Intelligent control equipment for sewage treatment based on ultraviolet-ozone linkage

Abstract

The application relates to the technical field of sewage treatment, and provides intelligent control equipment for sewage treatment based on ultraviolet-ozone linkage, which comprises an image acquisition module and an image processing module; the image acquisition module acquires each frame of sewage image of sewage in an ultraviolet-ozone linkage treatment area; the image processing module identifies particulate matters and flocculants in the sewage image; according to the distribution of the particulate matters and the flocculants in the sewage image, the water turbidity is determined; according to the change of the water turbidity of a plurality of continuous frames of sewage image, the turbidity change performance of each frame of sewage image is determined; according to the turbidity change performance and the water turbidity, the adjusting mode of the ultraviolet equipment power and the ozone injection amount is outputted, so that the conditions of excessive treatment or insufficient treatment of the sewage are avoided, the sewage treatment effect is obviously improved, the treatment cost is reduced, and the possibility of secondary pollution of the sewage is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sewage treatment, and particularly relates to a sewage treatment intelligent control device based on ultraviolet-ozone linkage. BACKGROUND

[0002] Industrial wastewater has complex components, and contains a large amount of refractory organic matter and suspended solids. Single technology (ultraviolet technology, ozone oxidation technology) has certain technical bottlenecks, and the treatment effect is difficult to meet the high-quality water quality discharge standard. Ultraviolet can catalyze the decomposition of ozone to produce hydroxyl radicals, and its oxidation ability is only second to fluorine. It can non-selectively degrade organic matter, and the reaction rate is increased by 3-5 times. The sewage treatment method based on ultraviolet-ozone linkage can effectively solve the problems of low efficiency, high cost and secondary pollution in traditional sewage treatment through technology integration and intelligent management.

[0003] The sewage treatment method based on ultraviolet-ozone linkage mainly uses ultraviolet penetration and ozone injection for sewage treatment. In the prior art, the ultraviolet device power and the ozone injection amount are fixed and unchanged. The ultraviolet device power determines the ultraviolet intensity, and the greater the ultraviolet device power, the greater the ultraviolet intensity. However, as the sewage treatment proceeds, the state of the sewage changes in real time. Using fixed ultraviolet device power and ozone injection amount may result in over-treatment or insufficient treatment of the sewage, which not only affects the sewage treatment effect, but also may increase the treatment cost, and even may cause secondary pollution of the sewage. SUMMARY

[0004] In order to solve the technical problem of poor sewage treatment effect caused by the fixed ultraviolet device power and ozone injection amount in the prior sewage treatment method based on ultraviolet-ozone linkage, the purpose of the present application is to provide a sewage treatment intelligent control device based on ultraviolet-ozone linkage, and the technical scheme adopted is as follows:

[0005] The present application provides a sewage treatment intelligent control device based on ultraviolet-ozone linkage, comprising:

[0006] An image acquisition module is configured to acquire each frame of sewage image of the sewage in the ultraviolet-ozone linkage treatment area;

[0007] An image processing module is configured to identify particulate matter and flocculation in the sewage image;

[0008] The water turbidity of the sewage image is determined according to the distribution of the particulate matter and the flocculation in the sewage image;

[0009] The turbidity change performance of each frame of sewage image is determined according to the change of the water turbidity of the several continuous frames of sewage image;

[0010] According to the turbidity change performance of each frame of sewage image and the water body turbidity, an adjusting mode corresponding to each frame of sewage image is output, and the adjusting mode is used to instruct to adjust the power of the ultraviolet device and the ozone injection amount.

[0011] In an exemplary embodiment, the particle and flocculate identification process comprises:

[0012] The sewage image is subjected to image segmentation to obtain a plurality of target regions;

[0013] According to the area and shape of each target region, a shape area performance of each target region is determined.

[0014] According to the shape area performance of each target region, each target region is divided into particles and flocculates.

[0015] In an exemplary embodiment, the shape area performance acquisition process comprises:

[0016] According to the area and perimeter of the target region, a circularity of the target region is determined based on the isoperimetric inequality; the circularity represents a degree to which the shape of the target region approximates a circle;

[0017] According to the area, the circularity and the elongation of the target region, a shape area performance of the target region is obtained; the elongation represents a degree to which the length of the target region exceeds the width.

[0018] In an exemplary embodiment, the water body turbidity acquisition process comprises:

[0019] A particle quantity and a particle area proportion in the sewage image are determined to obtain a particle distribution feature;

[0020] A flocculate quantity and a flocculate area proportion in the sewage image are determined to obtain a flocculate distribution feature;

[0021] The particle distribution feature, the flocculate distribution feature and an overall gray value of a sewage region in the sewage image are fused to obtain the water body turbidity; the water body turbidity is directly proportional to the particle distribution feature, and is inversely proportional to the flocculate distribution feature and the overall gray value.

[0022] In an exemplary embodiment, the particle distribution feature is a product of the particle quantity and the particle area proportion; and the flocculate distribution feature is a product of the flocculate quantity and the flocculate area proportion.

[0023] In an exemplary embodiment, the turbidity change performance acquisition process comprises:

[0024] determining a water turbidity difference between each two adjacent frames of the target sewage image and the reference sewage images; the target sewage image is any one frame of sewage image, and each reference sewage image is a plurality of frames of sewage image adjacent to the target sewage image;

[0025] determining an influence weight of each reference sewage image on the target sewage image based on a time interval between the target sewage image and each reference sewage image; the influence weight is inversely proportional to the time interval;

[0026] performing weighted summation on the water turbidity difference corresponding to each reference sewage image based on the influence weight of each reference sewage image, to obtain a turbidity change performance of the target sewage image.

