Filter system for improving denitrification efficiency of denitrification filter based on carbon and bacterium regulation and control

Abstract

The embodiment of the invention provides a filter system for improving the denitrification efficiency of a denitrification filter based on carbon and bacterium regulation and control. The filter system can solve the technical problem of low denitrification efficiency of the denitrification filter. The system comprises a water inlet and outlet structure, a filtering structure, an intelligent carbon bacterium adding structure and a monitoring structure, the water inlet and outlet structure is used for inputting to-be-treated sewage into the filtering structure; the filter structure comprises a filter tank and is used for carrying out denitrification treatment on to-be-treated sewage; the carbon bacterium intelligent adding structure comprises a carbon bacterium regulation and control unit, a carbon bacterium conveying pump, a carbon bacterium incubator, a sixth valve and a carbon bacterium conveying pipe which are connected in sequence; the carbon bacterium regulation and control unit is electrically connected with the carbon bacterium conveying pump, so that under the condition that the sixth valve is opened, the carbon bacterium regulation and control unit controls the carbon bacterium conveying pump to feed bacteria and carbon in the carbon bacterium incubator into the filter tank through a carbon bacterium conveying pipe with uniformly distributed carbon bacterium spraying holes according to the optimal carbon bacterium feeding amount. Therefore, the denitrification efficiency of the denitrification filter tank is improved through accurate feeding of the optimal carbon bacterium feeding amount and upgrading of the structure of the conveying pipe.

Description

Technical Field

[0001] The present application relates to the technical field of sewage treatment, and in particular to a filtration system for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation. Background Art

[0002] The goal of wastewater treatment is to remove pollutants and protect the aquatic environment. Denitrification is a crucial step in wastewater treatment. Filters can serve as efficient filtration devices for wastewater denitrification. To enhance denitrification efficiency, mixed bacterial communities can be cultivated within the filter. For example, under mixed trophic conditions, complex, non-specific interaction networks can form between autotrophic and heterotrophic bacterial communities, fostering the formation of a stable biological system with efficient denitrification.

[0003] Currently, denitrifying bacteria can be co-cultured in the filter, forming a sulfur-based co-culture denitrification system. This system includes heterotrophic and autotrophic denitrifiers. Compared to heterotrophic denitrifiers, autotrophic denitrifiers have a slower growth rate and longer startup time. Consequently, the proportion of heterotrophic denitrifiers in the population and their contribution to denitrification initially increase and then decrease, increasing with increasing influent nitrogen concentration and carbon-nitrogen ratio (C / N). When heterotrophic denitrifiers replace autotrophic denitrifiers to become the dominant bacterial population, the coupled bacterial population significantly shortens the lag phase of denitrifiers in a separate nutrient system, thereby enhancing denitrification efficiency. To improve denitrification efficiency, an appropriate carbon source is generally added to the water inlet of the denitrifying biological filter. This allows the carbon-water mixture to fully contact the filter surface air, fostering the growth of aerobic microbial communities. The carbon source required for autotrophic denitrification in the anaerobic zone is prematurely consumed by the aerobic microbial communities.

[0004] However, actual wastewater treatment conditions are often complex. Wastewater may contain substances that promote denitrification, such as easily degradable organic matter. It may also contain substances that inhibit denitrification, such as heavy metal ions or high concentrations of inhibitory compounds. Relying on a single theoretical formula for these two distinct scenarios cannot accurately predict carbon source requirements, potentially leading to insufficient or excessive carbon source input, thus reducing denitrification efficiency. Summary of the Invention

[0005] The embodiments of the present application provide a filtration system for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation, which can solve the technical problem of low denitrification efficiency of a denitrification filter.

[0006] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions: In the first aspect, the embodiment of the present application provides a filtration system for improving the denitrification efficiency of a denitrification filter based on carbon and bacteria regulation. The filtration system for improving the denitrification efficiency of a denitrification filter based on carbon and bacteria regulation includes: an inlet and outlet water structure, a filtration structure, a carbon bacteria intelligent dosing structure and a monitoring structure; the inlet and outlet water structure includes a sewage inlet pipe; one end of the sewage inlet pipe is connected to the filtration structure for inputting the sewage to be treated into the filtration structure; the filtration structure is used to denitrify the sewage to be treated; the filtration structure includes a filter tank; the carbon bacteria intelligent dosing structure includes a carbon bacteria regulation unit, a carbon bacteria delivery pump, a carbon bacteria incubator, a sixth valve, a carbon bacteria delivery pipe; the carbon bacteria incubator, the carbon bacteria delivery pump, the sixth valve , and the carbon bacteria delivery pipe are connected in sequence, and the carbon bacteria control unit and the carbon bacteria delivery pump are electrically connected, so that when the sixth valve is opened, the carbon bacteria control unit controls the carbon bacteria delivery pump according to the optimal carbon bacteria dosage to deliver the bacteria and carbon in the carbon bacteria incubator into the filter tank through the carbon bacteria delivery pipe provided with uniformly distributed carbon bacteria spray holes; the carbon bacteria delivery pipe includes a first pipe section extending in a direction away from the ground; the first pipe section is provided with carbon bacteria spray holes; a plurality of carbon bacteria spray holes are arranged at intervals in a direction away from the ground; the first pipe section is arranged in the filter tank; the end of the first pipe section away from the ground receives the bacteria and carbon input by the carbon bacteria delivery pump; wherein, under the first preset condition, the monitoring structure is configured to obtain the first monitoring The first monitoring data includes chemical oxygen demand of influent, ammonia nitrogen content, nitrate nitrogen content, nitrite nitrogen content, first total phosphorus content, first suspended solids content, first pH, dissolved oxygen content, temperature and first redox potential; the first monitoring data is sequentially cleaned, integrated, reduced and transformed to obtain influent monitoring data; the influent monitoring data is input into the dosage prediction model to obtain dosage prediction; the dosage prediction includes external carbon source dosage prediction and autotrophic denitrifying bacteria dosage prediction; the external carbon source dosage prediction and autotrophic denitrifying bacteria dosage prediction are feedforward controlled; in the case of the second preset condition, the monitoring structure is also configured The method is configured to obtain second monitoring data; the second monitoring data includes effluent chemical oxygen demand, total nitrogen content, second total phosphorus content, second suspended solids content, second pH value and second redox potential; the second monitoring data is sequentially subjected to data cleaning, data integration, data reduction and data transformation to obtain effluent monitoring data; the effluent monitoring data is input into an adjustment prediction model to obtain an adjusted predicted amount; the adjusted predicted amount includes an adjusted predicted amount for addition of an external carbon source and an adjusted predicted amount for addition of autotrophic denitrifying bacteria; feedback control is performed on the adjusted predicted amount for addition of an external carbon source and the adjusted predicted amount for addition of autotrophic denitrifying bacteria; the predicted amount for addition is adjusted according to the adjusted predicted amount to obtain an optimal carbon bacteria addition amount.

[0007] In this way, by setting up a carbon bacteria intelligent addition structure, in conjunction with the optimal carbon bacteria addition amount obtained based on the deep learning model, the carbon bacteria delivery pump is controlled according to the optimal carbon bacteria addition amount to deliver the bacteria and carbon in the carbon bacteria culture box through a carbon bacteria delivery pipe provided with evenly distributed carbon bacteria spray holes into the filter. In this way, the denitrification efficiency of the denitrification filter is significantly improved, the breadth and depth of the engineering application of the pyrite denitrification denitrification process are expanded, the consumption of carbon sources is significantly reduced, operating costs are saved, and higher economic and technical benefits are obtained. For example, after the backwash process of the biological filter is completed, a low-dose carbon source, denitrifying bacteria and combined nutrients are delivered to the anaerobic area through the intelligent dosing system, which effectively solves the problems of slow growth rate and long startup time of sulfur-based autotrophic denitrifying bacteria, and then improves the denitrification efficiency of the denitrification filter by realizing intelligent regulation of the addition ratio of carbon, bacteria and combined nutrients.

[0008] Furthermore, the hydraulic retention time within the pyrite filter layer is significantly reduced from 6-8 hours to 15-30 minutes, increasing the treatment capacity by 7-10 times compared to previously disclosed systems or devices. This application expands the breadth and depth of engineering applications for pyrite denitrification, significantly reduces carbon source consumption, saves operating costs, and achieves high economic and technical benefits.

[0009] Furthermore, by real-time monitoring of the inlet and outlet water quality data of the denitrification filter, the amount of carbon bacteria added is adjusted by a combination of feedforward and feedback based on a deep learning model, which improves the accuracy of the carbon bacteria addition and solves the problems of excessive energy consumption and drug consumption caused by adding carbon bacteria by manual experience or fixed coefficient addition method.

