AI-based secondary water supply energy-saving system and energy-saving method

Abstract

The invention discloses an AI-based secondary water supply energy-saving system and an energy-saving method, relates to the technical field of secondary water supply, and improves the energy efficiency of a water supply system through intelligent water pump control and pipe network monitoring. A partition monitoring device is installed, a real-time water pressure value, a flow value, an energy consumption value, a pipe network vibration strength value and water consumption behavior data of residents are collected, and the residents are divided into three grades of partitions in combination with water consumption habits. And a partition pressure optimization coefficient is calculated, and the operation state of the water pump is optimized in combination with a control strategy. And monitoring a water pump power disqualification condition, calculating a leakage coefficient, giving out an early warning, and proposing a repair strategy. And by combining the partition pressure optimization coefficient, the pipe network leakage coefficient and the resident water demand, the AI dynamic adjustment model automatically adjusts the power of the water pump, and automatically matches the water supply of each grade partition. The method effectively improves the energy-saving effect of the water supply system, ensures stable and reliable water supply, reduces energy consumption, and prolongs the service life of equipment.

Description

Technical Field

[0001] This invention relates to the field of secondary water supply technology, specifically to an AI-based energy-saving system and method for secondary water supply. Background Technology

[0002] With the acceleration of urbanization, the demand for water resources in modern high-rise residential communities continues to grow, posing a series of challenges to traditional water supply systems, especially secondary water supply systems in high-rise buildings. Pumps need to provide sufficiently high pressure to ensure water can be delivered smoothly to the top floors. However, the water pressure supplied to lower-floor residents is often much higher than the actual demand, requiring pressure regulation via pressure reducing valves. This single-pump water supply method not only wastes a significant amount of energy but also leads to low operating efficiency of the water supply system.

[0003] Traditional secondary water supply systems in residential communities use a single pump to provide water to the entire building or community. While this method is simple, it suffers from energy consumption issues due to the reliance on a single pump, diverse and unpredictable water usage habits, inaccurate pressure control, and a lack of energy-saving and intelligent matching. Therefore, it is necessary to propose an AI-based energy-saving system and method for secondary water supply to address these energy-saving challenges. Summary of the Invention

[0004] (a) Technical problems to be solved To address the shortcomings of existing technologies, this invention provides an AI-based energy-saving secondary water supply system and method to solve the problems mentioned in the background section.

[0005] (II) Technical Solution To achieve the above objectives, the present invention provides the following technical solution: an AI-based secondary water supply energy-saving system and method, comprising the following steps: Step 1: Install monitoring equipment in the residential buildings to collect structural data for each household; and collect total water consumption data for the entire area, including: real-time water pressure (Syl), real-time water flow rate (Llz), real-time water pump energy consumption (Hnz), and vibration intensity of the pipe network. ; Based on the household structure data, a household water demand coefficient Sx is constructed and evaluated to classify the households of each residential building into different levels of zones, including a first-level zone, a second-level zone, and a third-level zone. Step 2: Based on the household water demand coefficient Sx obtained in Step 1, and combined with the collected real-time water pressure value Syl, real-time water flow value Llz, and real-time water pump energy consumption value Hnz, optimize the water pump's operating status; for each level zone, calculate and obtain the water pressure optimization coefficient for the i-th level zone. And preset a second standard threshold R, when the water pressure optimization coefficient of the i-th level zone When the second standard threshold R is exceeded, it indicates that the water pump output power consumption of this level zone is not up to standard, triggering the first warning command to monitor the pressure of the pipeline network and repair the leaks in the pipeline network; Step 3: Based on Step 2, monitor the pipe network where the water pump's output power consumption is substandard; combine the collected real-time water pressure value Syl, real-time water flow value Llz, and pipe network vibration intensity value. By using AI to dynamically adjust the model and perform multi-dimensional data fusion analysis, the leakage coefficient of the pipeline network can be calculated. ; and preset the third standard threshold B and the pipeline leakage coefficient. Perform comparative analysis to generate corresponding evaluation results and corresponding strategies; Step 4: Optimize the water pressure using the water pressure coefficient of the i-th level zone. and pipeline leakage coefficient The optimal water pump output power coefficient ZYGL is obtained, and combined with the water demand coefficients of residents in each level zone, the output power of the water pumps in each zone is dynamically adjusted through an AI dynamic adjustment model, automatically matching the first, second, and third level zones. Preferably, Preferably, step one includes: S11. Install monitoring equipment in residential buildings to collect structural data for each household; and collect total water consumption data for the entire area, including: real-time water pressure value Syl, real-time water flow rate value Llz, real-time water pump energy consumption value Hnz, and vibration intensity value of the pipe network. ; S12. Using a convolutional neural network, construct an initial convolutional neural network model, and train and test the initial convolutional neural network model with total water consumption data and household structure data. Use the trained initial convolutional neural network model as the AI ​​dynamic adjustment model. At the same time, use the intermediate layer output of total water consumption data and household structure data as feature vectors to identify feature information. Use the obtained feature information to train and test the AI ​​dynamic adjustment model, and use the trained AI dynamic adjustment model as the data for prediction. S13. Using an AI dynamic adjustment model, score the household information data and household water use behavior data. After dimensionless processing, calculate the household water demand coefficient Sx, as shown in the following formula: ; In the formula, , , , and This is a weighting coefficient, the specific value of which is adjusted and set by the user. , , , , ,and , This indicates a rating of residents' water consumption. This indicates the household population score. This indicates the score for the resident's living area. Indicates floor rating. The table below shows the number of times residents use water during peak hours:

[0006] Preferably, step one also includes: S14. Preset the first standard threshold K, and compare and analyze the water demand coefficient Sx of residents to generate the first evaluation result, including: intelligently dividing the residents of each residential building into first-level zones, second-level zones and third-level zones. When the household water demand coefficient Sx < the first standard threshold K, it indicates that the user's water usage behavior is intelligently classified into the first-level zone and marked as such. ; When the first standard threshold K ≤ household water demand coefficient Sx < the first standard threshold K When the usage rate reaches 150%, it indicates that the user's water usage behavior has been intelligently categorized into the second-level partition and marked as such. ; When the household water demand coefficient Sx ≥ the first standard threshold K When the usage rate reaches 150%, it indicates that the user's water usage behavior has been intelligently categorized into the third-level partition and marked as such. .

[0007] Preferably, step two includes: S21. Based on the household water demand coefficient Sx obtained in step one, the AI ​​dynamic adjustment model is used to perform multi-dimensional data fusion calculation, combined with the collected real-time water pressure value Syl, real-time water flow value Llz, and real-time water pump energy consumption value Hnz, to optimize the water pump's operating status. After dimensionless processing, the water pressure optimization coefficient for the i-th level zone is calculated. The formula is as follows: ; In the formula, This indicates the real-time water flow rate. This represents the average water flow rate. This indicates the real-time water pressure value. This indicates the water pressure value required for water to reach the target grade zone. This indicates the real-time energy consumption of the water pump. This represents the ideal energy consumption value of the water pump, and k represents the seasonal adjustment coefficient, which is set differently according to the four seasons, including: k=2 in spring, k=3 in summer, k=2.5 in autumn, and k=1.5 in winter.

[0008] Preferably, step S21 includes: S22. Preset the second standard threshold R, and combine it with the water pressure optimization coefficient of the i-th level zone. A comparative analysis was conducted to generate a second evaluation result, including: When the water pressure optimization coefficient of the i-th level zone When the value is ≤ the second standard threshold R, it indicates that the pump output power consumption of the water pump in this grade zone is qualified, and continuous monitoring is required; When the water pressure optimization coefficient of the i-th level zone When the second standard threshold R is reached, it indicates that the water pump's output power consumption for that level zone is unqualified, triggering the first early warning command and generating the first strategy, which includes: monitoring the pressure of the pipeline network, repairing leaks in the pipeline network, and recalculating until the water pressure optimization coefficient for the i-th level zone is reached. Until it is less than or equal to the second standard threshold R.

[0009] Preferably, step three includes: S31. According to step two, monitor the pipeline network where the pump output power and energy consumption are substandard; combine the collected real-time water pressure value Syl, real-time water flow value Llz, real-time pump energy consumption value Hnz, and pipeline vibration intensity value. By using AI to dynamically adjust the model for multi-dimensional data fusion analysis, and after dimensionless processing, the pipeline leakage coefficient is calculated. The formula is as follows: ; In the formula, This indicates the real-time water flow rate. This represents the average water flow rate. This indicates the real-time water pressure value. This indicates the water pressure value required for water to reach the target zone. This indicates the vibration intensity value of the pipeline network. This indicates the standard value of vibration intensity in the pipeline network. and Indicates the weighting coefficient. , ,and .

[0010] Preferably, step three also includes: S32. Preset the third standard threshold B, and combine it with the pipeline leakage coefficient. A comparative analysis was conducted to generate a third evaluation result, including: When the pipeline leakage coefficient <Third standard threshold B When the leakage rate reaches 70%, it indicates that there is a first-level leakage in the pipeline network, triggering a second early warning instruction and generating a second strategy to completely replace the old pipeline network with a new one if there is leakage. When the third standard threshold B 70%≤pipeline leakage coefficient When the value is less than the third standard threshold B, it indicates that there is a secondary leakage in the pipeline network, triggering the third early warning instruction and generating the third strategy to repair the damaged parts of the pipeline network, including: tape repair, external wrapping repair and pipeline sealing test. When the pipeline leakage coefficient When the value is ≥ the third standard threshold B, it indicates that there is no leakage in the pipeline network, and continuous monitoring is required. Preferably, step four includes: S41, Combining the water pressure optimization coefficient of the i-th level zone and pipeline leakage coefficient After dimensionless processing, the optimal pump output power coefficient ZYGL is calculated and obtained using the following formula: ; In the formula, This represents the water pressure optimization coefficient for the i-th level zone. Indicates the leakage coefficient of the pipeline network. This represents the service life coefficient of the pipeline network. , where n represents the nth year.