[0027] In an exemplary embodiment, the obtaining process of the adjustment mode comprises:

[0028] determining a difference degree of the water turbidity of the target sewage image and the turbidity change performance, to obtain an adjustment direction of the target frame of sewage image, the adjustment direction being increasing or decreasing; the target sewage image is any one frame of sewage image;

[0029] obtaining an adjustment coefficient according to the adjustment direction and the adjustment degree of the target sewage image; the adjustment degree is obtained from the difference degree, the turbidity change performance and the water turbidity;

[0030] adjusting the original ultraviolet device power and the original ozone injection amount at the corresponding time of the target sewage image according to the adjustment coefficient.

[0031] In an exemplary embodiment, the obtaining process of the difference degree comprises: calculating a difference value of the water turbidity of the target sewage image and the turbidity change performance, and determining the difference degree according to the difference value, the difference degree being proportional to the difference value;

[0032] the obtaining process of the adjustment direction comprises: if the difference degree is greater than or equal to a preset value, the adjustment direction is increasing, otherwise the adjustment direction is decreasing.

[0033] In an exemplary embodiment, the obtaining process of the adjustment degree comprises: calculating a product of the water turbidity of the target sewage image and a turbidity weight, and adding the product to the turbidity change performance of the target sewage image, to obtain a sum value, and determining the adjustment degree of the target sewage image according to the sum value; the turbidity weight is an absolute value of a difference between the difference degree and the preset value.

[0034] In one exemplary embodiment, the adjusting the original ultraviolet device power and the original ozone injection amount at the corresponding time of the target sewage image according to the adjustment coefficient comprises: adding a value 1 to the adjustment coefficient, and multiplying the value 1 by the original ultraviolet device power and the original ozone injection amount at the corresponding time of the target sewage image respectively to obtain the adjusted ultraviolet device power and the ozone injection amount.

[0035] The present application has the following advantages: the present application obtains each frame of sewage image in the sewage treatment process, and the sewage treatment state presented by each frame of sewage image can be different. Then, each frame of sewage image is taken as a processing object, and the ultraviolet device power and the ozone injection amount at the corresponding time of each frame of sewage image are adjusted according to the sewage treatment state presented by each frame of sewage image, so that the ultraviolet device power and the ozone injection amount are related to the real-time sewage treatment state, thereby avoiding the situation of excessive sewage treatment or insufficient treatment, significantly improving the sewage treatment effect, reducing the processing cost, and reducing the possibility of secondary sewage pollution. In addition, the present application determines the adjustment mode corresponding to each frame of sewage image according to the turbidity change performance and the water turbidity of each frame of sewage image, which can ensure the accuracy and reliability of the obtained adjustment mode. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 is a structural schematic diagram of the sewage treatment intelligent control equipment based on ultraviolet-ozone linkage provided by one embodiment of the present application;

[0037] Figure 2 is an image processing flowchart of the image processing module of the sewage treatment intelligent control equipment based on ultraviolet-ozone linkage provided by one embodiment of the present application;

[0038] Figure 3 is a recognition flowchart of the particulate matter and the flocculent provided by one embodiment of the present application;

[0039] Figure 4 is an acquisition flowchart of the shape area performance provided by one embodiment of the present application;

[0040] Figure 5 is an acquisition flowchart of the water turbidity provided by one embodiment of the present application;

[0041] Figure 6 is an acquisition flowchart of the turbidity change performance provided by one embodiment of the present application;

[0042] Figure 7 is an acquisition flowchart of the adjustment mode provided by one embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to further illustrate the technical means and effects taken by the present application to achieve the predetermined inventive objectives, the specific embodiments, structures, features and effects of the present application are described in detail below in combination with the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The data information collected in this application is obtained with the full consent of the authorization.

[0045] The present embodiment provides a sewage treatment intelligent control device based on ultraviolet-ozone linkage, as shown in Figure 1 The image acquisition module can be a conventional image acquisition device, such as a high-resolution industrial camera. The image processing module can be a conventional processor, computer host and server, etc., configured in the sewage treatment monitoring room. The image acquisition module and the image processing module are signal connected, which can be connected by signal transmission line or wirelessly connected by wireless communication module.

[0046] The sewage treatment intelligent control device mainly analyzes the performance of the sewage quality in the sewage treatment process using ultraviolet-ozone linkage to help complete the sewage treatment. The device mainly embeds the ultraviolet (UV) unit and the ozone (O3) generator in the AOP (Advanced Oxidation Processes) sewage treatment integrated device to form a UV-O3 combined reaction zone (i.e. ultraviolet-ozone linkage treatment area), and helps to perform intelligent control by monitoring the sewage treatment state in real time.

[0047] In an exemplary embodiment, first introduce the various pretreatment processes before the sewage enters the ultraviolet-ozone linkage treatment. First, the sewage is pretreated in the order of "grating machine -> water collecting pool -> microwave machine", as shown in Table 1, which is an introduction of grating machine, water collecting pool and microwave machine.

[0048] Table 1

[0049]

[0050] Then the pretreated sewage is further treated in the order of "adjustment tank -> air floatation machine -> intermediate water tank", as shown in Table 2, which is an introduction of adjustment tank, air floatation machine and intermediate water tank.

