A decentralized sewage rapid infiltration treatment system and method based on digital AI processing

Abstract

The present application belongs to the technical field of sludge treatment, and discloses a distributed sewage rapid infiltration treatment system and method based on digital AI processing. The method realizes real-time monitoring of sewage discharge conditions through a remote monitoring system and a sensor information processing system; the digital twin model is used to monitor and predict the infiltration of sludge; the sewage treatment and infiltration conditions are evaluated according to the region, and the sewage discharge of different regions is adjusted according to the actual conditions. The present application uses digital AI to process images, combines sewage flow and concentration detection data, and predicts the service life of the infiltration material through digital twin processing technology, so that the infiltration material can be replaced at the best maintenance time. At the same time, the virtual reality of the infiltration rate of the infiltration material is calculated in blocks, the sewage discharge in different regions is controlled, the infiltration material is uniformly infiltrated, and the material utilization rate is improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of sludge treatment, and particularly relates to a decentralized sewage quick infiltration treatment system and method based on digital AI processing. BACKGROUND

[0002] The artificial quick infiltration treatment system is a method for treating sewage by using ordinary activated sludge method, has small one-time investment, and has the advantages of local sewage collection and reuse after treatment, reduced pipe network laying cost, and greatly improved sewage treatment efficiency. However, this treatment process is prone to clogging after being used for a period of time, which affects the sewage treatment effect. The reason is that the artificial quick infiltration treatment system uses natural medium with good permeability as the main filtration material instead of natural soil layer. The natural river sand filled artificially and mixed with a certain amount of special filler is used, and since there is a filtration link, clogging is inevitable.

[0003] Since the flow and concentration of sewage are constantly changing, it is difficult to maintain the filtration material at a certain time, and if the maintenance is late, clogging may occur, and if the maintenance is early, the cost is wasted. Moreover, the concentration and composition of sewage are constantly changing, which may cause uneven penetration of the filtration material in a wide area, resulting in waste of the filtration material after maintenance. SUMMARY

[0004] To overcome the problems in the related art, the application discloses a decentralized sewage quick infiltration treatment system and method based on digital AI processing.

[0005] The technical solution is as follows: a decentralized sewage quick infiltration treatment method based on digital AI processing, comprising:

[0006] S1, collecting sewage data through an input and output device, the sewage data including color, odor, pH value, total organic carbon TOC, total nitrogen TN, and total phosphorus TP parameters of the sewage, and performing data cleaning and preprocessing to remove invalid data and noise; judging the sewage quantity and type through video image processing;

[0007] S2, monitoring the sewage discharge condition in real time through a remote monitoring system and a sensor information processing system;

[0008] S3, monitoring and predicting the penetration condition of the sludge through a digital twin model, wherein the penetration condition includes penetration rate, material life, and concentration adjustment;

[0009] S4, evaluating the sewage treatment and penetration condition according to the region, and adjusting the sewage discharge quantity of different regions according to the prediction result of the digital twin model and the actual condition.

[0010] In step S2, the sewage discharge situation is monitored in real time by the remote monitoring system and the sensor information processing system, including: extracting features related to the treatment target from the collected sewage data, the features related to the treatment target including: the type, concentration and trend of pollutants;

[0011] The sensor information processing system monitors sewage data and the operating state of each device in real time, feeds the data back to the digital AI processor, and adjusts and optimizes the treatment process.

[0012] In step S3, the permeation of sludge is monitored and predicted by the digital twin model, including: the digital AI processor acquires the optimal digital twin model for the current sewage according to the extracted features and the preset treatment strategy, thereby predicting the operation of the entire system and determining the key maintenance points of the system operation; the preset treatment strategy includes: dilution or concentration comparison strategy, equal replacement strategy, pretreatment and staged treatment strategy, and flow regulation strategy; the digital AI processes the image, combines sewage flow and concentration detection data, and predicts the service life of the infiltration material through digital twin processing technology, so that the infiltration material is replaced at the best maintenance time; the digital twin model includes: using physical models, sensor updates, and operation history data for multidisciplinary, multi-physical quantity, multi-scale, and multi-probability simulation.

[0013] Further, the digital AI processing of the image includes analyzing the color concentration change of the filter material;

[0014] The digital twin processing technology includes material property analysis, environmental condition consideration, historical data analysis, failure mode and effect analysis (FMEA).

[0015] In step S4, the sewage discharge amount of different regions is adjusted according to the prediction results of the digital twin model combined with the actual situation, including:

[0016] The control unit automatically controls each device of the sewage treatment process according to the treatment strategy formulated by the digital AI processor, including the on-off of the pump, the on-off of the filter, the temperature and aeration amount of the bioreactor; through the processing of the data of the digital twin model, the virtual reality of the permeability of the infiltration material is calculated in blocks, and the discharge amount of sewage in different regions is controlled, so that the infiltration material is uniformly infiltrated;

[0017] The virtual reality of the permeability of the infiltration material is calculated in blocks, including:

[0018] Three-dimensional modeling of filter material: using virtual reality technology, creating a three-dimensional model and a physical model of the filter material, capturing the complex microstructure and pore geometry of the three-dimensional model and the physical model; establishing basic information for simulating fluid flow and permeability;

[0019] Permeability simulation: Using advanced computational fluid dynamics (CFD) software three-dimensional models for simulating how fluids pass through filtration media, simulating the flow of liquids or gases through the complex microstructure and pore geometry of filtration materials;

[0020] Material property analysis: Using virtual reality simulation to analyze the effects of different material properties, including porosity, fiber diameter, and tortuosity, on the permeability of filtration media;

[0021] Comparison of virtual reality and reality: Comparing the results of virtual reality simulation with real-world experiments to verify the accuracy of the simulation;

[0022] Predictive analysis: For manufacturers to understand the behavior of filtration materials under different conditions before physical manufacturing and testing; according to the images detected on site, as well as the image resolution, the actual area and shape of the site, the location and terrain of the discharge outlet, the discharge amount of sewage in different areas is controlled by dividing into equal or unequal blocks.