[0010] In a feasible implementation of the first aspect, the carbon bacteria transport pipe also includes a first annular pipe segment, a second annular pipe segment and a first bent pipe; the first annular pipe segment is connected to the first ends of multiple first pipe segments; the first annular pipe segment is connected to the carbon bacteria transport pump through the first bent pipe; the second annular pipe segment is connected to the second ends of multiple first pipe segments close to the ground; wherein the first annular pipe segment and the second annular pipe segment are both rectangular; the number of multiple first pipe segments is four, and they are respectively located at the vertices of the rectangle.

[0011] In a feasible implementation of the first aspect, the filtration system for improving the denitrification efficiency of the denitrification filter based on carbon and bacteria regulation further includes: a backwash structure and a backwash structure; the backwash structure includes a backwash air compressor, an air delivery pipe, a backwash pump, a fourth valve and a fifth valve; the fourth valve is connected to the backwash pump and is used to turn the backwash pump on or off; the fifth valve is connected to the air delivery pipe and is used to turn the air delivery pipe on or off; the backwash air compressor, the air delivery pipe and the filter are connected in sequence; the backwash structure includes a carbon and bacteria backwash pipe and a seventh valve; The water inlet and outlet structure also includes an outlet pipe, a clean water tank, a second valve and a third valve; the air-water chamber of the filter tank, the second valve, the third valve, the clean water tank and the outlet pipe are connected in sequence; the carbon bacteria backwash pipe is connected to the seventh valve and the outlet pipe; the third valve and the fourth valve are connected in parallel; when the second valve and the third valve are closed and the fourth valve and the fifth valve are opened, the backwash pump and the backwash air compressor are started; and when the seventh valve is opened regularly, the carbon bacteria backwash pipe is combined with the air delivery pipe to realize air-water flushing and cleaning of the filter structure.

[0012] In a feasible implementation of the first aspect, the filtration structure further includes a pyrite filler and a pebble supporting layer; the pyrite filler is arranged on the pebble supporting layer; and both the pyrite filler and the pebble supporting layer are located on the air-water chamber of the filter tank.

[0013] Through the intelligent dosing system, low-dose carbon source, denitrifying bacteria and combined nutrients are delivered to the anaerobic area to quickly expand the base of sulfur-based autotrophic denitrifying bacteria and accelerate the degradation of pyrite S. - Increase the electron release rate and reduce the consumption of carbon source.

[0014] In a feasible implementation of the first aspect, the carbon bacteria intelligent dosing structure also includes a scrubbing hole and an anti-falling cover, and the carbon bacteria delivery pipe also includes a second pipe section arranged on the first annular pipe section and connected to both the first annular pipe section and the first pipe section; the second pipe section extends in a direction away from the ground; a scrubbing hole and an anti-falling cover are provided at one end of the second pipe section away from the ground; the anti-falling cover is detachably arranged on the second pipe section and covers the scrubbing hole.

[0015] In the second aspect, the embodiment of the present application provides a filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacteria regulation. The filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacteria regulation includes: obtaining first monitoring data under a first preset condition; the first monitoring data includes influent chemical oxygen demand, ammonia nitrogen content, nitrate nitrogen content, nitrite nitrogen content, a first total phosphorus content, a first suspended solids content, a first pH, dissolved oxygen content, temperature and a first redox potential; performing data cleaning, data integration, data reduction and data transformation on the first monitoring data in sequence to obtain influent monitoring data; inputting the influent monitoring data into an addition amount prediction model to obtain an addition prediction amount; the addition prediction amount includes an external carbon source addition prediction amount and an autotrophic denitrifying bacteria addition prediction amount; performing feedforward control on the external carbon source addition prediction amount and the autotrophic denitrifying bacteria addition prediction amount; obtaining second monitoring data under a second preset condition; the second monitoring data includes effluent chemical oxygen demand, ammonia nitrogen content, nitrate nitrogen content, nitrite nitrogen content, a first total phosphorus content, a first suspended solids content, a first pH, a dissolved oxygen content, a temperature and a first redox potential; Oxygen demand, total nitrogen content, a second total phosphorus content, a second suspended solids content, a second pH value and a second redox potential; the second monitoring data is sequentially cleaned, integrated, reduced and transformed to obtain effluent monitoring data; the effluent monitoring data is input into an adjustment prediction model to obtain an adjusted predicted quantity; the adjusted predicted quantity includes an external carbon source addition adjustment predicted quantity and an autotrophic denitrifying bacteria addition adjustment predicted quantity; feedback control is performed on the external carbon source addition adjustment predicted quantity and the autotrophic denitrifying bacteria addition adjustment predicted quantity; according to the adjusted predicted quantity, the addition predicted quantity is adjusted to obtain an optimal carbon bacteria addition quantity, so that the filtration system for improving the denitrification efficiency of the denitrification filter based on carbon and bacteria regulation feeds carbon and bacteria into the filter according to the optimal carbon bacteria addition quantity through a carbon bacteria delivery pipe provided with evenly distributed carbon bacteria spray holes; wherein the carbon bacteria delivery pipe includes a first pipe section extending in a direction away from the ground; the first pipe section is provided with carbon bacteria spray holes; and a plurality of carbon bacteria spray holes are spaced apart in a direction away from the ground.

[0016] Based on the above description of the filtering method for improving the denitrification efficiency of the denitrification filter based on carbon and bacteria regulation provided in the embodiment of the present application, it can be known that the filtering method for improving the denitrification efficiency of the denitrification filter based on carbon and bacteria regulation includes, according to the optimal carbon bacteria dosage obtained based on the deep learning model, the bacteria and carbon in the carbon bacteria culture box are fed into the filter through a carbon bacteria delivery pipe provided with evenly distributed carbon bacteria spray holes. On the basis of precise delivery, the structure of the carbon bacteria delivery pipe is upgraded to quickly improve the nutritional environment for bacterial reproduction, thereby improving the denitrification efficiency of the denitrification filter. For example, after the backwash process of the biological filter is completed, a low-dose carbon source, denitrifying bacteria and combined nutrients are delivered to the anaerobic area through an intelligent dosing system, which effectively solves the problems of slow growth rate and long startup time of sulfur-based autotrophic denitrifying bacteria, and then improves the denitrification efficiency of the denitrification filter by realizing intelligent regulation of the addition ratio of carbon, bacteria and combined nutrients.

[0017] Furthermore, the hydraulic retention time within the pyrite filter layer is significantly reduced from 6-8 hours to 15-30 minutes, increasing the treatment capacity by 7-10 times compared to previously disclosed systems or devices. This application expands the breadth and depth of engineering applications for pyrite denitrification, significantly reduces carbon source consumption, saves operating costs, and achieves high economic and technical benefits.

[0018] Furthermore, by real-time monitoring of the inlet and outlet water quality data of the denitrification filter, the amount of carbon bacteria added is adjusted by a combination of feedforward and feedback based on a deep learning model, which improves the accuracy of the carbon bacteria addition and solves the problems of excessive energy consumption and drug consumption caused by adding carbon bacteria by manual experience or fixed coefficient addition method.

[0019] In a feasible implementation of the second aspect, the dosage prediction model is built based on a deep learning model, including a first input layer, a first intermediate hidden layer and a first output layer; wherein, the first input layer includes a fully connected layer for processing preprocessed water inlet monitoring data; the first intermediate hidden layer includes seven long short-term memory network layers; the long short-term memory network layer includes long short-term memory network neurons; the long short-term memory network neurons include a forgetting gate, an input gate and an output gate; the first output layer includes a regression layer; the regression layer uses the logistic function as the activation function.

[0020] In a feasible implementation method of the second aspect, the adjustment prediction model is built based on a deep learning model, and includes a second input layer, a second intermediate hidden layer and a second output layer; wherein, the second input layer includes a fully connected layer for processing the preprocessed water outlet monitoring data; the second intermediate hidden layer includes five long short-term memory network layers; the long short-term memory network layer includes long short-term memory network neurons; the long short-term memory network neurons include a forgetting gate, an input gate and an output gate; the second output layer includes a regression layer; the regression layer uses the logistic function as the activation function.

[0021] In a third aspect, an embodiment of the present application provides a filtration system for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation. The filtration system for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation includes: at least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method provided in the second aspect.

[0022] The filtration system for improving the denitrification efficiency of denitrification filters based on carbon and bacteria regulation implements the method provided in the second aspect, by providing an intelligent carbon bacteria dosing structure, in conjunction with the optimal carbon bacteria dosage obtained through a deep learning model, and controlling the carbon bacteria delivery pump according to the optimal carbon bacteria dosage to deliver bacteria and carbon from the carbon bacteria incubator into the filter through a carbon bacteria delivery pipe equipped with evenly distributed carbon bacteria spray holes. This significantly improves the denitrification efficiency of the denitrification filter, expands the breadth and depth of the application of pyrite denitrification process engineering, significantly reduces carbon source consumption, saves operating costs, and achieves high economic and technical benefits.