[0051] Table 2

[0052]

[0053] The sewage is then injected into the UV-O3 combined reaction zone. It should be understood that the UV-O3 combined reaction zone can be a square reaction tank, and the UV device and ozone generator are arranged in the reaction tank.

[0054] The industrial camera is placed in the middle of the UV-O3 combined reaction zone and above the sewage liquid surface. The height of the industrial camera above the sewage liquid surface is the minimum height that can meet the condition of capturing the entire sewage liquid surface, so as to ensure the clarity of each detail in the sewage image. At the same time, in order to ensure the clarity of the industrial camera, the lens needs to be cleaned regularly. It should be understood that the position of the industrial camera needs to be effectively fixed by means of auxiliary mechanisms such as fixing supports. In an exemplary embodiment, the image acquisition frequency of the industrial camera is one frame per 30 seconds. Through the preset acquisition frequency, each frame of sewage image in the UV-O3 combined reaction zone is obtained. The embodiment can also perform image preprocessing such as denoising on the collected each frame of sewage image.

[0055] The image processing module acquires each frame of sewage image collected by the industrial camera and performs image processing. The image processing process is as shown in Figure 2 The specific description of each processing step of the image processing module is as follows.

[0056] Step 1: Identify the particulate matter and flocculation in the sewage image.

[0057] Through the previous several preprocessing processes, the water turbidity (i.e. the turbidity of the water body) of the sewage injected into the UV-O3 combined reaction zone will be significantly reduced, but still contains a small amount of colloids, fine suspended solids and dissolved organic matter. This part of pollutants is further reduced by using UV irradiation and ozone injection to reduce the turbidity of the sewage. If the power of the UV device and the amount of ozone injection are set according to experience, it may affect the sewage treatment effect. Therefore, based on the changes of the sewage state in the UV-O3 combined reaction zone, the power of the UV device and the amount of ozone injection are dynamically adjusted to achieve a higher standard of sewage treatment effect.

[0058] Ozone molecules generate high-activity oxygen atoms and hydroxyl radicals under the action of ultraviolet light, which can destroy the surface charge of colloids in water, thereby causing colloids, suspended solids and organic matter in water to flocculate and precipitate. At the same time, due to the oxidation and rupture of the color-forming groups in the water by ozone, the colority of the wastewater is significantly reduced. To ensure higher quality of wastewater treatment results and not to cause secondary pollution, the power variation of the ultraviolet light and the variation of the ozone injection amount need to be changed based on the real-time turbidity variation of the wastewater. The turbidity of water is often reflected from the solid particles contained in the water and the color performance of the water. Under the combined action of ultraviolet-ozone, the tiny particles existing in the water will gradually be flocculated and precipitated. During the wastewater treatment process, the particulate matter and the flocculation will coexist for a period of time, and both of them have a certain influence on the judgment of the water turbidity. Therefore, it is necessary to first identify the particulate matter and the flocculation in the wastewater image. It should be understood that each frame of the wastewater image is a gray image after gray processing.

[0059] The following will be described by taking any one frame of the wastewater image as an example, which is set as a target wastewater image. In the target wastewater image, the gray value of the particulate matter and the flocculation in the wastewater and the gray value of the water body itself generally have obvious differences, and the particulate matter and the flocculation have obvious differences in shape and area size. Therefore, according to the differences in gray value, shape and area, the particulate matter and the flocculation in the target wastewater image are identified. In an exemplary embodiment, as shown in FIG. 1, a specific identification process of the particulate matter and the flocculation is as follows: Figure 3

[0060] Step 1-1: Image segmentation is performed on the wastewater image to obtain a plurality of target regions.

[0061] ​The target sewage image is segmented by threshold segmentation to obtain a background region (sewage region) and a substance existing region (the substance existing region includes particulate matter and flocculation, i.e., the substance existing region is each target region). In an exemplary embodiment, each connected domain in the target sewage image is determined, such as binarizing the target sewage image to obtain a binary image (distinguishing the background region and the foreground region, and the foreground region is the substance existing region), and then the connectivity of each pixel point is determined based on an 8-neighborhood to obtain each connected domain. Since the gray value of the sewage is quite different from the gray value of the particulate matter and the flocculation, the connected domains of the background region can be screened out by the gray value. Specifically, the average gray value of each connected domain is obtained, and then compared with a preset sewage standard gray value. The connected domain with an error within a preset range from the preset sewage standard gray value is determined as the background region, and the background region is screened out. The remaining each connected domain corresponds to the region of the particulate matter or the flocculation; or, usually, the area ratio of the sewage itself in the target sewage image is large, and the area ratio of the particulate matter and the flocculation in the target sewage image is small, so the area ratio of each connected domain can be obtained, and the connected domain with an area ratio greater than a preset ratio is determined as the background region.

[0062] After the background region is screened out, the corresponding region of each remaining connected domain in the target sewage image is set as a target region, thereby obtaining a plurality of target regions.

[0063] Step 1-2: According to the area and shape of each target region, the shape area performance of each target region is determined.

[0064] The flocculation is formed by the aggregation of particulate matter, and there is a large difference in shape performance, area size, etc. between the particulate matter and the flocculation. Then, according to the area and shape of each target region, the shape area performance of each target region is determined. In an exemplary embodiment, as shown in FIG. 1B, a specific acquisition process of the shape area performance is given as follows: Figure 4

[0065] Step 1-2-1: According to the area and perimeter of the target region, the circularity of the target region is determined based on the isoperimetric inequality.

