Intelligent water-saving building water supply and drainage system and control method thereof

Abstract

The invention discloses an intelligent water-saving building water supply and drainage system and a control method thereof. The water supply and drainage system comprises a rainwater collection module, a reclaimed water collection module, a water quality monitoring module, a water storage tank module, an intelligent decision module and an electromagnetic shunt water valve device. The control method comprises the steps of real-time collection of water quality parameters, real-time collection of water quantity demand data, decision making of dynamic water distribution, control of dynamic water distribution and self-optimization of a control system. The turbidity sensor, the chemical oxygen demand sensor and the pH sensor are integrated in the rainwater pipe and the reclaimed water pipe to obtain water quality data in real time, the water quality levels of rainwater and reclaimed water and the water quantity requirements at different moments and in different scenes are dynamically evaluated according to a neural network model, and higher flow dividing precision is achieved compared with traditional threshold value control; the sanitary and safe problems of pipeline pollution, soil heavy metal accumulation and the like caused by direct reuse of non-traditional water sources which are not effectively monitored are avoided, and the water supply requirements at different moments and in different scenes can be effectively met.

Description

Technical Field

[0001] The present invention belongs to the technical field of control systems, and relates to an intelligent water-saving building water supply and drainage system and a control method thereof. Background Art

[0002] Large buildings represented by public buildings and high-rise residential buildings are one of the main scenarios of water resource consumption. Among them, the water consumption in non-potable water scenarios such as toilet flushing, vehicle washing, equipment cooling, and greening irrigation accounts for a high proportion of the total building water consumption. The traditional building water supply and drainage system relies on tap water to meet all water use requirements, resulting in a large amount of high-quality water resources being consumed in non-essential scenarios, exacerbating the contradiction between water supply and demand.

[0003] Currently, there are the following difficulties in the collection and utilization of non-conventional water sources represented by rainwater and reclaimed water: 1) If non-conventional water sources are directly reused without effective monitoring, it may cause health and safety problems or equipment damage. For example, atmospheric pollutants and roof sediments usually contained in rainwater, and detergents and organic matters usually contained in reclaimed water may cause problems such as pollution and scaling of water supply and drainage pipes and heavy metal accumulation in greening soil; 2) The traditional water supply and drainage system relies on manual detection or simplified treatment, making it difficult to accurately evaluate water quality in real time; 3) There is a lack of a distribution mechanism for non-conventional water sources, and it is impossible to dynamically adjust the use according to water quality, which may lead to limited use or equipment blockage due to unqualified water quality; 4) The intelligent and automated management level of the traditional building water supply and drainage system involving non-conventional water sources is insufficient. Relying on manual operation to switch water sources, problems such as response lag and operation errors may occur, and it is impossible to dynamically adjust according to real-time water quality and water use requirements, resulting in water resource waste or the idleness of the reuse system; 5) The pollution degree of rainwater in the initial stage of heavy rainfall is usually relatively serious. If the water quality is not distinguished and all rainwater is recycled, it will cause pollutants to enter the water storage device, which is not conducive to the safety and sustainability of rainwater recycling.

[0004] Under the contradiction between water resource shortage and high water consumption in buildings, the utilization of non-conventional water sources such as rainwater and reclaimed water in traditional building water supply and drainage systems has defects such as "extensive collection, simple treatment, blind distribution, and inefficient management", resulting in serious waste of high-quality water resources and high risks of non-conventional water source reuse, and unable to meet the needs of intelligent water conservation, green buildings and sustainable development. There is an urgent need to build an efficient, safe and intelligent water resource recycling system by integrating water quality monitoring, intelligent diversion and automation control technologies to solve the building water conservation problem from the source. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the present invention proposes an intelligent water-saving building water supply and drainage system and a control method thereof, which are applicable to the collection and utilization of non-conventional water sources represented by rainwater and reclaimed water in buildings, and are beneficial to improving the intelligence, safety and efficiency of the water-saving building water supply and drainage system.