[0011] Preferably, step four also includes: S42. Combining the optimal pump output power coefficient ZYGL and the household water demand coefficient, the output power of the pumps in each grade zone is dynamically adjusted using an AI dynamic adjustment model. The specific details are as follows: When the water demand of residents in the first-level zone is monitored, the AI ​​dynamically adjusts the model by incorporating the water demand coefficient for residents in the first-level zone. Recalculate the optimal pump output power coefficient The water pump output power is dynamically adjusted to provide water to residents; When the water demand of residents in the second-level zone is monitored, the AI ​​dynamically adjusts the model by incorporating the water demand coefficient for residents in the second-level zone. Recalculate the optimal pump output power coefficient The water pump output power is dynamically adjusted to provide water to residents; When the water demand of residents in the third-level zone is monitored, the AI ​​dynamically adjusts the model by incorporating the water demand coefficient for residents in the third-level zone. Recalculate the optimal pump output power coefficient The output power of the water pump is dynamically adjusted to provide water to residents.

[0012] Preferably, an AI-based energy-saving secondary water supply system includes: The data acquisition unit is used to install monitoring equipment in residential buildings to collect structural data for each household; and to collect total water consumption data for the entire area, including: real-time water pressure (Syl), real-time water flow rate (Llz), real-time water pump energy consumption (Hnz), and vibration intensity of the pipe network. ; The tiered zoning units, combined with the water demand coefficient of residents, classify the residents of each residential building into first-tier zoning, second-tier zoning, and third-tier zoning. The first calculation unit is used to score the household structure data of each household and calculate the household water demand coefficient. ; The second calculation unit is used to combine the real-time water pressure value Syl, the real-time water flow value Llz, and the real-time water pump energy consumption value Hnz to calculate the water pressure optimization coefficient for the i-th level zone. ; The third calculation unit is used to combine the collected real-time water pressure value Syl, real-time water flow value Llz, and vibration intensity value of the pipeline network. By using AI to dynamically adjust the model and perform multi-dimensional data fusion analysis, the leakage coefficient of the pipeline network can be calculated. ; The fourth calculation unit is used to combine the water pressure optimization coefficient of the i-th level zone. and pipeline leakage coefficient Calculate and obtain the optimal pump output power coefficient ZYGL; The first assessment unit is used to analyze and determine the residents of each residential building, and classify them into first-level zones, second-level zones, and third-level zones. The second evaluation unit is used to analyze and judge whether the output power energy consumption of the water pump is qualified, and to provide strategies for the output power of water pumps with unqualified energy consumption. The third assessment unit is used to analyze and determine whether there is leakage in the pipeline network, and to provide strategies for primary and secondary leakage situations respectively; The matching unit combines the optimal water pump output power coefficient ZYGL with the water demand coefficient of residents in each level zone. Through AI dynamic adjustment model, it dynamically adjusts the output power of water pumps in each level zone. After recalculation, it automatically matches residents in the first, second, and third level zones to use the optimal water pump output power.

[0013] (III) Beneficial Effects This invention provides an AI-based energy-saving system and method for secondary water supply. It offers the following advantages: (1) This AI-based secondary water supply energy-saving system and energy-saving method can accurately divide water supply zones of different levels by intelligently analyzing the water demand and behavior habits of residents. This zone management method can not only effectively reduce the burden on the water pumps in each zone, but also dynamically adjust the water supply pressure according to the needs of different areas, thereby avoiding energy waste in the traditional single water pump water supply method and improving the overall operating efficiency of the water supply system.

[0014] (2) This AI-based secondary water supply energy-saving system and energy-saving method is based on real-time collected water pressure, flow rate and energy consumption data, combined with the water pressure optimization coefficient of the i-th level zone. The system can dynamically adjust the operating status of the water pump and optimize its output power. By accurately calculating and optimizing the water pump output power coefficient, it significantly reduces energy waste caused by excessively high or low water pressure, achieving the goal of energy conservation and consumption reduction.

[0015] (3) This AI-based secondary water supply energy-saving system and method utilizes distributed sensors to monitor the pressure, flow rate, and vibration intensity of the pipeline network in real time. Combined with an AI dynamic adjustment model, it performs multi-dimensional data fusion analysis. The system can accurately locate leakage points in the pipeline network and obtain the pipeline network leakage coefficient through calculation. By identifying and promptly repairing leaks, water waste and increased system energy consumption caused by leaks are effectively avoided, thus improving the stability and safety of the pipeline network.

