example implementations are now described with reference to the drawings; however, these implementations are merely examples of implementations and are not intended to limit the scope of what is described herein. Rather, the scope of the descriptions is to be accorded the broadest interpretation so as to encompass all similar technologies and functions. Various aspects, features, and embodiments of the disclosure will become more fully apparent and understood from the following description and appended claims, and appended claims, taken in conjunction with the accompanying drawings. Thus, example implementations will be described herein in the context of various methods and devices.

[0025] In this specification, the use of the phrases "one", "a", "the", and "said” is used to mean that there are one or more of the features / elements / etc.; the use of the phrases “include” and “comprise” is used to mean an open-ended inclusion of the specified element / feature / etc. and does not exclude additional features / elements / etc.; the use of the phrases “first” and “second” etc. is merely used as labels, and does not limit the number of objects.

[0026] In addition, the drawings are merely schematic and are not necessarily drawn to scale. Like reference numerals designate like elements throughout the drawings. Some of the blocks in the diagrams are functional blocks that represent functions implemented by software, hardware, or a combination of software and hardware. The functional blocks can be implemented in software, or in one or more hardware components or integrated circuits, or in different combinations thereof, as desired, and as is understood by those skilled in the art.

[0027] In the related art, in the intelligent water treatment process, the operating frequency of the dosing pump is adjusted as soon as the predicted value of the dosing amount changes, so as to change the dosing amount, and the dosing amount is adjusted only by one dosing pump. This way will increase the mechanical wear of the dosing pump and reduce the service life of the dosing pump. At the same time, the adjustment range of a single dosing pump is limited, and it cannot well adapt to the dynamic changes of the water quality to be treated.

[0028] Figure 1 A flowchart of a dosing control method in a water treatment process in an example embodiment of the present disclosure is shown. Referring to Figure 1 , the method comprises:

[0029] Step S110, obtaining a current feature value of a dosing amount prediction feature in a water treatment process, the dosing amount prediction feature comprising floc features, water inlet parameter features and water outlet parameter features;

[0030] Step S120, according to the current feature value of the dosing amount prediction feature, respectively based on the dosing amount classification prediction model and the dosing amount regression prediction model in the preset dosing amount prediction model, obtaining a first dosing amount prediction grade and a first dosing amount prediction value;

[0031] Step S130, determining a current dosing amount prediction value based on the overlapping relationship between the first dosing amount prediction grade and the first dosing amount prediction value;

[0032] Step S140, determining a first difference value between the current dosing amount prediction value and the current dosing amount value of the dosing pump, updating the current operating frequency of the dosing pump according to the first difference value, the first dosing amount grade to which the current dosing amount prediction value belongs and the second dosing amount grade to which the current dosing amount value of the dosing pump belongs, and controlling the dosing pump to perform dosing operation in the water treatment process according to the current operating frequency.

[0033] In Figure 1In the technical solution provided by the embodiment, the dosing amount prediction grade is obtained according to the dosing amount classification prediction model, the dosing amount prediction value is obtained according to the dosing amount regression prediction model, the current dosing amount prediction value is determined according to the dosing amount prediction grade and the dosing amount prediction value, the first difference between the current dosing amount prediction value and the current actual dosing amount value of the dosing pump and the relationship between the first dosing amount grade to which the current dosing amount prediction value belongs and the second dosing amount grade to which the current actual dosing amount value of the dosing pump belongs are determined, and the current operating frequency of the dosing pump is updated, so as to control the dosing amount in the water treatment process according to the updated current operating frequency. Compared with the related art, on the one hand, the prediction accuracy of the dosing amount prediction value is improved by constraining the dosing amount prediction value through the dosing amount prediction grade; on the other hand, the current operating frequency of the dosing pump is updated through the first difference and the relationship between the first dosing amount grade and the second dosing amount grade, so that the dosing pump can be adjusted frequently while ensuring the dosing accuracy, which is conducive to prolonging the service life of the dosing pump.

[0034] Next, first, the specific implementation of "step S110, obtaining the current characteristic value of the dosing amount prediction characteristic in the water treatment process" will be described in detail.

[0035] In order to more clearly illustrate the water treatment process of the present disclosure, first, the water treatment process of the present disclosure will be described in combination with Figure 2 An exemplary Figure 2 A schematic diagram of a water treatment system in an exemplary embodiment of the present disclosure is shown. Referring to Figure 2 , the water treatment system can include a water inlet tank 21, a flocculation tank 22, a sedimentation tank 23, a filter tank 24 and a water outlet tank 25. The water inlet tank 21 can adjust the water quantity of the incoming water, and at the same time, it can buffer the sudden change of the raw water quality. The flocculation tank 22 is used to add flocculants such as polyaluminum chloride to the water, so that the fine suspended particles, colloids and other impurities in the water are destabilized and aggregated to form larger flocs, so as to be separated by subsequent sedimentation. The sedimentation tank 23 allows the large flocs formed in the flocculation tank to settle to the bottom of the tank by gravity, so as to separate the solid and liquid and remove most of the suspended solids, silt and other impurities in the water. The filter tank 24 further removes the residual fine suspended particles, colloids, bacteria and other impurities in the water through filter media such as quartz sand and activated carbon, so as to improve the clarity and transparency of the water and make the water quality meet higher standards. The water outlet tank 25 is used to store the treated clear water to provide stable water supply for the water use link. At the same time, the water quality of the treated water can also be monitored in the water outlet tank 25, such as detecting pH, turbidity, suspended solids and other indicators, to ensure that the outlet water quality meets the relevant standards and use requirements.

[0036] For example, a water inlet parameter detection device, such as a water inlet pH detection device, a water inlet temperature detection device, a water inlet turbidity detection device, and a water inlet flow rate detection device, can be arranged between the water inlet tank 21 and the flocculation tank 22. An underwater camera can be arranged in the flocculation tank 22 to capture flocculation images and obtain flocculation features. An underwater camera can also be arranged in the sedimentation tank 23 to capture flocculation sedimentation videos. A dosing pump can be arranged between the water inlet tank 21 and the flocculation tank 22 to add flocculants to the water.

[0037] In an exemplary embodiment, the dosing amount prediction features include flocculation features, water inlet parameter features, and water outlet parameter features. The dosing amount prediction features can be understood as features associated with the dosing amount and can be used to reflect or affect the dosing amount.

[0038] In an exemplary embodiment, the flocculation features can be determined by flocculation images captured by a camera. For example, an underwater camera can be arranged in the flocculation tank, and the underwater camera can be installed on the inner wall of the flocculation tank. The underwater camera can capture flocculation images of the water in the flocculation tank, and the camera can send the captured flocculation images to a server. After receiving the flocculation images, the server can perform feature extraction processing on the flocculation images to obtain the flocculation features. The flocculation features can include flocculation area distribution features, flocculation quantity per unit area, flocculation average particle size, and the like.

[0039] For example, a flocculation recognition model can be pre-trained to extract flocculation features. For example, a large number of historical flocculation images can be pre-collected, and then the historical flocculation images can be manually labeled to label the contours or boundaries of each flocculation in the flocculation images. The contours or boundaries correspond to flocculation areas and flocculation particle sizes, and the number of flocculations in the flocculation images, which are used as training data.

[0040] The machine learning model is trained by the training data, so that the machine learning model can identify the outline or boundary of the floc in the image, the area of each floc, and the number of flocs in the image according to the identification. The existing target detection model can also be fine-tuned by the training data to train the target detection model to detect and identify the floc, so as to obtain the floc identification model. Through the floc identification model, the floc in the image containing the floc can be accurately identified, and the area and particle size of the identified floc and the number of flocs in the image can be determined. Then, the identification result of the floc identification model is analyzed and processed to obtain the floc characteristics. For example, the area distribution of the identified floc (such as the number ratio of different areas, etc.), the average of all floc particle sizes, the average floc particle size, the number of flocs per unit area according to the number of flocs in the image and the real scene area indicated by the image, and the like are obtained. Of course, the floc characteristics can include other characteristics such as floc morphology and edge sharpness, which are not specially limited in the example embodiment.

[0041] In an example embodiment, the water inlet parameter characteristics include water inlet pH value, water inlet flow rate, water inlet turbidity, and water inlet temperature. As described above, water inlet pH value detection equipment, water inlet flow rate detection equipment, water inlet turbidity detection equipment, and water inlet temperature detection equipment can be installed between the water inlet tank and the flocculation tank. These water inlet parameter detection equipment can send the detected water inlet parameters to the server, and the server can obtain the water inlet parameter characteristics according to the data sent by these water inlet parameter detection equipment.

[0042] In an example embodiment, the water outlet parameter characteristics include water outlet turbidity, water outlet pH, and water outlet suspended solids content. For example, water outlet turbidity detection equipment, water outlet pH detection equipment, and water outlet suspended solids content detection equipment can be configured in the water outlet tank to detect the water outlet parameter characteristics. These water outlet parameter detection equipment can send the detected water outlet parameter characteristics to the server.

[0043] In an example embodiment, the water inlet parameters can be detected at regular intervals, and the latest detected water inlet parameters and the currently detected water inlet parameters are compared. When the change of any water inlet parameter exceeds the corresponding preset threshold, the camera is started to shoot the floc image, and the current water inlet parameter characteristics, the shot floc image, and the water outlet parameter characteristics are sent to the server for the server to perform the dosage prediction control according to the present disclosure.

[0044] In other words, in the present disclosure, the water inlet parameter can be collected at a timing, and then it is determined whether to re-predict the coagulant dosage according to the fluctuation of the water inlet parameter. For example, when the water inlet parameter changes greatly, the re-prediction control of the coagulant dosage is performed again. When the water inlet parameter does not change or the water inlet parameter does not change greatly compared with the last water inlet parameter, the coagulant dosage corresponding to the previous water inlet parameter can be directly used for coagulant control. In this way, the coagulant dosage prediction needs to be performed at each sampling time, which can improve the coagulant control efficiency and save the computing resources.

