Sewage treatment intelligent control equipment based on ultraviolet-ozone linkage

Abstract

The invention relates to the technical field of sewage treatment, and provides sewage treatment intelligent control equipment based on ultraviolet-ozone linkage, which comprises an image acquisition module and an image processing module, and is characterized in that 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 flocculates in the sewage images, determines the water turbidity according to the distribution of the particulate matters and flocculates in the sewage images, determines the turbidity change expression of each frame of sewage image according to the change condition of the water turbidity of a plurality of continuous frames of sewage images, and determines the turbidity change expression of each frame of sewage image according to the turbidity change expression and the water turbidity. According to the invention, by adjusting the power of the output ultraviolet equipment and the ozone injection amount, the situation of excessive treatment or insufficient treatment of the sewage is avoided, the sewage treatment effect is remarkably improved, the treatment cost can be reduced, and the possibility of secondary pollution of the sewage is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage treatment, and in particular to an intelligent sewage treatment control device based on ultraviolet-ozone linkage. Background Art

[0002] Industrial wastewater has a complex composition, containing a large amount of difficult-to-degrade organic matter and suspended solids. Single technologies (ultraviolet technology, ozone oxidation technology) all have certain technical bottlenecks, and the treatment effect is difficult to achieve high-quality water discharge standards. Ultraviolet light can catalyze the decomposition of ozone to produce hydroxyl radicals, whose oxidizing power is second only to fluorine. It can non-selectively degrade organic matter and increase the reaction rate by 3-5 times. The wastewater treatment method based on ultraviolet-ozone linkage can effectively solve the problems of low efficiency, high cost, and secondary pollution of traditional wastewater treatment through technological integration and intelligent management.

[0003] The UV-ozone combined wastewater treatment method primarily utilizes UV penetration and ozone injection to treat wastewater. Currently, the UV device power and ozone injection rate are fixed. The UV device power determines the UV intensity; the higher the UV device power, the greater the UV intensity. However, as wastewater treatment progresses, its state changes in real time. Using fixed UV device power and ozone injection rates can result in over- or under-treatment of wastewater, which not only affects treatment effectiveness but also increases treatment costs and may even cause secondary pollution. Summary of the Invention

[0004] In order to solve the technical problem of poor sewage treatment effect in the existing sewage treatment method based on ultraviolet-ozone linkage due to the fixed power of ultraviolet equipment and the ozone injection amount, the purpose of the present invention is to provide an intelligent sewage treatment control device based on ultraviolet-ozone linkage. The technical solution adopted is as follows:

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

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

[0007] An image processing module, configured to identify particles and flocculants in the sewage image;

[0008] determining the water turbidity of the sewage image based on the distribution of particulate matter and flocculants in the sewage image;

[0009] According to the change of water turbidity of a number of consecutive frames of sewage images, the turbidity change performance of each frame of sewage image is determined;

[0010] According to the turbidity change performance of each frame of sewage image and the turbidity of the water body, the adjustment method corresponding to each frame of sewage image is output, and the adjustment method is used to indicate the adjustment of the ultraviolet device power and the ozone injection amount.

[0011] In an exemplary embodiment, the process of identifying particles and flocs includes:

[0012] performing image segmentation on the sewage image to obtain multiple target areas;

[0013] Determine the shape and area representation of each target area according to the area and shape of each target area;

[0014] According to the shape and area of ​​each target area, each target area is divided into particles and flocs.

[0015] In an exemplary embodiment, the process of obtaining the shape area representation includes:

[0016] Based on the isoperimetric inequality, the circularity of the target area is determined according to the area and perimeter of the target area; the circularity represents the degree to which the shape of the target area is close to a circle;

[0017] The shape and area representation of the target area is obtained based on the area, the circularity, and the elongation of the target area; the elongation represents the extent to which the length of the target area exceeds the width.

[0018] In an exemplary embodiment, the process of obtaining the water turbidity includes:

[0019] Determining the number of particles and the area ratio of the particles in the sewage image to obtain a distribution characteristic of the particles;

[0020] Determining the number of flocs and the area ratio of the flocs in the sewage image to obtain floc distribution characteristics;

[0021] The water turbidity is obtained by fusing the particle distribution characteristics, the floc distribution characteristics and the overall grayscale value of the sewage area in the sewage image; the water turbidity is proportional to the particle distribution characteristics and inversely proportional to the floc distribution characteristics and the overall grayscale value.

[0022] In an exemplary embodiment, the particle distribution characteristic is the product of the number of particles and the area ratio of particles; the floc distribution characteristic is the product of the number of flocs and the area ratio of flocs.