[0016] (4) This AI-based secondary water supply energy-saving system and method, by combining the water demand coefficient of residents and the real-time water supply demand, can dynamically adjust the output power of water pumps at each zone level to ensure that the water pressure of each zone is within a reasonable range. This not only guarantees the water pressure needs of high-rise residents, but also avoids waste caused by excessive water pressure for low-rise residents, while providing a more precise water supply solution and ensuring a balance between water supply quality and energy-saving effect. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the steps of an AI-based energy-saving secondary water supply method according to the present invention; Figure 2 This is a schematic diagram of the block flow of an AI-based secondary water supply energy-saving system according to the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Example 1 Please see Figure 1 This invention provides an AI-based secondary water supply and energy-saving method, comprising the following steps: Step 1: Install monitoring equipment in the residential buildings to collect structural data for each household; and collect total water consumption data for the entire area, including: real-time water pressure (Syl), real-time water flow rate (Llz), real-time water pump energy consumption (Hnz), and vibration intensity of the pipe network. ; Based on the household structure data, a household water demand coefficient Sx is constructed and evaluated to classify the households of each residential building into different levels of zones, including a first-level zone, a second-level zone, and a third-level zone. Step 2: Based on the household water demand coefficient Sx obtained in Step 1, and combined with the collected real-time water pressure value Syl, real-time water flow value Llz, and real-time water pump energy consumption value Hnz, optimize the water pump's operating status; for each level zone, calculate and obtain the water pressure optimization coefficient for the i-th level zone. And preset a second standard threshold R, when the water pressure optimization coefficient of the i-th level zone When the second standard threshold R is exceeded, it indicates that the water pump output power consumption of this level zone is not up to standard, triggering the first warning command to monitor the pressure of the pipeline network and repair the leaks in the pipeline network; Step 3: Based on Step 2, monitor the pipe network where the water pump's output power consumption is substandard; combine the collected real-time water pressure value Syl, real-time water flow value Llz, and pipe network vibration intensity value. By using AI to dynamically adjust the model and perform multi-dimensional data fusion analysis, the leakage coefficient of the pipeline network can be calculated. ; and preset the third standard threshold B and the pipeline leakage coefficient. Perform comparative analysis to generate corresponding evaluation results and corresponding strategies; Step 4: Optimize the water pressure using the water pressure coefficient of the i-th level zone. and pipeline leakage coefficient The system obtains the optimal water pump output power coefficient ZYGL and combines it with the water demand coefficient of residents in each level zone. Through AI dynamic adjustment model, it dynamically adjusts the output power of water pumps in each zone and automatically matches the first-level zone, the second-level zone, and the third-level zone.

[0020] In this embodiment, by intelligently analyzing residents' water demand and habits, the system can accurately divide water supply zones into different levels. Based on real-time collected water pressure, flow rate, and energy consumption data, combined with the zone pressure optimization coefficient Popp, the system can dynamically adjust the operating status of water pumps and optimize their output power. By utilizing distributed sensors to monitor the pressure, flow rate, and vibration intensity of the pipeline network in real time, and combining this with an AI dynamic adjustment model for multi-dimensional data fusion analysis, the system can accurately locate leakage points in the pipeline network and calculate the pipeline network leakage coefficient. By identifying and promptly repairing leaks, the system effectively avoids water waste and increased system energy consumption caused by leaks, thus improving the stability and safety of the pipeline network. By combining residents' water demand coefficients with real-time water supply needs, the system can dynamically adjust the output power of the zone pumps to ensure that the water pressure in each zone is within a reasonable range. This not only guarantees the water pressure needs of high-rise residents but also avoids waste caused by excessively high water pressure in low-rise residents, while providing a more precise water supply solution and ensuring a balance between water quality and energy efficiency.

[0021] Example 2 This embodiment is an explanation of Embodiment 1. Specifically, step one includes: S11. Install monitoring equipment in residential buildings to collect structural data for each household; and collect total water consumption data for the entire area, including: real-time water pressure value Syl, real-time water flow rate value Llz, real-time water pump energy consumption value Hnz, and vibration intensity value of the pipe network. ; S12. Using a convolutional neural network, construct an initial convolutional neural network model, and train and test the initial convolutional neural network model with total water consumption data and household structure data. Use the trained initial convolutional neural network model as the AI ​​dynamic adjustment model. At the same time, use the intermediate layer output of total water consumption data and household structure data as feature vectors to identify feature information. Use the obtained feature information to train and test the AI ​​dynamic adjustment model, and use the trained AI dynamic adjustment model as the data for prediction. S13. Using an AI dynamic adjustment model, score the household information data and household water use behavior data. After dimensionless processing, calculate the household water demand coefficient Sx, as shown in the following formula: ; In the formula, , , , and This is a weighting coefficient, the specific value of which is adjusted and set by the user. , , , , ,and , This indicates a rating of residents' water consumption. This indicates the household population score. This indicates the score for the resident's living area. Indicates floor rating. The table below shows the number of times residents use water during peak hours:

[0022] In this embodiment, by intelligently analyzing residents' water consumption, population, residential area, residential floor, and peak water usage frequency, the system can formulate water supply plans for different types of users based on actual water demand, thereby improving water supply efficiency, saving energy and reducing consumption, increasing user satisfaction, and effectively managing the health and stability of the water supply system.

[0023] Example 3 This embodiment is an explanation of embodiment 2. Specifically, step one also includes: S14. Preset the first standard threshold K, and compare and analyze the water demand coefficient Sx of residents to generate the first evaluation result, including: intelligently dividing the residents of each residential building into first-level zones, second-level zones and third-level zones. When the household water demand coefficient Sx < the first standard threshold K, it indicates that the user's water usage behavior is intelligently classified into the first-level zone and marked as such. ; When the first standard threshold K ≤ household water demand coefficient Sx < the first standard threshold K When the usage rate reaches 150%, it indicates that the user's water usage behavior has been intelligently categorized into the second-level partition and marked as such. ; When the household water demand coefficient Sx ≥ the first standard threshold K When the usage rate reaches 150%, it indicates that the user's water usage behavior has been intelligently categorized into the third-level partition and marked as such. .

[0024] In this embodiment, water supply zones of different levels are accurately divided by comparing and analyzing the water demand coefficients of residents with standard thresholds. This zoned management method not only effectively reduces the burden on water pumps in each zone, but also dynamically adjusts the water supply pressure according to the needs of different areas, thereby avoiding energy waste in the traditional single-pump water supply method and improving the overall operating efficiency of the water supply system.