[0023] In a fourth aspect, an embodiment of the present application provides a computer-readable medium having computer program instructions stored thereon, and the computer program instructions can be executed by a processor to implement the method provided in the second aspect.

[0024] The computer program instructions in the computer-readable medium implement the method provided in the second aspect by providing an intelligent carbon bacteria dosing structure, in conjunction with an optimal carbon bacteria dosage determined based on a deep learning model. The carbon bacteria delivery pump is controlled based on the optimal carbon bacteria dosage to deliver bacteria and carbon from a carbon bacteria incubator to a filter tank via a carbon bacteria delivery pipe equipped with evenly distributed carbon bacteria spray holes. This significantly improves the denitrification efficiency of the denitrification filter, expands the breadth and depth of engineering applications for pyrite denitrification, significantly reduces carbon source consumption, saves operating costs, and achieves high economic and technical benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A schematic diagram of the structure of a filtration system for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation provided in an embodiment of the present application; Figure 2 A cross-sectional view of a carbon bacteria control structure and a filter tank in a filtration system for improving the denitrification efficiency of a denitrification filter tank based on carbon and bacteria control provided in an embodiment of the present application; Figure 3 A schematic diagram of a carbon bacteria control structure in a filtration system for improving the denitrification efficiency of a denitrification filter based on carbon and bacteria control provided in an embodiment of the present application; Figure 4 A system topology diagram of a filtration system for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation provided in an embodiment of the present application; Figure 5 A schematic diagram of a process for a filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation provided in an embodiment of the present application; Figure 6 A schematic diagram of a process for a filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation provided in an embodiment of the present application; Figure 7A schematic diagram of the process of intelligently adding carbon bacteria in a filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacteria regulation provided in an embodiment of the present application; Figure 8 A structural diagram of a carbon bacteria dosage prediction model for a filtration method for improving denitrification efficiency of a denitrification filter based on carbon and bacteria regulation provided in an embodiment of the present application; Figure 9 A structural diagram of a prediction model for adjusting the amount of carbon bacteria added in a filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacteria regulation provided in an embodiment of the present application; Figure 10 Schematic diagram of the change in nitrate nitrogen concentration in the filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation provided in the embodiments of the present application; Figure 11 Schematic diagram of the change in nitrite nitrogen concentration in the filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation provided in the embodiments of the present application; Figure 12 Schematic diagram of changes in ammonia nitrogen concentration in a filtration method for improving denitrification efficiency of a denitrification filter based on carbon and bacterial regulation provided in an embodiment of the present application; Figure 13 Schematic diagram of the change in total nitrogen concentration in the filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation provided in the embodiments of the present application; Figure 14 Schematic diagram of pH changes in a filtration method for improving denitrification efficiency of a denitrification filter based on carbon and bacterial regulation provided in an embodiment of the present application; Figure 15 Schematic diagram of the change in dissolved oxygen concentration in the filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation provided in the embodiments of the present application; Figure 16 Schematic diagram of water temperature changes in a filtration method for improving denitrification efficiency of a denitrification filter based on carbon and bacterial regulation provided in an embodiment of the present application; Figure 17 Schematic diagram of the changes in redox potential in the filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation provided in the embodiments of the present application; Figure 18 Schematic diagram of the change of chemical oxygen demand in the filtration method for improving the denitrification efficiency of the denitrification filter based on carbon and bacterial regulation provided in the embodiment of the present application; Figure 19 Schematic diagram of the changes in total phosphorus in the filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation provided in the embodiments of the present application; Figure 20 Schematic diagram of the changes in suspended matter in the filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation provided in the embodiments of the present application; Figure 21A schematic diagram of the change in nitric nitrogen concentration in the filter after a short backwash in the filtration method for improving the denitrification efficiency of the denitrification filter based on carbon and bacterial regulation provided in the embodiment of the present application; Figure 22 A schematic diagram of the nitrate-nitrogen removal effect after long-term backwashing of the filter in the filtration method for improving the denitrification efficiency of the denitrification filter based on carbon and bacterial regulation provided in an embodiment of the present application; Figure 23 This is a schematic diagram of the structure of a filtration system for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present invention will be described below in conjunction with the accompanying drawings in the embodiments of the present invention. In the description of the embodiments of the present invention, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0027] In addition, in order to facilitate the clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit differences. At the same time, in the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0028] The principles and features of the present application are described below. The examples given are only used to explain the present application and are not used to limit the scope of the present application.

[0029] The embodiment of the present application provides a filtration system that improves the denitrification efficiency of a denitrification filter based on carbon and bacteria regulation, and is applicable to various sewage treatment scenarios. By setting up a carbon bacteria intelligent addition structure, in conjunction with the optimal carbon bacteria addition amount obtained based on a deep learning model, the carbon bacteria delivery pump is controlled according to the optimal carbon bacteria addition amount to deliver the bacteria and carbon in the carbon bacteria culture box into the filter through a carbon bacteria delivery pipe provided with evenly distributed carbon bacteria spray holes. In this way, the denitrification efficiency of the denitrification filter is significantly improved, the breadth and depth of the application of pyrite denitrification process engineering are expanded, the consumption of carbon sources is significantly reduced, operating costs are saved, and higher economic and technical benefits are achieved.

[0030] like Figure 1 、 Figure 2 and Figure 3 As shown, in some embodiments, the filtration system for improving the denitrification efficiency of a denitrification filter based on carbon and bacteria regulation includes: an inlet and outlet water structure 100, a filtration structure 200, a carbon bacteria intelligent dosing structure 300 and a monitoring structure 400.

[0031] The water inlet and outlet structure 100 includes a sewage inlet pipe 101. One end of the sewage inlet pipe is connected to the filter structure for inputting the sewage to be treated into the filter structure.

[0032] The filter structure 200 is used for denitrification of the wastewater to be treated. The filter structure includes a filter tank for filtering the wastewater. The filter tank can be a vertical box filter tank. The filter tank can be a downflow filter tank, which is a high-efficiency filtration device for denitrification of wastewater. In some embodiments, the filter structure also includes pyrite filler and a pebble support layer. The pyrite filler is arranged on the pebble support layer. The pyrite filler and the pebble support layer are both located on the air-water chamber of the filter tank. Exemplarily, a multi-layer structure is provided inside the filter tank, with an anti-oxygen cover covering the top, pyrite filler and a pebble support layer filled inside, and water and gas separation is performed through a filter cap at the bottom, and the treated water enters the clear water tank through the air-water chamber. The pyrite filler in the filter tank provides an anaerobic environment, the pebble support layer is used to stabilize the filter material, the filter cap prevents the loss of the filler, and the air-water chamber combined with the backwash function ensures operating efficiency.

[0033] like Figure 3 As shown, the carbon bacteria intelligent dosing structure 300 includes a carbon bacteria control unit, a carbon bacteria delivery pump, a carbon bacteria incubator, a sixth valve FM6, and a carbon bacteria delivery pipe. The carbon bacteria incubator, the carbon bacteria delivery pump, the sixth valve FM6, and the carbon bacteria delivery pipe are connected in sequence, and the carbon bacteria control unit and the carbon bacteria delivery pump are electrically connected. The carbon bacteria control unit can be set as follows Figure 1 In some embodiments, the carbon bacteria intelligent dosing structure 300 further includes a metering module, a PLC control module and a dosing execution unit, wherein the dosing execution unit includes a dosing and electric valve.

[0034] Carbon bacteria transport pipe, as one of the important components for transporting bacteria and carbon, such as Figure 3 As shown, the filter includes a first pipe section 301 extending away from the ground. First pipe section 301 is provided with carbon bacteria injection holes. Multiple carbon bacteria injection holes are spaced apart, facing away from the ground. First pipe section 301 is disposed within the filter tank. The end of first pipe section 301, facing away from the ground, receives bacteria and carbon from a carbon bacteria delivery pump.

[0035] like Figure 3 As shown, in one implementation, the carbon bacteria transport pipe further includes a first annular pipe segment 302, a second annular pipe segment 303, and a first bent pipe 304. The first annular pipe segment 302 is connected to the first ends 301a of the plurality of first pipe segments 301. The first annular pipe segment 302 is connected to the carbon bacteria transport pump via the first bent pipe 304. The second annular pipe segment 303 is connected to the second ends 301b of the plurality of first pipe segments 301, which are closer to the ground. The first annular pipe segment 302 and the second annular pipe segment 303 are both rectangular. There are four first pipe segments 301, each located at a vertex of the rectangle.

[0036] like Figure 3 As shown, in some embodiments, the carbon bacteria intelligent dosing structure further includes a scrubbing hole and an anti-falling cover, and the carbon bacteria delivery pipe further includes a second pipe section 305 provided on the first annular pipe section 302 and connected to both the first annular pipe section 302 and the first pipe section 301. The second pipe section 305 extends in a direction away from the ground. A scrubbing hole and an anti-falling cover are provided at one end of the second pipe section 305 facing away from the ground. The anti-falling cover is detachably provided on the second pipe section and covers the scrubbing hole. Open the anti-falling cover and use a long-handled brush to clean the adhesions on the packing layer and the inner wall of the delivery pipe.