[0066] Take any target region as an example for description. The isoperimetric inequality, also known as the isoperimetric theorem, states that among closed geometric shapes with equal perimeter, the circle has the largest area. Another statement is that among geometric shapes with equal area, the circle has the smallest perimeter. Helvig proposed that the relationship between the perimeter length of a closed curve and the area enclosed by the curve can be expressed by an inequality, which is called the isoperimetric inequality.

[0067] ​Based on the isoperimetric inequality, the isoperimetric quotient of the target region can be obtained, and the isoperimetric quotient is essentially the circularity, which represents the degree to which the shape of the target region approximates a circle. In an exemplary embodiment, the circularity is quantified as follows:

[0068]

[0069] wherein Cir t,k represents the circularity of the kth target region in the tth frame of sewage image, S t,k represents the area of the kth target region in the tth frame of sewage image (i.e., the number of pixel points contained in the target region); C t,k represents the perimeter of the kth target region in the tth frame of sewage image, i.e., the number of edge pixel points of the edge of the kth target region, and π represents the circular constant.

[0070] The above formula mainly uses the relationship between the area and the perimeter to analyze the circularity performance of the target region. From the area formula of a circle s = πr 2 , it can be seen that the closer the calculation result of Cir t,k is to 1, the closer the shape of the kth target region in the tth frame of sewage image approximates a circle. Since the flocculation is generated by the aggregation of particulate matter, the shape of the flocculation usually exhibits irregularity, and therefore the circularity of the particulate matter is greater than that of the flocculation.

[0071] Step 1-2-2: Obtain the shape area performance of the target region according to the area, circularity and elongation of the target region.

[0072] Determine the elongation of the target region, which represents the degree to which the length of the target region exceeds the width, and the greater the length of the target region is greater than the width, the greater the elongation. In an exemplary embodiment, the center point of the target region is determined, straight lines in various directions passing through the center point are obtained, the number of pixel points on the line segment in the target region of each straight line is obtained, so as to determine the line segment with the largest number of pixel points, which is defined as the long axis of the target region. Then, a perpendicular line of the long axis corresponding straight line passing through the center point of the target region is made, the line segment of the perpendicular line in the target region is obtained, which is defined as the short axis of the target region, and the number of pixel points on the short axis is obtained. The ratio of the number of pixel points of the long axis to the number of pixel points of the short axis is calculated, which is the elongation of the target region. Therefore, the numerical range of the elongation is greater than 1.

[0073] According to the area, circularity and elongation of the target region, the shape-area performance of the target region is obtained. The shape-area performance represents the possibility that the current region belongs to the particulate matter. As can be known from the above analysis, compared with the flocculation, the area of the particulate matter is smaller, the circularity of the particulate matter is larger, and the elongation of the particulate matter is smaller. Moreover, since the flocculation is generated by the aggregation of the particulate matter, the aggregation process has randomness, so the flocculation shows the characteristics of poor circularity, large area and large elongation in the shape-area direction. Therefore, the shape-area performance of the target region is inversely proportional to the area and the elongation of the target region, and is proportional to the circularity. In an exemplary embodiment, a quantitative manner of the shape-area performance is given as follows:

[0074]

[0075] wherein SA t,k represents the shape-area performance of the kth target region in the tth sewage image, τ t,K represents the area ratio of the kth target region in the tth sewage image, the area ratio being the ratio of the number of pixel points in the kth target region to the total number of pixel points in the tth sewage image, minL t,k represents the number of pixel points of the minor axis of the kth target region in the tth sewage image, maxL t,k represents the number of pixel points of the major axis of the kth target region in the tth sewage image, the essence being the reciprocal of the elongation.

[0076] Step 1-3: According to the shape-area performance of each target region, the target regions are divided into particulate matter and flocculation.

[0077] Through step 1-2, the shape-area performance of each target region in the tth sewage image is obtained. The greater the shape-area performance, the more the target region belongs to the particulate matter. Therefore, according to the shape-area performance of each target region, the target regions are divided into particulate matter and flocculation. In an exemplary embodiment, a shape-area performance threshold is preset, the numerical range of the shape-area performance threshold being 0-1, and the specific numerical value thereof being set by judgment, such as 0.5.

[0078] The shape-area performance of each target region is compared with the size of the shape-area performance threshold. The target region corresponding to the shape-area performance greater than or equal to the shape-area performance threshold is determined as the particulate matter region, i.e., is recognized as the particulate matter. The target region corresponding to the shape-area performance less than the shape-area performance threshold is determined as the flocculation region, i.e., is recognized as the flocculation.

[0079] It should be understood that in industrial wastewater treatment, there are usually more refractory organic matter, suspended solids and the like, so there are usually both particulate matter and flocculation in the sewage image, and the flocculation is formed by the aggregation of particulate matter. Accordingly, the application is applicable to the scene where both particulate matter and flocculation exist in the sewage image, and subsequent data processing is performed according to the distribution of particulate matter and flocculation. The application is not applicable to the scene where only particulate matter or flocculation exists in the sewage image, or neither particulate matter nor flocculation exists. If only particulate matter or flocculation is identified after identifying the sewage image, or neither particulate matter nor flocculation is identified, the subsequent image processing process is not executed, and the application stops executing.

[0080] Step 2: According to the distribution of particulate matter and flocculation in the sewage image, the water turbidity of the sewage image is determined.