[0025] Example 4 This embodiment is an explanation of embodiment 2. Specifically, step two includes: S21. Based on the household water demand coefficient Sx obtained in step one, the AI ​​dynamic adjustment model is used to perform multi-dimensional data fusion calculation, combined with the collected real-time water pressure value Syl, real-time water flow value Llz, and real-time water pump energy consumption value Hnz, to optimize the water pump's operating status. After dimensionless processing, the water pressure optimization coefficient for the i-th level zone is calculated. The formula is as follows: ; In the formula, This indicates the real-time water flow rate. This represents the average water flow rate. This indicates the real-time water pressure value. This indicates the water pressure value required for water to reach the target grade zone. This indicates the real-time energy consumption of the water pump. This represents the ideal energy consumption value of the water pump, and k represents the seasonal adjustment coefficient, which is set differently according to the four seasons, including: k=2 in spring, k=3 in summer, k=2.5 in autumn, and k=1.5 in winter.

[0026] In this embodiment, based on real-time collected water pressure, flow rate, and energy consumption data, combined with the zone pressure optimization coefficient Popp, the system can dynamically adjust the operating status of the water pump and optimize its output power. By accurately calculating the optimal water pump output power, energy waste caused by excessively high or low water pressure is significantly reduced, achieving the goal of energy conservation and consumption reduction.

[0027] Example 5 This embodiment is an explanation of embodiment 4. Specifically, step S21 includes: S22. Preset the second standard threshold R, and combine it with the water pressure optimization coefficient of the i-th level zone. A comparative analysis was conducted to generate a second evaluation result, including: When the water pressure optimization coefficient of the i-th level zone When the value is ≤ the second standard threshold R, it indicates that the pump output power consumption of the water pump in this grade zone is qualified, and continuous monitoring is required; When the water pressure optimization coefficient of the i-th level zone When the second standard threshold R is reached, it indicates that the water pump's output power consumption for that level zone is unqualified, triggering the first early warning command and generating the first strategy, which includes: monitoring the pressure of the pipeline network, repairing leaks in the pipeline network, and recalculating until the water pressure optimization coefficient for the i-th level zone is reached. Until it is less than or equal to the second standard threshold R.

[0028] In this embodiment, by comparing and analyzing the threshold and the partition pressure optimization coefficient Popp, it is possible to accurately determine whether the pump output power is within acceptable energy consumption, and to provide strategies for unacceptable energy consumption, thus providing a scientific basis for achieving the goal of energy conservation and consumption reduction.

[0029] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by those skilled in the art for each set of sample data; as long as it does not affect the ratio between the parameter and the quantized value, it is acceptable.

[0030] Example 6 This embodiment is an explanation of embodiment 5. Specifically, step three includes: S31. According to step two, monitor the pipeline network where the pump output power and energy consumption are substandard; combine the collected real-time water pressure value Syl, real-time water flow value Llz, real-time pump energy consumption value Hnz, and pipeline vibration intensity value. By using AI to dynamically adjust the model for multi-dimensional data fusion analysis, and after dimensionless processing, the pipeline leakage coefficient is calculated. The formula is as follows: ; In the formula, This indicates the real-time water flow rate. This represents the average water flow rate. This indicates the real-time water pressure value. This indicates the water pressure value required for water to reach the target zone. This indicates the vibration intensity value of the pipeline network. This indicates the standard value of vibration intensity in the pipeline network. and Indicates the weighting coefficient. , ,and .

[0031] In this embodiment, distributed sensors are used to monitor the pressure, flow rate, and vibration intensity of the pipeline network in real time. Combined with an AI dynamic adjustment model, multi-dimensional data fusion analysis is performed. The system can accurately locate leakage points in the pipeline network and calculate the pipeline network leakage coefficient. This improves the accuracy of calculations.

[0032] Example 7 This embodiment is an explanation of embodiment 6. Specifically, step three also includes: S32. Preset the third standard threshold B, and combine it with the pipeline leakage coefficient. A comparative analysis was conducted to generate a third evaluation result, including: When the pipeline leakage coefficient <Third standard threshold B When the leakage rate reaches 70%, it indicates that there is a first-level leakage in the pipeline network, triggering a second early warning instruction and generating a second strategy to completely replace the old pipeline network with a new one if there is leakage. When the third standard threshold B 70%≤pipeline leakage coefficient When the value is less than the third standard threshold B, it indicates that there is a secondary leakage in the pipeline network, triggering the third early warning instruction and generating the third strategy to repair the damaged parts of the pipeline network, including: tape repair, external wrapping repair and pipeline sealing test. When the pipeline leakage coefficient When the value is ≥ the third standard threshold B, it indicates that there is no leakage in the pipeline network and continuous monitoring is required.

[0033] In this embodiment, the pipeline leakage coefficient is used. By comparing and analyzing thresholds, leakage problems can be identified in advance and repaired in a timely manner, effectively avoiding water waste and increased system energy consumption caused by leakage, and improving the stability and safety of the pipeline network.

[0034] Example 8 This embodiment is an explanation of embodiment 7. Specifically, step four includes: S41, Combining the water pressure optimization coefficient of the i-th level zone and pipeline leakage coefficient After dimensionless processing, the optimal pump output power coefficient ZYGL is calculated and obtained using the following formula: ; In the formula, This represents the water pressure optimization coefficient for the i-th level zone. Indicates the leakage coefficient of the pipeline network. This represents the service life coefficient of the pipeline network. , where n represents the nth year.