[0023] Further, in the material property analysis, using virtual reality simulation to analyze the effects of different material properties on the permeability of filtration media includes:

[0024] First, in the permeability influence execution cycle of the filtration medium, the single different material property factor influence result and the filtration medium permeability influence result of each different area are obtained, the single different material property factor influence result is represented as the demand of the filtration medium for each material property, specifically the demand of the filtration medium for porosity, fiber diameter, and tortuosity, and the filtration medium permeability influence result is represented as the permeability limit value of the permeability influence of the filtration medium in different areas and dynamic adaptive permeability variance threshold ; dynamic adaptive permeability variance threshold , representing the intention of the material to influence the permeability of the filtration medium;

[0025] Dynamic adaptive permeability variance threshold changes dynamically with the change of material permeation, and the threshold decreases when the overall material permeation is high, and the threshold increases when the overall material permeation is low, which is represented as follows:

[0026] ;

[0027] wherein, is the decay rate of the control function, is the average permeability of the current different area and its adjacent area, is a constant to prevent from decaying to zero, causing the material permeation to be completely the same, representing the maximum tolerance of the material to the uneven permeation, reflecting the permeability influence result of the filtration medium;

[0028] In the second step, each different region detects its own penetration state and exchanges information with adjacent different regions. Each different region compares its own penetration rate with the penetration rate limit value of the filter medium, and calculates the penetration rate variance of each different region and adjacent regions according to the penetration variance function. with the penetration rate limit value of the filter medium In the second step, each different region detects its own penetration state and exchanges information with adjacent different regions. Each different region compares its own penetration rate with the penetration rate limit value of the filter medium, and calculates the penetration rate variance of each different region and adjacent regions according to the penetration variance function. When the penetration rate of a certain different region and the penetration influence process of the filter medium is triggered.

[0029] The expression of the penetration variance function is as follows:

[0030] ;

[0031] In the expression, the penetration rate of the current different region and its adjacent regions is , and the total number of the current different region and its adjacent regions is .

[0032] In the third step, the overload different region is the source different region, the target different region is selected from the adjacent regions of the source different region, and the penetration rate of the adjacent region of the source different region is used as the target different region. The target different region is prioritized according to the size of the target different region penetration rate good effect occupancy rate.

[0033] In the fourth step, the source different region selects the target different region in turn according to the priority, filters the filter medium switched to the selected target different region, and performs penetration update. The switched filter medium includes the filter medium with replaced and adjusted porosity, fiber diameter and tortuosity.

[0034] In the fifth step, the penetration influence of the filter medium is ended when the penetration rate of the source different region or all target different regions are updated, and the penetration influence process of the filter medium is ended. Otherwise, return to the fourth step to select the next target different region for penetration update according to the priority of the target different region.

[0035] In the second step, each different region detects its own penetration state and exchanges information with adjacent different regions. Each different region obtains the current penetration rate good effect occupancy rate through the three-dimensional model and the physical model, calculates the filter medium utility of each filter medium in the different region according to the filter medium utility function formula, calculates the average filter medium experience as the average filter medium experience, calculates the penetration state according to the filter medium utilization rate and the average penetration rate of the filter medium, and exchanges penetration information with the three-dimensional model and the physical model of the adjacent different regions through the X2 interface between the three-dimensional model and the physical model.

[0036] ​The filter medium utility function formula is expressed as:

[0037] ;

[0038] In the formula, is the filter medium utility function, are respectively the current penetration resistance value of the filter medium and the maximum penetration resistance value that meets the current service capability of the filter medium, are respectively the current rate of the filter medium and the minimum rate required by the current service of the filter medium, is the utility function for different material properties, and is expressed as follows:

[0039] ;

[0040] In the formula, are respectively the material state value and the filter medium demand value, are respectively the threshold parameter and the scaling parameter set to make the value range of the function in and satisfy when .

[0041] In the fourth step, the screening switches the filter medium of the selected target different area, comprising:

[0042] (1) selecting the filter medium in the source different area that can be switched to the selected target different area as a switchable filter medium set, and calculating the utility of each filter medium in the switchable filter medium set to the material according to the material utility function formula;

[0043] (2) calculating the penetration influence utility value of each filter medium in the switchable filter medium set according to the penetration influence utility function formula of the filter medium, and prioritizing the filter medium according to the penetration influence utility value of the filter medium, and the source different area selects the filter medium to be switched in turn according to the priority;

[0044] The material utility function formula is expressed as:

[0045] ;

[0046] In the formula, is the filter medium in the switchable filter medium set, are respectively the penetration rate of the filter medium to the source different area and the target different area, are respectively the change amount of the material utility function of the filter medium to the source different area and the target different area when the filter medium is switched, and are expressed as follows:

[0047] ;

[0048] In the formula, current permeability of different regions, adaptive permeability variance threshold in switching under current permeability of different regions, utility function of permeability size to material, the expression is:

[0049] ;

[0050] In the formula, permeability size, respectively, the threshold values of the set light and heavy penetration, indicating that when the different regions are in the light penetration state, the less the filter medium is received, the lower the utilization rate is, and the utility is 0; when the different regions are in the heavy penetration state, the filter medium has a positive impact on the different regions material, so the utility is 1; when the different regions are in the medium penetration, with the increase of the permeability, the utility obtained by the different regions receiving the filter medium is higher, the heavy penetration different region tends to switch the filter medium with large permeability to obtain greater utility gain, and the target different region tends to receive the filter medium with large permeability; the permeability influence function formula of the filter medium is represented by an adaptive dynamic function which is continuously adjusted according to the permeability influence result of the filter medium and the single different material attribute factor influence result:

[0051] ;

[0052] In the formula, respectively, the source different region and the selected target different region, filter medium, permeability influence function of filter medium, permeability influence function of the switchable filter medium set, permeability influence function of filter medium in ideal state, permeability influence function of the source different region, permeability influence function of the selected target different region, filter medium in the switchable filter medium set, respectively, the current penetration resistance value of the filter medium and the maximum penetration resistance value that can be received by the current service of the filter medium, respectively, the current rate of the filter medium and the minimum rate required by the current service of the filter medium.