[0045] Of course, the water inlet parameter, the floc image and the water outlet parameter can also be collected at a timing, and then the related data can be sent to the server to perform the prediction control of the coagulant dosage at a timing. That is, the fluctuation of the water inlet parameter is not determined, and the prediction control of the coagulant dosage is directly performed at a timing. The present exemplary embodiment does not specially limit this.

[0046] In an exemplary embodiment, the current characteristic value of the coagulant dosage prediction feature can be understood as the specific value of each coagulant dosage prediction feature collected at the current sampling time, such as the water inlet temperature value, the water inlet pH value, etc.

[0047] Next, the specific embodiment of “step S120, obtaining the first coagulant dosage prediction level and the first coagulant dosage prediction value based on the coagulant dosage classification prediction model and the coagulant dosage regression prediction model in the preset coagulant dosage prediction model respectively according to the current characteristic value of the coagulant dosage prediction feature” is described in detail.

[0048] In an exemplary embodiment, the current characteristic value of each coagulant dosage prediction feature can be input into the coagulant dosage regression prediction model corresponding to the coagulant dosage prediction feature in the preset coagulant dosage prediction model, and the candidate coagulant dosage prediction value corresponding to each coagulant dosage prediction feature can be obtained according to the output of each coagulant dosage regression prediction model. The first coagulant dosage prediction value can be obtained according to each candidate coagulant dosage prediction value. At the same time, the characteristic value of each coagulant dosage prediction feature can be input into the coagulant dosage classification prediction model corresponding to the coagulant dosage prediction feature in the preset coagulant dosage prediction model, and the candidate coagulant dosage prediction level corresponding to each coagulant dosage prediction feature can be obtained according to the output of each coagulant dosage classification prediction. Each candidate coagulant dosage prediction level can obtain the first coagulant dosage prediction level.

[0049] Exemplarily, Figure 3 A flowchart for illustrating a method for determining a preset coagulant dosage prediction model in an exemplary embodiment of the present disclosure is shown. Referring to FIG. 3, Figure 3 The method can include steps S310 to S370. Wherein:

[0050] In step S310, a first label data set corresponding to each dosing amount prediction feature is generated according to historical data corresponding to each dosing amount prediction feature and historical dosing amount values corresponding to the historical data.

[0051] For example, the feature values of the historical inflow parameter features and the correct dosing amount values corresponding to the feature values can be collected to obtain the first label data set corresponding to the inflow parameter features. The historical flocculation images are collected, and the flocculation features of the historical flocculation images are extracted. The first label data set corresponding to the flocculation features is obtained according to the extracted flocculation features and the correct dosing amount values corresponding to the historical flocculation images. The feature values of the historical outflow parameter features and the correct dosing amount values corresponding to the feature values are collected to generate the first label data set corresponding to the outflow parameter features. In other words, one dosing amount prediction feature corresponds to one label data set, and the number of dosing amount prediction features corresponds to the number of first label data sets.

[0052] The correct dosing amount value can be understood as the dosing amount that can make the water quality reach the preset standard under the feature value.

[0053] In an exemplary embodiment, the historical data of the dosing amount prediction features can be collected, and if the dosing amount corresponding to the historical data is not the correct dosing amount value, the historical data can be removed, that is, the collected historical data is filtered according to whether it corresponds to a normal dosing amount value, to obtain the first label data set corresponding to each dosing amount prediction feature.

[0054] In step S320, a second label data set corresponding to each dosing amount prediction feature is generated according to the historical data corresponding to each dosing amount prediction feature and the dosing amount grade to which the historical data corresponding to the historical data belongs in the different dosing amount grades corresponding to the dosing amount prediction feature.

[0055] In an exemplary embodiment, the different dosing amount grades corresponding to each dosing amount prediction feature can be determined in advance. Different dosing amount grades correspond to different dosing amount ranges.

[0056] For example, the number of levels of the dosing amount grades corresponding to different dosing amount prediction features is the same, and the levels representing the same dosing degree have the same level identifier, such as the dosing amount grades corresponding to each dosing amount prediction feature are divided into three levels of low, medium and high. However, the dosing amount ranges indicated by the dosing amount grades of the same level corresponding to different dosing amount prediction features can be the same or different, such as the dosing amount range indicated by the low-level dosing amount corresponding to the inflow parameter features can be [a1, b1], and the dosing amount range indicated by the low-level dosing amount corresponding to the flocculation features can be [a2, b2]. Wherein, a1, a2, b1, b2 are different values.

[0057] For example, the determination of the different dosing amount levels corresponding to any dosing amount prediction feature can include: collecting historical data of the dosing amount prediction feature, and clustering the collected historical data; determining different dosing amount prediction levels according to the dosing amount indicated by the historical data in each cluster category in the clustering result.

[0058] For example, for each dosing amount prediction feature, the historical data of the dosing amount prediction feature can be collected, and the historical data can also be filtered according to whether there is a correct dosing amount value, so as to obtain the historical data of the dosing amount prediction feature. For example, the first historical data corresponds to the water inflow parameter feature, the second historical data corresponds to the flocculation feature, and the third historical data corresponds to the water outflow parameter feature. Then, the first clustering is performed on the first historical data to obtain the first clustering result, the second clustering is performed on the second historical data to obtain the second clustering result, and the third clustering is performed on the third historical data to obtain the third clustering result.

[0059] In the above example, the number of cluster categories of each dosing amount prediction feature is the same, that is, the K value in the clustering algorithm is the same, that is, the K values of the first clustering, the second clustering, and the third clustering are the same, for example, all are 3. The specific K value can be determined according to experience or test results, and the present example embodiment does not specially limit this. For example, different K values are taken, the clustering results of different K values are tested, and the K value with the best test effect is selected as the final K value.

[0060] For example, the size relationship of the dosing amount degree between the different dosing amount levels corresponding to different cluster categories can be determined according to the size relationship of the average values of the dosing amount indicated by the historical data in each cluster category in the clustering result; and the dosing amount range indicated by the dosing amount level corresponding to the cluster category can be determined according to the minimum value and the maximum value of the dosing amount indicated by the historical data in the cluster category.

[0061] For example, when the K value is 3, each cluster category corresponds to one level, and there are three levels in total. The average value of the correct dosing amount value corresponding to the historical data in the cluster category 1 is c1, the average value of the correct dosing amount value corresponding to the historical data in the cluster category 2 is c2, and the average value of the correct dosing amount value corresponding to the historical data in the cluster category 3 is c3. The size relationship of c1, c2, and c3 is c1 < c2 < c3. Therefore, the cluster category 1 corresponds to the first dosing amount level, the cluster category 2 corresponds to the second dosing amount level, and the cluster category 3 corresponds to the third dosing amount level. That is, the dosing amount degree of the first dosing amount level is less than that of the second dosing amount level, and the dosing amount degree of the second dosing amount level is less than that of the third dosing amount level. For example, the first dosing amount level is a low dosing amount level, the second dosing amount level is a medium dosing amount level, and the third dosing amount level is a high dosing amount level.

[0062] For example, the range of the dosing amount indicated by each dosing amount level can be determined according to the minimum and maximum values of the dosing amounts indicated by the historical data in the cluster category corresponding to the dosing amount level. For example, there are 100 historical data in a dosing amount level, and the 100 historical data correspond to 100 dosing amount values. The interval range composed of the minimum and maximum values of the 100 dosing amount values is the range of the dosing amount indicated by the dosing amount level.

[0063] Taking the first dosing amount level, the second dosing amount level, and the third dosing amount level as examples, the range of the dosing amount corresponding to the dosing amount level determined according to the clustering result can have a situation that there is an overlapping interval between the dosing ranges indicated by different dosing amount levels. At this time, manual verification and adjustment can be performed to make the dosing amount ranges of adjacent dosing amount levels continuous and non-overlapping. Alternatively, the range of the dosing amount corresponding to the dosing amount level obtained according to the clustering result can be used as an initial dosing amount range, and the initial dosing amount range can be adjusted according to a first preset rule to obtain the final dosing amount range corresponding to the dosing amount level.

[0064] For example, the first preset rule can include: in the case that there is an overlapping interval between the dosing amount ranges indicated by adjacent dosing amount levels, the overlapping interval is used as a buffer interval, i.e., the dosing amount of the buffer interval belongs to both adjacent dosing amount levels, and the dosing amount of the non-overlapping part belongs to the respective dosing amount level. That is, the dosing amount range indicated by each dosing amount level is composed of a non-overlapping interval and a buffer interval. In this way, when data labeling is performed, the dosing amount level of the historical data whose dosing amount value falls within the buffer interval has two labels. Subsequently, when prediction is performed, the final output result is also selected by class confidence, e.g., the class whose confidence is greater than 0.9 is the final prediction class. In this way, the problem of low prediction accuracy caused by unreasonable interval range division of the dosing amount level can be avoided to the greatest extent.

[0065] For example, the first preset rule can also include: the overlapping interval is divided equally and allocated to the dosing amount ranges indicated by adjacent dosing amount levels, i.e., the overlapping interval is divided into two equal parts by the median value of the overlapping interval. The final dosing amount range corresponding to the lower level in the adjacent dosing amount levels is from the minimum value in the initial dosing amount range corresponding to the lower level to the median value of the overlapping interval, and the final dosing amount range corresponding to the higher level in the adjacent dosing amount levels is from the median value of the overlapping interval to the maximum value in the initial dosing amount range corresponding to the higher level.