[0035] In this embodiment, by combining the household water demand coefficient and real-time water supply demand, the optimal water pump output power is calculated, providing a more accurate water supply solution and ensuring a balance between water supply quality and energy saving.

[0036] Example 9 This embodiment is an explanation of embodiment 8. Specifically, step S41 includes: S42. Combining the optimal pump output power coefficient ZYGL and the household water demand coefficient, the output power of the pumps in each grade zone is dynamically adjusted using an AI dynamic adjustment model. The specific details are as follows: When the water demand of residents in the first-level zone is monitored, the AI ​​dynamically adjusts the model by incorporating the water demand coefficient for residents in the first-level zone. Recalculate the optimal pump output power coefficient The water pump output power is dynamically adjusted to provide water to residents; When the water demand of residents in the second-level zone is monitored, the AI ​​dynamically adjusts the model by incorporating the water demand coefficient for residents in the second-level zone. Recalculate the optimal pump output power coefficient The water pump output power is dynamically adjusted to provide water to residents; When the water demand of residents in the third-level zone is monitored, the AI ​​dynamically adjusts the model by incorporating the water demand coefficient for residents in the third-level zone. Recalculate the optimal pump output power coefficient The output power of the water pump is dynamically adjusted to provide water to residents.

[0037] In this embodiment, by matching the resident's water demand coefficient with the optimal pump output power coefficient, the system can dynamically adjust the output power of the zone pumps to ensure that the water pressure in each zone is within a reasonable range. This not only guarantees the water pressure needs of residents on higher floors but also avoids waste caused by excessively high water pressure for residents on lower floors. It also provides a more precise water supply solution, ensuring a balance between water quality and energy efficiency. For example, a resident living on the 21st floor uses 7m³ / month in summer. 3 / month, 3 people, living area 80m² 2 The peak water usage times are twice a day, in the morning and evening. Substitute these values ​​into the formula to calculate. , , , The corresponding water pump output power is 13.98KW.

[0038] Example 10 Please refer to an AI-based energy-saving secondary water supply system. Figure 2 ,include: The data acquisition unit is used to install monitoring equipment in residential buildings to collect structural data for each household; and to collect total water consumption data for the entire area, including: real-time water pressure (Syl), real-time water flow rate (Llz), real-time water pump energy consumption (Hnz), and vibration intensity of the pipe network. ; The tiered zoning units, combined with the water demand coefficient of residents, classify the residents of each residential building into first-tier zoning, second-tier zoning, and third-tier zoning. The first calculation unit is used to score the household structure data of each household and calculate the household water demand coefficient. ; The second calculation unit is used to combine the real-time water pressure value Syl, the real-time water flow value Llz, and the real-time water pump energy consumption value Hnz to calculate the water pressure optimization coefficient for the i-th level zone. ; The third calculation unit is used to combine the collected real-time water pressure value Syl, real-time water flow value Llz, and vibration intensity value of the pipeline network. By using AI to dynamically adjust the model and perform multi-dimensional data fusion analysis, the leakage coefficient of the pipeline network can be calculated. ; The fourth calculation unit is used to combine the water pressure optimization coefficient of the i-th level zone. and pipeline leakage coefficient Calculate and obtain the optimal pump output power coefficient ZYGL; The first assessment unit is used to analyze and determine the residents of each residential building, and classify them into first-level zones, second-level zones, and third-level zones. The second evaluation unit is used to analyze and judge whether the output power energy consumption of the water pump is qualified, and to provide strategies for the output power of water pumps with unqualified energy consumption. The third assessment unit is used to analyze and determine whether there is leakage in the pipeline network, and to provide strategies for primary and secondary leakage situations respectively; The matching unit combines the optimal water pump output power coefficient ZYGL with the water demand coefficient of residents in each level zone. Through AI dynamic adjustment model, it dynamically adjusts the output power of water pumps in each level zone. After recalculation, it automatically matches residents in the first, second, and third level zones to use the optimal water pump output power.

[0039] In this embodiment, through the coordinated operation of the various unit modules, the system can not only effectively optimize water supply pressure and pump power, but also monitor pipeline leakage in real time and intelligently adjust water supply strategies to ensure the efficient, safe, and energy-saving operation of the water supply system. This intelligent water supply management mode will promote the improvement of the overall operating efficiency and reliability of the water supply system, while achieving the goals of energy conservation and emission reduction.