[0006] The first aspect of the present application discloses an intelligent water-saving building water supply and drainage system, including a rainwater collection module, a reclaimed water collection module, a water quality monitoring module, a water storage tank module, an intelligent decision-making module, and an electromagnetic flow diversion valve device;

[0007] The rainwater collection module includes a roof water collection device, a ground water collection device, and a rainwater pipe; the roof water collection device includes a roof diversion slope and a roof water collection trough for converging and guiding roof rainwater into the rainwater pipe; the ground water collection device includes a ground diversion slope and a ground water collection trough for converging and guiding ground rainwater into the rainwater pipe; the rainwater pipe is used for connecting the roof water collection device and the ground water collection device to the electromagnetic flow diversion valve device;

[0008] The reclaimed water collection module includes a reclaimed water special interface, a reclaimed water pipe, a check valve device, and an impurity interception device; the reclaimed water special interface is used to dock with the non-fecal sewage drainage point inside the building; the reclaimed water pipe is used for connecting the reclaimed water special interface and the electromagnetic flow diversion valve device; the check valve device is used to ensure the one-way flow of reclaimed water in the reclaimed water pipe; the impurity interception device uses a stainless steel filter screen to intercept impurities in the reclaimed water;

[0009] The water quality monitoring module is arranged in the rainwater pipe and the reclaimed water pipe and forms a wireless connection with the intelligent decision-making module; the water quality monitoring module includes a turbidity sensor, a chemical oxygen demand sensor, and a pH sensor; the turbidity sensor is used to obtain the turbidity data of rainwater and reclaimed water; the chemical oxygen demand sensor is used to obtain the chemical oxygen demand data of rainwater and reclaimed water; the pH sensor is used to obtain the pH data of rainwater and reclaimed water;

[0010] The water storage tank module includes a toilet flushing water storage tank, a greening irrigation water storage tank, a vehicle washing water storage tank, an equipment cooling water storage tank, a standby water storage tank, and a water level sensor; the toilet flushing water storage tank, the greening irrigation water storage tank, the vehicle washing water storage tank, and the equipment cooling water storage tank are respectively used to meet the water source requirements for toilet flushing, greening irrigation, vehicle washing, and equipment cooling; the standby water storage tank is used to store rainwater and reclaimed water whose water quality conditions do not meet the water source requirements for toilet flushing, greening irrigation, vehicle washing, and equipment cooling; the water level sensor is installed in the toilet flushing water storage tank, the greening irrigation water storage tank, the vehicle washing water storage tank, the equipment cooling water storage tank, and the standby water storage tank, used to monitor the water level and record the current season and time, and forms a wireless connection with the intelligent decision-making module;

[0011] The electromagnetic flow dividing valve device is located between the rainwater pipe, the intermediate water pipe and the water storage tank module; according to the current direction and current intensity applied to the electromagnetic flow dividing valve device, the water flow channel direction and the water flow channel opening degree of the electromagnetic flow dividing valve device are controlled, so as to control the water flow direction and flow rate;

[0012] The intelligent decision-making module receives the data of the water quality monitoring module and the water level sensor through wireless connection, and outputs the prediction result to the electromagnetic flow dividing valve device through wireless connection; the intelligent decision-making module adopts neural network model technology, and the neural network model includes an input layer, a hidden layer and an output layer; the input layer has a total of 13 nodes, which are used to receive the normalized water quality data and water volume demand data. The water quality data includes the turbidity data of rainwater, the chemical oxygen demand data of rainwater, the pH data of rainwater, the turbidity data of intermediate water, the chemical oxygen demand data of intermediate water and the pH data of intermediate water; the water volume demand data includes the water level data of the flushing water storage tank, the water level data of the greening irrigation water storage tank, the water level data of the vehicle washing water storage tank, the water level data of the equipment cooling water storage tank, the water level data of the standby water storage tank, the current season data and the current time data; the hidden layer is used for data processing and feature extraction; the output layer is used to generate a prediction result, and the prediction result is the water volume respectively entering the flushing water storage tank, the greening irrigation water storage tank, the vehicle washing water storage tank, the equipment cooling water storage tank and the standby water storage tank; according to the prediction result, a control quantity is further generated, and the control quantity includes the current direction and current intensity applied to the electromagnetic flow dividing valve device; the neural network model uses the past historical data of the intelligent water-saving building water supply and drainage system as training data.