[0053] Another object of the present application is to provide a decentralized sewage fast infiltration treatment system based on digital AI processing, which implements the decentralized sewage fast infiltration treatment method based on digital AI processing, and the system comprises:

[0054] A digital AI processor is used to process and analyze sewage data, receive signals from sensors in the sensor information processing system (5), and calculate the best processing strategy based on the sensor signal data.

[0055] A control unit is connected to the digital AI processor and automatically controls the sewage treatment process according to the instructions of the AI processor.

[0056] Input and output devices, including cameras and water quality detectors for collecting sewage data, including sewage color, odor, pH value; output devices including display screen, printer or data interface, to display the processing results, or store the data;

[0057] Filtering devices and percolation devices, including physical filters and chemical filters, for separating solid impurities and harmful substances in sewage;

[0058] Sensor information processing system for monitoring sewage data and the running state of each device;

[0059] Remote monitoring system for transmitting data and status of sewage treatment system to remote monitoring center through wireless materials;

[0060] Energy consumption control system for managing and optimizing the energy consumption of the sewage treatment system.

[0061] Further, the control unit automatically controls the sewage treatment process, including controlling the on-off of each device, controlling the speed of the pump, and controlling the operation of the filter;

[0062] In the filtering device and percolation device, the chemical filter is used to remove harmful heavy metal ions;

[0063] In the sensor information processing system, the water level sensor monitors the height of the sewage, and the dissolved oxygen sensor detects the oxygen content in the sewage. These data, together with the digital AI processor, constitute a real-time monitoring and feedback control system for the sewage treatment process;

[0064] The remote monitoring system obtains the active sludge permeability and the service life prediction data of the active sludge through video images, transmission lines and storage systems.

[0065] The energy consumption control system accesses solar and wind renewable energy systems, and automatically switches between renewable energy and conventional energy power supply according to the sewage treatment system.

[0066] In combination with all the above technical solutions, the application has the beneficial effects that the application provides a distributed sewage rapid infiltration treatment system and method based on digital AI processing, uses digital AI to process images, combines sewage flow and concentration detection data, and predicts the service life of the infiltration material through digital twin processing technology, so that the infiltration material is replaced at the optimal maintenance time. At the same time, the virtual reality of the infiltration material permeability is calculated by block, the discharge amount of the sewage in different areas is controlled, the infiltration material is uniformly infiltrated, and the material utilization rate is improved. The application predicts and processes data through the digital twin model, obtains the optimal discharge scheme, and improves the service life of the system. BRIEF DESCRIPTION OF DRAWINGS

[0067] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and serve to explain the principles of the present disclosure, together with the description;

[0068] Figure 1 is a schematic diagram of a distributed sewage rapid infiltration treatment system based on digital AI processing provided by the embodiments of the application;

[0069] Figure 2 is a flow chart of a distributed sewage rapid infiltration treatment method based on digital AI processing provided by the embodiments of the application;

[0070] In the figure: 1, digital AI processor; 2, control unit; 3, input and output device; 4, filtration device and infiltration device; 5, sensor information processing system; 6, remote monitoring system; 7, energy consumption control system. DETAILED DESCRIPTION

[0071] In order to make the above-mentioned purposes, features and advantages of the application more obvious and easy to understand, the specific embodiments of the application will be described in detail below in combination with the drawings. In the following description, a large number of specific details are set forth in order to facilitate a full understanding of the application. However, the application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the spirit of the application, so the application is not limited by the specific implementation disclosed below.

[0072] The innovation of the present application lies in that the present application realizes real-time monitoring of sewage discharge conditions through a remote monitoring system and a sensor information processing system; through a digital twin model, the system adopts an advanced artificial intelligence algorithm to realize real-time monitoring and optimization of various parameters in the sewage treatment process and to monitor and predict the permeation of sludge, thereby improving the treatment efficiency and water quality. The digital AI is used to process images, combined with sewage flow and concentration detection data, to predict the service life of the infiltration material through digital twin processing technology, so that the infiltration material is replaced at the optimal maintenance time. At the same time, the permeability of the infiltration material is calculated by block, the discharge of sewage in different areas is controlled, the infiltration material is uniformly infiltrated, and the material utilization rate is improved. The new decentralized sewage treatment method realizes intelligentization, high efficiency, and self-adaptation to different treatment requirements.

[0073] As shown in Embodiment 1, Figure 1 The decentralized sewage quick infiltration treatment system based on digital AI processing provided by the embodiment of the present application comprises:

[0074] a digital AI processor 1, a control unit 2, an input and output device 3, a filtering device and an infiltration device 4, a sensor information processing system 5, a remote monitoring system 6, and an energy consumption control system 7.

[0075] The digital AI processor 1 is a designed hardware and software system for processing and analyzing a large amount of sewage data. The digital AI processor 1 receives signals from various sensors in the sensor information processing system 5, such as water quality sensors, flow sensors, etc., and calculates the best treatment strategy according to these data. The digital AI processor 1 learns and continuously optimizes its processing algorithm to provide more efficient and accurate sewage treatment.

[0076] The control unit 2 is a hardware device connected with the digital AI processor 1, and the function of the control unit 2 is to automatically control the process of sewage treatment according to the instructions of the AI processor, including controlling the on-off of each device, controlling the speed of the pump, controlling the operation of the filter, etc.

[0077] The input and output device 3 includes input devices such as cameras, water quality detectors, etc. for collecting sewage data such as color, odor, pH value, etc. of sewage. The output device can be a display screen, a printer or a data interface, and the input and output device 3 displays the processing results to the operator or stores the data for subsequent analysis and optimization.

[0078] Filtering device and percolation device 4: including physical filter and chemical filter, used for separating solid impurities and harmful substances in sewage. The physical filter such as filter screen can filter out large impurities; the chemical filter can remove some harmful chemical substances such as heavy metal ions and the like. Microorganisms can decompose organic matter in sewage. This process can further reduce the pollution degree of sewage. Generally, a percolation field or a percolation tank is used to further infiltrate the sewage treated by the biological reactor into the soil. In this process, some nutrients in the sewage can be absorbed by the soil, and at the same time, the water in the sewage can also be purified by the soil.