[0040] The above formulas are all derived from software simulation using a large amount of data, and are selected to be close to the actual values. The coefficients in the formulas are set by those skilled in the art according to the actual situation. The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or changes made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. An AI-based energy-saving method for secondary water supply, characterized in that, Includes the following steps: Step 1: Install monitoring equipment in the residential building to collect household structure data for each household; The system also collects total water consumption data for the entire area, including: real-time water pressure (Syl), real-time water flow rate (Llz), real-time pump energy consumption (Hnz), and vibration intensity of the pipe network. ; Based on the household structure data, a household water demand coefficient Sx is constructed and evaluated to classify the households of each residential building into different levels of zones, including a first-level zone, a second-level zone, and a third-level zone. Step 2: Based on the household water demand coefficient Sx obtained in Step 1, and combined with the collected real-time water pressure value Syl, real-time water flow value Llz, and real-time water pump energy consumption value Hnz, optimize the water pump's operating status; for each level zone, calculate and obtain the water pressure optimization coefficient for the i-th level zone. And preset a second standard threshold R, when the water pressure optimization coefficient of the i-th level zone When the second standard threshold R is exceeded, it indicates that the water pump output power consumption of this level zone is not up to standard, triggering the first warning command to monitor the pressure of the pipeline network and repair the leaks in the pipeline network; Step 3: Based on Step 2, monitor the pipe network where the water pump's output power consumption is substandard; combine the collected real-time water pressure value Syl, real-time water flow value Llz, and pipe network vibration intensity value. By using AI to dynamically adjust the model and perform multi-dimensional data fusion analysis, the leakage coefficient of the pipeline network can be calculated. ; and preset the third standard threshold B and the pipeline leakage coefficient. Perform comparative analysis to generate corresponding evaluation results and corresponding strategies; Step 4: Optimize the water pressure using the water pressure coefficient of the i-th level zone. and pipeline leakage coefficient The system obtains the optimal water pump output power coefficient ZYGL and combines it with the water demand coefficient of residents in each level zone. Through AI dynamic adjustment model, it dynamically adjusts the output power of water pumps in each zone and automatically matches the first-level zone, the second-level zone, and the third-level zone.

2. The AI-based energy-saving method for secondary water supply according to claim 1, characterized in that, Step one includes: S11. Install monitoring equipment in residential buildings to collect structural data for each household; and collect total water consumption data for the entire area, including: real-time water pressure value Syl, real-time water flow rate value Llz, real-time water pump energy consumption value Hnz, and vibration intensity value of the pipe network. ; S12. Using a convolutional neural network, construct an initial convolutional neural network model, and train and test the initial convolutional neural network model with total water consumption data and household structure data. Use the trained initial convolutional neural network model as the AI ​​dynamic adjustment model. At the same time, use the intermediate layer output of total water consumption data and household structure data as feature vectors to identify feature information. Use the obtained feature information to train and test the AI ​​dynamic adjustment model, and use the trained AI dynamic adjustment model as the data for prediction. S13. Using an AI dynamic adjustment model, score the household information data and household water use behavior data. After dimensionless processing, calculate the household water demand coefficient Sx, as shown in the following formula: ； In the formula, , , , and These are the weighting coefficients. This indicates a rating of residents' water consumption. This indicates the household population score. This indicates the score for the resident's living area. Indicates floor rating. This indicates the number of times residents use water during peak hours.

3. The AI-based energy-saving method for secondary water supply according to claim 2, characterized in that, Step one also includes: S14. Preset the first standard threshold K, and compare and analyze the water demand coefficient Sx of residents to generate the first evaluation result, including: intelligently dividing the residents of each residential building into first-level zones, second-level zones and third-level zones. When the household water demand coefficient Sx < the first standard threshold K, it indicates that the user's water usage behavior is intelligently classified into the first-level zone and marked as such. ; When the first standard threshold K ≤ household water demand coefficient Sx < the first standard threshold K When the usage rate reaches 150%, it indicates that the user's water usage behavior has been intelligently categorized into the second-level partition and marked as such. ; When the household water demand coefficient Sx ≥ the first standard threshold K When the usage rate reaches 150%, it indicates that the user's water usage behavior has been intelligently categorized into the third-level partition and marked as such. .

4. The AI-based energy-saving method for secondary water supply according to claim 2, characterized in that, Step two includes: S21. Based on the household water demand coefficient Sx obtained in step one, the AI ​​dynamic adjustment model is used to perform multi-dimensional data fusion calculation, combined with the collected real-time water pressure value Syl, real-time water flow value Llz, and real-time water pump energy consumption value Hnz, to optimize the water pump's operating status. After dimensionless processing, the water pressure optimization coefficient for the i-th level zone is calculated. The formula is as follows: ； In the formula, This indicates the real-time water flow rate. This represents the average water flow rate. This indicates the real-time water pressure value. This indicates the water pressure value required for water to reach the target grade zone. This indicates the real-time energy consumption of the water pump. This represents the ideal energy consumption value of the water pump, and k represents the seasonal adjustment coefficient, which is set differently according to the four seasons, including: k=2 in spring, k=3 in summer, k=2.5 in autumn, and k=1.5 in winter.

5. The AI-based energy-saving method for secondary water supply according to claim 4, characterized in that, Step two also includes: S22. Preset the second standard threshold R, and combine it with the water pressure optimization coefficient of the i-th level zone. A comparative analysis was conducted to generate a second evaluation result, including: When the water pressure optimization coefficient of the i-th level zone When the value is ≤ the second standard threshold R, it indicates that the pump output power consumption of the water pump in this grade zone is qualified, and continuous monitoring is required; When the water pressure optimization coefficient of the i-th level zone When the second standard threshold R is reached, it indicates that the water pump's output power consumption for that level zone is unqualified, triggering the first early warning command and generating the first strategy, which includes: monitoring the pressure of the pipeline network, repairing leaks in the pipeline network, and recalculating until the water pressure optimization coefficient for the i-th level zone is reached. Until it is less than or equal to the second standard threshold R.