[0023] In an exemplary embodiment, the process of obtaining the turbidity change performance includes:

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

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

[0026] Based on the influence weight of each reference sewage image, the water turbidity differences corresponding to each reference sewage image are weightedly summed to obtain the turbidity change representation of the target sewage image.

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

[0028] Determine the degree of difference between the water turbidity and the turbidity change performance of the target sewage image, and obtain the adjustment direction of the target frame sewage image, wherein the adjustment direction is increase or decrease; the target sewage image is any frame sewage image;

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

[0030] According to the adjustment coefficient, the original ultraviolet device power and the original ozone injection amount at the corresponding moment of the target sewage image are adjusted.

[0031] In an exemplary embodiment, the process of obtaining the degree of difference includes: calculating the difference between the turbidity of the target sewage image and the turbidity change expression, and determining the degree of difference based on the difference, wherein the degree of difference is proportional to the difference;

[0032] The process of acquiring 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.

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

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

[0035] The present invention has the following beneficial effects: the present invention obtains each frame of sewage image in a time sequence during the sewage treatment process, and the sewage treatment status presented by each frame of sewage image may be different. Therefore, each frame of sewage image is used as the treatment object, and according to the sewage treatment status presented by each frame of sewage image, the ultraviolet device power and ozone injection amount at the corresponding moment of each frame of sewage image are adjusted accordingly, so that the ultraviolet device power and ozone injection amount are related to the real-time sewage treatment status, thereby avoiding the situation of over-treatment or under-treatment of sewage, not only significantly improving the sewage treatment effect, but also reducing the treatment cost and the possibility of secondary pollution of sewage. In addition, the present invention determines the adjustment method corresponding to each frame of sewage image based on the turbidity change performance of each frame of sewage image and the turbidity of the water body, which can ensure the accuracy and reliability of the obtained adjustment method. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0037] Figure 2 This is an image processing flow chart of an image processing module of an intelligent control device for sewage treatment based on ultraviolet-ozone linkage provided by one embodiment of the present invention;

[0038] Figure 3 is a flow chart for identifying particulate matter and flocculants provided by one embodiment of the present invention;

[0039] Figure 4 This is a flowchart for obtaining shape area representation provided by one embodiment of the present invention;

[0040] Figure 5 This is a flow chart for obtaining water turbidity provided by one embodiment of the present invention;

[0041] Figure 6 This is a flow chart for obtaining turbidity change performance provided by one embodiment of the present invention;

[0042] Figure 7 This is a flowchart of obtaining an adjustment method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] To further illustrate the technical means and effects employed by the present invention to achieve its intended objectives, the following detailed description of the specific embodiments, structures, features, and effects of the present invention is provided in conjunction with the accompanying drawings and preferred embodiments. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which this invention pertains. The data and information collected in this application were obtained with full consent and authorization.

[0045] This embodiment provides a sewage treatment intelligent control device based on ultraviolet-ozone linkage, such as Figure 1 As shown, the system consists of two parts: an image acquisition module and an image processing module. 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, or server, and is deployed in the sewage treatment monitoring room. The signal connection between the image acquisition module and the image processing module can be achieved through a wired connection using a signal transmission line or a wireless connection using a wireless communication module.

[0046] Intelligent sewage treatment control equipment primarily assists with sewage treatment by analyzing the performance of sewage quality during the UV-ozone treatment process. The equipment integrates an ultraviolet (UV) unit and an ozone (O3) generator into the existing Advanced Oxidation Processes (AOP) sewage treatment system, creating a combined UV-O3 reaction zone (i.e., the UV-ozone treatment zone). This system monitors sewage treatment status in real time to facilitate intelligent regulation.

[0047] In an exemplary embodiment, the various pretreatment processes before wastewater enters the UV-ozone system are described. The wastewater is first pretreated in the order of "grid machine -> water collection tank -> microwave machine," as shown in Table 1. Table 1 describes the grid machine, water collection tank, and microwave machine.

[0048] Table 1

[0049]

[0050] The pretreated sewage is then treated in the order of "equalization tank -> flotation machine -> intermediate water tank", as shown in Table 2, which introduces the equalization tank, flotation machine and intermediate water tank.

[0051] Table 2

[0052]

[0053] The wastewater is then injected into the UV-O3 combined treatment area, which can be a square reaction tank equipped with UV equipment and an ozone generator.

[0054] The industrial camera is placed in the middle of the UV-ozone linkage treatment area and above the sewage level. The height above the sewage level is the minimum height that satisfies the condition that the entire sewage level can be photographed 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 it is necessary to use auxiliary mechanisms such as fixed brackets to effectively fix the position of the industrial camera. In an exemplary embodiment, the image acquisition frequency of the industrial camera is one frame every 30 seconds, and each frame of sewage image of the sewage in the UV-ozone linkage treatment area is obtained by presetting the acquisition frequency. This embodiment can also perform image preprocessing such as denoising on each frame of sewage image collected.