[0079] Sensor information processing system 5: used for monitoring sewage data and the running state of each device. For example, the water level sensor can monitor the height of the sewage, and the dissolved oxygen sensor can detect the oxygen content in the sewage. These data together with the digital AI processor constitute a real-time monitoring and feedback control system for the sewage treatment process. In the embodiment of the present application, the sensors are water level sensors, dissolved oxygen sensors, temperature sensors, humidity sensors, volume sensors, etc. Common sensors on the market are used to transmit signals through electronic signals, materials, RS23, RS485 and other communication protocols.

[0080] Remote monitoring system 6: transmits the data and state of the sewage treatment system to the remote monitoring center through wireless materials. The operator can monitor the running state of the sewage treatment system in real time at the remote monitoring center, so as to discover and solve problems in time.

[0081] The remote monitoring system 6 is mainly a video image, a transmission line, and a storage system. The video image is analyzed by AI image analysis to obtain the permeability of the activated sludge, so as to obtain the service life prediction data of the activated sludge.

[0082] Energy consumption control system 7: the system is used for managing and optimizing the energy consumption of the sewage treatment system. It can access renewable energy systems such as solar energy and wind energy, and automatically switch to use renewable energy or conventional energy power supply according to the needs of the sewage treatment system, so as to reduce the operation cost and improve the sustainability of the system.

[0083] Embodiment 2, as shown in Figure 2 The distributed sewage rapid infiltration treatment method based on digital AI processing provided by the embodiment of the present application comprises:

[0084] S1, collecting sewage data through input and output devices, the sewage data including: color, odor, pH value, total organic carbon TOC, total nitrogen TN, total phosphorus TP parameters of sewage, and performing data cleaning and preprocessing to remove invalid data and noise; judging the amount and type of sewage through video image processing;

[0085] S2, real-time monitoring of sewage discharge conditions through a remote monitoring system and a sensor information processing system;

[0086] S3, monitoring and predicting the permeation of sludge through a digital twin model, wherein the permeation includes permeation rate, material life, and concentration adjustment;

[0087] S4, assessing sewage treatment and permeation according to regions, and adjusting sewage discharge in different regions according to the prediction results of the digital twin model and actual conditions.

[0088] In step S1, real-time monitoring of sewage discharge conditions through a remote monitoring system and a sensor information processing system includes extracting features related to treatment targets from collected sewage data, wherein the features related to treatment targets include types, concentrations, and trends of pollutants;

[0089] The sensor information processing system monitors sewage data and the operating status of each device in real time, feeds the data back to a digital AI processor, and adjusts and optimizes the treatment process.

[0090] In step S2, the digital twin model includes using physical models, sensor updates, and operating history data to simulate multidisciplinary, multi-physical, multi-scale, and multi-probability.

[0091] The monitoring and prediction of sludge permeation through the digital twin model include:

[0092] The digital AI processor obtains the optimal digital twin model for the current sewage according to the extracted features and the preset treatment strategy, thereby predicting the operation of the entire system and determining the key maintenance points of the system operation; the preset treatment strategy includes dilution or concentration comparison strategy, equal replacement strategy, pretreatment and staged treatment strategy, and flow regulation strategy.

[0093] The digital AI is used to process images, combined with sewage flow and concentration detection data, to predict the service life of the permeable material through digital twin processing technology, so that the permeable material is replaced at the optimal maintenance time;

[0094] It can be understood that the core advantage of the present application is to improve the utilization rate of materials and reduce the replacement cycle times. Due to the differences in sewage concentration, flow and the like, the penetration on the whole filter material is uneven, so that the use of the filter material exists insufficient condition, and the early replacement will cause the waste of materials, and the late replacement will cause the imperfect use, so that the replacement of the filter material is predicted by combining prediction with data measurement, and the processing method of the digital AI twin model is more economical and environmental. Backwashing is worth using a filter membrane for a membrane bioreactor and the like, and the present application is a treatment of ordinary activated sludge method, that is, the most basic and common way, mainly applied in towns and cities.

[0095] In the embodiment of the present application, the digital AI processes the image, including analyzing the color concentration change of the filter material;

[0096] The digital twin processing technology includes material property analysis, environmental condition consideration, historical data analysis, failure mode and effect analysis FMEA.

[0097] In step S3, the sewage treatment and penetration are evaluated according to the region, and the sewage discharge of different regions is adjusted according to the actual situation, including:

[0098] The control unit automatically controls each device of the sewage treatment process according to the treatment strategy formulated by the digital AI processor, including the on-off of the pump, the on-off of the filter, the temperature and the aeration amount of the bioreactor;

[0099] At the same time, through the data processing of the digital twin model, the virtual reality of the infiltration material permeability is calculated in blocks, the sewage discharge in different regions is controlled, and the infiltration material is uniformly penetrated.

[0100] The virtual reality of the infiltration material permeability is calculated in blocks, including:

[0101] Three-dimensional modeling of filter material: using virtual reality technology, creating a three-dimensional model and physical model of the filter material, accurately capturing its complex microstructure and pore geometry; establishing accurate basic information for simulating fluid flow and permeability;

[0102] Permeability simulation: then using a three-dimensional model of advanced computational fluid dynamics CFD software to simulate how fluid passes through the filter medium, simulating the flow of liquid or gas through the complex microstructure and pore geometry of the filter material;

[0103] Material property analysis: using virtual reality simulation to help analyze the influence of different material properties, such as porosity, fiber diameter and tortuosity, on the permeability of the filter medium;

[0104] Reality vs. Virtuality: Comparing the results of virtual reality simulations to real-world experiments to validate the accuracy of the simulations;

[0105] Predictive Analysis: This simulation can be used for predictive analysis, helping manufacturers understand how filtration materials will behave under different conditions before physical manufacturing and testing; according to the images detected in the field, as well as the image resolution, the actual area and shape of the field, the location of the pollution outlet and the terrain, the area is divided into equal or unequal blocks to control the discharge of sewage in different areas.