[0013] The second aspect of the present application discloses a control method for an intelligent water-saving building water supply and drainage system, including the following steps:

[0014] S1. Real-time acquisition of water quality data: When rainwater flows through the rainwater pipe and intermediate water flows through the intermediate water pipe, the water quality monitoring module is used to obtain the water quality data of rainwater and intermediate water;

[0015] S2. Real-time acquisition of water volume demand data: The water volume demand data is obtained through a water level sensor;

[0016] S3. Decision-making on dynamic water diversion: The normalized water quality data and water volume demand data are input into the intelligent decision-making module, and the generated prediction result is the water volume respectively entering the flushing water storage tank, the greening irrigation water storage tank, the vehicle washing water storage tank, the equipment cooling water storage tank and the standby water storage tank. According to the prediction result, a control quantity is further generated, and the control quantity includes the current direction and current intensity applied to the electromagnetic flow dividing valve device;

[0017] S4. Control of water dynamic diversion: According to the control quantity generated by the intelligent decision-making module, control the current direction and current intensity applied to the electromagnetic water diversion valve device, so as to control the water flow channel direction and the water flow channel opening degree of the electromagnetic water diversion valve device, and further control the water flow direction and flow rate, so that the rainwater collected by the rainwater collection module or the reclaimed water collected by the reclaimed water collection module enters the toilet flushing water storage tank, the greening irrigation water storage tank, the vehicle washing water storage tank, the equipment cooling water storage tank or the standby water storage tank;

[0018] S5. Self-optimization of the control system: During the use of the intelligent water-saving building water supply and drainage system, continuously collect water demand data through the water level sensor, obtain the relationship between the water demand for toilet flushing, greening irrigation, vehicle washing and equipment cooling changing with seasons and time, and use the gradient descent method to update the weight parameters of the neural network model to ensure that the neural network model realizes self-optimization according to the water demand data, and further ensure that the intelligent water-saving building water supply and drainage system automatically adapts to the scenarios of water quality fluctuations and changes in user water use habits.

[0019] Preferably, in step S5, construct a comprehensive loss function including the water demand for toilet flushing, greening irrigation storage, vehicle washing and equipment cooling, so as to optimize the parameters θ of the neural network model; the comprehensive loss function L(θ) satisfies the following expression:

[0020]

[0021] Among them, β i (i = 1, 2, 3, 4) are respectively the weight coefficients of the water demand for toilet flushing, greening irrigation storage, vehicle washing and equipment cooling, and β i are all not less than 0, and satisfy β1 + β2 + β3 + β4 = 1; Q i (i = 1, 2, 3, 4) are respectively the water demand changing with time for toilet flushing, greening irrigation storage, vehicle washing and equipment cooling;

[0022] When updating the weight parameters of the neural network model using the gradient descent method, the parameters θ of the neural network model satisfy the following expression:

[0023]

[0024] Among them, η is the learning rate.

[0025] Compared with the prior art, the beneficial effects of the present invention are as follows: Aiming at the collection and utilization of rainwater and reclaimed water in buildings, an intelligent water-saving building water supply and drainage system and its control method are disclosed. The water supply and drainage system includes a rainwater collection module, a reclaimed water collection module, a water quality monitoring module, a water storage tank module, an intelligent decision-making module, and an electromagnetic flow splitting valve device; the control method includes real-time collection of water quality parameters, real-time collection of water volume demand data, decision-making on dynamic water flow splitting, control of dynamic water flow splitting, and self-optimization of the control system; by integrating turbidity, chemical oxygen demand, and pH sensors in the rainwater pipe and reclaimed water pipe to obtain water quality data in real time, dynamically evaluating the water quality grades of rainwater and reclaimed water and the water volume demands at different times and in different scenarios according to the neural network model, a higher flow splitting accuracy than traditional threshold control is achieved, avoiding health and safety problems such as pipeline pollution and soil heavy metal accumulation caused by the direct reuse of non-conventional water sources without effective monitoring, and effectively meeting the water supply demands at different times and in different scenarios; by constructing a self-optimization mechanism based on water supply demands, a closed loop of "data collection - decision-making control - feedback optimization" is formed to ensure that the control system automatically adapts to scenarios of water quality fluctuations and changes in user water usage habits; through the deep integration of "sensor network - intelligent algorithm - automation equipment", a safe, efficient, and adaptive building water resource recycling system is constructed, filling the technical gaps in non-real-time monitoring, non-intelligent allocation, and non-closed-loop management of traditional systems, and providing a green, economical, standardized, and replicable solution for the water-saving transformation of large public buildings and high-rise residential buildings. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a connection schematic diagram of an intelligent water-saving building water supply and drainage system of the present invention;

[0027] Figure 2 It is a schematic diagram of the neural network model shown in the embodiment of the present invention;