[0066] Similarly, for the case that the initial dosing amount ranges corresponding to adjacent dosing amount levels are discontinuous, the adjustment can also be performed based on a second preset rule.

[0067] Exemplarily, the second preset rule can comprise: taking a range interval between the initial dosing amount ranges corresponding to adjacent dosing amount grades as a buffer interval, and the buffer interval belongs to the adjacent dosing amount grades.

[0068] Exemplarily, the second preset rule can also comprise: taking a range interval between the initial dosing amount ranges corresponding to adjacent dosing amount grades as a buffer interval, and dividing the buffer interval into two equal parts by the median value of the buffer interval, and assigning the two equal parts to the adjacent dosing amount grades. That is, the final dosing amount range corresponding to the lower grade of the adjacent dosing amount grades is from the minimum value in the initial dosing amount range corresponding to the lower grade to the median value of the buffer interval, and the final dosing amount range corresponding to the higher grade of the adjacent dosing amount grades is from the median value of the buffer interval to the maximum value in the initial dosing amount range corresponding to the higher grade.

[0069] In an exemplary factual manner, if there is an overlapping interval between the dosing amount ranges indicated by the dosing amount grades that are not adjacent, such as the overlapping interval between the dosing amount ranges corresponding to the lower dosing amount grade and the higher dosing amount grade, the K value is adjusted and the clustering is performed again, and the dosing amount grades are determined again according to the clustering results. The dosing amount ranges indicated by the dosing amount grades that are not adjacent can also be adjusted based on the dosing amount range indicated by the intermediate dosing amount grade between the dosing amount grades that are not adjacent, so as to ensure that there is no overlapping interval between the dosing amount ranges indicated by the dosing amount grades that are not adjacent, such as taking the minimum value of the intermediate dosing amount grade as the upper limit value of the lower dosing amount grade among the dosing amount grades that are not adjacent, and taking the maximum value of the intermediate dosing amount grade as the lower limit value of the higher dosing amount grade among the dosing amount grades that are not adjacent.

[0070] Adjusting the initial dosing amount range based on the above-mentioned manner can ensure the rationality of the determined dosing amount range, and ensure that the dosing amount range corresponding to the dosing amount grade is continuous and there is no fault, so that the current dosing amount prediction value can be more accurately determined according to the overlapping relationship between the first dosing amount prediction value and the first dosing amount prediction grade in the subsequent step.

[0071] Through the above-mentioned manner, the dosing amount range indicated by the different dosing amount grades corresponding to different dosing amount prediction features can be automatically determined based on the historical data. Compared with the manual determination of the dosing amount grade, this clustering automatic determination of the dosing amount grade not only improves the determination efficiency of the dosing amount grade, but also provides a basis for the determination of the dosing amount grade, so that the determined dosing amount grade has high explainability and reliability.

[0072] For example, after obtaining the dosing amount range indicated by the different dosing amount grades corresponding to each dosing amount prediction feature, the first label data set corresponding to each dosing amount prediction feature can be copied to generate a first label copy data set. For any first label copy data set corresponding to a dosing amount prediction feature, the correct dosing amount value label in the first label copy data set is modified to the specific dosing amount grade to which the correct dosing amount value belongs in the different dosing amount grades corresponding to the dosing amount prediction feature, thereby generating a second label data set.

[0073] For example, the first label data set A corresponding to the water inflow parameter feature is copied to generate the first label copy data set A1 corresponding to the water inflow parameter feature. According to the dosing amount range indicated by the different dosing amount grades corresponding to the water inflow parameter feature, it is determined which range in the dosing amount range indicated by the different dosing amount grades corresponding to the water inflow parameter feature the label of the training data in A1, i.e. the specific correct dosing amount value, belongs to, thereby obtaining which grade in the different dosing amount grades corresponding to the water inflow parameter feature the training data in A1 belongs to. The grade is taken as a new training label, thereby generating a second label data set.

[0074] In other words, the training data in the first label data set and the second label data set can be the same, but the labels of the two are different. The label of each training data in the first label data set is a specific dosing amount value, and the label of each training data in the second label data set is a dosing amount grade.

[0075] In step S330, a first number of candidate regression prediction models are trained based on the first label data set corresponding to each dosing amount prediction feature, respectively, to obtain a second number of dosing amount regression prediction models.

[0076] In an exemplary embodiment, the first number is an integer greater than 1. The candidate regression prediction model can include any machine learning model capable of regression prediction, such as a neural network model, a support vector machine-based regression model, etc., which is not specially limited in the present exemplary embodiment.

[0077] For example, the first number is 3. Based on the first label data set corresponding to the water inflow parameter feature, three candidate regression prediction models are trained, and according to the training results, three dosing amount regression prediction models can be obtained. Based on the first label data set corresponding to the flocculation feature, three candidate regression prediction models are trained, and according to the training results, three dosing amount regression prediction models can be obtained. Based on the first label data set corresponding to the water outflow parameter feature, three candidate regression prediction models are trained, and according to the training results, three dosing amount regression prediction models can be obtained. That is, a total of nine dosing amount regression prediction models can be obtained. That is, the second number and the first number are in a multiple relationship, and the second number is three times the first number.

[0078] In step S340, a third number of candidate classification prediction models are trained based on the second label data set corresponding to each dosing amount prediction feature, respectively, to obtain a fourth number of dosing classification prediction models.

[0079] In an exemplary embodiment, the third number is an integer greater than 1. The candidate classification prediction model can include any machine learning model capable of classification prediction, such as a neural network classification model, a decision tree classification model, etc., which is not particularly limited in the present exemplary embodiment.

[0080] Taking the third number as 4 as an example, similarly, four dosing classification prediction models can be obtained based on each dosing amount prediction feature, and a total of twelve dosing classification prediction models can be obtained. That is, the fourth number and the third number are also in a multiple relationship, and the fourth number is also three times the third number.

[0081] In step S350, the second number of dosing regression prediction models are tested, and a target dosing regression prediction model is determined from the second number of dosing regression prediction models according to the test results.

[0082] For example, the second number of dosing regression prediction models can be tested by a test data set, such as testing the prediction accuracy of the model, and the dosing regression prediction model with a prediction accuracy greater than a preset threshold is determined as the target dosing regression prediction model. The preset threshold can be determined according to requirements or experience, which is not particularly limited in the present exemplary embodiment.

[0083] The dosing regression prediction model corresponding to each dosing amount prediction feature can also be selected, and the dosing regression prediction model with a test accuracy ranking in the top N is selected as a candidate target dosing regression prediction model, and the target dosing regression prediction model is obtained according to the collection of the candidate target dosing regression prediction model corresponding to each dosing amount prediction feature. Wherein, N is greater than or equal to 1 and less than the first number.

[0084] In step S360, the fourth number of dosing classification prediction models are tested, and a target dosing classification prediction model is determined from the fourth number of dosing classification prediction models according to the test results.

[0085] Exemplarily, the specific implementation of step S360 can refer to step S350, which will not be described here.

[0086] In step S370, the preset dosing amount prediction model is determined according to the target dosing regression prediction model and the target dosing classification prediction model.

[0087] Exemplarily, the preset dosing amount prediction model can be obtained according to the collection of the target dosing amount regression prediction model and the target dosing amount classification prediction model. In other words, the preset dosing amount prediction model can be composed of a plurality of target dosing amount regression prediction models and a plurality of target dosing amount classification prediction models.

[0088] Through the steps S310 to S370 described above, in the process of generating the preset dosing amount prediction model, data labeling and training are respectively performed based on a plurality of dosing amount prediction features, so as to obtain a plurality of target dosing amount regression prediction models and a plurality of target dosing amount classification prediction models. The plurality of models can adapt to a plurality of different water quality environments, so as to ensure the accuracy and reliability of the dosing amount prediction under different water quality environments.

[0089] Exemplarily, as described above, each model in the preset dosing amount prediction model is input with a single dosing amount prediction feature, therefore, for each dosing amount prediction feature, the dosing amount prediction feature can be input into the dosing amount regression prediction model in the preset dosing amount prediction model with the dosing amount prediction feature as the single input, and the candidate dosing amount prediction value corresponding to the dosing amount prediction feature can be obtained according to the output of the dosing amount regression prediction model.

[0090] Taking the dosing amount regression prediction as an example, the number of dosing amount prediction values that can be predicted by each dosing amount prediction feature is determined according to the number of dosing amount regression prediction models in the preset dosing amount prediction model with the dosing amount prediction feature as the single input. For example, if the water inlet parameter feature corresponds to two dosing amount regression prediction models, then two candidate dosing amount prediction values can be predicted by the water inlet parameter feature. In other words, the number of candidate dosing amount prediction values that can be predicted by each dosing amount prediction feature is the same as the number of target dosing amount regression prediction models corresponding to the dosing amount prediction feature in the preset dosing amount regression prediction model.

[0091] In an exemplary embodiment, a first dosing amount prediction value can be obtained according to the mean value of the candidate dosing amount prediction values corresponding to each dosing amount prediction feature, and a first dosing amount prediction level can be obtained according to the candidate dosing amount prediction level with the largest number in the candidate dosing amount prediction levels corresponding to each dosing amount prediction feature.

[0092] Next, the specific embodiment of "step S130, determining the current dosing amount prediction value based on the overlapping relationship between the first dosing amount prediction level and the first dosing amount prediction value" will be described in detail.

[0093] For example, one embodiment of step S130 can include: when the first dosage prediction value belongs to the first dosage range interval indicated by the first dosage prediction level, determining the first dosage prediction value as the current dosage prediction value; when the first dosage prediction value does not belong to the first dosage range interval indicated by the first dosage prediction level, matching the current feature value of the dosage prediction feature with the feature values of the dosage prediction features in the experience library, and determining the current dosage prediction value according to the dosage indicated by the feature value of the dosage prediction feature that is matched successfully.