[0106] In the embodiment of the present application, in the material property analysis, the influence of different material properties on the permeability of the filter medium is analyzed by virtual reality simulation, which includes:

[0107] First, in the permeability influence execution cycle of the filter medium, the influence result of each single different material property factor and the permeability influence result of the filter medium in each different area are obtained, the influence result of each single different material property factor is represented as the demand of the filter medium for each material property, specifically the demand of the filter medium for porosity, fiber diameter and tortuosity, and the permeability influence result of the filter medium is represented as the permeability limit value of the influence of the permeability of the filter medium in different areas and dynamic adaptive permeability variance threshold ; dynamic adaptive permeability variance threshold , which represents the intention of the material to influence the permeability of the filter medium;

[0108] dynamic adaptive permeability variance threshold dynamically changes with the change of material permeability, and the threshold decreases when the overall material permeability is high, and the threshold increases when the overall material permeability is low, which is represented as follows:

[0109] ;

[0110] In the formula, is the decay rate of the control function, is the average permeability of the current different area and its adjacent area, is a constant to prevent from decaying to zero, causing the material permeability to be completely the same, which represents the maximum tolerance of the material to the uneven permeability and reflects the permeability influence result of the filter medium;

[0111] Second, each different area detects its own permeation state and interacts with the adjacent different area, and each different area compares its own permeability with the permeability limit value of the filter medium , and at the same time calculates the permeability variance of each different area and its adjacent area according to the permeability variance function , when a certain different area and The permeability of the time-triggered filtering medium affects the process;

[0112] The expression of the permeability variance function is:

[0113] ;

[0114] In the formula, is the permeability of the current different area and its adjacent area, is the sum of the number of the current different area and its adjacent area;

[0115] In the third step, the overload different area is the source different area, the target different area is screened in the adjacent area of the source different area, and the permeability of the adjacent area of the target different area is selected as the target different area, and the target different area is prioritized according to the size of the target different area permeability good effect occupancy rate;

[0116] In the fourth step, the source different area selects the target different area in turn according to the priority, screens the filtering medium switched to the selected target different area, and performs permeation update; the switched filtering medium includes the filtering medium with replaced and adjusted porosity, fiber diameter and tortuosity;

[0117] In the fifth step, the permeability of the filtering medium is affected, and the process ends when the permeability of the source different area is less than or equal to the permeability of all target different areas, or all target different areas are permeated and updated. Otherwise, return to the fourth step to select the next target different area according to the target different area priority for permeation update.

[0118] In the second step, each different area detects its own permeation state and interacts with adjacent different areas, including: the three-dimensional model and the physical model of each different area obtain the current permeability good effect occupancy rate, calculate the filtering medium utility of each filtering medium in the different area according to the filtering medium utility function formula, calculate the filtering medium average experience as the filtering medium average permeability, calculate the permeation state according to the filtering medium utilization rate and the filtering medium average permeability, and interact with the three-dimensional model and the physical model of its adjacent different areas through the X2 interface between the three-dimensional model and the physical model to exchange permeation information;

[0119] The filtering medium utility function formula is:

[0120] ;

[0121] In the formula, is the filtering medium utility function, is the current permeation resistance value of the filtering medium and the maximum permeation resistance value that meets the current service of the filtering medium, respectively the current rate of the filter medium and the minimum rate required to meet the current service of the filter medium, The utility function for different material properties is expressed as follows:

[0122] ;

[0123] In the formula, respectively the material state value and the filter medium demand value, respectively the threshold parameter and the scaling parameter set to make the value range of the function and when satisfy .

[0124] In the fourth step, the screening switches the filter medium of the selected target different area, comprising:

[0125] (1) selecting the filter medium in the source different area that can be switched to the selected target different area as a switchable filter medium set, and calculating the utility of each filter medium in the switchable filter medium set to the material according to the material utility function formula;

[0126] (2) calculating the permeability influence utility value of each filter medium in the switchable filter medium set according to the permeability influence utility function formula of the filter medium, and prioritizing the filter medium according to the permeability influence utility value of the filter medium, and the source different area selects the filter medium to be switched in turn according to the priority;

[0127] The material utility function formula is expressed as:

[0128] ;

[0129] In the formula, is the filter medium in the switchable filter medium set, respectively the permeability of the filter medium to the source different area and the target different area, respectively the change amount of the material utility function of the source different area and the target different area when switching the filter medium, and are expressed as follows:

[0130] ;

[0131] In the formula, is the current permeability of the different area, is the self-adaptive permeability variance threshold when switching the current permeability of the different area, is the utility function of the permeability to the material, and the expression is:

[0132] ;

[0133] In the formula, wherein, respectively, are the set light and heavy permeability threshold values, indicating that when different areas are in a light permeability state, the less filter medium is received, the lower the utilization rate is, and the utility is 0; when different areas are in a heavy permeability state, the filter medium has a positive impact on different areas of materials, so the utility is 1; when different areas are in a medium permeability state, as the permeability increases, the utility obtained by different areas receiving the filter medium is higher, the heavy permeability different area tends to switch to the filter medium with large permeability to obtain greater utility gain, and the target different area tends to receive the filter medium with large permeability; the permeability influence function formula of the filter medium is represented as a self-adaptive dynamic function continuously adjusted according to the filter medium permeability influence result and the single different material attribute factor influence result:

[0134] ;

[0135] wherein, respectively, are the source different area and the selected target different area, is the filter medium, is the permeability influence function of the filter medium, is the permeability influence function of the switchable filter medium set, is the permeability influence function of the filter medium in an ideal state, is the permeability influence function of the source different area, is the permeability influence function of the selected target different area, is the filter medium in the switchable filter medium set, respectively, are the current permeability resistance value of the filter medium and the maximum permeability resistance value that can be received by the current service of the filter medium, respectively, are the current rate of the filter medium and the minimum rate required by the current service of the filter medium.

[0136] It can be understood that in the embodiments of the present application, the present application performs block calculation on the virtual reality technology of the filter material permeability, controls the discharge amount of sewage in different areas, makes the filter material uniformly permeate, and improves the material utilization rate. The present application avoids the blockage of part of the area caused by the traditional direct discharge method, which affects the service life of the whole material, and further improves the efficiency of sewage treatment. In the block calculation, the filter material is divided into smaller and more manageable blocks or areas for simulation, and the calculation method allows detailed analysis of the fluid flow in different areas of the filter material, making the simulation more accurate.