[0055] The image processing module obtains each frame of sewage image collected by the industrial camera and performs image processing. The image processing process is as follows: Figure 2 As shown, each processing step of the image processing module is described in detail below.

[0056] Step 1: Identify particles and flocs in sewage images.

[0057] Through several previous pretreatment processes, the turbidity of the sewage injected into the UV-ozone linkage treatment area (i.e., the turbidity of the water body) will be significantly reduced, but it still contains a small amount of colloids, fine suspended matter, and dissolved organic matter. These pollutants are further reduced by ultraviolet irradiation and ozone injection. If the power of the UV equipment and the ozone injection amount are set based on experience, the sewage treatment effect may be affected. Therefore, based on the changes in the sewage state in the UV-ozone linkage treatment area, the power of the UV equipment and the ozone injection amount are dynamically adjusted to achieve a higher standard of sewage treatment effect.

[0058] Under the influence of ultraviolet light, ozone molecules generate highly reactive oxygen atoms and hydroxyl radicals. These substances disrupt the surface charge of colloids in the water, causing colloids, suspended matter, and organic matter to flocculate and precipitate. Furthermore, due to the oxidative breakdown of chromogenic groups in the water by ozone, the color of the wastewater is significantly reduced. To ensure higher-quality wastewater treatment results and prevent secondary pollution, changes in UV power and ozone injection must be based on real-time changes in wastewater turbidity. Water turbidity is often reflected in the presence of solid particles and the color of the water. Under the combined action of UV and ozone, tiny particles in the water gradually flocculate and precipitate. During the wastewater treatment process, particulate matter and flocculants coexist for a period of time, and both have a certain impact on the determination of water turbidity. Therefore, it is necessary to first identify particulate matter and flocculants in the wastewater image. It should be understood that each frame of the wastewater image is a grayscale image after grayscale processing.

[0059] The following description takes an arbitrary sewage image as an example and sets it as the target sewage image. In the target sewage image, there is generally a significant difference between the grayscale values ​​of the particles and flocs in the sewage and the grayscale value of the sewage water itself. Moreover, there is a significant difference between the particles and flocs in terms of shape and area. Therefore, based on the differences in grayscale value, shape, and area, the particles and flocs in the target sewage image are identified. In an exemplary embodiment, Figure 3 As shown, a specific identification process of particles and flocs is given as follows:

[0060] Step 1-1: Segment the sewage image to obtain multiple target areas.

[0061] The target sewage image is segmented using threshold segmentation into a background region (sewage region) and a substance-existing region (the substance-existing region includes particulate matter and flocculants, i.e., the substance-existing region is the target region). In an exemplary embodiment, each connected domain in the target sewage image is determined. For example, the target sewage image is binarized to obtain a binary image (distinguishing between background and foreground regions, with the foreground region being the substance-existing region). The connectivity of each pixel is then determined based on an 8-neighborhood to obtain each connected domain. Since the grayscale value of sewage is quite different from the grayscale value of particulate matter and flocculants, the connected domains of the background area can be screened out by the grayscale value. Specifically: the average grayscale value of each connected domain is obtained, and then compared with the preset sewage standard grayscale value. The connected domain whose error with the preset sewage standard grayscale value is within the preset range is determined as the background area, and the background area is screened out. The areas corresponding to the retained connected domains are the areas of particulate matter or flocculants; or, under normal circumstances, the area of ​​the sewage itself accounts for a larger proportion in the area of ​​the target sewage image, and the area of ​​particulate matter and flocculants accounts for a smaller proportion in the area of ​​the target sewage image. In this case, the area ratio of each connected domain can be obtained, and the connected domain with an area ratio greater than the preset ratio can be determined as the background area.

[0062] After the background area is screened out, the corresponding areas of the remaining connected domains in the target sewage image are set as target areas, thereby obtaining multiple target areas.

[0063] Step 1-2: Determine the shape and area representation of each target area based on the area and shape of each target area.

[0064] Flocs are formed by the aggregation of particles, and are quite different from particles in terms of shape, area, etc. Therefore, the shape and area of ​​each target area are determined based on the area and shape of each target area. In an exemplary embodiment, Figure 4 As shown, a specific process of obtaining the shape area expression is given below:

[0065] Step 1-2-1: Based on the isoperimetric inequality, determine the circularity of the target area according to the area and perimeter of the target area.

[0066] Let's take any target area as an example. The isoperimetric inequality, also known as the isoperimetric theorem, states that among closed geometric shapes with equal perimeter lengths, the circle has the largest area. Another way to put it is that among geometric shapes with equal areas, the circle has the smallest perimeter length. Hurwitz proposed that the relationship between the perimeter length of a closed curve and the area enclosed by the curve can be expressed as an inequality, which is called the isoperimetric inequality.