[0028] Figure 3 It is a flowchart of the control method of an intelligent water-saving building water supply and drainage system of the present invention;

[0029] Reference numerals: 1 - rainwater collection module, 11 - roof water collection device, 111 - roof diversion slope, 112 - roof water collection tank, 12 - ground water collection device, 121 - ground diversion slope, 122 - ground water collection tank, 13 - rainwater pipe, 2 - reclaimed water collection module, 21 - dedicated reclaimed water interface, 22 - reclaimed water pipe, 23 - check valve device, 24 - impurity interception device, 3 - water quality monitoring module, 31 - turbidity sensor, 32 - chemical oxygen demand sensor, 33 - pH sensor, 4 - intelligent decision-making module, 5 - electromagnetic flow splitting valve device, 6 - water storage tank module, 61 - flushing water storage tank, 62 - greening irrigation water storage tank, 63 - vehicle washing water storage tank, 64 - equipment cooling water storage tank, 65 - standby water storage tank, 66 - water level sensor. Specific embodiments

[0030] The following further describes the embodiments of the present invention in conjunction with the accompanying drawings and reference numerals, so that those skilled in the art can implement it after studying this specification. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0031] The first aspect of this application discloses an intelligent water-saving building water supply and drainage system as Figure 1-2 shown, which includes a rainwater collection module 1, a reclaimed water collection module 2, a water quality monitoring module 3, a water storage tank module 6, an intelligent decision-making module 4, and an electromagnetic flow diversion valve device 5;

[0032] The rainwater collection module 1 includes a roof water collection device 11, a ground water collection device 12, and a rainwater pipe 13; the roof water collection device 11 includes a roof diversion slope 111 and a roof water collection trough 112, which are used to converge and guide roof rainwater into the rainwater pipe 13; the ground water collection device 12 includes a ground diversion slope 121 and a ground water collection trough 122, which are used to converge and guide ground rainwater into the rainwater pipe 13; the rainwater pipe 13 is used for the connection between the roof water collection device 11 and the ground water collection device 12 and the electromagnetic flow diversion valve device 5;

[0033] The reclaimed water collection module 2 includes a reclaimed water special interface 21, a reclaimed water pipe 22, a check valve device 23, and an impurity interception device 24; the reclaimed water special interface 21 is used to connect with non-fecal sewage drainage points inside the building, including drainage points such as laundry water and bath water; the reclaimed water pipe 22 is used for the connection between the reclaimed water special interface 21 and the electromagnetic flow diversion valve device 5; the check valve device 23 is used to ensure the one-way flow of reclaimed water in the reclaimed water pipe 22; the impurity interception device 24 uses a stainless steel filter screen to intercept impurities in the reclaimed water;

[0034] The water quality monitoring module is arranged in the rainwater pipe and the reclaimed water pipe and forms a wireless connection with the intelligent decision-making module; the water quality monitoring module 3 includes a turbidity sensor 31, a chemical oxygen demand sensor 32, and a pH sensor 33; the turbidity sensor 31 is used to obtain the turbidity data of rainwater and reclaimed water; the chemical oxygen demand sensor 32 is used to obtain the chemical oxygen demand data of rainwater and reclaimed water; the pH sensor 33 is used to obtain the pH data of rainwater and reclaimed water;

[0035] The water storage tank module 6 includes a toilet flushing water storage tank 61, a greening irrigation water storage tank 62, a vehicle washing water storage tank 63, an equipment cooling water storage tank 64, a spare water storage tank 65 and a water level sensor 66; the toilet flushing water storage tank 61, the greening irrigation water storage tank 62, the vehicle washing water storage tank 63 and the equipment cooling water storage tank 64 are respectively used to meet the water source requirements for toilet flushing, greening irrigation, vehicle washing and equipment cooling; the spare water storage tank 65 is used to store rainwater and reclaimed water whose water quality conditions do not meet the water source requirements for toilet flushing, greening irrigation, vehicle washing and equipment cooling; the water level sensor 66 is installed in the toilet flushing water storage tank 61, the greening irrigation water storage tank 62, the vehicle washing water storage tank 63, the equipment cooling water storage tank 64 and the spare water storage tank 65, and is used to monitor the water level and record the current season and time, and forms a wireless connection with the intelligent decision-making module 4; in a specific implementation, ultraviolet disinfection devices are provided in the toilet flushing water storage tank 61, the greening irrigation water storage tank 62, the vehicle washing water storage tank 63, the equipment cooling water storage tank 64 and the spare water storage tank 65 and are started regularly for sterilization;