[0137] According to the images detected on site, and the image resolution, the actual area and shape on site, the position and terrain of the pollution outlet, the present application is divided into equal or unequal blocks, so as to help AI better analyze the permeability of each block.

[0138] In the embodiment of the present application, the prior art artificial rapid infiltration treatment system is mainly maintained through regular maintenance or according to the funding situation, which has low maintenance efficiency and high cost. Through the use of digital AI processing technology, the cost-effectiveness of the maintenance of the artificial rapid infiltration treatment system is improved, and the use cost of the whole set of filtration material in the whole life cycle is reduced.

[0139] From the above embodiment, it can be seen that the traditional sludge treatment has no treatment scheme, and only the filler is simply replaced on a regular basis, which causes the filtration material to be unable to be fully utilized, resulting in great waste. The present application can fully utilize the utilization rate of the whole filtration material, thereby reducing the maintenance frequency and improving the service life of the material.

[0140] According to the different concentrations and types of sewage, a preset treatment scheme can be established by using a digital twin model, thereby improving the adsorption utilization rate of the filtration material, reducing the replacement of the filtration material, and improving the utilization efficiency.

[0141] The digital twin model of the present application integrates sewage flow, type, filler type, thickness, biofilm adhesion rate, air temperature, weather conditions, and field data to form a simulation and prediction of reality, thereby effectively improving the capacity and application efficiency of the whole sludge treatment.

[0142] The distributed sewage rapid infiltration treatment system and method based on digital AI processing of the present application represent an innovative technology in the field of sewage treatment. This system uses advanced artificial intelligence algorithms to monitor and optimize various parameters in the sewage treatment process, thereby improving the treatment efficiency and water quality. Compared with traditional sewage treatment technologies, this system is more intelligent, efficient, and can adapt to different processing needs.

[0143] Traditional sludge treatment itself is a low-cost sewage treatment solution, so general monitoring and treatment schemes will result in large investment. However, improving the technical content of sludge treatment and saving filler usage has always been the development direction pursued by operation and management units. Therefore, the distributed sewage rapid infiltration treatment system and method based on digital AI processing only needs a high-definition image camera and processing software, as well as the original flow monitoring parameters of the sewage discharge system, to better improve the conversion efficiency of sludge treatment filler, save materials and maintenance period, and has good application value.

[0144] Existing digital twin technology is often applied to manufacturing and other scenarios that require a lot of assembly and combination, and is less applied in small scenarios. The present application realizes the application in a low-cost scenario.

[0145] In embodiment 3, as another embodiment of the present application, the distributed sewage rapid infiltration treatment method based on digital AI processing provided by the embodiment of the present application comprises:

[0146] The first step is data collection and preprocessing: sewage data such as color, odor, pH value, total organic carbon (TOC), total nitrogen (TN), total phosphorus (TP), etc. are collected through input and output devices, and data cleaning and preprocessing are performed to remove invalid data and noise. Or directly through video image processing, judge the amount and type of sewage.

[0147] The second step is feature extraction: from the collected sewage data, features related to the processing target are extracted, such as the type, concentration, and trend of pollutants. The sensor information processing system monitors the sewage data and the operating state of each device in real time, and feeds back the data to the digital AI processor to adjust and optimize the processing process.

[0148] The third step is to develop a processing strategy: the digital AI processor develops an optimal model for the current sewage based on the extracted features and the pre-set processing strategy, thereby predicting the operation of the entire system and determining the key maintenance points of the system operation.

[0149] The fourth step is to control the sewage treatment process: the control unit automatically controls the various devices of the sewage treatment process according to the processing strategy developed by the digital AI processor, such as the on-off of the pump, the on-off of the filter, the temperature and aeration of the bioreactor, etc. At the same time, through the processing of the data of the digital twin model, the permeability of the infiltration material is calculated in blocks, and the discharge of the sewage in different areas is controlled, so that the infiltration material is uniformly infiltrated, and the material utilization rate is improved.

[0150] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in a certain embodiment can be referred to the relevant description of other embodiments.

[0151] The information interaction, execution process, etc. between the above devices / units, since based on the same concept as the method embodiments of the present application, the specific functions and the technical effects brought about can be referred to the method embodiment part, which will not be repeated here.

[0152] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific name of each functional unit and module is only for the convenience of mutual distinction, and does not limit the protection scope of the present application. The specific working process of the unit and module in the above system can refer to the corresponding process in the foregoing method embodiment.

[0153] The embodiment of the present application further provides a computer device, which comprises at least one processor, a memory and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to realize the steps in any one of the above method embodiments.

[0154] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, wherein the computer program is executable on a processor to realize the steps in any one of the above method embodiments.

[0155] The embodiment of the present application further provides an information data processing terminal, which is used to realize the steps in any one of the above method embodiments when executed on an electronic device, and provides a filtering medium input interface.

[0156] The embodiment of the present application further provides a server, which is used to realize the steps in any one of the above method embodiments when executed on an electronic device.

[0157] The embodiment of the present application provides a computer program product, which, when executed on an electronic device, enables the electronic device to execute the steps in any one of the above method embodiments.

[0158] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on such understanding, the present application implements all or part of the processes in the above-mentioned embodiment methods, which can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of each method embodiment when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer-readable medium at least includes any entity or device capable of carrying the computer program code to the photographing device / terminal equipment, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, such as a U disk, mobile hard disk, magnetic disk or optical disk, etc.

[0159] To further illustrate the effects of the embodiments of the present application, the following experiments are performed.

[0160] To verify the advantages of the decentralized wastewater rapid infiltration treatment system based on digital AI processing in saving filler replacement time and reducing cost, the following experimental scheme can be designed:

[0161] Filler service life: control group (traditional system): the average service life of the filler is 12 months. Experimental group (AI system): the expected service life of the filler is increased to 18 months.

[0162] Filler replacement cost: control group: the cost of replacing the filler each time is 8000 yuan. Experimental group: due to the reduction in replacement frequency, the total replacement cost within two years is expected to be reduced to 6000 yuan.

[0163] Filler replacement frequency: control group: needs to be replaced once a year. Experimental group: replaced once every 18 months.

[0164] Water treatment efficiency: COD degradation rate: 85% for the control group and 88% for the experimental group. BOD removal rate: 80% for the control group and 83% for the experimental group.