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

[0068]

[0069] Among them, Cir t,k represents the circularity of the kth target area in the tth moment, i.e., the tth frame sewage image, S t,k represents the area of ​​the kth target region in the tth frame sewage image (i.e., the number of pixels contained in the target region); C t,k represents the perimeter of the kth target area in the tth frame sewage image, that is, the number of edge pixels on the edge of the kth target area, and π represents pi.

[0070] The above formula mainly uses the relationship between area and perimeter to analyze the circularity of the target area. According to the area formula of a circle s=πr 2 It can be seen that when Cir t,k The closer the calculated result is to 1, the closer the shape of the kth target area in the tth frame sewage image is to a circle. Since flocs are formed by the aggregation of particles, the shape of flocs is usually irregular. Therefore, the circularity of particles should be greater than that of flocs.

[0071] Step 1-2-2: Obtain the shape and area representation of the target area based on the area, circularity, and elongation of the target area.

[0072] Determine the elongation of the target area. The elongation characterizes the extent to which the length of the target area exceeds the width. The greater the length of the target area is than the width, the greater the elongation. In an exemplary embodiment, determine the center point of the target area, obtain straight lines in various directions passing through the center point, obtain the number of pixels on the line segments of the straight lines in various directions in the target area, and thus determine the line segment with the largest number of pixels, which is defined as the long axis of the target area. Then make a perpendicular line to the straight line corresponding to the long axis through the center point of the target area, obtain the line segment of the perpendicular line in the target area, define it as the short axis of the target area, and obtain the number of pixels on the short axis. Calculate the ratio of the number of pixels on the long axis to the number of pixels on the short axis, and this ratio is the elongation of the target area. Therefore, the numerical range of the elongation is greater than 1.

[0073] According to the area, circularity and elongation of the target area, the shape and area performance of the target area is obtained. The shape and area performance characterizes the possibility that the current area belongs to particulate matter. From the above analysis, it can be seen that compared with flocs, the area of ​​particulate matter is smaller, and the circularity of particulate matter is larger and the elongation is smaller. Moreover, since flocs are generated by the aggregation of particulate matter, the aggregation process is random, so the flocs show the characteristics of poor circularity, large area and large elongation in the shape-area direction. Therefore, the shape and area performance of the target area is inversely proportional to the area and elongation of the target area, and is directly proportional to the circularity. In an exemplary embodiment, a quantitative method of shape and area performance is given as follows:

[0074]

[0075] Among them, SA t,k represents the shape and area of ​​the kth target area in the tth frame sewage image, τ t,K Indicates the area ratio of the kth target area in the tth frame sewage image. The area ratio is the ratio of the number of pixels in the kth target area to the total number of pixels in the tth frame sewage image. minL t,k Indicates the number of pixels on the short axis of the kth target area in the tth frame sewage image, maxL t,k represents the number of pixels on the long axis of the kth target area in the tth frame sewage image, It is essentially the reciprocal of elongation.

[0076] Step 1-3: Divide each target area into particles and flocs according to its shape and area.

[0077] Through steps 1 and 2, the shape and area representation of each target region in the sewage image of frame t is obtained. The larger the shape and area representation, the more likely the target region is particulate matter. Therefore, based on the shape and area representation of each target region, each target region is classified as particulate matter or flocculent matter. In an exemplary embodiment, a shape and area representation threshold is preset. The value of this shape and area representation threshold ranges from 0 to 1, and the specific value is set based on the judgment needs, such as 0.5.

[0078] The shape and area expressions of each target area are compared with the shape and area expression threshold, and the target area corresponding to the shape and area expression greater than or equal to the shape and area expression threshold is determined as the particle matter area, that is, identified as the particle matter; the target area corresponding to the shape and area expression less than the shape and area expression threshold is determined as the flocculent area, that is, identified as the flocculent.

[0079] It should be understood that in industrial wastewater treatment, there are usually many difficult-to-degrade organic matter, suspended matter, etc., so there are usually both particulate matter and flocs in the sewage image, and flocs are formed by the aggregation of particulate matter. Accordingly, the present invention is applicable to scenarios where both particulate matter and flocs exist in the sewage image, and subsequent data processing is performed based on the distribution of particulate matter and flocs. The present invention is not applicable to scenarios where only particulate matter or flocs exist in the sewage image, or where neither particulate matter nor flocs exist. If only particulate matter or flocs are identified after the sewage image is identified, or neither particulate matter nor flocs are identified, the subsequent image processing process will no longer be executed, and the present invention will stop executing.