[0094] For example, when the first dosage prediction value does not belong to the dosage range interval corresponding to the first dosage prediction level, the current feature value of the water inlet parameter feature, the current feature value of the water outlet parameter feature, and the current feature value of the floc feature are combined into a first data record, the first data record and the second data record in the experience library are calculated for similarity, and the current dosage prediction value is determined according to the dosage corresponding to the second data record with the largest similarity.

[0095] For example, the medium dosage level is taken as the first dosage prediction level, and the dosage range indicated by each dosage prediction feature corresponding to the medium dosage level can be different. In one example embodiment, as long as the first dosage prediction value falls into the dosage range indicated by any target dosage prediction feature corresponding to the medium dosage level, it is considered that the first dosage prediction value belongs to the dosage range indicated by the medium dosage level, and if the first dosage prediction value does not fall into the dosage range indicated by any target dosage prediction feature corresponding to the medium dosage level, it is considered that the first dosage prediction value does not belong to the dosage range indicated by the medium dosage level. The target dosage prediction feature includes the dosage prediction feature with the same candidate dosage prediction level and the first dosage prediction level determined finally. For example, there are six models in the target dosage classification prediction model, four of which have a prediction result of the medium dosage level, and two of which have a prediction result of the low dosage level, i.e., the second prediction dosage level is the medium dosage level. Therefore, the dosage prediction features input by the four target dosage classification prediction models with the prediction result of the medium dosage level are the target dosage prediction features.

[0096] For example, another embodiment of step S130 can include: obtaining the water flow and water turbidity detected by the multiple detection points in the process from the raw water point to the water inlet point, and in the case that the water flow is greater than a third preset value and / or the water turbidity is greater than a fourth preset value, adjusting the first coagulant dosage range indicated by the first coagulant dosage prediction level according to historical experience to obtain a second coagulant dosage range; when the first coagulant dosage prediction value is within the second coagulant dosage range, determining the first coagulant dosage prediction value as the current coagulant dosage prediction value; when the first coagulant dosage prediction value is not within the second coagulant dosage range, determining the current coagulant dosage prediction value according to the minimum value of the first coagulant dosage prediction value and the first coagulant dosage range indicated by the first coagulant dosage prediction level.

[0097] The third preset value and the fourth preset value can be determined according to requirements, and the example embodiment does not make special limitations thereon. For example, the third preset value can be the maximum value of the water inlet flow of all water inlet parameter features in the training data multiplied by a coefficient greater than 1.

[0098] For example, the first coagulant dosage range indicated by the first coagulant dosage prediction level corresponding to the target coagulant dosage prediction feature can be adjusted according to historical experience. For example, when the target coagulant dosage prediction feature includes the water inlet parameter feature, the similarity of the current water inlet parameter feature value and the historical water inlet parameter feature values stored in the database is calculated, and a plurality of historical water inlet parameter feature values similar to the current water inlet parameter feature value are selected. The interval corresponding to the minimum value and the maximum value of the historical coagulant dosage values corresponding to the plurality of historical water inlet parameter feature values is taken as the second coagulant dosage range corresponding to the first coagulant dosage prediction level of the water inlet parameter feature.

[0099] For example, when the first coagulant dosage prediction value is within the second coagulant dosage range corresponding to any target coagulant dosage prediction feature, the first coagulant dosage prediction value is determined as the current coagulant dosage prediction value, otherwise, the minimum value of the first coagulant dosage range indicated by the first coagulant dosage prediction level corresponding to the target coagulant dosage prediction feature and the first coagulant dosage prediction value is determined as the current coagulant dosage prediction value. In this way, the coagulant dosage can be first adjusted and controlled based on the current coagulant dosage prediction value, and then whether the coagulant dosage needs to be adjusted is determined according to the coagulant effect, such as the settling velocity of the floc in the sedimentation tank, so that the coagulant dosage can be adjusted in time while avoiding the situation that the coagulant dosage is too large to cause secondary pollution to the water.

[0100] It should be noted that the adjustment of the first coagulant dosage range indicated by the first coagulant dosage prediction level to the second coagulant dosage range is only used in this comparison, and the first coagulant dosage range is still stored in the database, and the first coagulant dosage range in the database is still used to determine the current coagulant dosage prediction value next time.

[0101] In the present disclosure, the dosing prediction can be performed by different kinds of models, and the prediction results of different kinds of models can be verified and constrained with each other, so as to improve the accuracy of the predicted dosing amount prediction value. At the same time, by taking each dosing amount prediction feature as an individual input, the dosing amount can be predicted from multiple angles by multiple dosing amount prediction features, so that the model can adapt to multiple different water quality environments, and further improve the accuracy and reliability of the predicted dosing amount.

[0102] Next, the specific implementation of "step S140, determining a first difference value between the current dosing amount prediction value and the current dosing amount value of the dosing pump, updating the current operating frequency of the dosing pump according to the first difference value, the first dosing amount grade to which the current dosing amount prediction value belongs, and the second dosing amount grade to which the current dosing amount value of the dosing pump belongs, and controlling the dosing pump to perform the dosing operation in the water treatment process according to the current operating frequency" will be described in detail.

[0103] In an exemplary embodiment, the absolute value of the difference between the current dosing amount prediction value obtained in step S130 and the current actual dosing amount value of the dosing pump can be determined to obtain a first difference value. At the same time, the first dosing amount grade to which the current dosing amount prediction value belongs and the second dosing amount grade to which the current actual dosing amount value of the dosing pump belongs can be determined. Wherein, in the case that there is an overlap between the first dosing amount prediction grade and the first dosing amount prediction value, the first dosing amount grade can be the above-mentioned first dosing amount prediction grade, otherwise, the current dosing amount prediction value can be matched with the first dosing amount range indicated by different dosing amount grades corresponding to each dosing amount prediction feature respectively, from which the target dosing amount grade to which the current dosing amount prediction value belongs is determined, and the first dosing amount grade is determined according to the most number of target dosing amount grades.

[0104] Exemplarily, the current dosing amount value of the dosing pump can be understood as the current actual dosing amount value of the dosing pump, which is essentially the dosing amount prediction value determined in the last dosing amount prediction or the dosing amount value adjusted by human being to the dosing amount prediction value determined in the last dosing amount prediction, therefore, the determination method of the second dosing amount grade is similar to that of the first dosing amount grade, which will not be described here.

[0105] Next, the specific implementation of step S140 will be described in further detail. Figure 4 to Figure 6 The specific implementation of step S140 will be described in further detail.

[0106] Exemplarily, Figure 4 A flowchart showing a method for updating the current operating frequency of the dosing pump in an exemplary embodiment of the present disclosure is shown. Referring to Figure 4The method can include steps S410-S440. In step S410, it is determined whether the first dosing amount level and the second dosing amount level are the same. If yes, go to step S420; if no, go to step S440. In step S420, it is determined whether the first difference is less than or equal to a first preset value. If yes, go to step S430; if no, go to step S440. In step S430, the current operating frequency of the dosing pump is not updated. In step S440, the current operating frequency of the dosing pump is updated according to the current dosing amount prediction value.

[0107] In other words, in the present disclosure, in the case where the first dosing amount level and the second dosing amount level are different or the first difference is greater than the first preset value, the current operating frequency of the dosing pump is updated according to the current dosing amount prediction value; in the case where the first dosing amount level and the second dosing amount level are the same and the first difference is less than or equal to the first preset value, the current operating frequency of the dosing pump is not updated.

[0108] In an exemplary embodiment, the first preset value can be determined according to experience or requirements. The first preset value can be a dynamic value that can change with different water treatment conditions or water quality targets. However, under any condition, the first preset value is less than the difference between the maximum value and the minimum value of the target range interval, wherein the target range interval is the range interval with the smallest interval length among the range intervals corresponding to the dosing amount levels.

[0109] For example, in the case where the first dosing amount level and the second dosing amount level are the same, it is indicated that the current dosing amount prediction value and the current dosing amount value of the dosing pump (i.e., the current actual dosing amount value) belong to the same dosing amount level. In the case where both belong to the same dosing amount level and differ slightly, it is indicated that the dosing effects of both are not significantly different. Therefore, at this time, the operating frequency of the dosing pump can not be adjusted, and the current actual dosing amount value can be continued to be used for dosing. Otherwise, the operating frequency of the dosing pump is adjusted. In this way, by using the dosing amount level to constrain the dosing amount difference, the operating frequency of the dosing pump can be adjusted less frequently under the premise of ensuring the accuracy of the dosing amount, thereby prolonging the service life of the dosing pump as much as possible.

[0110] In an exemplary embodiment, the dosing pump includes a first dosing pump and a second dosing pump. Exemplarily, Figure 5 A flowchart of a method for adjusting the current operating frequencies of the first dosing pump and the second dosing pump in an exemplary embodiment of the present disclosure is shown. Referring to FIG. 5, the method can include steps S510-S580. In step S510, it is determined whether the first dosing amount level and the second dosing amount level are the same. If yes, go to step S520; if no, go to step S540. In step S520, it is determined whether the first difference is less than or equal to a first preset value. If yes, go to step S530; if no, go to step S540. In step S530, the current operating frequency of the first dosing pump is not updated. In step S540, the current operating frequency of the first dosing pump is updated according to the current dosing amount prediction value. Figure 5 The method can include steps S510-S580. In step S510, it is determined whether the first dosing amount level and the second dosing amount level are the same. If yes, go to step S520; if no, go to step S540. In step S520, it is determined whether the first difference is less than or equal to a first preset value. If yes, go to step S530; if no, go to step S540. In step S530, the current operating frequency of the first dosing pump is not updated. In step S540, the current operating frequency of the first dosing pump is updated according to the current dosing amount prediction value.