[0037] The monitoring structure 400 is used to monitor the first monitoring data and the second monitoring data. Figure 2 As shown, in some embodiments, a portion of the monitoring structure 400 is disposed at the water inlet pipe 101 for monitoring first monitoring data. Another portion of the monitoring structure 400 is disposed at the water outlet pipe for monitoring second monitoring data. The monitoring structure 400 is connected to the carbon bacteria intelligent dosing device via a data interface to transmit water quality data in real time.

[0038] Combined Figure 3 and Figure 4 When the sixth valve FM6 is open, the carbon bacteria regulation unit controls the carbon bacteria delivery pump according to the optimal carbon bacteria dosage to deliver the bacteria and carbon in the carbon bacteria incubator into the filter tank through the carbon bacteria delivery pipe provided with evenly distributed carbon bacteria spray holes.

[0039] Among them, the optimal carbon bacteria dosage is obtained based on the deep learning model, which is described in detail in the examples below and will not be repeated here.

[0040] Combined Figure 1 and Figure 4In some embodiments, the filtration system for improving the denitrification efficiency of the denitrification filter based on carbon and bacteria regulation also includes: a backwash structure and a backwash structure.

[0041] The backwash structure includes a backwash air compressor, an air delivery pipe, a backwash pump, a fourth valve FM4, and a fifth valve FM5. The fourth valve FM4 is connected to the backwash pump and is used to turn the backwash pump on and off. The fifth valve FM5 is connected to the air delivery pipe and is used to turn the air delivery pipe on and off. The backwash air compressor, air delivery pipe, and filter tank are sequentially connected.

[0042] The backwash structure includes a carbon bacteria backwash pipe and a seventh valve FM7.

[0043] The water inlet and outlet structure also includes an outlet pipe 102, a clean water tank, a second valve FM2, and a third valve FM3. The filter's air-water chamber, the second valve FM2, the third valve FM3, the clean water tank, and the outlet pipe are sequentially connected. A carbon bacteria backwash pipe connects the seventh valve FM7 to the outlet pipe. Valve FM7 is regularly opened to clean the delivery pipe and packing layer through the carbon bacteria backwash pipe combined with air and water flushing.

[0044] The third valve FM3 and the fourth valve FM4 are connected in parallel.

[0045] In this way, when the second valve FM2 and the third valve FM3 are closed and the fourth valve FM4 and the fifth valve FM5 are opened, the backwash pump and the backwash air compressor are started. Also, when the seventh valve FM7 is opened periodically, the carbon bacteria backwash pipe is combined with the air delivery pipe, and the air and water work together to remove the blockages and suspended particles on the surface of the filler inside the filter, and discharge the sewage to achieve air-water flushing and cleaning of the filter structure. In some embodiments, an upflow high-speed water flow backwash is adopted, which is opposite to the direction of the filter operation. For example, the flushing intensity is 7L / (m 2 ·s), and the flushing time was gradually increased from 5 min to 2 h.

[0046] Both excessive and insufficient backwashing have a certain impact on the filter. Excessive backwashing not only increases operating energy consumption but also affects the microbial community. Insufficient backwashing will shorten the filter's operating cycle. The backwashing effect will directly affect the filter's head loss, the water quality of the effluent, and the filter's operating cycle. The embodiments of the present application provide a method that can avoid both excessive and insufficient backwashing.

[0047] In some embodiments, the water inlet and outlet structure 100 further includes a filter, a regulating tank, a sewage pump, a return pipe, and an eighth valve FM8. The filter is mounted at the front end of the water inlet pipe. The regulating tank is connected to the sewage pump. The sewage pump is connected to the first valve FM1. The return pipe is connected to the regulating tank and the eighth valve FM8.

[0048] In this way, combined Figure 1 and Figure 4 The sewage enters the filter through the inlet pipe to remove large particles of impurities, passes through the regulating tank and enters the filtration system through the sewage pump. After treatment, the clean water flows into the clean water tank. If the water quality is not up to standard, the clean water is returned to the regulating tank through the eighth valve FM8 for further treatment.

[0049] In this way, when the first valve FM1, the second valve FM2 and the third valve FM3 are opened, the sewage pump is started to complete the water intake, treatment and discharge process. If the water quality monitoring fails, the third valve FM3 is closed and the eighth valve FM8 is opened to start the return pipe to return water to the regulating tank.

[0050] In this way, during the pyrite mixed culture denitrification process, the process system timely regulates the carbon source and autotrophic denitrifying microbial flora in the anaerobic zone of the pyrite particle filter layer after backwashing, accelerates the electron release rate of pyrite, expands the contribution ratio of sulfur-based autotrophic denitrification to denitrification efficiency, saves carbon source, and reduces operating costs. The optimal addition position is determined through field pilot experiments, and then field pilot experiments are conducted using relatively accurate theoretical values ​​of added carbon sources as a reference to determine the optimal dosage of the added carbon source. Through the deep learning-based carbon bacteria dosage prediction model and carbon bacteria dosage adjustment prediction model, feedforward and feedback adjustments of carbon and bacteria dosage are performed to ensure that the effluent water quality meets the standards. This more precise and scientific method of adding carbon source to the biological pool is currently the more ideal carbon source addition strategy.

[0051] The following is a detailed description of the method for obtaining the optimal carbon bacteria dosage.

[0052] Figure 5 This is a flow chart of a filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation provided in the embodiment of the present application. Figure 5 and Figure 7 As shown, in some embodiments, the filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation includes the following steps: S1. Acquire first monitoring data under a first preset condition.

[0053] The first preset condition includes different collection conditions for different data in the first monitoring data. In some embodiments, the first monitoring data is obtained during the filtering process.

[0054] The first monitoring data includes the influent chemical oxygen demand (COD), ammonia nitrogen content (NH4-N), nitrate nitrogen content (NO3-N), nitrite nitrogen content (NO2-N), first total phosphorus content (TP), first suspended solids content (SSO), first pH, dissolved oxygen content (DO), temperature (Temperature) and first oxidation-reduction potential (ORP).

[0055] COD, which indicates the amount of oxygen required for the oxidation and decomposition of organic matter in water, is an important indicator for measuring the content of organic pollutants in water. The higher the COD, the more serious the organic pollution in the water.

[0056] NH4-N is nitrogen in water in the form of ammonium ions (NH4) or free ammonia (NH3). It is an important indicator for measuring nitrogen pollution in water bodies. It mainly comes from domestic sewage, industrial wastewater and agricultural runoff.

[0057] NO3-N refers to nitrogen in the form of nitrate ions (NO3) in water. It is a form in the nitrogen cycle and is usually generated by nitrification of ammonia nitrogen.

[0058] NO2-N represents nitrogen in the form of nitrite ions (NO2) in water, an intermediate product in nitrogen conversion. High concentrations of nitrite nitrogen may be the result of incomplete nitrification in water and are toxic to humans.

[0059] TP, which refers to the total amount of all forms of phosphorus in water, including organic phosphorus and inorganic phosphorus, is one of the important indicators for measuring the degree of eutrophication of water bodies.

[0060] SS0 refers to the content of insoluble particulate matter in water, including sediment, organic matter, microorganisms, etc. The higher the SS content, the greater the turbidity of the water.

[0061] pH is used to indicate the acidity or alkalinity of water. A pH < 7 is acidic, a pH = 7 is neutral, and a pH > 7 is alkaline. Water pH that is too high or too low can affect aquatic life and treatment processes.

[0062] DO, which represents the amount of dissolved oxygen in water, is an important indicator of the water's ability to purify itself. Low DO levels can lead to anaerobic conditions, which are detrimental to the health of aquatic ecosystems.

[0063] Temperature: The temperature of water bodies will affect chemical reaction rates, dissolved oxygen content and microbial activity, and have an important impact on water treatment effects and aquatic ecosystems.

[0064] ORP, which stands for Redox Potential of water, is an indicator of the activity of chemical reactions in water. A positive value indicates an oxidizing environment, while a negative value indicates a reducing environment.

[0065] These indicators are common parameters in the field of water quality monitoring and water treatment. They are used to assess the degree of water pollution and the treatment effect, and can help judge the water quality status and the operation of the water treatment process.

[0066] like Figure 6 As shown, the first preset condition also includes: when a small amount of bubbles begin to emerge from the filter, a small amount of sample is taken from the air-water chamber to test for TN. If TN is less than 10 mg / L, the sampling time corresponding to this TN is recorded as the starting time of the filtration timer ΔT. If the filtration timer ΔT is greater than 2 minutes, a backwash request is issued. If the filtration timer ΔT is less than 2 minutes, the head loss value ΔP is measured. If the head loss value ΔP is greater than 2 minutes, a backwash request is issued. If the filtration timer ΔP is less than 2 minutes, a determination is made as to whether the filtration timer ΔT is greater than 2 minutes.