[0080] Step 2: Determine the water turbidity of the sewage image based on the distribution of particulate matter and flocculants in the sewage image.

[0081] With the combined action of ultraviolet light and ozone, some particles in the sewage will be decomposed and then flocculated and precipitated under the action of ozone, resulting in a gradual decrease in particles and an increase in flocculants in the sewage. Therefore, the turbidity of the sewage image is determined based on the distribution of particles and flocculants in the sewage image. In an exemplary embodiment, Figure 5 As shown, a specific process for obtaining water turbidity is given as follows:

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

[0083] After obtaining the individual particle and floc regions in the sewage image, each particle region is considered a particle, and each floc region is considered a floc, thereby obtaining the number of particles and flocs in the sewage image. The sum of the number of pixels in all particle regions is then calculated, and the ratio of this sum to the total number of pixels in the sewage image is used as the particle area ratio. The sum of the number of pixels in all floc regions is then calculated, and the ratio of this sum to the total number of pixels in the sewage image is used as the floc area ratio.

[0084] Since the number of particles and the area ratio of particles in the sewage image can reflect the distribution characteristics of particles in the sewage image, the particle distribution characteristics are obtained based on the number of particles and the area ratio of particles. In an exemplary embodiment, the particle distribution characteristics are the product of the number of particles and the area ratio of particles.

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

[0086] Since the number of flocs and the proportion of the floc area in the sewage image can reflect the floc distribution characteristics in the sewage image, the floc distribution characteristics are obtained based on the number of flocs and the proportion of the floc area. In an exemplary embodiment, the floc distribution characteristics are the product of the number of flocs and the proportion of the floc area.

[0087] Step 2-3: The turbidity of the water body is obtained by fusing the particle distribution characteristics, floc distribution characteristics and the overall grayscale value of the sewage area in the sewage image.

[0088] The particle distribution characteristics and floc distribution characteristics jointly represent the density of particulate matter. The larger the particle distribution characteristics and the smaller the floc distribution characteristics, the greater the particle density, the more turbid the sewage, and the greater the turbidity of the water. At the same time, the darker the grayscale color of the sewage (i.e., the smaller the grayscale value), the more turbid the water is and the greater the turbidity.

[0089] With the combined effect of ultraviolet light and ozone, the turbidity of sewage water should maintain a continuous downward trend, that is, the grayscale value of the sewage area in the sewage image will become larger and larger, and there will be more and more flocs and fewer and fewer particulate matter, that is, the distribution characteristics of particulate matter will gradually weaken, and the distribution characteristics of flocs will gradually become stronger.

[0090] Obtain the grayscale value of the sewage area in the sewage image. In an exemplary embodiment, the sewage area is the background area mentioned above. Then, obtain the average grayscale value of each pixel point in the background area in the sewage image as the overall grayscale value of the sewage area.

[0091] The particle distribution characteristics of the sewage image, the floc distribution characteristics, and the overall grayscale value of the sewage area are integrated to obtain the water turbidity of the sewage image. The water turbidity is proportional to the particle distribution characteristics and inversely proportional to the floc distribution characteristics and the overall grayscale value of the sewage area. In an exemplary embodiment, a specific method for quantifying water turbidity is provided as follows:

[0092]

[0093] Among them, WG t N represents the turbidity of the sewage image in frame t; t,KL represents the number of particles in the sewage image of the tth frame, τ t,KL N represents the area ratio of particles in the sewage image of the tth frame. t,KL ×τ t,KL represents the particle distribution characteristics of the t-th frame sewage image; N t,XN represents the number of flocculants in the t-th frame sewage image, τ t,XN Indicates the proportion of flocculent area in the t-th frame sewage image, N t,XN ×τ t,XNrepresents the flocculent distribution characteristics of the sewage image in the tth frame; norm represents the 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 the natural constant e as the base. t represents the overall grayscale value of the sewage area in the t-th frame sewage image, Indicates the negative correlation normalization of the overall gray value.

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

[0095] Step 2 obtains the water turbidity for each frame of the sewage image. Under the combined effects of UV and ozone, water turbidity gradually decreases. When water turbidity is high, the high transmittance of strong UV light can effectively penetrate the suspended solids layer, ensuring the continuous generation of free radicals. However, when water turbidity is low, strong UV light is not required. The ozone injection rate is analyzed in the same way.

[0096] As sewage treatment proceeds, the turbidity of the water body is constantly changing. Therefore, based on the changes in the turbidity of several consecutive frames of sewage images, the turbidity change performance of each frame of sewage image is determined, which is used to regulate the power of the 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 changes, it will have a certain impact 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. Figure 6 As shown, a specific process for obtaining the turbidity change performance is given below:

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

[0098] Reference sewage images for the target sewage image are determined based on the target sewage image, where each reference sewage image is a plurality of preceding sewage images adjacent to the target sewage image. In one exemplary embodiment, the number of reference sewage images for the target sewage image is three, namely, the preceding three sewage images adjacent to the target sewage image. For example, if the target sewage image is the sixth sewage image, the reference sewage images for the target sewage image are the third, fourth, and fifth sewage images, respectively.