[0111] In step S510, a target operating frequency corresponding to the current dosing amount prediction value is determined according to a first mapping relationship between the dosing amount and the operating frequency of the dosing pump.

[0112] For example, there is a first mapping relationship between the operating frequency of the pump and the dosing amount that can be provided at the operating frequency. The first mapping relationship between the dosing amount and the operating frequency of the dosing pump can be determined according to a characteristic curve between the flow rate and the frequency of the pump, and then the operating frequency corresponding to the current dosing amount prediction value is determined as the target operating frequency through the first mapping relationship.

[0113] In step S520, a dosing pump with a higher update priority is determined from the first dosing pump and the second dosing pump based on the cumulative operating duration and the current load state of the dosing pump.

[0114] For example, the dosing pump can be scored according to the cumulative operating duration and the current load state of the dosing pump, and the dosing pump with a higher score is selected as the dosing pump with a higher update priority. For example, a first score is determined according to the reciprocal of the cumulative operating duration of the dosing pump, a second score is determined according to the reciprocal of the current load state, and a target score of the dosing pump is determined according to the weighted sum of the first score and the second score, and then the dosing pump with a higher target score is determined as the dosing pump with a higher update priority from the first dosing pump and the second dosing pump. The operating frequency of the dosing pump with a higher update priority is adjusted first to make the equivalent operating frequency of the first dosing pump and the second dosing pump equal to the target operating frequency. In this way, the number of adjustments of the first dosing pump and the second dosing pump can be balanced according to the actual situation, and the single pump is prevented from being in a high-load operating state for a long time, thereby prolonging the service life of the dosing pump.

[0115] In step S530, a current total equivalent operating frequency of the first dosing pump and the second dosing pump is determined.

[0116] For example, the flow rate and the operating frequency of the first dosing pump and the second dosing pump are the same and satisfy a linear relationship, and the first dosing pump and the second dosing pump are operated in parallel. Based on this, the current total equivalent operating frequency can be determined according to the sum of the first current actual operating frequency of the first dosing pump and the second current actual operating frequency of the second dosing pump. The current actual operating frequency can be understood as the actual operating frequency of the first dosing pump and the second dosing pump currently being executed before updating.

[0117] In step S540, it is determined whether the target operating frequency is greater than the current total equivalent operating frequency. If yes, go to step S550, otherwise go to step S560.

[0118] In step S550, a first difference between the target operating frequency and the current total equivalent operating frequency and a second difference between the current actual operating frequency corresponding to the updating priority high dosing pump and the maximum operating frequency are determined, and the current operating frequencies of the first and second dosing pumps are updated according to the relationship between the first difference and the second difference.

[0119] For example, one embodiment of step S550 can include: in the case that the first difference is less than or equal to the second difference, updating the current operating frequency of the updating priority high dosing pump according to the first difference, and not updating the current operating frequency of the updating priority low dosing pump; in the case that the first difference is greater than the second difference, updating the current operating frequency of the updating priority high dosing pump to the maximum operating frequency of the updating priority high dosing pump, determining a fourth difference between the target operating frequency and the maximum operating frequency of the updating priority high dosing pump, and updating the current operating frequency of the updating priority low dosing pump according to the fourth difference.

[0120] For example, in the case that the first difference is less than or equal to the second difference, it is indicated that the current operating frequency of the updating priority high dosing pump is updated only, which can meet the demand of the target operating frequency, i.e., the sum of the current operating frequency and the first difference is taken as the updated current operating frequency of the updating priority high dosing pump. In the case that the first difference is greater than the second difference, it is indicated that even if the operating frequency of the updating priority high dosing pump is adjusted to the maximum, the total equivalent operating frequency of the first and second dosing pumps cannot reach the target operating frequency, and it is necessary to continue to adjust the current operating frequency of the updating priority low dosing pump, i.e., the first difference indicated operating frequency is added to the basis of the current operating frequency of the updating priority low dosing pump as the updated current operating frequency of the updating priority low dosing pump.

[0121] In this way, in the case that the target running frequency is greater than the current total equivalent running frequency, the current running frequency of the dosing pump with the high update priority is adjusted preferentially, if the total equivalent frequency of the current actual running frequency of the dosing pump with the low update priority and the current running frequency of the dosing pump with the high update priority after the update can meet the demand of the target running frequency, the running frequency of the dosing pump with the low update priority is not adjusted, if the demand of the target running frequency cannot be met, the current actual running frequency of the dosing pump with the high update priority is first determined as the maximum running frequency allowed, and then the current actual running frequency of the dosing pump with the low update priority is adjusted in a small range. In this way, the load of the dosing pump with the low update priority can be avoided to be further increased, and the possibility that the mechanical wear of the dosing pump with the low update priority is aggravated due to frequent adjustment can be avoided, so that the service life of the dosing pump is prolonged to the maximum extent on the premise of meeting the demand of the dosing amount.

[0122] In step S560, it is judged whether the target running frequency is greater than the current actual running frequency of the dosing pump with the high update priority, if yes, the process proceeds to step S570, otherwise, the process proceeds to step S580.

[0123] In step S570, a third difference between the target running frequency and the current total equivalent running frequency is determined, the current running frequency of the dosing pump with the high update priority is updated according to the third difference, and the current running frequency of the dosing pump with the low update priority is not updated.

[0124] For example, in the case that the target running frequency is less than the current total equivalent running frequency and greater than the current actual running frequency of the dosing pump with the high update priority, it is explained that the total equivalent running frequency of the first dosing pump and the second dosing pump can meet the target running frequency only by reducing the current actual running frequency of the dosing pump with the high update priority. Therefore, the current running frequency of the dosing pump with the high update priority is updated to the running frequency corresponding to the running frequency of the dosing pump with the high update priority after the current actual running frequency of the dosing pump with the high update priority is reduced by the third difference, and the current running frequency of the dosing pump with the low update priority is not updated.

[0125] In step S580, the current running frequency of the dosing pump with the high update priority is updated to the target running frequency, and the dosing pump with the low update priority is controlled to be in the off state.

[0126] For example, in the case that the target running frequency is less than the current actual running frequency of the dosing pump with the high update priority, it is explained that the target running frequency is small at this time, and only one dosing pump is needed to meet the demand of the dosing amount, so the dosing pump with the low update priority can be turned off at this time, and the current running frequency of the dosing pump with the high update priority is updated to the target running frequency.

[0127] Through the steps S510 to S580, the running frequencies of the two dosing pumps can be adjusted according to the current load states and cumulative running time lengths of the first and second dosing pumps, so as to meet the current dosing amount demand, avoid a certain pump being in a high-load running state for a long time, prolong the service life of the pump, and improve the control accuracy and dosing range of the dosing amount through the dosing amount control of the two dosing pumps.

[0128] Exemplarily, Figure 6 A flowchart of another method for updating the current running frequencies of the first and second dosing pumps in an exemplary embodiment of the present disclosure is shown. Referring to Figure 6 The method can include steps S610 to S630. Wherein:

[0129] In step S610, a target running frequency corresponding to the current dosing amount prediction value is determined according to a first mapping relationship between the dosing amount and the running frequency of the dosing pump.

[0130] Exemplarily, the specific implementation of step S610 can refer to the related description in step S510 described above, which will not be repeated here.

[0131] In step S620, the total equivalent running frequency of the first and second dosing pumps is taken as the target running frequency, the adjustment priority of a single pump is higher than that of a double pump simultaneous adjustment, the current running frequencies of the first and second dosing pumps are in their respective safe running frequency intervals as constraint conditions, a multi-objective optimization function with dosing pump life and dosing pump energy consumption as optimization objectives is solved, and the first running frequency change value of the first dosing pump and the second running frequency change value of the second dosing pump are determined according to the solving result.

[0132] Exemplarily, a multi-objective optimization function with dosing pump life and dosing pump energy consumption as optimization objectives can be constructed in advance, and the current running frequencies of the first and second dosing pumps are updated according to the solving result of the target optimization function.

[0133] In an exemplary embodiment, the multi-objective optimization function is determined according to a dosing pump life optimization function and a dosing pump energy consumption optimization function.

[0134] The drug feeding pump life optimization function is determined according to a first running frequency change value of the first drug feeding pump, a second running frequency change value of the second drug feeding pump, a first cumulative running time length of the first drug feeding pump, and a second cumulative running time length of the second drug feeding pump. The drug feeding pump energy consumption optimization function is determined according to a first running frequency of the first drug feeding pump, a first relationship index between the first running frequency and a power of the first drug feeding pump, a second running frequency of the second drug feeding pump, and a second relationship index between the second running frequency and a power of the second drug feeding pump.

[0135] For example, the drug feeding pump life optimization function can be represented by formula (1) as follows, the drug feeding pump energy consumption optimization function can be represented by formula (2) as follows, and the multi-objective optimization function can be represented by formula (3) as follows:

[0136] (1)

[0137] In formula (1), is a running frequency adjustment weight of the first drug feeding pump, is a running frequency adjustment weight of the second drug feeding pump, is a weight of the cumulative running time length, is the first running frequency change value of the first drug feeding pump, is the second running frequency change value of the second drug feeding pump, is the cumulative running time length of the first drug feeding pump, is the cumulative running time length of the second drug feeding pump, is a rated life time length of the first drug feeding pump, is a rated life time length of the second drug feeding pump.

[0138] (2)

[0139] In formula (2), is a power coefficient of the first drug feeding pump, is a power coefficient of the second drug feeding pump, m is a first relationship index between the power and the frequency of the first drug feeding pump, n is a second relationship index between the power and the frequency of the second drug feeding pump, is the first running frequency of the first drug feeding pump before updating, is the second running frequency of the second drug feeding pump before updating, is the first running frequency change value of the first drug feeding pump, is the second running frequency change value of the second drug feeding pump.