[0036] The electromagnetic flow dividing valve device 5 is located between the rainwater pipe 13, the reclaimed water pipe 22 and the water storage tank module 6; according to the current direction and current intensity applied to the electromagnetic flow dividing valve device 5, the water flow channel direction and the water flow channel opening degree of the electromagnetic flow dividing valve device 5 are controlled, so as to control the water flow direction and flow rate;

[0037] The intelligent decision-making module 4 receives the data of the water quality monitoring module 3 and the water level sensor 66 through wireless connection, and outputs the prediction result to the electromagnetic flow dividing valve device 5 through wireless connection; the intelligent decision-making module 4 adopts neural network model technology, and the neural network model includes an input layer (I1, I2, … I 12 ), a hidden layer (h1 [1] , h2 [1] , … h n [3]) and an output layer (O1, O2, O3, O4); the input layer has a total of 13 nodes, which are used to receive the normalized water quality data and water volume demand data. The water quality data includes the turbidity data of rainwater, the chemical oxygen demand data of rainwater, the pH data of rainwater, the turbidity data of reclaimed water, the chemical oxygen demand data of reclaimed water, and the pH data of reclaimed water; the water volume demand data includes the water level data of the flushing water storage tank, the water level data of the greening irrigation water storage tank, the water level data of the vehicle washing water storage tank, the water level data of the equipment cooling water storage tank, the water level data of the standby water storage tank, the current season data, and the current time data; the hidden layer is used for data processing and feature extraction; the output layer is used to generate a prediction result, and the prediction result is the water volume entering the flushing water storage tank 61, the greening irrigation water storage tank 62, the vehicle washing water storage tank 63, the equipment cooling water storage tank 64, and the standby water storage tank 65 respectively; a control quantity is further generated according to the prediction result, and the control quantity includes the current direction and current intensity applied to the electromagnetic flow splitting valve device 5; the neural network model uses the historical data of the intelligent water-saving building water supply and drainage system as training data.

[0038] The second aspect of the present application discloses a control method for an intelligent water-saving building water supply and drainage system as shown in Figure 3 and includes the following steps:

[0039] S1. Real-time collection of water quality parameters: When rainwater flows through the rainwater pipe 13 and reclaimed water flows through the reclaimed water pipe 22, the water quality data of rainwater and reclaimed water are obtained through the water quality monitoring module 3; the sampling period Δt is 60 s, so as to balance data real-time performance and system energy consumption;

[0040] S2. Real-time collection of water volume demand data: The water volume demand data is obtained through the water level sensor 64;

[0041] S3. Decision-making on dynamic water flow splitting: The normalized water quality data and water volume demand data are input into the intelligent decision-making module 4, and the generated prediction result is the water volume entering the flushing water storage tank 61, the greening irrigation water storage tank 62, the vehicle washing water storage tank 63, the equipment cooling water storage tank 64, and the standby water storage tank 65 respectively. A control quantity is further generated according to the prediction result, and the control quantity includes the current direction and current intensity applied to the electromagnetic flow splitting valve device 5;

[0042] S4. Control of water dynamic diversion: According to the control quantity generated by the intelligent decision-making module 4, control the current direction and current intensity applied to the electromagnetic water diversion valve device 5, so as to control the water flow channel direction and water flow channel opening degree of the electromagnetic water diversion valve device 5, and further control the water flow direction and flow rate, so that the rainwater collected by the rainwater collection module 1 or the reclaimed water collected by the reclaimed water collection module 2 enters the toilet flushing water storage tank 61, the greening irrigation water storage tank 62, the vehicle washing water storage tank 63, the equipment cooling water storage tank 64 or the standby water storage tank 65;

[0043] S5. Self-optimization of the control system: The intelligent water-saving building water supply and drainage system continuously collects water demand data through the water level sensor 66 during use, obtains the relationship between the water demand for toilet flushing, greening irrigation, vehicle washing and equipment cooling changing with seasons and time, and updates the weight parameters of the neural network model by using the gradient descent method to ensure that the neural network model realizes self-optimization according to the water demand data, and further ensures that the intelligent water-saving building water supply and drainage system automatically adapts to the scenarios of water quality fluctuations and changes in user water use habits; In specific implementation, a comprehensive loss function including the water demand for toilet flushing, greening irrigation storage, vehicle washing and equipment cooling is constructed to optimize the parameters θ of the neural network model; The comprehensive loss function L(θ) satisfies the following expression:

[0044]

[0045] where β i (i = 1, 2, 3, 4) are the weight coefficients of the water demand for toilet flushing, greening irrigation storage, vehicle washing and equipment cooling respectively, and β i are all not less than 0 and satisfy β1 + β2 + β3 + β4 = 1; Q i (i = 1, 2, 3, 4) are the water demand changing with time for toilet flushing, greening irrigation storage, vehicle washing and equipment cooling respectively;

[0046] When updating the weight parameters of the neural network model by using the gradient descent method, the parameters θ of the neural network model satisfy the following expression:

[0047]

[0048] where η is the learning rate, and its value range is [0.01, 0.1], which is used to balance the convergence speed and accuracy of the gradient descent method.

[0049] It can be seen that by integrating turbidity, chemical oxygen demand, and pH sensors in rainwater pipes and reclaimed water pipes to obtain water quality data in real time, dynamically evaluating the water quality grades of rainwater and reclaimed water and the water volume requirements at different times and in different scenarios according to the neural network model, a higher diversion accuracy than traditional threshold control can be achieved, avoiding health and safety problems such as pipeline pollution and soil heavy metal accumulation caused by the direct reuse of non-conventional water sources without effective monitoring, and effectively meeting the water supply requirements at different times and in different scenarios; by constructing a self-optimizing mechanism based on water supply requirements, a closed loop of "data collection - decision control - feedback optimization" is formed to ensure that the control system automatically adapts to scenarios of water quality fluctuations and changes in user water use habits; through the deep integration of "sensor network - intelligent algorithm - automation equipment", a safe, efficient, and adaptive building water resource recycling system is constructed, filling the technical gaps of traditional systems in non-real-time monitoring, non-intelligent distribution, and non-closed-loop management, and providing a green, economic, standardized, and replicable solution for the water-saving transformation of large public buildings and high-rise residential buildings.

[0050] The above are one or more embodiments of the present invention, and the description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the appended claims.

Claims

1. An intelligent water-saving building water supply and drainage system, characterized in that: It includes a rainwater collection module, a grey water collection module, a water quality monitoring module, a water storage tank module, an intelligent decision-making module and an electromagnetic diversion water valve device; The rainwater collection module includes a roof water collection device, a ground water collection device and a rainwater pipe; the roof water collection device includes a roof diversion slope and a roof water collection tank, which are used to collect and guide roof rainwater into the rainwater pipe; the ground water collection device includes a ground diversion slope and a ground water collection tank, which are used to collect and guide ground rainwater into the rainwater pipe; the rainwater pipe is used to connect the roof water collection device and the ground water collection device with the electromagnetic diversion water valve device; The grey water collection module includes a grey water dedicated interface, a grey water pipe, a check valve device and an impurity interception device; the grey water dedicated interface is used to connect with the non-fecal sewage drainage point inside the building; the grey water pipe is used to connect the grey water dedicated interface and the electromagnetic diversion valve device; the check valve device is used to ensure that the grey water flows in one direction in the grey water pipe; the impurity interception device uses a stainless steel filter to intercept impurities in the grey water; The water quality monitoring module is arranged in the rainwater pipe and the grey water pipe, and forms a wireless connection with the intelligent decision-making module; the water quality monitoring module includes a turbidity sensor, a chemical oxygen demand sensor and a pH sensor; the turbidity sensor is used to obtain turbidity data of rainwater and grey water; the chemical oxygen demand sensor is used to obtain chemical oxygen demand data of rainwater and grey water; the pH sensor is used to obtain pH data of rainwater and grey water; The water tank module includes a toilet flushing water tank, a greening irrigation water tank, a vehicle washing water tank, an equipment cooling water tank, a spare water tank and a water level sensor; the toilet flushing water tank, the greening irrigation water tank, the vehicle washing water tank and the equipment cooling water tank are respectively used to meet the water source requirements of toilet flushing, greening irrigation, vehicle washing and equipment cooling; the spare water tank is used to store rainwater and grey water whose water quality conditions do not meet the water source requirements of toilet flushing, greening irrigation, vehicle washing and equipment cooling; the water level sensor is installed in the toilet flushing water tank, the greening irrigation water tank, the vehicle washing water tank, the equipment cooling water tank and the spare water tank, and is used to monitor the water level and record the current season and time, and is wirelessly connected to the intelligent decision-making module; The electromagnetic diverter valve device is located between the rainwater pipe, the medium water pipe and the water storage tank module; the direction and opening of the water flow channel of the electromagnetic diverter valve device are controlled according to the direction and intensity of the current applied to the electromagnetic diverter valve device; The intelligent decision-making module receives data from the water quality monitoring module and the water level sensor via a wireless connection, and outputs a prediction result to the electromagnetic diversion water valve device via a wireless connection.