[0099] Determine the water turbidity difference between the target sewage image and each adjacent two frames of sewage images in each reference sewage image. Specifically: for the t-th frame sewage image, its reference sewage images are the t-1th frame sewage image, the t-2th frame sewage image, and the t-3th frame sewage image. Calculate the water turbidity difference between the t-2th frame sewage image and the t-3th frame sewage image. The water turbidity difference is specifically the absolute value of the difference in water turbidity, and obtain the water turbidity difference corresponding to the t-3th frame sewage image; calculate the water turbidity difference between the t-1th frame sewage image and the t-2th frame sewage image, and obtain the water turbidity difference corresponding to the t-2th frame sewage image; calculate the water turbidity difference between the t-th frame sewage image and the t-1th frame sewage image, and obtain the water turbidity difference corresponding to the t-1th frame 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, determine the influence weight of each reference sewage image on the target sewage image.

[0101] Different reference sewage images have different importance to the target sewage image. The closer the reference sewage image is 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 is in analyzing the turbidity change 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. The closer the reference sewage image is to the target sewage image, the higher its influence weight. It should be understood that, under the premise that the closer the reference sewage image is to the target sewage image, the higher its influence weight, the influence weight of each reference sewage image on the target sewage image is set artificially, and the sum of the influence weights of each reference sewage image on the target sewage image is 1. For example, the influence weight of the sewage image in the t-1 frame is the highest, which is 0.5, the influence weight of the sewage image in the t-2 frame is second, which is 0.3, and the influence weight of the sewage image in the t-3 frame is the lowest, which is 0.2.

[0102] Step 3-3: Based on the influence weights of the reference sewage images, perform weighted summation on the water turbidity differences corresponding to the reference sewage images to obtain the turbidity change representation of the target sewage image.

[0103] The quantitative formula for the turbidity change 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-1×α t-1 ;

[0105] Among them, WP t Indicates the turbidity change of the sewage image in frame t, ΔWG t-3 Indicates the water turbidity difference corresponding to the sewage image in the t-3th frame, ΔWG t-2 Indicates the water turbidity difference corresponding to the sewage image in frame t-2, ΔWG t-1 represents the water turbidity difference corresponding to the sewage image in frame t-1; α t-3 represents the influence weight of the sewage image in the t-3th frame, α t-2 represents the influence weight of the sewage image in frame t-2, a t-1 Represents the influence weight of the sewage image in frame t-1.

[0106] It should be understood that for the first several frames of sewage images in the time sequence, for example, the first three frames of sewage images in the time sequence, since there are not enough sewage images before them (that is, there are not enough reference sewage images), the turbidity change performance of the first several frames of sewage images in the time sequence will no longer be obtained, that is, the ultraviolet equipment power and ozone injection amount of the first several frames of sewage images in the time sequence will not be adjusted, and they will be controlled according to the pre-set ultraviolet equipment power and ozone injection amount.

[0107] Step 4: Output the adjustment method corresponding to each frame of sewage image according to the turbidity change performance of each frame of sewage image and the turbidity of the water body.

[0108] It is not rigorous to adjust the UV device power and ozone injection amount based solely on the turbidity change of the target sewage image. A comprehensive analysis based on the turbidity of the target sewage image is also required. Therefore, based on the turbidity change of the target sewage image and the turbidity of the water body, an adjustment method corresponding to the target sewage image is output. The adjustment method is used to indicate the adjustment of the UV device power and ozone injection amount. In an exemplary embodiment, Figure 7 As shown, a specific acquisition process of the adjustment method is given as follows:

[0109] Step 4-1: Determine the degree of difference between the water turbidity and the turbidity change expression of the target sewage image, and obtain the adjustment direction of the target frame sewage image.

[0110] For the target sewage image, if its turbidity changes significantly, that is, the water turbidity changes rapidly, and its water turbidity is small, it means that the sewage treatment effect at the time corresponding to the target sewage image is good, and a large UV device power and ozone injection amount are not required. In other words, the UV device power and ozone injection amount need to be appropriately reduced to avoid excessive sewage treatment. On the contrary, if its turbidity changes slightly, that is, the water turbidity changes slowly, and its water turbidity is large, it means that the sewage treatment effect at the time corresponding to the target sewage image is poor, and the turbidity of the water body is still high, then a large UV device power and ozone injection amount are required. In other words, the UV device power and ozone injection amount need to be appropriately increased to improve the sewage treatment effect.