[0140] (3)

[0141] In formula (3), is a weight of the life optimization function, which can be customized according to the needs of the user, such as the user needs to prioritize the protection of the device, that is, the life optimization priority, is greater than 0.5 and less than 1, is a weight of the energy consumption optimization function.

[0142] In solving the above multi-objective optimization function, the total equivalent operating frequency of the first dosing pump and the second dosing pump is the target operating frequency, the adjustment priority of a single pump is higher than that of double pump simultaneous adjustment, and the current operating frequency of the first dosing pump and the second dosing pump is in the respective safe operating frequency interval as the constraint condition, to obtain the first operating frequency change value of the first dosing pump and the second operating frequency change value of the second dosing pump.

[0143] In step S630, the current operating frequency of the first dosing pump is updated according to the first operating frequency change value, and the current operating frequency of the second dosing pump is updated according to the second operating frequency change value.

[0144] For example, after obtaining the first operating frequency change value and the second operating frequency change value according to the solving result of the multi-objective optimization function, the current operating frequency of the first dosing pump can be updated to the sum of the current actual operating frequency of the first dosing pump and the first operating frequency change value, for example, before updating, the current actual operating frequency of the first dosing pump is , the first operating frequency change value is , then the current operating frequency of the first dosing pump is updated to .

[0145] In an exemplary embodiment, the solving process of the multi-objective optimization function can be assisted by a pre-trained machine learning model. For example, a machine learning model can be trained to learn to predict the life loss and energy consumption of the dosing pump according to different operating frequency combinations of the first dosing pump and the second dosing pump based on historical operating data. In the case where the operating frequency of both dosing pumps must be adjusted to meet the target operating frequency, the trained machine learning model can quickly determine the final operating frequency combination in the double pump operating frequency combination that meets the target operating frequency, thereby obtaining the solving result of the multi-objective optimization function.

[0146] Through the above steps S610 to S630, the life and energy consumption of the first dosing pump and the second dosing pump can be optimized by the multi-objective optimization function, which can prolong the life of the dosing pump while minimizing the energy consumption of the dosing pump.

[0147] In an example embodiment, the method for dosing control in the water treatment process of the present disclosure can further include: determining a first feature value of a remaining life prediction feature corresponding to the first dosing pump according to the first historical operation data of the first dosing pump, obtaining a first predicted remaining life of the first dosing pump based on the first feature value and a dosing pump remaining life prediction model; determining a second feature value of a remaining life prediction feature corresponding to the second dosing pump according to the second historical operation data of the second dosing pump, obtaining a second predicted remaining life of the second dosing pump based on the second feature value and the dosing pump remaining life prediction model; in the case where the difference between the first predicted remaining life and the second predicted remaining life is greater than a second preset value, taking the minimum difference between the first predicted remaining life and the second predicted remaining life as a new added optimization target to update the multi-objective optimization function, and updating the current operation frequency of the first dosing pump and the second dosing pump according to the solution result of the updated multi-objective optimization function.

[0148] In an example embodiment, the remaining life prediction features of the dosing pump can include the total cumulative operation time length of the dosing pump, the distribution of the cumulative operation time length at each operation frequency, the number of start-stop times, the load time length, the number of fault times, etc. Of course, other features that affect the life of the dosing pump can also be included, and the present example embodiment does not make special limitations thereto.

[0149] For example, a dosing pump remaining life prediction model can be trained in advance, and the remaining life of the first dosing pump and the remaining life of the second dosing pump are predicted by the dosing pump life prediction model every fixed time. In the case where the difference between the first predicted remaining life of the first dosing pump and the second predicted remaining life of the second dosing pump is greater than a second preset value, the minimum difference between the first predicted remaining life and the second predicted remaining life or less than the second preset value can be taken as a new added optimization target and added to the above multi-objective optimization function to update the multi-objective optimization function. The updated multi-objective optimization function can be represented by the following formula (4):

[0150] (4)

[0151] In formula (4), pshouming 1 is the first predicted remaining life, pshouming 2 is the second predicted remaining life.

[0152] By taking the predicted residual service life of the first and second dosing pumps as a newly added optimization target, the long-term cumulative error of the original multi-objective optimization function can be corrected, the accuracy of the optimization solution result can be improved, and the situation that the cumulative running time of the two dosing pumps is greatly different due to the inaccurate solution result of the original multi-objective optimization function can be avoided, thereby the situation that a single pump is excessively used can be avoided to the greatest extent, the service life of the pump is prolonged, and the hardware cost in the water treatment process is reduced.

[0153] In an exemplary embodiment, the first and second dosing pumps can also be primary and backup to each other, and when any one of the dosing pumps fails, the other dosing pump is started to perform the current dosing control. In other words, in the present disclosure, the two dosing pumps that are primary and backup to each other can be reused, and when both of the dosing pumps are normal, the two dosing pumps can be used at the same time to perform more accurate and wider range of dosing adjustment to cope with various possible emergency situations, and when any one of the dosing pumps fails, the other dosing pump can continue to perform dosing control as a backup pump to ensure the continuity of the production process.

[0154] In addition, it should be noted that the above-described figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present application, and are not for limiting purposes. It is easy to understand that the processes shown in the above-described figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be executed synchronously or asynchronously, for example, in multiple modules.

[0155] Further, the exemplary embodiments of the present disclosure also provide a dosing control device in a water treatment process. Referring to Figure 7 As shown in the figure, the dosing control device 700 in the water treatment process includes the following program modules: a current characteristic value acquisition module 710 configured to acquire a current characteristic value of a dosing amount prediction characteristic in a water treatment process, the dosing amount prediction characteristic including a floc characteristic, an influent parameter characteristic, and an effluent parameter characteristic; a prediction module 720 configured to obtain a first dosing amount prediction grade and a first dosing amount prediction value based on a dosing amount classification prediction model and a dosing amount regression prediction model in a preset dosing amount prediction model, respectively, according to the current characteristic value of the dosing amount prediction characteristic; a current dosing amount prediction value determination module 730 configured to determine a current dosing amount prediction value based on an overlapping relationship between the first dosing amount prediction grade and the first dosing amount prediction value; and a dosing pump control module 740 configured to determine a first difference value between the current dosing amount prediction value and a current dosing amount value of a dosing pump, update a current running frequency of the dosing pump according to the first difference value, a first dosing amount grade to which the current dosing amount prediction value belongs, and a second dosing amount grade to which the current dosing amount value of the dosing pump belongs, and control the dosing pump to perform a dosing operation in the water treatment process according to the current running frequency.

[0156] In an example embodiment, based on the foregoing embodiments, the medicament adding pump control module 740 can be specifically configured to: in a case where the first medicament adding amount level and the second medicament adding amount level are different or the first difference is greater than the first preset value, update the current operating frequency of the medicament adding pump according to the current medicament adding amount prediction value; in a case where the first medicament adding amount level and the second medicament adding amount level are the same and the first difference is less than or equal to the first preset value, not update the current operating frequency of the medicament adding pump.

[0157] In an example embodiment, the medicament adding pump comprises a first medicament adding pump and a second medicament adding pump; the updating the current operating frequency of the medicament adding pump according to the current medicament adding amount prediction value comprises: determining a target operating frequency corresponding to the current medicament adding amount prediction value according to a first mapping relationship between medicament adding amount and operating frequency of the medicament adding pump; determining a medicament adding pump with a higher updating priority from the first medicament adding pump and the second medicament adding pump based on cumulative operating time length and current load state of the medicament adding pump; in a case where the target operating frequency is greater than a current total equivalent operating frequency of the first medicament adding pump and the second medicament adding pump, determining a first difference between the target operating frequency and the current total equivalent operating frequency and a second difference between a current actual operating frequency and a maximum operating frequency of the medicament adding pump with the higher updating priority, and updating the current operating frequency of the first medicament adding pump and the second medicament adding pump according to a relationship between the first difference and the second difference; in a case where the target operating frequency is less than the current total equivalent operating frequency of the first medicament adding pump and the second medicament adding pump and greater than the current actual operating frequency of the medicament adding pump with the higher updating priority, determining a third difference between the target operating frequency and the current total equivalent operating frequency, updating the current operating frequency of the medicament adding pump with the higher updating priority according to the third difference, and not updating the current operating frequency of the medicament adding pump with a lower updating priority; in a case where the target operating frequency is less than or equal to the current operating frequency of the medicament adding pump with the higher updating priority, updating the current operating frequency of the medicament adding pump with the higher updating priority to the target operating frequency, and controlling the medicament adding pump with the lower updating priority to be in a closed state.

[0158] In an exemplary embodiment, the updating the current operating frequency of the first and second dosing pumps according to the relationship between the first difference and the second difference comprises: in the case that the first difference is less than or equal to the second difference, updating the current operating frequency of the dosing pump with the higher updating priority according to the first difference, and not updating the current operating frequency of the dosing pump with the lower updating priority; in the case that the first difference is greater than the second difference, updating the current operating frequency of the dosing pump with the higher updating priority to the maximum operating frequency of the dosing pump with the higher updating priority, determining a fourth difference between the target operating frequency and the maximum operating frequency of the dosing pump with the higher updating priority, and updating the current operating frequency of the dosing pump with the lower updating priority according to the fourth difference.