6. The AI-based energy-saving method for secondary water supply according to claim 5, characterized in that, Step three includes: S31. According to step two, monitor the pipeline network where the pump output power and energy consumption are substandard; combine the collected real-time water pressure value Syl, real-time water flow value Llz, real-time pump energy consumption value Hnz, and pipeline vibration intensity value. By using AI to dynamically adjust the model for multi-dimensional data fusion analysis, and after dimensionless processing, the pipeline leakage coefficient is calculated. The formula is as follows: ； In the formula, This indicates the real-time water flow rate. This represents the average water flow rate. This indicates the real-time water pressure value. This indicates the water pressure value required for water to reach the target zone. This indicates the vibration intensity value of the pipeline network. This indicates the standard value of vibration intensity in the pipeline network. and This represents the weighting coefficient.

7. The AI-based energy-saving method for secondary water supply according to claim 6, characterized in that, Step three also includes: S32. Preset the third standard threshold B, and combine it with the pipeline leakage coefficient. A comparative analysis was conducted to generate a third evaluation result, including: When the pipeline leakage coefficient <Third standard threshold B When the leakage rate reaches 70%, it indicates that there is a first-level leakage in the pipeline network, triggering a second early warning instruction and generating a second strategy to completely replace the old pipeline network with a new one if there is leakage. When the third standard threshold B 70%≤pipeline leakage coefficient When the value is less than the third standard threshold B, it indicates that there is a secondary leakage in the pipeline network, triggering the third early warning instruction and generating the third strategy to repair the damaged parts of the pipeline network, including: tape repair, external wrapping repair and pipeline sealing test. When the pipeline leakage coefficient When the value is ≥ the third standard threshold B, it indicates that there is no leakage in the pipeline network and continuous monitoring is required.

8. The AI-based energy-saving method for secondary water supply according to claim 7, characterized in that, Step four includes: S41, Combining the water pressure optimization coefficient of the i-th level zone and pipeline leakage coefficient After dimensionless processing, the optimal pump output power coefficient ZYGL is calculated and obtained using the following formula: ； In the formula, This represents the water pressure optimization coefficient for the i-th level zone. Indicates the leakage coefficient of the pipeline network. This represents the service life coefficient of the pipeline network. , where n represents the nth year.

9. The AI-based energy-saving method for secondary water supply according to claim 8, characterized in that, Step four also includes: S42. Combining the optimal pump output power coefficient ZYGL and the household water demand coefficient, the output power of the pumps in each grade zone is dynamically adjusted using an AI dynamic adjustment model. The specific details are as follows: When the water demand of residents in the first-level zone is monitored, the AI ​​dynamically adjusts the model by incorporating the water demand coefficient for residents in the first-level zone. Recalculate the optimal pump output power coefficient The water pump output power is dynamically adjusted to provide water to residents; When the water demand of residents in the second-level zone is monitored, the AI ​​dynamically adjusts the model by incorporating the water demand coefficient for residents in the second-level zone. Recalculate the optimal pump output power coefficient The water pump output power is dynamically adjusted to provide water to residents; When the water demand of residents in the third-level zone is monitored, the AI ​​dynamically adjusts the model by incorporating the water demand coefficient for residents in the third-level zone. Recalculate the optimal pump output power coefficient The output power of the water pump is dynamically adjusted to provide water to residents.

10. An AI-based energy-saving secondary water supply system, comprising the AI-based energy-saving method for secondary water supply as described in any one of claims 1-9, comprising: The data acquisition unit is used to install monitoring equipment in residential buildings to collect and acquire the resident structure data of each household. The system also collects total water consumption data for the entire area, including: real-time water pressure (Syl), real-time water flow rate (Llz), real-time pump energy consumption (Hnz), and vibration intensity of the pipe network. ; The tiered zoning units, combined with the water demand coefficient of residents, classify the residents of each residential building into first-tier zoning, second-tier zoning, and third-tier zoning. The first calculation unit is used to score the household structure data of each household and calculate the household water demand coefficient. ; The second calculation unit is used to combine the real-time water pressure value Syl, the real-time water flow value Llz, and the real-time water pump energy consumption value Hnz to calculate the water pressure optimization coefficient for the i-th level zone. ; The third calculation unit is used to combine the collected real-time water pressure value Syl, real-time water flow value Llz, and vibration intensity value of the pipeline network. By using AI to dynamically adjust the model and perform multi-dimensional data fusion analysis, the leakage coefficient of the pipeline network can be calculated. ; The fourth calculation unit is used to combine the water pressure optimization coefficient of the i-th level zone. and pipeline leakage coefficient Calculate and obtain the optimal pump output power coefficient ZYGL; The first assessment unit is used to analyze and determine the residents of each residential building, and classify them into first-level zones, second-level zones, and third-level zones. The second evaluation unit is used to analyze and judge whether the output power energy consumption of the water pump is qualified, and to provide strategies for the output power of water pumps with unqualified energy consumption. The third assessment unit is used to analyze and determine whether there is leakage in the pipeline network, and to provide strategies for primary and secondary leakage situations respectively; The matching unit combines the optimal water pump output power coefficient ZYGL with the water demand coefficient of residents in each level zone. Through AI dynamic adjustment model, it dynamically adjusts the output power of water pumps in each level zone. After recalculation, it automatically matches residents in the first, second, and third level zones to use the optimal water pump output power.

Images