[0111] The greater the difference between the water turbidity and turbidity change of the target sewage image, the greater the control range will be, whether reducing the power of the ultraviolet equipment and the ozone injection amount or increasing the power of the ultraviolet equipment and the ozone injection amount.

[0112] In an exemplary embodiment, the difference between the water turbidity of the target sewage image and the turbidity change performance is calculated. The larger the difference, that is, the more the water turbidity exceeds the turbidity change performance, that is, the water turbidity changes slowly, and its water turbidity is large, indicating that the sewage treatment effect at the corresponding moment of the target sewage image is poor, and the turbidity of the water body is still high. In principle, the numerical range of the difference is (-1, 1). The degree of difference is determined based on the difference, and the degree of difference is proportional to the difference. In an exemplary embodiment, the difference is normalized, and the normalized result is used as the degree of difference. Among them, the normalization method can be: the difference is added to the value 1 and then divided by 2.

[0113] The adjustment direction is determined based on the degree of difference. The adjustment direction is either increasing or decreasing, i.e., increasing the power of the ultraviolet device and the amount of ozone injected, or decreasing the power of the ultraviolet device and the amount of ozone injected. A numerical value is preset, which serves as a dividing point between the degree of difference. The adjustment direction is determined based on the relationship between the degree of difference and the preset value. If the degree of difference is greater than or equal to the preset value, the degree of difference is large, and the adjustment direction is increasing. If the degree of difference is less than the preset value, the degree of difference is small, and the adjustment direction is decreasing. In principle, the numerical range of the preset value is (0, 1), and the specific numerical value is obtained according to actual needs. Alternatively, a large number of historical sewage treatment processes are obtained, and the time when the ultraviolet device power and the ozone injection amount are increased or decreased during each treatment process are determined. The specific numerical value of the preset value is determined based on the numerical relationship between the turbidity of the sewage water body and the turbidity change performance during the increase or decrease. In this embodiment, 0.5 is used as an example.

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

[0115] The degree of adjustment of the target sewage image is determined based on the degree of difference of the target sewage image, the turbidity variation, and the water turbidity. Specifically, the absolute difference between the degree of difference of the target sewage image and a preset value is calculated, which is defined as the turbidity weight. The product of the water turbidity of the target sewage image and the turbidity weight is calculated. Finally, this product is added to the turbidity variation of the target sewage image. The resulting sum determines the degree of adjustment of the target sewage image.

[0116] Q t =norm(WP t +A t ×WG t );

[0117] Among them, Q t Indicates the adjustment degree of the sewage image in frame t, A t Represents the turbidity weight of the sewage image at frame t.

[0118] According to the adjustment direction and adjustment degree of the sewage image of the tth frame, the adjustment coefficient γ of the sewage image of the tth frame is obtained. t Among them, if the adjustment direction is increasing, 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, adjust the original ultraviolet device power and the original ozone injection amount at the corresponding moment of the target sewage image.

[0120] The original ultraviolet device power and the original ozone injection amount at the time corresponding to the target sewage image are obtained. The original ultraviolet device power and the original ozone injection amount are the ultraviolet device power and the ozone injection amount determined before the time corresponding to the target sewage image.

[0121] Add the value 1 to the adjustment coefficient of the target sewage image, and multiply it by the original UV device power and original ozone injection amount at the corresponding moment of the target sewage image to obtain the adjusted UV device power and ozone injection amount. A quantification method is given below:

[0122]

[0123] in, represents the adjusted UV device power at the corresponding moment of the t-th frame sewage image, P t represents the original UV device power at the corresponding moment of the t-th frame sewage image, represents the adjusted ozone injection amount at the corresponding moment of the t-th frame sewage image, It represents the original ozone injection amount at the corresponding moment of the t-th frame sewage image.

[0124] Based on the adjusted UV device power and ozone injection rate at the corresponding moment of the t-th frame of sewage image, the UV device is controlled to operate at the adjusted UV device power, and the ozone generator is controlled to operate at the adjusted ozone injection rate. It should be understood that if the adjusted UV device power is greater than the maximum allowable power of the UV device, the UV device is controlled to operate at its maximum allowable power, and if the adjusted ozone injection rate is greater than the maximum allowable ozone injection rate, ozone is injected at the maximum allowable ozone injection rate.

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

[0126] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0127] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. An intelligent sewage treatment control device based on ultraviolet-ozone linkage, characterized in that: include: An image acquisition module is used to obtain each frame of sewage image in the ultraviolet-ozone linkage treatment area; An image processing module, configured to identify particles and flocculants in the sewage image; determining the water turbidity of the sewage image based on the distribution of particulate matter and flocculants in the sewage image; According to the change of water turbidity of a number of consecutive frames of sewage images, the turbidity change performance of each frame of sewage image is determined; According to the turbidity change performance of each frame of sewage image and the turbidity of the water body, the adjustment method corresponding to each frame of sewage image is output, and the adjustment method is used to indicate the adjustment of the ultraviolet device power and the ozone injection amount.