[0067] In some embodiments, before executing step S1, that is, in order to start a small amount of bubbles to emerge from the filter tank, the method also includes: S011, turning on the computer and the control program, inputting the set value of the head loss value ΔP, the set value of the filtration time T, and the set value of the total nitrogen content TN of the effluent.

[0068] For example, the set value of the total nitrogen content TN of the effluent is 10 mg / L, the set value of the head loss value ΔP is 2 minutes, and the set value of the filtration time T is 2 minutes.

[0069] S012, start the sewage inlet pump to start water intake, and at the same time, quickly take in low-dose carbon source, denitrifying bacteria and combined nutrients into the anaerobic area of ​​the pyrite filler area.

[0070] S013, after the water reaches the specified water level and the computer receives the water level relay signal, it temporarily turns off the water inlet pump and enters a short-term bacterial culture static stage.

[0071] After a period of stagnant air, a small amount of bubbles began to emerge from the denitrification filter. During the filtration process, the system monitored and, based on the first monitoring data, comprehensively adjusted the carbon and bacteria dosage, filter speed, and, in extreme cases, tailwater return treatment.

[0072] S2, performing data cleaning, data integration, data reduction and data transformation on the first monitoring data in sequence to obtain water inflow monitoring data.

[0073] In some embodiments, the water inlet monitoring data is input into a water inlet monitoring data preprocessing structure for data cleaning, data integration, data reduction, and data transformation processing to obtain preprocessed water inlet monitoring data, so as to make the data more suitable as an input set of a deep learning model.

[0074] Through data cleaning to remove irrelevant data, fill missing values, smooth noise data, etc., through data integration, data from multiple data sources are merged and stored in a unified database. Through data reduction, the amount of data is minimized to obtain a smaller data set while maintaining the original appearance of the data. Through data transformation, the data is normalized, discretized, and sparsely processed to obtain pre-processed water inlet monitoring data.

[0075] In some embodiments, Z-score normalization is used to normalize the water inlet monitoring data to improve the convergence speed of the prediction model. The calculation principle is shown in the formula: Where μ and σ are the mean and standard deviation of the inlet monitoring data, respectively, x is the inlet monitoring data, and x′ is the standardized inlet monitoring data.

[0076] S3, inputting the water inlet monitoring data into the dosage prediction model to obtain the dosage prediction amount.

[0077] The dosage prediction includes the external carbon source dosage prediction and the autotrophic denitrifying bacteria dosage prediction, and the external carbon source dosage prediction and the autotrophic denitrifying bacteria dosage prediction are feedforward controlled.

[0078] like Figure 8 As shown, in some embodiments, the dosage prediction model is built based on a deep learning model, including a first input layer, a first intermediate hidden layer and a first output layer.

[0079] The first input layer includes a fully connected layer for processing preprocessed influent monitoring data. The first intermediate hidden layer includes seven long short-term memory (LSTM) layers. The LSTM layers include LSTM neurons. LSTM neurons include a forget gate, an input gate, and an output gate. The first output layer includes a regression layer. The regression layer uses a logistic function as an activation function. Exemplarily, a sigmoid function is used as the activation function, and the final output is the carbon source dosage and the autotrophic denitrifying bacteria dosage.

[0080] The number of neurons in the hidden layer is determined using the following formula: Among them, N i Number of neurons in the input layer, N o is the number of neurons in the output layer, N sis the number of samples in the training set, and α is an arbitrary value variable that can be set by yourself, usually 2-10.

[0081] The training of the carbon bacteria dosage prediction model (i.e., dosage prediction model) is based on the early stopping strategy, using historical monitoring and operation data as the training set, and optimizing the neural network parameters using the mini-batch gradient descent (MBGD) algorithm, the Dropout method, and the L2 regularization algorithm. The Adam algorithm is used to dynamically adjust the learning rate.

[0082] The model performance is evaluated using mean absolute error (MAE), root mean square error (RMSE), and symmetric mean absolute percentage error (SMAPE), all in the range [0, +∞). The smaller the error, the better the model performance, and vice versa. The definition of SMAPE is as shown in the formula, where n is the total number of samples, y i is the observed value, y′ i is the predicted value.

[0083]

[0084] S4. Under the second preset condition, obtain second monitoring data.

[0085] The second preset condition includes obtaining the second monitoring data while obtaining the first monitoring data.

[0086] The second monitoring data include effluent chemical oxygen demand, total nitrogen content, second total phosphorus content, second suspended solids content, second pH and second redox potential.

[0087] S5, performing data cleaning, data integration, data reduction and data transformation on the second monitoring data in sequence to obtain water outlet monitoring data.

[0088] The water discharge monitoring data preprocessing module preprocesses the water discharge monitoring data by removing irrelevant data, filling missing values, and smoothing noise data through data cleaning. Data from multiple data sources is merged and stored in a unified database through data integration. Data reduction is used to minimize the amount of data while maintaining the original appearance of the data to obtain a smaller data set. Data transformation is used to normalize, discretize, and sparsify the data to obtain preprocessed water discharge monitoring data. Z-score standardization is used to normalize the water discharge monitoring data to improve the convergence speed of the prediction model. The calculation principle is shown in the formula: Where μ and σ are the mean and standard deviation of the effluent monitoring data, respectively; x is the effluent monitoring data; and x′ is the standardized effluent monitoring data.

[0089] S6, inputting the water outlet monitoring data into the adjustment prediction model to obtain the adjustment prediction amount.

[0090] The adjustment prediction amount includes the adjustment prediction amount of external carbon source addition and the adjustment prediction amount of autotrophic denitrifying bacteria addition, and feedback control is performed on the adjustment prediction amount of external carbon source addition and the adjustment prediction amount of autotrophic denitrifying bacteria addition.

[0091] like Figure 9 As shown, in some embodiments, the adjustment prediction model is built based on a deep learning model, and includes a second input layer, a second intermediate hidden layer and a second output layer.

[0092] The second input layer includes a fully connected layer for processing preprocessed water discharge monitoring data. The second intermediate hidden layer includes five long short-term memory (LSTM) layers. The LSTM layers include LSTM neurons. LSTM neurons include a forget gate, an input gate, and an output gate. The second output layer includes a regression layer. The regression layer uses the logistic function as the activation function. Exemplarily, the sigmoid function is used as the activation function.

[0093] The number of neurons in the hidden layer is determined using the following formula: where N i Number of neurons in the input layer, N o is the number of neurons in the output layer, N s is the number of samples in the training set, and α is an arbitrary value variable that can be set by yourself, usually 2-10.

[0094] The training of the carbon bacteria dosage adjustment prediction model is based on the early stopping strategy, using historical monitoring and operation data as the training set, and optimizing the neural network parameters using the mini-batch gradient descent (MBGD) algorithm, the Dropout method, and the L2 regularization algorithm. The Adam algorithm is used to dynamically adjust the learning rate.

[0095] The model performance is evaluated using mean absolute error (MAE), root mean square error (RMSE), and symmetric mean absolute percentage error (SMAPE), all in the range [0, +∞). The smaller the error, the better the model performance, and vice versa. The definition of SMAPE is as shown in the formula, where n is the total number of samples, y i is the observed value, y′ i is the predicted value.

[0096]

[0097] S7, according to the adjusted predicted amount, the predicted amount of addition is adjusted to obtain the optimal carbon bacteria addition amount, so that the filtration system based on carbon and bacteria regulation to improve the denitrification efficiency of the denitrification filter tank can input carbon and bacteria into the filter tank according to the optimal carbon bacteria addition amount through the carbon bacteria delivery pipe provided with evenly distributed carbon bacteria spray holes.

[0098] The carbon bacteria delivery pipe includes a first pipe section extending in a direction away from the ground. The first pipe section is provided with carbon bacteria spray holes. A plurality of carbon bacteria spray holes are spaced apart in a direction away from the ground.

[0099] To illustrate the excellent performance of the filtration system provided in this application for improving the denitrification efficiency of denitrification filters based on carbon and bacterial regulation in sewage treatment, quantitative analysis of total nitrogen and nitrate nitrogen indicators and integration of multi-level real-time monitoring data were obtained through testing. Furthermore, quantitative detection of key physical and chemical parameters of the water environment and integration of multi-level real-time monitoring data were also conducted to demonstrate the removal effect on "a certain low carbon-nitrogen ratio sewage." A detailed description is provided below with reference to the accompanying drawings.