2. According to claim 1, an intelligent water-saving building water supply and drainage system is characterized in that: The intelligent decision-making module adopts neural network model technology, and the neural network model includes an input layer, a hidden layer and an output layer; the input layer has a total of 13 nodes for receiving normalized water quality data and water demand data, the water quality data includes rainwater turbidity data, rainwater chemical oxygen demand data, rainwater pH data, grey water turbidity data, grey water chemical oxygen demand data and grey water pH data; the water demand data includes water level data of toilet flushing water tanks, water level data of greening irrigation water tanks, water level data of vehicle washing water tanks, and water level data of equipment cooling water tanks. The invention discloses a method for preparing a water-saving building water supply and drainage system according to the present invention, wherein the water level data of the standby water tank, the current season data and the current time data are respectively entered into the toilet flushing water tank, the greening irrigation water tank, the vehicle washing water tank, the equipment cooling water tank and the standby water tank; the control quantity is further generated according to the prediction result, and the control quantity includes the current direction and current intensity applied to the electromagnetic diversion water valve device; the neural network model uses the past historical data of the intelligent water-saving building water supply and drainage system as training data.

3. A control method for an intelligent water-saving building water supply and drainage system, characterized in that: An intelligent water-saving building water supply and drainage system as claimed in any one of claims 1 to 2 comprises the following steps: S1. Real-time collection of water quality parameters: When rainwater flows through the rainwater pipe and the intermediate water flows through the intermediate water pipe, the water quality data of rainwater and intermediate water are obtained through the water quality monitoring module; S2. Real-time collection of water demand data: obtaining water demand data through water level sensors; S3, decision on water dynamic diversion: input the normalized water quality data and water demand data into the intelligent decision-making module, and generate prediction results of the water volumes entering the toilet flushing water tank, the greening irrigation water tank, the vehicle washing water tank, the equipment cooling water tank and the standby water tank, and further generate control quantities based on the prediction results, including the current direction and current intensity applied to the electromagnetic diversion water valve device; S4, control of water dynamic diversion: according to the control amount generated by the intelligent decision-making module, control the direction and current intensity of the current applied to the electromagnetic diversion water valve device, thereby controlling the direction and opening of the water flow channel of the electromagnetic diversion water valve device, and then controlling the direction and flow of water flow, so that the rainwater collected by the rainwater collection module or the gray water collected by the gray water collection module enters the toilet flushing water tank, the greening irrigation water tank, the vehicle washing water tank, the equipment cooling water tank or the spare water tank; S5. Self-optimization of the control system: The intelligent water-saving building water supply and drainage system continuously collects water demand data through water level sensors during use, obtains the correlation between the water demand for flushing toilets, green irrigation, vehicle washing and equipment cooling that changes with the season and time, and uses the gradient descent method to update the weight parameters of the neural network model to ensure that the neural network model is self-optimized according to the water demand data, thereby ensuring that the intelligent water-saving building water supply and drainage system automatically adapts to scenarios where water quality fluctuates and users' water use habits change.

4. The control method of an intelligent water-saving building water supply and drainage system according to claim 3 is characterized in that: In step S5, a comprehensive loss function including the water demand for toilet flushing, green irrigation storage, vehicle washing and equipment cooling is constructed to optimize the parameter θ of the neural network model; the comprehensive loss function L(θ) satisfies the following expression: Among them, β i (i=1,2,3,4) are the weight coefficients of water demand for toilet flushing, green irrigation, vehicle washing and equipment cooling, respectively. i are not less than 0 and satisfy β1+β2+β3+β4=1; Q i (i=1,2,3,4) are the time-varying water demands for toilet flushing, green irrigation, vehicle washing and equipment cooling respectively; The gradient descent method is used to update the weight parameters of the neural network model, and the parameters θ of the neural network model satisfy the following expression: Where η is the learning rate.

Images