[0159] In an exemplary embodiment, the dosing pump comprises a first dosing pump and a second dosing pump, and the updating the current operating frequency of the dosing pump according to the current dosing amount prediction value comprises: determining a target operating frequency corresponding to the current dosing amount prediction value according to a first mapping relationship between the dosing amount and the operating frequency of the dosing pump; taking the total equivalent operating frequency of the first and second dosing pumps as the target operating frequency, the adjusting priority of a single pump being higher than the priority of simultaneous adjustment of the double pumps, and the current operating frequencies of the first and second dosing pumps being within the respective safe operating frequency intervals as the constraint conditions, solving a pre-constructed multi-objective optimization function with the service life of the dosing pump and the energy consumption of the dosing pump as the optimization objectives, and determining a first operating frequency change value of the first dosing pump and a second operating frequency change value of the second dosing pump according to the solving result; updating the current operating frequency of the first dosing pump according to the first operating frequency change value, and updating the current operating frequency of the second dosing pump according to the second operating frequency change value; wherein the multi-objective optimization function is determined according to a dosing pump service life optimization function and a dosing pump energy consumption optimization function, the dosing pump service life optimization function is determined according to the first operating frequency change value of the first dosing pump, the second operating frequency change value of the second dosing pump, the first cumulative operating time length of the first dosing pump, and the second cumulative operating time length of the second dosing pump, and the dosing pump energy consumption optimization function is determined according to the first operating frequency of the first dosing pump, a first relationship index between the first operating frequency and the power of the first dosing pump, the second operating frequency of the second dosing pump, and a second relationship index between the second operating frequency and the power of the second dosing pump.

[0160] In an example embodiment, the device further comprises a multi-objective optimization function updating module configured to: determine a first feature value of the remaining life prediction feature corresponding to the first chemical feeding pump according to the first historical operation data of the first chemical feeding pump, obtain the first predicted remaining life of the first chemical feeding pump based on the first feature value and the chemical feeding pump remaining life prediction model; determine a second feature value of the remaining life prediction feature corresponding to the second chemical feeding pump according to the second historical operation data of the second chemical feeding pump, obtain the second predicted remaining life of the second chemical feeding pump based on the second feature value and the chemical feeding pump remaining life prediction model; in the case that the difference between the first predicted remaining life and the second predicted remaining life is greater than a second preset value, take the minimum difference between the first predicted remaining life and the second predicted remaining life as a newly added optimization objective to update the multi-objective optimization function, and update the current operation frequency of the first chemical feeding pump and the second chemical feeding pump according to the solving result of the updated multi-objective optimization function.

[0161] In an example embodiment, determining the current chemical feeding amount prediction value based on the first chemical feeding amount prediction level and the first chemical feeding amount prediction value comprises: in the case that the first chemical feeding amount prediction value belongs to the first chemical feeding amount range interval indicated by the first chemical feeding amount prediction level, determining the first chemical feeding amount prediction value as the current chemical feeding amount prediction value; in the case that the first chemical feeding amount prediction value does not belong to the first chemical feeding amount range interval indicated by the first chemical feeding amount prediction level, matching the current feature value of the chemical feeding amount prediction feature with the feature values of the chemical feeding amount prediction features in the experience library, and determining the current chemical feeding amount prediction value according to the chemical feeding amount indicated by the feature value of the chemical feeding amount prediction feature that matches successfully.

[0162] The specific details of each part of the above device have been described in detail in the method part embodiment, and the undisclosed details can be referred to the embodiment content of the method part, thus no longer be described.

[0163] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, such division is not mandatory. In fact, according to example embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into embodied by multiple modules or units.

[0164] Moreover, although individual steps of the methods in the present disclosure are described in a particular order in the figures, this is not required or implied as to the order of execution of the steps, nor is it required that all of the steps be executed to achieve the desired result. Additionally or alternatively, certain steps can be omitted, multiple steps can be combined into a single step, a single step can be broken into multiple steps, etc.

[0165] An exemplary embodiment of the present disclosure also provides a computer program product. The computer program product includes a computer program which, when executed by a processor, implements the above-described dosing control method in a water treatment process.

[0166] In an embodiment, the computer program product can be a tangible product containing the computer program, such as a computer-readable storage medium storing the computer program. The readable storage medium can be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, etc. signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory (Flash), mechanical hard disk (HDD), solid state disk (SSD), etc. For example, the computer program product can be implemented as a non-volatile storage medium storing the computer program, such as read-only memory, Nand flash, etc.

[0167] In an embodiment, the computer program product can be an intangible product containing the computer program. For example, the computer program product can be implemented as a virtual digital product, such as an executable file, installation package, etc. digital file storing the computer program.

[0168] The code of the computer program can be written in one or more programming languages. Programming languages such as C, Java, C++, Python, etc. The program code can be executed entirely on a user computing device, or partially on a user computing device, or as a standalone software package, or partially on a user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any kind of network, such as a local area network (LAN), a wide area network (WAN), etc., or can be connected to an external computing device (for example, through an Internet connection provided by an operator).

[0169] A computer program can be carried by a signal bearing medium or a transmission medium such as an electrical, magnetic, optical, electromagnetic, infrared, or a carrier wave. An electronic device can convert the signal bearing computer program into a digital signal and then execute the computer program. When the computer program is executed on the electronic device, the code of the computer program causes the electronic device to perform (more specifically, can cause a processor of the electronic device to perform) the method steps of various exemplary embodiments of the present disclosure.

[0170] An exemplary embodiment of the present disclosure further provides an electronic device, which can include a processor and a memory. The memory stores executable instructions of the processor, such as a computer program. The processor performs the method steps of various exemplary embodiments of the present disclosure by executing the executable instructions. In addition, the electronic device can further include a display for displaying a graphical user interface.

[0171] An exemplary embodiment of the present disclosure further provides an electronic device. The electronic device can include a processor and a memory. The memory stores executable instructions of the processor, such as a computer program. The processor performs the method steps of various exemplary embodiments of the present disclosure by executing the executable instructions. In addition, the electronic device can further include a display for displaying a graphical user interface.

[0172] The electronic device is exemplarily illustrated in the form of a general computing device below. Figure 8 It should be understood that the electronic device is not limited to the form of a general computing device. Figure 8 The electronic device 800 shown is merely an example and should not limit the function and use range of the embodiments of the present disclosure.

[0173] As shown in Figure 8 The electronic device 800 can include a processor 810, a memory 820, a bus 830, an I / O (input / output) interface 840, a network adapter 850, and a display 860.

[0174] The memory 820 can include a volatile memory such as a RAM 821, a cache unit 822, and a non-volatile memory such as a ROM 823. The memory 820 can further include one or more program modules 824, which include but are not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof can include an implementation of a network environment. For example, the program modules 824 can include the modules in the above-described apparatus.

[0175] The processor 810 can include one or more processing units, such as: an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor, and / or an NPU (Neural-Network Processing Unit), etc.

[0176] The processor 810 can be configured to execute executable instructions stored in the memory 820, such as to perform the dosing control method in the water treatment process described above.

[0177] The bus 830 is configured to enable connection between different components of the electronic device 800, and can include a data bus, an address bus, and a control bus.

[0178] The electronic device 800 can communicate with one or more external devices 900 (such as a keyboard, a mouse, an external controller, etc.) through the I / O interface 840.

[0179] The electronic device 800 can communicate with one or more networks through the network adapter 850, such as to provide a mobile communication solution (e.g., 3G / 4G / 5G, etc.), or to provide a wireless communication solution (e.g., a wireless local area network, Bluetooth, near field communication, etc.). The network adapter 850 can communicate with other modules of the electronic device 800 through the bus 830.

[0180] The electronic device 800 can display a graphical user interface through the display 860, such as to display an interface showing the current operating frequency of the dosing pump after being updated.

[0181] Although Figure 8 Other hardware and / or software modules can also be provided in the electronic device 800, such as: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc., which are not shown in FIG. 8.

[0182] In addition, the above-described figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is readily understood that the processes shown in the above-described figures do not indicate or limit the time sequence of these processes. In addition, it is readily understood that these processes can be executed synchronously or asynchronously, for example, in multiple modules.

[0183] From the above, it can be seen that the technical solutions of the present disclosure can be implemented as a method, device, system, computer program product, storage medium, electronic device, etc. Those skilled in the art can understand that various aspects of the present disclosure can be specifically implemented in the following forms: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be referred to as "circuitry", "module" or "system" respectively.

[0184] It should be understood that the present disclosure is not limited to the specific methods steps or structural aspects described above and illustrated in the drawings, and various modifications and changes can be made without departing from the scope thereof. Based on the specific embodiments provided by the present disclosure, those skilled in the art will easily think of other embodiments. Therefore, the specific embodiments provided by the present disclosure are only exemplary, and the scope and spirit of the present disclosure are indicated by the claims, and should cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field not disclosed by the present disclosure.