[0100] For example, the parameter values ​​of the influent concentration of the "low carbon-nitrogen ratio sewage" to be treated include influent COD of 40±10.23 mg / L, NH4 + -N is 6.5±0.53mg / L, NO3 - -N is 18±2.77mg / L, DO is 2mg / L, pH is 7.3±1.34, SS is 20±1.20mg / L, and TP is 2.65±0.8mg / L. The operating parameters that need to be pre-set for the system provided in this application include three main parameters: C / N, bacterial dosage, and filtration rate. As shown in Table 1, the specific values ​​of the operating parameters for different time periods. It is understood that the test process period is 60 days.

[0101] Table 1 Reactor operating parameters First, through Figures 10 to 13 The quantitative analysis of total nitrogen and nitrate nitrogen indicators and the integration of multi-level real-time monitoring data are explained. Using a downflow denitrification biological filter with pyrite as the filter medium, the parameter value of "a low carbon-nitrogen ratio sewage" is NO3 - -N, NO2 - -N、NH4 + -N and TN index water concentrations are as described above and will not be described in detail. Figure 10 As shown, NO3 - -N operation trend, in the initial stage of water inflow, the sulfur autotrophic denitrification process is gradually activated, and the sulfur autotrophic bacteria use S 2- Reduction of NO3 -, with the formation of biofilm, the removal efficiency gradually increases. In the reaction phase II, the system operates stably, and the ORP is stable at -150~-50mV, reflecting the continuous hypoxia. In this phase, the efficiency of the electron transport chain is maximized, and continuous steady-state denitrification is achieved. In the final phase III of the reaction, the temperature drops briefly, heat production decreases, and the system is resistant to NO3 - -N finally reached 87.9%.

[0102] like Figure 11 As shown, NO2 - -N operation trend, in the initial stage of water inflow, the accumulation of intermediate products leads to a short-term increase in the initial NO (due to uneven denitrification chain rate), and is also related to the reaction water temperature. The temperature increases from 18.5 to 21.5℃, which accelerates the enzymatic reaction. The second stage of the reaction: At this time, there is no accumulation of intermediate products, and the denitrification path is complete (NO3 - -N→NO2 - -N→N), outlet NO2 - -N≤0.02mg / L. The outlet water temperature is stable at 21.0~21.5℃, and the metabolic rate of the denitrification reaction bacteria is constant. In the third stage of the reaction, the removal rate is finally stabilized at 95%. During the entire reaction process, the denitrification enzyme is less active in the early stage of operation, resulting in the initial NO2 - -N accumulates briefly (0.32-0.39 mg / L) and is completely reduced in the later stage as the enzyme activity increases, achieving a high degradation rate.

[0103] like Figure 12 As shown, NH4 + -N operation trend, in the first stage reaction, heterotrophic bacteria utilize NH4 + Synthesize cell substances, but the proportion of sulfur autotrophic bacteria is low and the removal is limited. At the same time, the pH value gradually decreases during the reaction process, inhibiting the activity of nitrifying bacteria and avoiding NH4 + -N to NO3 - -N conversion. In the second stage, the proportion of heterotrophic bacteria in the mature biofilm increases, and the assimilation of NH4 + -N amount increases. In the final stage of operation, the activity of nitrifying bacteria approaches zero due to the low pH (<6.8), and NH4 + The -N removal rate was maintained at 5%, mainly relying on heterotrophic bacteria assimilation.

[0104] like Figure 13 As shown in the figure, the TN operation trend is that at the initial stage of the sewage treatment system, the microbial community is not yet mature, the abundance of nitrifying bacteria and denitrifying bacteria is extremely low, and the system can only achieve limited TN removal through physical interception and basic ammonification, with a removal rate of only 20%. In the middle stage II of the reaction, the nitrification-denitrification reaction path is opened, and the efficient denitrification reaction begins, with a removal rate of 55%. In the late stage III of the reaction, the functional bacterial community evolves and enriches NO2 --N, NO3 - -N is the substrate of the denitrifying bacteria, and its nitrite reductase activity is enhanced, ultimately making the reaction degradation rate reach 85%.

[0105] The filtration system described above, which improves the denitrification efficiency of denitrification filters through carbon and bacterial regulation, integrates multi-level monitoring data for total nitrogen and nitrate nitrogen to build a dynamic learning framework for detection optimization. By continuously learning the nonlinear characteristics of water quality monitoring data, the system not only accurately predicts the amount of carbon bacteria to be added, but also feeds back into the water quality monitoring system through feature correlation analysis, significantly improving the early warning capabilities and control response efficiency of abnormal conditions in total nitrogen indicators, forming a closed-loop optimization mechanism.

[0106] Secondly, through Figures 14 to 17 This paper describes the quantitative detection of key physical and chemical parameters of the water environment and the integration of multi-level real-time monitoring data. A downflow denitrifying biofilter was used with pyrite as the filter media. The parameters for "a certain low carbon-nitrogen ratio wastewater," including pH, DO, water temperature, and ORP, were as described above and are omitted for clarity.

[0107] like Figure 14 As shown in the figure, the pH trend during the reaction is mainly due to the acid production effect of sulfur autotrophic denitrification (sulfuric acid produced by pyrite oxidation) and the buffering effect of pyrite. The reaction is shown in the following formula: In the initial stage of water inflow, the pH of the water is high (7.3-8.6), the pyrite has sufficient neutralization capacity, and the pH slowly drops to 6.6. When the reaction reaches stage II, the acid production increases (so NO3 - -N removal rate (82%), pyrite was partially consumed, and the pH dropped to 6.4-6.5. In the final stage III of the reaction, the system stabilized, with the pH maintained between 6.4 and 6.7. The overall reaction trend showed that at high influent pH, sulfur oxidation and acid production dominated, leading to a significant pH drop. At low influent pH, buffering capacity was saturated, and the pH drop was less pronounced, consistent with the chemical-microbial synergistic mechanism of the pyrite denitrification biofilter.

[0108] like Figure 15 As shown in the figure, the DO operation trend is that in the initial stage of water inflow, the microbial activity gradually increases, the DO consumption efficiency improves, and the effluent DO drops from 0.6mg / L to 0.3mg / L. In the reaction to stage II, the system operates stably, and the effluent DO is maintained at 0.2-0.4mg / L (partial rebound due to influent DO fluctuation). In the final stage III of the reaction, the biofilm matures, the DO consumption efficiency reaches the peak, and the effluent DO is stable at ≤0.3mg / L. The overall reaction process presents an anoxic environment because sulfur autotrophic denitrifying bacteria preferentially utilize nitrate (NO3 - ) rather than oxygen as the electron acceptor, resulting in rapid consumption of DO.

[0109] like Figure 16 As shown in the water temperature operation trend, sulfur autotrophic denitrifying bacteria oxidize sulfide (such as S 2- 、S 0 ) to obtain energy, while converting nitrate (NO3 - ) is reduced to nitrogen (N). This process involves an exothermic reaction, in which some of the Gibbs free energy (ΔG) released is dissipated as heat, causing the filter bed to heat up locally. Therefore, at all stages of the reaction, the overall outlet water temperature is slightly higher than the inlet water temperature.

[0110] like Figure 17 As shown in the figure, during the initial stage of water inflow, the ORP dropped from +180 mV to -120 mV (Δ = 300 mV), indicating the rapid formation of an anoxic environment. During the reaction stage II, the system operated stably, with the ORP stabilizing between -150 and -115 mV (fluctuation ≤ ±20 mV). In the final stage III, the ORP values ​​remained low, reflecting the strong reducing ability of the sulfur autotrophic bacteria.

[0111] The above-mentioned filtration system for improving the denitrification efficiency of the denitrification filter based on carbon and bacterial regulation constructs a multi-level real-time monitoring data integration framework based on the key physical and chemical parameters of the water environment (pH, temperature, ORP, DO), and builds a dynamic learning system to achieve water quality control optimization.

[0112] Again, through Figures 18 to 20 This paper describes the integration of quantitative detection of basic pollutants and multi-level real-time monitoring data. A downflow denitrification biofilter was used, using pyrite as the filter media. The influent concentrations of COD, TP, and SS indicators are as described above and are not repeated here.

[0113] like Figure 18 As shown in the COD operation trend, in the initial stage of operation I, the COD removal mechanism is mainly due to the adsorption of heterotrophic bacteria. Under anoxic conditions, heterotrophic bacteria preferentially adsorb easily degradable organic matter (such as carbohydrates and short-chain fatty acids), and the adsorption amount accounts for 50% to 60% of the removal amount. At the same time, part of the COD is used by denitrifying bacteria to reduce NO3 - -N, generating CO2 and N2. During the mid-stage II, microbial-secreted EPS decomposes under anoxic conditions, releasing an internal carbon source and promoting COD removal. During the final stage III, endogenous respiration intensifies, and microorganisms decompose their own cellular material in the absence of a sufficient carbon source, ultimately maintaining a stable COD removal rate of 34%.