[0081] With the combined action of ultraviolet-ozone, part of the particulate matter in the sewage will be decomposed, and then flocculation and precipitation under the action of ozone, resulting in gradual decrease of particulate matter and gradual increase of flocculation in the sewage. Therefore, according to the distribution of particulate matter and flocculation in the sewage image, the water turbidity of the sewage image is determined. In an exemplary embodiment, as shown in FIG. 2, a specific process for obtaining water turbidity is as follows: Figure 5

[0082] Step 2-1: Determine the number of particulate matter and the area ratio of particulate matter in the sewage image to obtain the distribution characteristics of particulate matter.

[0083] After obtaining each particulate matter region and flocculation region in the sewage image, each particulate matter region is regarded as each particulate matter, and each flocculation region is regarded as each flocculation, so as to obtain the number of particulate matter and the number of flocculation in the sewage image. Then, the sum of the number of pixel points of all particulate matter regions is calculated, and the ratio of the sum to the total number of pixel points of the sewage image is taken as the area ratio of particulate matter; the sum of the number of pixel points of all flocculation regions is calculated, and the ratio of the sum to the total number of pixel points of the sewage image is taken as the area ratio of flocculation.

[0084] Since the number of particulate matter and the area ratio of particulate matter in the sewage image can reflect the distribution characteristics of particulate matter in the sewage image, the distribution characteristics of particulate matter are obtained according to the number of particulate matter and the area ratio of particulate matter. In an exemplary embodiment, the distribution characteristics of particulate matter are the product of the number of particulate matter and the area ratio of particulate matter.

[0085] Step 2-2: Determine the number of flocculation and the area ratio of flocculation in the sewage image to obtain the distribution characteristics of flocculation.

[0086] ​Since the number of flocculation and the area proportion of flocculation in the sewage image can reflect the distribution characteristics of flocculation in the sewage image, the distribution characteristics of flocculation are obtained according to the number of flocculation and the area proportion of flocculation, and in an exemplary embodiment, the distribution characteristics of flocculation are the product of the number of flocculation and the area proportion of flocculation.

[0087] Step 2-3: The water turbidity is obtained by fusing the particulate matter distribution characteristics, the flocculation distribution characteristics, and the overall gray value of the sewage region in the sewage image.

[0088] The particulate matter distribution characteristics and the flocculation distribution characteristics jointly represent the concentration degree of particulate matter. The greater the particulate matter distribution characteristics and the smaller the flocculation distribution characteristics, the greater the concentration degree of particulate matter, the more turbid the sewage, and the greater the water turbidity. At the same time, the more black the gray color of the sewage (i.e., the smaller the gray value), the more turbid the water, and the greater the water turbidity.

[0089] With the combined action of ultraviolet-ozone, the water turbidity of the sewage should maintain a continuous downward trend, that is, the gray value of the sewage region in the sewage image will become larger and larger, and the more and more flocculation and the less and less particulate matter, that is, the particulate matter distribution characteristics gradually weaken, and the flocculation distribution characteristics gradually strengthen.

[0090] The gray value of the sewage region in the sewage image is obtained, and in an exemplary embodiment, the background region in the above is the sewage region, so the average value of the gray values of the pixel points of the background region in the sewage image is obtained as the overall gray value of the sewage region.

[0091] The water turbidity of the sewage image is obtained by fusing the particulate matter distribution characteristics, the flocculation distribution characteristics, and the overall gray value of the sewage region. The water turbidity is proportional to the particulate matter distribution characteristics, and inversely proportional to the flocculation distribution characteristics and the overall gray value of the sewage region. In an exemplary embodiment, a specific quantification method of the water turbidity is given as follows:

[0092]

[0093] wherein, WG t represents the water turbidity of the t-th frame of sewage image; N t,KL represents the number of particulate matter in the t-th frame of sewage image, τ t,KL represents the area proportion of particulate matter in the t-th frame of sewage image, N t,KL x τ t,KL represents the particulate matter distribution characteristics of the t-th frame of sewage image; N t,XN represents the number of flocculation in the t-th frame of sewage image, τ t,XN represents the area proportion of flocculation in the t-th frame of sewage image, N t,XN x τ t,XNfloc distribution feature of the t-th frame sewage image; norm represents a normalization function, which can be normalized in the following way: 1-exp(-x), where x is the object to be normalized, and exp represents the exponential function with natural constant e as the base. G t the overall gray value of the sewage area of the t-th frame sewage image, indicating the negative correlation normalization of the overall gray value.

[0094] Step 3: According to the change of the water turbidity of several consecutive frames of sewage images, the turbidity change performance of each frame of sewage image is determined.

[0095] Step 2: The water turbidity of each frame of sewage image is obtained. Under the combined action of ultraviolet-ozone, the water turbidity is gradually reduced. When the water turbidity is high, the high penetration rate of strong ultraviolet light can effectively penetrate the suspended matter layer, ensuring the continuous generation of free radicals, and when the water turbidity is low, it is not necessary to use strong ultraviolet light. The amount of ozone injection is also analyzed in the same way.

[0096] With the progress of sewage treatment, the water turbidity is continuously changing. Therefore, according to the change of the water turbidity of several consecutive frames of sewage images, the turbidity change performance of each frame of sewage image is determined, so as to control the power of ultraviolet equipment and the amount of ozone injection. Since there is a certain correlation between the water turbidity of several frames of sewage images before the target sewage image and the water turbidity of the target sewage image, especially when the water turbidity of several frames of sewage images before the target sewage image is changing, it will have a certain influence on the water turbidity of the target sewage image. Therefore, the turbidity change performance of the target sewage image is determined by the water turbidity of several frames of sewage images before the target sewage image. As shown in Figure 6 , a specific process for obtaining the turbidity change performance is given as follows:

[0097] Step 3-1: Determine the water turbidity difference between each adjacent two frames of sewage images in the target sewage image and each reference sewage image.