2. The intelligent sewage treatment control device based on ultraviolet-ozone linkage according to claim 1 is characterized in that: The process of identifying particles and flocs includes: performing image segmentation on the sewage image to obtain multiple target areas; Determine the shape and area representation of each target area according to the area and shape of each target area; According to the shape and area of ​​each target area, each target area is divided into particles and flocs.

3. The intelligent sewage treatment control device based on ultraviolet-ozone linkage according to claim 2 is characterized in that: The process of obtaining the shape and area representation includes: Based on the isoperimetric inequality, the circularity of the target area is determined according to the area and perimeter of the target area; the circularity represents the degree to which the shape of the target area is close to a circle; The shape and area representation of the target area is obtained based on the area, the circularity, and the elongation of the target area; the elongation represents the extent to which the length of the target area exceeds the width.

4. The intelligent sewage treatment control device based on ultraviolet-ozone linkage according to claim 1 is characterized in that: The process of obtaining the water turbidity includes: Determining the number of particles and the area ratio of the particles in the sewage image to obtain a distribution characteristic of the particles; Determining the number of flocs and the area ratio of the flocs in the sewage image to obtain floc distribution characteristics; The water turbidity is obtained by fusing the particle distribution characteristics, the floc distribution characteristics and the overall grayscale value of the sewage area in the sewage image; the water turbidity is proportional to the particle distribution characteristics and inversely proportional to the floc distribution characteristics and the overall grayscale value.

5. The intelligent sewage treatment control device based on ultraviolet-ozone linkage according to claim 4 is characterized in that: The particle distribution characteristic is the product of the number of particles and the area ratio of the particles; the floc distribution characteristic is the product of the number of flocs and the area ratio of the flocs.

6. The intelligent sewage treatment control device based on ultraviolet-ozone linkage according to claim 1 is characterized in that: The process of obtaining the turbidity change performance includes: Determine the water turbidity difference between each two adjacent frames of sewage images in the target sewage image and each reference sewage image; the target sewage image is any frame of sewage image, and each reference sewage image is a plurality of previous frames of sewage image adjacent to the target sewage image; determining, based on a time interval between the target sewage image and each reference sewage image, an influence weight of each reference sewage image on the target sewage image; wherein the influence weight is inversely proportional to the time interval; Based on the influence weight of each reference sewage image, the water turbidity differences corresponding to each reference sewage image are weightedly summed to obtain the turbidity change representation of the target sewage image.

7. The intelligent sewage treatment control device based on ultraviolet-ozone linkage according to claim 1 is characterized in that: The process of obtaining the adjustment method includes: Determine the degree of difference between the water turbidity and the turbidity change performance of the target sewage image, and obtain the adjustment direction of the target frame sewage image, wherein the adjustment direction is increase or decrease; the target sewage image is any frame sewage image; Obtaining an adjustment coefficient according to an adjustment direction and adjustment degree of the target sewage image; the adjustment degree is obtained from the difference degree, turbidity change performance and water turbidity; According to the adjustment coefficient, the original ultraviolet device power and the original ozone injection amount at the corresponding moment of the target sewage image are adjusted.

8. The intelligent sewage treatment control device based on ultraviolet-ozone linkage according to claim 7 is characterized in that: The process of obtaining the degree of difference includes: calculating the difference between the turbidity of the target sewage image and the turbidity change performance, and determining the degree of difference according to the difference, wherein the degree of difference is proportional to the difference; The process of acquiring 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.

9. The intelligent sewage treatment control device based on ultraviolet-ozone linkage according to claim 8 is characterized in that: The process of obtaining the adjustment degree includes: calculating the product of the water turbidity of the target sewage image and the turbidity weight, adding the product to the turbidity change performance of the target sewage image, and determining the adjustment degree of the target sewage image based on the obtained sum; the turbidity weight is the absolute value of the difference between the difference degree and the preset value.

10. The intelligent sewage treatment control device based on ultraviolet-ozone linkage according to any one of claims 7 to 9, characterized in that: The adjusting of the original ultraviolet device power and the original ozone injection amount at the time corresponding to the target sewage image according to the adjustment coefficient includes: adding a value 1 to the adjustment coefficient, and multiplying the values ​​by the original ultraviolet device power and the original ozone injection amount at the time corresponding to the target sewage image, respectively, to obtain the adjusted ultraviolet device power and ozone injection amount.

Images