[0114] like Figure 19 As shown in the TP operating trend, pyrite releases Fe through oxidation reaction 2 and Fe 3 , and phosphate (PO 3) to form FePO or Fe(PO)(OH) precipitates, directly removing phosphorus. Pyrite enhances the sustained release of iron ions and, through the metabolic activity of sulfur-oxidizing bacteria, maintains the system's acid-base balance, reducing sulfate accumulation and thus improving phosphorus adsorption efficiency. P-accumulating bacteria release phosphorus under anoxic / anaerobic conditions and absorb excessive amounts of phosphorus under aerobic conditions. However, due to the predominantly anoxic system, biological phosphorus removal contributes only 38% to the overall operational period.

[0115] like Figure 20 As shown in the figure, the SS operation trend is that during the reaction process, SS is mainly in the form of particles. On the one hand, it is removed by gravity sedimentation. On the other hand, it is affected by the reaction potential and initially forms micro-flocs through the "bridging effect" and then settles, ultimately achieving a filtration effect of 89%.

[0116] The above-mentioned filtration system based on carbon and bacteria regulation to improve the denitrification efficiency of the denitrification filter not only realizes the accurate prediction of the carbon bacteria dosage, but also systematically integrates the standardized detection data of COD, TP and SS during the model training process, analyzes the nonlinear coupling relationship between them and the metabolic activity of carbon bacteria, and forms a closed-loop optimization system of "data-driven-model iteration-detection enhancement", which significantly improves the warning timeliness and control response accuracy of abnormal water quality under complex working conditions.

[0117] Finally, through Figure 21 and Figure 22 Describe the intelligent optimization of backwash parameters and system behavior learning of denitrifying biological filter.

[0118] After the filter has been running stably for 60 days, the filter is backwashed. Studies have shown that air-water combined backwashing has a good backwashing effect, but the flushing of gas will damage the anaerobic environment in the filter and affect the growth and reproduction of autotrophic denitrifying microorganisms. Therefore, in this test phase, upflow high-speed water backwashing is used, which is opposite to the direction of filter operation, and the flushing intensity is 7L / (m 2 ·s), and the flushing time was gradually increased from 5 min to 2 h.

[0119] When the backwash time is set to 5 minutes, Figure 21 As shown, after the backwash is completed, the sampled water NO3 - -N concentration starts to rise from 0.63mg / L and reaches its peak 30min after backwashing. This indicates that the backwashing process causes part of the bacteria in the filter to separate from the filter media and be discharged with the flushing water. The air washing process destroys the anaerobic environment inside the filter and impacts the living environment of the autotrophic denitrifying bacteria. Within 30-90min after backwashing, the effluent NO3 - The -N concentration began to decrease and remained at 1.32-1.58 mg / L, indicating that with the normal operation of the filter, the bacterial community inside the filter gradually proliferated after the addition of carbon source, and the effluent water quality was improved.

[0120] like Figure 21 As shown, the NO3 content of the filter outlet water is within 90-180 minutes. - The -N concentration is still lower than the effluent before backwashing, indicating that the recovery period of the denitrifying deep bed filter caused by backwashing is relatively long. In other words, appropriately extending the backwash cycle is beneficial to improving the operation performance of the denitrifying deep bed filter and ensuring the effluent quality.

[0121] When the backwash time is extended to 2h, the NO3 - -N removal effect is as follows Figure 22 As shown. Figure 22 It can be seen that in the first day, system NO3 - The -N removal rate was only 6.3%, with almost no denitrification effect, indicating that backwashing had a significant impact on the microorganisms in the filter and required a certain amount of time to recover. - The 3--N removal rate gradually increased, indicating that the autotrophic denitrifying microorganisms in the system gradually adapted to the environment after backwashing, continued to grow and reproduce, and the denitrification process proceeded steadily. On the 13th day, the NO3 - The -N concentration dropped to 2.1 mg / L and the removal rate reached 88.5%, indicating that the denitrification and denitrification capacity of the system has been fully restored.

[0122] In the related art, compared with heterotrophic denitrifying microorganisms, the slow growth rate and long startup time of autotrophic denitrifying bacteria are the biggest obstacles to the promotion and application of their processes. Autotrophic denitrifying bacteria such as Denitrifying Thiobacillus grow relatively slowly, with a lag phase of about 8 hours, and then enter a logarithmic growth phase that lasts about 20-24 hours. After that, the bacteria enter a stable phase, and after 48 hours of growth, the bacteria enter a decline phase. In addition, the doubling time of heterotrophic denitrifying microorganisms is 2.4-4 hours, which is 5-30 times faster than that of autotrophic denitrifying bacteria. In terms of competing for electron acceptors and growth space, heterotrophic denitrifying bacteria have significantly stronger competitive and anti-competitive abilities than autotrophic denitrifying bacteria. In contrast, the embodiment of the present application determines the optimal addition position and dosage so that after the backwash process of the biological filter is completed, the anaerobic zone can quickly establish a stable mixed-culture denitrification system and suitable environmental conditions, directly preventing DO from consuming about 17.8% of the carbon source in advance and the aerobic microbial flora from consuming the carbon source in advance. By delivering low-dose carbon sources, denitrifying bacteria and combined nutrients in the anaerobic area through the intelligent dosing system, the problems of slow growth rate and long start-up time of sulfur-based autotrophic denitrifying bacteria can be effectively solved. Then, by realizing intelligent control of the ratio of added carbon, bacteria and combined nutrients, the denitrification efficiency of the denitrification filter can be improved.

[0123] In this embodiment, using pyrite as the primary filler, the denitrification contribution of sulfur-based autotrophic denitrifying bacteria in the treatment of secondary tailwater with a low C / N ratio is increased. Pyrite provides an electron donor to replace part of the carbon source, reducing the carbon source by approximately 30%. The downflow filter can meet average filtration rates of 5-8.5 m / h and peak or forced filtration rates of 6-12 m / h.

[0124] In the embodiment of the present application, during the secondary tailwater treatment process with a low C / N ratio, under the condition of a nitrate-nitrogen removal rate of about 80%, the hydraulic retention time is reduced from the original 6-8 hours to 15-30 minutes, thereby increasing the engineering breadth of the pyrite denitrification process, which is currently only applied to artificial wetlands and biological retention ponds.

[0125] Compared with the quartz sand denitrification biological filter, while maintaining the same technical parameters such as filter media filling height, floor space, processing load, fan type and filter media layer resistance, the filtration method provided in the embodiment of the present application for improving the denitrification efficiency of the denitrification filter based on carbon and bacterial regulation reduces the carbon source consumption by 41.3%.

[0126] Based on the same application concept, the embodiments of the present application also provide a filtration system for improving the denitrification efficiency of a denitrification filter based on carbon and bacteria regulation. The corresponding method of the filtration system for improving the denitrification efficiency of a denitrification filter based on carbon and bacteria regulation can be the filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacteria regulation in the aforementioned embodiments, and its principle of solving the problem is similar to that of this method. Figure 12 This is a schematic diagram of the structure of a filtration system based on carbon and bacteria regulation to improve the denitrification efficiency of the denitrification filter provided in the embodiment of the present application. Figure 23 As shown, in some embodiments, the filtration system 001 for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation includes at least one processor 011 and a memory 012 in communication with the at least one processor. The memory 012 stores instructions executable by the at least one processor 011. The instructions are executed by the at least one processor 011 to enable the at least one processor 011 to perform the filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation provided in the embodiments of the present application.

[0127] Another embodiment of the present application further provides a computer-readable storage medium having computer program instructions stored thereon, which can be executed by a processor to implement the methods and / or technical solutions of any one or more embodiments of the present application.

[0128] Specifically, the present embodiment can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0129] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0130] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0131] Computer program code for performing the operations of the present application can be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0132] The flow chart or block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the equipment, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a structure, program segment or a part of code, and the part of the structure, program segment or code comprises one or more executable instructions for realizing the logical function of the specification. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated system for hardware that performs the function or operation of the specification, or can be implemented with a combination of dedicated hardware and computer instructions.

[0133] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0134] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or page components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0135] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0136] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0137] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program code.

[0138] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0139] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a device claim may also be implemented by a single unit or device through software or hardware. Terms such as "first" and "second" are used to indicate names and do not imply any particular order.