[0098] According to the target sewage image, the reference sewage images of the target sewage image are determined, wherein each reference sewage image is the previous several frames of sewage images adjacent to the target sewage image. In an exemplary embodiment, the number of reference sewage images of the target sewage image is three, which are the previous three sewage images adjacent to the target sewage image, for example: if the target sewage image is the 6th frame of sewage image, the reference sewage images of the target sewage image are the 3rd frame of sewage image, the 4th frame of sewage image and the 5th frame of sewage image.

[0099] The water turbidity difference of each adjacent two frames of sewage images in the target sewage image and each reference sewage image is determined. Specifically, for the tthframe of sewage image, each reference sewage image is the t-1thframe of sewage image, the t-2thframe of sewage image and the t-3thframe of sewage image respectively. The water turbidity difference of the t-2thframe of sewage image and the t-3thframe of sewage image is calculated, which is specifically the absolute value of the difference of the water turbidity, to obtain the water turbidity difference corresponding to the t-3thframe of sewage image. The water turbidity difference of the t-1thframe of sewage image and the t-2thframe of sewage image is calculated to obtain the water turbidity difference corresponding to the t-2thframe of sewage image. The water turbidity difference of the tthframe of sewage image and the t-1thframe of sewage image is calculated to obtain the water turbidity difference corresponding to the t-1thframe of sewage image. Thus, the water turbidity difference corresponding to each reference sewage image is obtained.

[0100] Step 3-2: Based on the time interval between the target sewage image and each reference sewage image, the influence weight of each reference sewage image on the target sewage image is determined.

[0101] Different reference sewage images have different importance to the target sewage image. The closer the reference sewage image to the target sewage image, that is, the shorter the time interval between the reference sewage image and the target sewage image, the deeper the influence of the reference sewage image on the target sewage image, that is, the more reliable the reference sewage image in analyzing the turbidity change performance of the target sewage image. Therefore, based on the time interval between the target sewage image and each reference sewage image, the influence weight of each reference sewage image on the target sewage image is determined, the influence weight is inversely proportional to the time interval, and the closer the reference sewage image to the target sewage image, the higher the influence weight. It should be understood that under the premise of meeting: the closer the reference sewage image to the target sewage image, the higher the influence weight, the influence weight of each reference sewage image on the target sewage image is artificially set, and the sum of the influence weight of each reference sewage image on the target sewage image is 1, such as the influence weight of the t-1thframe of sewage image is the highest, which is 0.5, the influence weight of the t-2thframe of sewage image is the second, which is 0.3, and the influence weight of the t-3thframe of sewage image is the lowest, which is 0.2.

[0102] Step 3-3: Based on the influence weight of each reference sewage image, the water turbidity difference corresponding to each reference sewage image is weighted and summed to obtain the turbidity change performance of the target sewage image.

[0103] The quantitative formula of the turbidity change performance of the target sewage image is as follows:

[0104] WP t =ΔWG t-3 ×α t-3 +ΔWG t-2 ×α t-2 +ΔWG t-1Xa t-1 ;

[0105] wherein, WP t represents the turbidity variation performance of the t-th frame sewage image, ΔWG t-3 represents the water turbidity difference corresponding to the t-3-th frame sewage image, ΔWG t-2 represents the water turbidity difference corresponding to the t-2-th frame sewage image, ΔWG t-1 represents the water turbidity difference corresponding to the t-1-th frame sewage image; a t-3 represents the influence weight of the t-3-th frame sewage image, a t-2 represents the influence weight of the t-2-th frame sewage image, a t-1 represents the influence weight of the t-1-th frame sewage image.

[0106] It should be understood that for the first several frames of sewage images in time sequence, such as the first three frames of sewage images in time sequence, since there is not enough number of sewage images (i.e. there is not enough number of reference sewage images) before them, the turbidity variation performance of the first several frames of sewage images in time sequence is no longer obtained, i.e. the ultraviolet device power and the ozone injection amount of the first several frames of sewage images in time sequence are not adjusted, but are controlled according to the ultraviolet device power and the ozone injection amount preset for them.

[0107] Step 4: output the adjustment mode corresponding to each frame of sewage image according to the turbidity variation performance and the water turbidity of each frame of sewage image.

[0108] It is not rigorous enough to adjust the ultraviolet device power and the ozone injection amount only according to the turbidity variation performance of the target sewage image, and it is also necessary to comprehensively analyze in combination with the water turbidity of the target sewage image. Therefore, according to the turbidity variation performance and the water turbidity of the target sewage image, the adjustment mode corresponding to the target sewage image is output, and the adjustment mode is used to indicate the adjustment of the ultraviolet device power and the ozone injection amount. In an exemplary embodiment, as shown in FIG. 8, a specific acquisition process of the adjustment mode is given as follows: Figure 7

[0109] Step 4-1: determine the difference degree of the water turbidity and the turbidity variation performance of the target sewage image, and obtain the adjustment direction of the target frame of sewage image.