[0165] Data application and analysis

[0166] Service life comparison: the service life of the filler in the experimental group is 50% longer than that in the control group.

[0167] Cost saving analysis: within two years, the experimental group saves 4000 US dollars in replacement cost compared with the control group.

[0168] Frequency reduction: The experimental group had one less filler replacement cycle than the control group.

[0169] Process efficiency improvement: Although the improvement is not significant, the experimental group has improved water treatment efficiency.

[0170] Through the experimental results, the advantages of the decentralized wastewater rapid infiltration treatment system based on digital AI processing in extending the service life of the filler and reducing the replacement cost can be evaluated. This will help to reduce the overall operating cost and improve the economic efficiency and sustainability of the system. At the same time, this experiment can also demonstrate the potential value of the AI system in improving the wastewater treatment efficiency and reducing the environmental impact.

[0171] The above is only a preferred specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any modification, equivalent replacement and improvement made by any person skilled in the art within the technical scope disclosed by the present application, as long as it is within the spirit and principles of the present application, should be covered within the protection scope of the present application.

Claims

1. A decentralized sewage rapid infiltration treatment method based on digital AI processing, characterized in that: The method includes: S1, collects sewage data through input and output devices, including: sewage color, odor, pH value, total organic carbon (TOC), total nitrogen (TN), and total phosphorus (TP) parameters, and performs data cleaning and preprocessing to remove invalid data and noise; and determines sewage volume and type through video image processing; S2, real-time monitoring of sewage discharge through remote monitoring system and sensor information processing system; S3, using a digital twin model to monitor and predict the permeability of sludge, including permeability, material life, and concentration adjustment; S4, assess the sewage treatment and infiltration situation by region, and adjust the sewage discharge volume in different regions based on the prediction results of the digital twin model and the actual situation; In step S2, the real-time monitoring of sewage discharge by the remote monitoring system and the sensor information processing system includes: extracting features related to the treatment target from the collected sewage data, wherein the features related to the treatment target include: type, concentration, and change trend of pollutants; The sensor information processing system monitors sewage data and the operating status of each device in real time, and feeds the data back to the digital AI processor to adjust and optimize the treatment process; In step S3, the digital twin model is used to monitor and predict the infiltration of sludge, including: the digital AI processor obtains the optimal digital twin model for the current sewage based on the extracted features and the preset treatment strategy, thereby predicting the operation of the entire system and determining the key maintenance points of the system operation; the preset treatment strategy includes: dilution or concentration comparison strategy, equal replacement strategy, pretreatment and graded treatment strategy, and flow regulation strategy; digital AI is used to process the image, combined with sewage flow and concentration detection data, and the life of the infiltration material is predicted through digital twin processing technology, so that the infiltration material can be replaced at the optimal maintenance time; the digital twin model includes: using physical models, sensor updates, and historical operation data to perform multi-disciplinary, multi-physical quantity, multi-scale, and multi-probability simulations; In step S4, the sewage discharge volume in different areas is adjusted according to the prediction results of the digital twin model and the actual situation, including: The control unit automatically controls various equipment in the sewage treatment process, including pump and filter power on / off, and the temperature and aeration volume of the bioreactor, based on the treatment strategy developed by the digital AI processor. By processing data from the digital twin model, the control unit performs block-by-block calculations of the permeability virtual reality of the infiltration material, controlling the discharge volume of sewage in different areas and ensuring uniform permeation of the infiltration material. The block calculation of the virtual reality of the permeability of the filtration material includes: 3D modeling of filter materials: Using virtual reality technology, create 3D and physical models of filter materials, capturing their complex microstructures and pore geometry; and establishing basic information for simulating fluid flow and permeability. Permeability simulation: Using advanced computational fluid dynamics (CFD) software, a three-dimensional model is used to simulate how fluid passes through the filter media, simulating the flow of liquid or gas through the complex microstructure and pore geometry of the filter material; Material property analysis: Virtual reality simulations are used to analyze the impact of different material properties, including porosity, fiber diameter, and tortuosity, on the permeability of the filter media. Reality vs. Virtuality: Comparing the results of VR simulations with real-world experiments to verify the accuracy of the simulations; Predictive analysis: used by manufacturers to understand the behavior of filter materials under different conditions before physical manufacturing and testing. Based on on-site inspection images, image resolution, actual site area and shape, and the location and topography of sewage outlets, the wastewater can be divided into equal or unequal blocks to control the discharge volume of sewage in different areas. In material property analysis, virtual reality simulation is used to analyze the impact of different material properties on the permeability of the filter medium, including: The first step is to obtain the influence results of each single material attribute factor and the influence results of the filter medium permeability in each different area during the permeability impact execution cycle of the filter medium. The influence results of each single material attribute factor are expressed as the requirements of the filter medium for various material properties, specifically the requirements of the filter medium for porosity, fiber diameter and tortuosity. The influence results of the filter medium permeability are expressed as the permeability limit values ​​of the filter medium in different areas. and dynamic adaptive permeability variance threshold ; Dynamic adaptive permeability variance threshold , represents the intention of the material’s effect on the permeability of the filter medium; Dynamic adaptive permeability variance threshold It changes dynamically with the change of material permeability. When the overall permeability of the material is high, the threshold value decreases, and when the overall permeability of the material is low, the threshold value increases, as shown below: ； Where, To control the decay rate of the function, is the average permeability of different areas and their neighboring areas at present, is a constant, preventing The decay to zero results in the same material penetration, which represents the maximum tolerance of the material to uneven penetration and reflects the impact of the filter medium permeability. In the second step, each area detects its own permeability status and exchanges information with adjacent areas. Each area will Permeability limit of the filter medium Compare and calculate the permeability variance of different areas and neighboring areas according to the permeability variance function , when a different area and The permeability influencing process of the filter medium is triggered; The expression of the penetration variance function is: ； Where, is the current permeability of different areas and their neighboring areas, is the sum of the number of current different areas and their neighboring areas; In the third step, different overload areas are source areas, and different target areas are selected from the neighboring areas of different source areas. The neighboring areas of the target area are taken as different target areas, and the target areas are prioritized according to the penetration rate, effect and occupancy rate of the target areas; In the fourth step, the source regions select target regions in order of priority, and filter media are switched to the selected target regions to perform infiltration renewal; the switched filter media include filter media with adjusted porosity, fiber diameter, and tortuosity; The fifth step is to determine the effect of the permeability of the filter medium on the final decision. Or if all target different areas have been updated for infiltration, the permeability impact process of the filter medium ends. Otherwise, return to step 4 and select the next target different area for infiltration update according to the priority of the target different areas.