Claims

1. A filtration system based on carbon and bacterial regulation to improve the denitrification efficiency of denitrification filter, characterized in that: include: Water inlet and outlet structure, filtration structure, carbon bacteria intelligent dosing structure and monitoring structure; The water inlet and outlet structure includes a sewage inlet pipe; one end of the sewage inlet pipe is connected to the filter structure for inputting the sewage to be treated into the filter structure; The filtering structure is used for denitrification of the wastewater to be treated; The filtering structure includes a filter tank; The carbon bacteria intelligent dosing structure includes a carbon bacteria control unit, a carbon bacteria delivery pump, a carbon bacteria incubator, a sixth valve, and a carbon bacteria delivery pipe; the carbon bacteria incubator, the carbon bacteria delivery pump, the sixth valve, and the carbon bacteria delivery pipe are connected in sequence, and the carbon bacteria control unit and the carbon bacteria delivery pump are electrically connected, so that when the sixth valve is opened, the carbon bacteria control unit controls the carbon bacteria delivery pump according to the optimal carbon bacteria dosage to deliver the bacteria and carbon in the carbon bacteria incubator through the carbon bacteria delivery pipe provided with uniformly distributed carbon bacteria spray holes into the filter tank; the carbon bacteria delivery pipe includes a first pipe section extending in a direction away from the ground; the carbon bacteria spray holes are provided on the first pipe section; a plurality of the carbon bacteria spray holes are arranged at intervals in a direction away from the ground; the first pipe section is arranged in the filter tank; the end of the first pipe section away from the ground receives the bacteria and carbon input by the carbon bacteria delivery pump; Wherein, under the first preset condition, the monitoring structure is configured to obtain first monitoring data; the first monitoring data includes influent chemical oxygen demand, ammonia nitrogen content, nitrate nitrogen content, nitrite nitrogen content, first total phosphorus content, first suspended solids content, first pH, dissolved oxygen content, temperature and first redox potential; the first monitoring data is sequentially subjected to data cleaning, data integration, data reduction and data transformation to obtain influent monitoring data; the influent monitoring data is input into the dosage prediction model to obtain dosage prediction; the dosage prediction includes external carbon source dosage prediction and autotrophic denitrifying bacteria dosage prediction; the external carbon source dosage prediction and the autotrophic denitrifying bacteria dosage prediction are feedforward controlled; under the second preset condition In this case, the monitoring structure is further configured to obtain second monitoring data; the second monitoring data includes effluent chemical oxygen demand, total nitrogen content, a second total phosphorus content, a second suspended solids content, a second pH value and a second redox potential; the second monitoring data are sequentially subjected to data cleaning, data integration, data reduction and data transformation to obtain effluent monitoring data; the effluent monitoring data is input into an adjustment prediction model to obtain an adjusted predicted amount; the adjusted predicted amount includes an external carbon source addition adjustment predicted amount and an autotrophic denitrifying bacteria addition adjustment predicted amount; feedback control is performed on the external carbon source addition adjustment predicted amount and the autotrophic denitrifying bacteria addition adjustment predicted amount; the addition predicted amount is adjusted according to the adjusted predicted amount to obtain the optimal carbon bacteria addition amount.

2. The filtration system for improving denitrification efficiency of denitrification filter based on carbon and bacteria regulation according to claim 1 is characterized in that: The carbon bacteria conveying pipe also includes a first annular pipe section, a second annular pipe section and a first bent pipe; The first annular pipe segment is connected to the first ends of the plurality of first pipe segments; the first annular pipe segment is connected to the carbon bacteria delivery pump through the first bent pipe; The second annular pipe segment is in communication with the second ends of the plurality of first pipe segments close to the ground; The first annular pipe segment and the second annular pipe segment are both rectangular; the number of the first pipe segments is four, and they are respectively located at the vertices of the rectangles.

3. The filtration system for improving denitrification efficiency of denitrification filter based on carbon and bacteria regulation according to claim 1 or 2, characterized in that: Also includes: Backwash structure and backwash structure; The backwash structure includes a backwash air compressor, an air delivery pipe, a backwash pump, a fourth valve, and a fifth valve; the fourth valve is connected to the backwash pump and is used to turn the backwash pump on or off; the fifth valve is connected to the air delivery pipe and is used to turn the air delivery pipe on or off; the backwash air compressor, the air delivery pipe, and the filter tank are connected in sequence; Backwash structure, including carbon bacteria backwash pipe and seventh valve; The water inlet and outlet structure also includes a water outlet pipe, a clean water tank, a second valve and a third valve; the air-water chamber of the filter tank, the second valve, the third valve, the clean water tank, and the water outlet pipe are connected in sequence; the carbon bacteria backwash pipe is connected to the seventh valve and the water outlet pipe; The third valve and the fourth valve are connected in parallel; When the second valve and the third valve are closed and the fourth valve and the fifth valve are opened, the backwash pump and the backwash air compressor are started; and when the seventh valve is opened regularly, the carbon bacteria backwash pipe is combined with the air delivery pipe to achieve air-water flushing and cleaning of the filter structure.

4. The filtration system for improving denitrification efficiency of denitrification filter based on carbon and bacteria regulation according to claim 3 is characterized in that: The filtering structure further comprises a pyrite filler and a pebble supporting layer; the pyrite filler is arranged on the pebble supporting layer; the pyrite filler and the pebble supporting layer are both located on the air-water chamber of the filter tank.

5. The filtration system for improving denitrification efficiency of denitrification filter based on carbon and bacteria regulation according to claim 2 is characterized in that: The carbon bacteria intelligent dosing structure also includes a scrubbing hole and an anti-falling cover. The carbon bacteria transport pipe also includes a second pipe section arranged on the first annular pipe section and connected to both the first annular pipe section and the first pipe section; the second pipe section extends in a direction away from the ground; the scrubbing hole and the anti-falling cover are provided at one end of the second pipe section away from the ground; the anti-falling cover is detachably arranged on the second pipe section and covers the scrubbing hole.

6. A filtration method for improving the denitrification efficiency of a denitrification filter based on carbon and bacterial regulation, characterized in that: include: Under the first preset condition, first monitoring data is obtained; the first monitoring data includes influent chemical oxygen demand, ammonia nitrogen content, nitrate nitrogen content, nitrite nitrogen content, a first total phosphorus content, a first suspended solids content, a first pH value, a dissolved oxygen content, a temperature, and a first redox potential; Performing data cleaning, data integration, data reduction, and data transformation on the first monitoring data in sequence to obtain water inflow monitoring data; Inputting the influent monitoring data into a dosage prediction model to obtain a dosage prediction amount; the dosage prediction amount includes an external carbon source dosage prediction amount and an autotrophic denitrifying bacteria dosage prediction amount; and performing feedforward control on the external carbon source dosage prediction amount and the autotrophic denitrifying bacteria dosage prediction amount; Under the second preset condition, second monitoring data is obtained; the second monitoring data includes effluent chemical oxygen demand, total nitrogen content, a second total phosphorus content, a second suspended solids content, a second pH value, and a second redox potential; Performing data cleaning, data integration, data reduction, and data transformation on the second monitoring data in sequence to obtain water outlet monitoring data; Inputting the effluent monitoring data into an adjustment prediction model to obtain an adjustment prediction amount; the adjustment prediction amount includes an external carbon source addition adjustment prediction amount and an autotrophic denitrifying bacteria addition adjustment prediction amount; performing feedback control on the external carbon source addition adjustment prediction amount and the autotrophic denitrifying bacteria addition adjustment prediction amount; According to the adjusted predicted amount, the predicted amount of addition is adjusted to obtain an optimal carbon bacteria addition amount, so that the filtration system for improving the denitrification efficiency of the denitrification filter based on carbon and bacteria regulation feeds carbon and bacteria into the filter according to the optimal carbon bacteria addition amount through a carbon bacteria delivery pipe provided with evenly distributed carbon bacteria spray holes; The carbon bacteria conveying pipe includes a first pipe section extending in a direction away from the ground; the carbon bacteria spray holes are provided on the first pipe section; and a plurality of the carbon bacteria spray holes are arranged at intervals in a direction away from the ground.

7. The filtration method for improving denitrification efficiency of a denitrification filter based on carbon and bacterial regulation according to claim 1, characterized in that: The dosage prediction model is built based on a deep learning model and includes a first input layer, a first intermediate hidden layer and a first output layer; Among them, the first input layer includes a fully connected layer for processing preprocessed water inlet monitoring data; the first intermediate hidden layer includes seven long short-term memory network layers; the long short-term memory network layer includes long short-term memory network neurons; the long short-term memory network neurons include a forgetting gate, an input gate and an output gate; the first output layer includes a regression layer; the regression layer uses the logistic function as the activation function.

8. The filtration method for improving denitrification efficiency of a denitrification filter based on carbon and bacterial regulation according to claim 1 or 2, characterized in that: The adjustment prediction model is built based on a deep learning model and includes a second input layer, a second intermediate hidden layer, and a second output layer; Among them, the second input layer includes a fully connected layer for processing the preprocessed water outlet monitoring data; the second intermediate hidden layer includes five long short-term memory network layers; the long short-term memory network layer includes long short-term memory network neurons; the long short-term memory network neurons include a forget gate, an input gate and an output gate; the second output layer includes a regression layer; the regression layer uses the logistic function as the activation function.

9. A filtration system based on carbon and bacterial regulation to improve the denitrification efficiency of denitrification filter, characterized in that: include: at least one processor; a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 6 to 8.

10. A computer-readable medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the method according to any one of claims 6 to 8.

Images