[0110] ​For the target sewage image, if the turbidity change performance is large, that is, the water body turbidity changes rapidly, and the water body turbidity is small, it indicates that the sewage treatment effect at the corresponding moment of the target sewage image is good, and it is not necessary to have a large ultraviolet device power and ozone injection amount, that is, it is necessary to appropriately reduce the ultraviolet device power and ozone injection amount to avoid causing excessive sewage treatment. On the contrary, if the turbidity change performance is small, that is, the water body turbidity changes slowly, and the water body turbidity is large, it indicates that the sewage treatment effect at the corresponding moment of the target sewage image is poor, and the turbidity degree of the water body is still high, so it is necessary to have a large ultraviolet device power and ozone injection amount, that is, it is necessary to appropriately increase the ultraviolet device power and ozone injection amount to improve the sewage treatment effect.

[0111] The difference degree of the water body turbidity and the turbidity change performance of the target sewage image is obtained, and the greater the difference degree, the greater the regulation range whether the ultraviolet device power and the ozone injection amount are reduced or increased.

[0112] In an exemplary embodiment, the difference value of the water body turbidity and the turbidity change performance of the target sewage image is calculated, and the greater the difference value, that is, the greater the degree to which the water body turbidity exceeds the turbidity change performance, that is, the water body turbidity changes slowly and the water body turbidity is large, it indicates that the sewage treatment effect at the corresponding moment of the target sewage image is poor, and the turbidity degree of the water body is still high. In principle, the numerical range of the difference value is (-1, 1). The difference degree is determined according to the difference value, and the difference degree is proportional to the difference value. In an exemplary embodiment, the difference value is normalized, and the result after normalization is used as the difference degree. Wherein, the normalization method can be: the difference value is added to the value 1 and then divided by 2.

[0113] The adjustment direction is determined according to the difference degree, and the adjustment direction is to increase or reduce, that is, to increase the ultraviolet device power and the ozone injection amount, or to reduce the ultraviolet device power and the ozone injection amount. A value is preset, and the preset value is used as a dividing point of the high and low of the difference degree, so as to determine the adjustment direction according to the size relationship between the difference degree and the preset value, if the difference degree is greater than or equal to the preset value, the difference degree is large, and the adjustment direction is to increase, if the difference degree is less than the preset value, the difference degree is small, and the adjustment direction is to reduce. Wherein, in principle, the numerical range of the preset value is (0, 1), and the specific value thereof is obtained by actual needs, or: a large number of sewage treatment processes are obtained, the time when the ultraviolet device power and the ozone injection amount are increased or reduced in each treatment process is determined, and the specific value of the preset value is determined according to the numerical relationship between the water body turbidity and the turbidity change performance at the time of increasing or reducing the ultraviolet device power and the ozone injection amount. In this embodiment, 0.5 is taken as an example.

[0114] Step 4-2: Obtain the adjustment coefficient according to the adjustment direction and the adjustment degree of the target sewage image.

[0115] According to the difference degree of the target sewage image, the turbidity change performance and the water body turbidity, an adjustment degree of the target sewage image is obtained, specifically: the difference between the difference degree of the target sewage image and a preset value is calculated, which is defined as a turbidity weight. The product of the water body turbidity of the target sewage image and the turbidity weight is calculated, and finally the product is added to the turbidity change performance of the target sewage image, and the sum value is used to determine the adjustment degree of the target sewage image.

[0116] Q t = norm(WP t + A t × WG t );

[0117] wherein, Q t represents the adjustment degree of the t-th frame sewage image, A t represents the turbidity weight of the t-th frame sewage image.

[0118] According to the adjustment direction and the adjustment degree of the t-th frame sewage image, an adjustment coefficient γ t of the t-th frame sewage image is obtained. If the adjustment direction is to increase, then γ t = Q t ; if the adjustment direction is to decrease, then γ t = -Q t .

[0119] Step 4-3: According to the adjustment coefficient, the original ultraviolet device power and the original ozone injection amount of the target sewage image corresponding to the moment are adjusted.

[0120] The original ultraviolet device power and the original ozone injection amount corresponding to the moment of the target sewage image are obtained, which are the ultraviolet device power and the ozone injection amount determined before the moment corresponding to the target sewage image.

[0121] The value 1 is added to the adjustment coefficient of the target sewage image, and is multiplied by the original ultraviolet device power and the original ozone injection amount corresponding to the moment of the target sewage image, respectively, to obtain the adjusted ultraviolet device power and ozone injection amount. A quantitative method is given as follows:

[0122]

[0123] wherein, represents the adjusted ultraviolet device power corresponding to the moment of the t-th frame sewage image, P t represents the original ultraviolet device power corresponding to the moment of the t-th frame sewage image, represents the adjusted ozone injection amount corresponding to the moment of the t-th frame sewage image, represents the original ozone injection amount corresponding to the moment of the t-th frame sewage image.

[0124] According to the adjusted ultraviolet device power and the adjusted ozone injection amount corresponding to the time of the t-th frame sewage image, the ultraviolet device is controlled to operate according to the adjusted ultraviolet device power, and the ozone generator is controlled to operate according to the adjusted ozone injection amount. It should be understood that if the adjusted ultraviolet device power is greater than the maximum allowable power of the ultraviolet device, the ultraviolet device is controlled to operate according to the maximum allowable power thereof, and if the adjusted ozone injection amount is greater than the maximum allowable injection amount of ozone, the ozone is injected according to the maximum allowable injection amount of ozone.

[0125] In the subsequent regulation process, for each frame of sewage image in the subsequent, the ultraviolet device power and the ozone injection amount can be continuously regulated in real time until the sewage is completely purified.