2. The decentralized sewage rapid infiltration treatment method based on digital AI processing according to claim 1 is characterized in that: The digital AI processes the image by: analyzing the changes in color concentration of the filter material; The digital twin processing technology includes: material property analysis, environmental conditions consideration, historical data analysis, and failure mode and effect analysis FMEA.

3. The decentralized sewage rapid infiltration treatment method based on digital AI processing according to claim 1 is characterized in that: In the second step, each of the different regions detects its own permeability status and exchanges information with adjacent different regions, including: obtaining the current permeability excellent effect occupancy rate through the 3D model and physical model of each different region, calculating the filter medium utility of each filter medium in the different region according to the filter medium utility function formula, calculating the average filter medium utility as the average filter medium experience, calculating the permeability status based on the filter medium utilization rate and the average filter medium permeability, and exchanging permeability information with the 3D model and physical model of the adjacent different regions through the X2 interface between the 3D model and the physical model; The filter medium utility function formula is expressed as: ； Where, is the filter medium utility function, They are the current penetration resistance value of the filter medium and the maximum penetration resistance value that can be accepted by the filter medium at the current business. They are the current rate of the filter medium and the minimum rate required to meet the current business of the filter medium, is the utility function for different material properties, which is expressed as follows: ； Where, are the material status value and the filter medium requirement value respectively, In order to make the function range in He Dang Time Satisfaction The threshold and scaling parameters are set.

4. The decentralized sewage rapid infiltration treatment method based on digital AI processing according to claim 3 is characterized in that: In the fourth step, the filter medium is switched to the selected target different area, including: (1) Select the filter media in different source areas that can be switched to different target areas as the switchable filter media set, and calculate the utility of each filter medium in the switchable filter media set to the material according to the material utility function formula; (2) Calculate the permeability impact utility value of each filter medium in the set of switching filter media according to the permeability impact utility function formula of the filter medium, sort the filter media according to the permeability impact utility value of the filter medium, and select the filter medium to be switched in different source areas according to the priority; The material utility function formula is expressed as: ； Where, is a filter medium in a switchable filter medium set, are the permeability of the filter medium to different source areas and target areas, respectively. The changes in the material utility function of different source areas and target areas caused by switching the filter medium are expressed as follows: ； Where, is the current penetration rate in different regions, is the adaptive permeability variance threshold in switching under the current permeability of different regions, is the utility function of permeability on the material, and the expression is: ； Where, is the permeability, are the threshold values ​​set for light permeability and heavy permeability, respectively, indicating that when different areas are in a light permeability state, the less filter media they receive, the lower the utilization rate, and the utility is 0; when different areas are in a heavy permeability state, the filter media will have a positive impact on the materials in different areas, so the utility is 1; when different areas are in a medium permeability state, as the permeability increases, the utility obtained by different areas receiving the filter media increases. In heavy permeability, different areas tend to switch to filter media with high permeability to obtain greater utility gains, and target different areas tend to receive filter media with high permeability; the filter medium permeability influence function formula is an adaptive dynamic function that continuously adjusts according to the filter medium permeability influence results and the influence results of a single different material property factor: ； Where, They are different source regions and different selected target regions, As filter media, is the permeability influence function of the filter medium, is the permeability influence function of the switchable filter media set, is the permeability influence function of the filter medium under ideal conditions, is the permeability influence function under different source areas, is the permeability influence function under different regions of the selected target, is a filter medium in a switchable filter medium set, They are the current penetration resistance value of the filter medium and the maximum penetration resistance value that can be accepted by the filter medium at the current business. They are respectively the current rate of the filter medium and the minimum rate required to meet the current business of the filter medium.

5. A decentralized sewage rapid infiltration treatment system based on digital AI processing, characterized in that: The system implements the decentralized sewage rapid infiltration treatment method based on digital AI processing as described in any one of claims 1 to 4, and the system includes: A digital AI processor (1) is used to process and analyze sewage data, receive signals from various sensors in the sensor information processing system (5), and calculate the best treatment strategy based on the signal data of each sensor; A control unit (2) is connected to the digital AI processor (1) and automatically controls the sewage treatment process according to instructions of the AI ​​processor; Input and output devices (3), the input device includes a camera and a water quality detector for collecting sewage data, the sewage data including the color, odor, and pH value of the sewage; the output device includes a display screen, a printer or a data interface for displaying the processing results or storing the data; Filtration and percolation devices (4), including physical filters and chemical filters, for separating solid impurities and harmful substances from sewage; Sensor information processing system (5), used to monitor sewage data and the operating status of each device; A remote monitoring system (6) for transmitting data and status of the sewage treatment system to a remote monitoring center via wireless materials; Energy consumption control system (7) is used to manage and optimize the energy consumption of the sewage treatment system.

6. The decentralized sewage rapid infiltration treatment system based on digital AI processing according to claim 5 is characterized in that: In the control unit (2), the process of automatically controlling sewage treatment includes controlling the power on and off of various devices, controlling the speed of the pump, and controlling the operation of the filter; In the filtration and percolation devices (4), chemical filters are used to remove harmful heavy metal ions; In the sensor information processing system (5), the height of the sewage is monitored by the water level sensor, and the dissolved oxygen sensor detects the oxygen content in the sewage. These data, together with the digital AI processor, constitute a real-time monitoring and feedback control system for the sewage treatment process; The remote monitoring system (6) obtains the activated sludge permeability through video images, transmission lines, and storage systems, and obtains the service life prediction data of the activated sludge; The energy consumption control system (7) is connected to a solar energy and wind energy renewable energy system, and uses renewable energy or conventional energy for power supply according to the automatic switching of the sewage treatment system.

Images