Claims

1. A method of chemical dosage control in a water treatment process, characterized by, The method comprises the following steps: obtaining current characteristic values of dosing amount prediction characteristics in a water treatment process, the dosing amount prediction characteristics including flocculation characteristics, influent parameter characteristics, and effluent parameter characteristics; based on the current characteristic values of the dosing amount prediction characteristics, obtaining a first dosing amount prediction grade and a first dosing amount prediction value based on a dosing amount classification prediction model and a dosing amount regression prediction model in a preset dosing amount prediction model, respectively; determining a current dosing amount prediction value based on an overlapping relationship between the first dosing amount prediction grade and the first dosing amount prediction value; determining a first difference value between the current dosing amount prediction value and a current dosing amount value of a dosing pump, updating a current operating frequency of the dosing pump according to the first difference value, the first dosing amount grade to which the current dosing amount prediction value belongs, and a second dosing amount grade to which the current dosing amount value of the dosing pump belongs, and controlling the dosing pump to perform dosing operation in the water treatment process according to the current operating frequency; wherein the updating of the current operating frequency of the dosing pump according to the first difference value, the first dosing amount grade to which the current dosing amount prediction value belongs, and the second dosing amount grade to which the current dosing amount value of the dosing pump belongs comprises: in the case that the first dosing amount grade and the second dosing amount grade are different or the first difference value is greater than a first preset value, updating the current operating frequency of the dosing pump according to the current dosing amount prediction value; the dosing pump comprises a first dosing pump and a second dosing pump, and the updating of the current operating frequency of the dosing pump according to the current dosing amount prediction value comprises: determining a target operating frequency corresponding to the current dosing amount prediction value according to a first mapping relationship between the dosing amount and the operating frequency of the dosing pump; taking the total equivalent operating frequency of the first dosing pump and the second dosing pump as the target operating frequency, the adjustment priority of a single pump being higher than the priority of simultaneous adjustment of a double pump, and the current operating frequencies of the first dosing pump and the second dosing pump being within their respective safe operating frequency intervals as constraint conditions, solving a multi-objective optimization function pre-constructed with dosing pump service life and dosing pump energy consumption as optimization objectives, and determining a first operating frequency change value of the first dosing pump and a second operating frequency change value of the second dosing pump according to the solving result; updating the current operating frequency of the first dosing pump according to the first operating frequency change value, and updating the current operating frequency of the second dosing pump according to the second operating frequency change value; wherein the multi-objective optimization function is determined according to a dosing pump service life optimization function and a dosing pump energy consumption optimization function, the dosing pump service life optimization function is determined according to the first operating frequency change value of the first dosing pump, the second operating frequency change value of the second dosing pump, a first cumulative operating time length of the first dosing pump, and a second cumulative operating time length of the second dosing pump, and the dosing pump energy consumption optimization function is determined according to a first operating frequency of the first dosing pump, a first relationship index between the first operating frequency and the power of the first dosing pump, a second operating frequency of the second dosing pump, and a second relationship index between the second operating frequency and the power of the second dosing pump.

2. The method of claim 1, wherein, The step of updating the current operating frequency of the dosing pump based on the first difference, the first dosing level to which the current dosing predicted value belongs, and the second dosing level to which the current dosing value of the dosing pump belongs includes: If the first dosing level and the second dosing level are the same and the first difference is less than or equal to the first preset value, the current operating frequency of the dosing pump will not be updated.

3. The method of claim 2, wherein, The dosing pump includes a first dosing pump and a second dosing pump; updating the current operating frequency of the dosing pump based on the current predicted dosing amount includes: Based on the first mapping relationship between the dosage and the operating frequency of the dosing pump, the target operating frequency corresponding to the current predicted dosage is determined; Based on the cumulative runtime and current load status of the dosing pump, the dosing pump with the higher update priority is determined from the first dosing pump and the second dosing pump; If the target operating frequency is greater than the current total equivalent operating frequency of the first dosing pump and the second dosing pump, a first difference between the target operating frequency and the current total equivalent operating frequency and a second difference between the current actual operating frequency and the maximum operating frequency of the dosing pump with higher update priority are determined. Based on the relationship between the first difference and the second difference, the current operating frequencies of the first dosing pump and the second dosing pump are updated. If the target operating frequency is less than the current total equivalent operating frequency of the first and second dosing pumps but greater than the current actual operating frequency of the dosing pump with higher update priority, a third difference between the target operating frequency and the current total equivalent operating frequency is determined. The current operating frequency of the dosing pump with higher update priority is updated based on the third difference, while the current operating frequency of the dosing pump with lower update priority is not updated. If the target operating frequency is less than or equal to the current operating frequency of the dosing pump with the higher update priority, the current operating frequency of the dosing pump with the higher update priority is updated to the target operating frequency, and the dosing pump with the lower update priority is controlled to be in a closed state.

4. The method of claim 3, wherein, The step of updating the current operating frequencies of the first and second dosing pumps based on the relationship between the first and second differences includes: If the first difference is less than or equal to the second difference, the current operating frequency of the dosing pump with the higher update priority is updated according to the first difference, and the current operating frequency of the dosing pump with the lower update priority is not updated. If the first difference is greater than the second difference, the current operating frequency of the dosing pump with the higher update priority is updated to the maximum operating frequency of the dosing pump with the higher update priority. A fourth difference between the target operating frequency and the maximum operating frequency of the dosing pump with the higher update priority is determined, and the current operating frequency of the dosing pump with the lower update priority is updated according to the fourth difference.

5. The method of claim 1, wherein, The method further includes: determine a first feature value of a residual life prediction feature corresponding to the first chemical dosing pump according to first historical operation data of the first chemical dosing pump, and obtain a first predicted residual life of the first chemical dosing pump based on the first feature value and a residual life prediction model of the chemical dosing pump; determine a second feature value of a residual life prediction feature corresponding to the second chemical dosing pump according to second historical operation data of the second chemical dosing pump, and obtain a second predicted residual life of the second chemical dosing pump based on the second feature value and the residual life prediction model of the chemical dosing pump; in a case where a difference between the first predicted residual life and the second predicted residual life is greater than a second preset value, take the minimum difference between the first predicted residual life and the second predicted residual life as a new added optimization target to update the multi-objective optimization function, and update the current operation frequency of the first chemical dosing pump and the second chemical dosing pump according to a solving result of the updated multi-objective optimization function.

6. The method of claim 1, wherein, The current chemical dosing amount prediction value is determined based on an overlapping relationship between a first chemical dosing amount prediction level and a first chemical dosing amount prediction value. In a case where the first chemical dosing amount prediction value belongs to a first chemical dosing amount range interval indicated by the first chemical dosing amount prediction level, the first chemical dosing amount prediction value is determined as the current chemical dosing amount prediction value. In a case where the first chemical dosing amount prediction value does not belong to the first chemical dosing amount range interval indicated by the first chemical dosing amount prediction level, a current feature value of a chemical dosing amount prediction feature is matched with feature values of the chemical dosing amount prediction feature in an experience library, and a current chemical dosing amount prediction value is determined according to a chemical dosing amount indicated by a feature value of the chemical dosing amount prediction feature that is matched successfully.

7. A chemical feed control device in a water treatment process, characterized by The method comprises: a current feature value acquisition module configured to acquire a current feature value of a chemical dosing amount prediction feature in a water treatment process, the chemical dosing amount prediction feature comprising a floc feature, an inlet water parameter feature and an outlet water parameter feature; a prediction module configured to obtain a first chemical dosing amount prediction level and a first chemical dosing amount prediction value based on a chemical dosing amount classification prediction model and a chemical dosing amount regression prediction model in a preset chemical dosing amount prediction model respectively according to the current feature value of the chemical dosing amount prediction feature; a current chemical dosing amount prediction value determination module configured to determine a current chemical dosing amount prediction value based on an overlapping relationship between a first chemical dosing amount prediction level and a first chemical dosing amount prediction value; a chemical dosing pump control module configured to determine a first difference value between the current chemical dosing amount prediction value and a current chemical dosing amount value of a chemical dosing pump, update a current operation frequency of the chemical dosing pump according to the first difference value, a first chemical dosing amount level to which the current chemical dosing amount prediction value belongs and a second chemical dosing amount level to which the current chemical dosing amount value of the chemical dosing pump belongs, and control the chemical dosing pump to perform a chemical dosing operation in the water treatment process according to the current operation frequency; wherein the current operation frequency of the chemical dosing pump is updated according to the first difference value, the first chemical dosing amount level to which the current chemical dosing amount prediction value belongs and the second chemical dosing amount level to which the current chemical dosing amount value of the chemical dosing pump belongs, comprising: in a case where the first chemical dosing amount level and the second chemical dosing amount level are different or the first difference value is greater than a first preset value, the current operation frequency of the chemical dosing pump is updated according to the current chemical dosing amount prediction value; The medicating pump comprises a first medicating pump and a second medicating pump, and the updating of the current operating frequency of the medicating pump according to the current medicating amount prediction value comprises: determining a target operating frequency corresponding to the current medicating amount prediction value according to a first mapping relationship between the medicating amount and the operating frequency of the medicating pump; taking the total equivalent operating frequency of the first medicating pump and the second medicating pump as the target operating frequency, taking the adjustment priority of a single pump higher than the priority of simultaneous adjustment of double pumps, and taking the current operating frequencies of the first medicating pump and the second medicating pump in respective safe operating frequency intervals as constraint conditions, solving a multi-objective optimization function pre-constructed with the service life of the medicating pump and the energy consumption of the medicating pump as optimization objectives, and determining a first operating frequency change value of the first medicating pump and a second operating frequency change value of the second medicating pump according to a solving result; updating the current operating frequency of the first medicating pump according to the first operating frequency change value, and updating the current operating frequency of the second medicating pump according to the second operating frequency change value. The multi-objective optimization function is determined according to a medicating pump service life optimization function and a medicating pump energy consumption optimization function, the medicating pump service life optimization function is determined according to the first operating frequency change value of the first medicating pump, the second operating frequency change value of the second medicating pump, a first cumulative operating time length of the first medicating pump, and a second cumulative operating time length of the second medicating pump, and the medicating pump energy consumption optimization function is determined according to a first operating frequency of the first medicating pump, a first relationship index between the first operating frequency and the power of the first medicating pump, a second operating frequency of the second medicating pump, and a second relationship index between the second operating frequency and the power of the second medicating pump.

8. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the method of any one of claims 1 to 6.

9. An electronic device, comprising: The computer program is executed by the processor to implement the method of any one of claims 1 to 6. The computer program is executed by the processor to implement the method of any one of claims 1 to 6. The computer program is executed by the processor to implement the method of any one of claims 1 to 6. The computer program is executed by the processor to implement the method of any one of claims 1 to 6. The computer program is executed by the processor to implement the method of any one of claims 1 to 6.

Images