[0126] It should be noted that the above-mentioned embodiment sequence of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0127] Each of the embodiments in the specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments.

Claims

1. A sewage treatment intelligent control device based on ultraviolet-ozone linkage, characterized in that, The method comprises the following steps: An image acquisition module is configured to acquire a plurality of frames of sewage images of sewage in an ultraviolet-ozone combined treatment area; An image processing module is configured to identify particulate matter and flocculation in the sewage images; The water turbidity of the sewage images is determined according to the distribution of the particulate matter and the flocculation in the sewage images; The turbidity variation performance of each frame of the sewage images is determined according to the variation of the water turbidity of a plurality of continuous frames of the sewage images; An adjustment mode corresponding to each frame of the sewage images is output according to the turbidity variation performance and the water turbidity of each frame of the sewage images, wherein the adjustment mode is used to indicate adjustment of the power of the ultraviolet device and the amount of ozone injection. The process of obtaining the turbidity variation performance comprises the following steps: The water turbidity difference between each adjacent two frames of the sewage images in the target sewage image and each reference sewage image is determined, wherein the target sewage image is any frame of the sewage images, and each reference sewage image is a plurality of frames of the sewage images adjacent to the target sewage image; The influence weight of each reference sewage image on the target sewage image is determined based on the time interval between the target sewage image and each reference sewage image, wherein the influence weight is inversely proportional to the time interval; The water turbidity difference corresponding to each reference sewage image is weighted and summed based on the influence weight of each reference sewage image, so as to obtain the turbidity variation performance of the target sewage image. The process of obtaining the adjustment mode comprises the following steps: The difference degree of the water turbidity and the turbidity variation performance of the target sewage image is determined, so as to obtain the adjustment direction of the target frame of the sewage image, wherein the adjustment direction is to increase or decrease; The adjustment coefficient is obtained according to the adjustment direction and the adjustment degree of the target sewage image, wherein the adjustment degree is obtained from the difference degree, the turbidity variation performance and the water turbidity; The original power of the ultraviolet device and the original amount of ozone injection at the corresponding time of the target sewage image are adjusted according to the adjustment coefficient. The process of adjusting the original power of the ultraviolet device and the original amount of ozone injection at the corresponding time of the target sewage image according to the adjustment coefficient comprises the following steps: adding the value 1 to the adjustment coefficient, and multiplying the result by the original power of the ultraviolet device and the original amount of ozone injection at the corresponding time of the target sewage image respectively, so as to obtain the adjusted power of the ultraviolet device and the adjusted amount of ozone injection.

2. The intelligent control device for sewage treatment based on ultraviolet-ozone linkage according to claim 1, wherein The process of identifying the particulate matter and the flocculation comprises the following steps: The sewage images are subjected to image segmentation to obtain a plurality of target regions; The shape area performance of each target region is determined according to the area and the shape of each target region; Each target region is divided into particulate matter and flocculation according to the shape area performance of each target region.

3. The intelligent control device for sewage treatment based on ultraviolet-ozone linkage according to claim 2, characterized in that, The process of obtaining the shape area performance comprises the following steps: The circularity of a target region is determined based on the area and the circumference of the target region according to the isoperimetric inequality, wherein the circularity represents the degree to which the shape of the target region approximates a circle; The shape area performance of the target region is obtained according to the area, the circularity and the elongation of the target region, wherein the elongation represents the degree to which the length of the target region exceeds the width.

4. The intelligent control device for sewage treatment based on ultraviolet-ozone linkage according to claim 1, wherein the ultraviolet-ozone generator is a device that generates ultraviolet rays and ozone by using a high voltage. The process of obtaining the water turbidity comprises the following steps: Determine the number of particulates and the area proportion of particulates in the sewage image to obtain particulate distribution characteristics; Determine the number of flocculation and the area proportion of flocculation in the sewage image to obtain flocculation distribution characteristics; Fuse the particulate distribution characteristics, the flocculation distribution characteristics and the overall gray value of the sewage region in the sewage image to obtain the water turbidity; the water turbidity is proportional to the particulate distribution characteristics, and is inversely proportional to the flocculation distribution characteristics and the overall gray value.

5. The intelligent control device for sewage treatment based on ultraviolet-ozone linkage according to claim 4, characterized in that, The particulate distribution characteristics is the product of the number of particulates and the area proportion of particulates; the flocculation distribution characteristics is the product of the number of flocculation and the area proportion of flocculation.

6. The intelligent control device for sewage treatment based on ultraviolet-ozone linkage according to claim 1, wherein the ultraviolet-ozone linkage is configured to be connected to a sewage treatment tank. The acquisition process of the difference degree includes: calculating the difference value between the water turbidity of the target sewage image and the turbidity change performance, and determining the difference degree according to the difference value; the difference degree is proportional to the difference value; The acquisition process of the adjustment direction includes: if the difference degree is greater than or equal to a preset value, the adjustment direction is increasing, otherwise the adjustment direction is decreasing.

7. The intelligent control device for sewage treatment based on ultraviolet-ozone linkage according to claim 6, wherein the ultraviolet-ozone linkage is configured to be connected to the sewage treatment device. The acquisition process of the adjustment degree includes: calculating the product of the water turbidity of the target sewage image and the turbidity weight, and adding the turbidity change performance of the target sewage image, and determining the adjustment degree of the target sewage image according to the sum value; the turbidity weight is the absolute value of the difference between the difference degree and the preset value.

Images