Intelligent water quality adjusting system of direct drinking water equipment

Abstract

This utility model relates to the field of water quality regulation technology, and more particularly to an intelligent water quality regulation system for direct drinking water equipment, comprising: a four-dimensional fusion sensor module, a dynamic regulation control module, an intelligent early warning and maintenance module, and a personalized interactive terminal. This utility model is the first to apply a UKF-BP neural network to a direct drinking water quality regulation system. By combining the advantages of uncertain Kalman filtering and backpropagation neural networks, it can achieve more precise water quality regulation. The four-dimensional fusion sensor design effectively solves the problems of scattered sensor layout and excessive size in traditional solutions. Based on dynamic regulation algorithms and intelligent energy management, the system achieves a 30% reduction in energy consumption, reducing energy waste, enhancing the stability and safety of water quality, significantly improving the safety of users' drinking water, reducing the risk of substandard water quality, and providing users with a healthier and safer drinking water environment.

Description

Technical Field

[0001] This utility model relates to the field of water quality regulation technology, specifically to an intelligent water quality regulation system for direct drinking water equipment. Background Technology

[0002] Currently, direct drinking water equipment still faces some technical bottlenecks in water quality regulation, affecting equipment performance improvement and user experience. These bottlenecks manifest in the following ways:

[0003] 1. Limited Adjustment Strategies: Most existing direct drinking water systems use fixed mixing ratios or preset mode switching, such as combinations of reverse osmosis and ultrafiltration, for water quality adjustment. These systems fail to consider real-time changes in water quality and personalized user needs, resulting in an inability to dynamically optimize based on different water source conditions and user requirements. The lack of intelligent adjustment mechanisms prevents the system from effectively adapting to complex water quality changes, impacting water quality stability and reliability.

[0004] 2. Dispersed Sensor Layout: Traditional direct drinking water equipment often uses multiple independent sensors to monitor water quality parameters such as pH value, conductivity, and turbidity. This sensor layout results in a large equipment size, increasing production and maintenance costs. Furthermore, dispersed sensors suffer from poor coordination during data acquisition and processing, making it difficult to achieve accurate integration and effective feedback of water quality data, thus affecting the accuracy and response speed of water quality regulation.

[0005] 3. Inefficient Energy Management: In existing direct drinking water equipment, the operating parameters are often not effectively linked to real-time flow and water quality data. This leads to problems such as ineffective heating and excessive pressurization during actual operation, resulting in energy waste and inefficient equipment operation. Therefore, how to reduce equipment energy consumption and improve overall efficiency through precise energy management has become a key issue that water quality regulation systems need to address.

[0006] 4. Lack of User Interaction: Most current direct drinking water devices lack personalized settings and cannot adjust water quality parameters, such as TDS and pH values, according to the needs of different user groups. Different users have different water quality requirements; some users are more concerned about the mineral content of the water, while others are more concerned about the acidity or alkalinity. Therefore, existing devices cannot meet the personalized needs of different user groups, resulting in a poor user experience and limiting the widespread application of these devices.

[0007] No solutions have yet been proposed to address the related technical issues. Utility Model Content

[0008] To address the problems in related technologies, this utility model proposes an intelligent water quality regulation system for direct drinking water equipment, overcoming the aforementioned technical issues in existing technologies. The purpose of this utility model is to apply UKF-BP neural networks to a direct drinking water quality regulation system for the first time. By combining the advantages of uncertain Kalman filtering and backpropagation neural networks, more precise water quality regulation can be achieved. The four-dimensional fusion sensor design effectively solves the problems of scattered sensor layout and excessive size in traditional solutions. Based on dynamic adjustment algorithms and intelligent energy management, the system achieves a 30% reduction in energy consumption, effectively reducing energy waste and making the equipment operate more efficiently, greatly enhancing the stability and safety of water quality.

[0009] To achieve the above objectives, this utility model provides the following technical solution: an intelligent water quality adjustment system for a direct drinking water device, comprising:

[0010] The four-dimensional fusion sensor module integrates a pH sensor, conductivity sensor, turbidity sensor and residual chlorine sensor into one unit, and adopts a three-dimensional spatial stacking layout and time-synchronized data acquisition.

[0011] The dynamic adjustment and control module includes an adaptive adjustment unit based on the UKF-BP neural network model and an energy consumption optimization unit based on the fuzzy PID algorithm;

[0012] The intelligent early warning and maintenance module has a built-in LSTM filter life prediction model and a three-level fault diagnosis mechanism;

[0013] The personalized interactive terminal supports custom settings and visualization of water quality parameters.

[0014] Preferably, the four-dimensional fusion sensor module includes:

[0015] The temperature compensation circuit ensures that the measurement error of the pH sensor, conductivity sensor, turbidity sensor, and residual chlorine sensor is less than ±1% in an environment of -5℃ to 50℃.

[0016] The high-speed data acquisition unit enables synchronous acquisition of multiple parameters at a rate of 10 times per second.

[0017] Preferably, the adaptive adjustment unit executes the following control logic:

[0018] D i = [1 / (θ×Y+1)]×[α] p ×(1+β t )+γ n ×(1+δ t )+ε pn ]+C

[0019] Among them, D i For the opening degree of the mixing valve, αp γn is the weighting coefficient between pH value and conductivity, β t δ t ε is the temperature correction factor. pn θ is the interaction coefficient, θ is the membrane module characteristic parameter, and Y is the filter cartridge usage time.

[0020] Preferably, the energy consumption optimization unit adjusts the booster pump power through real-time flow feedback, including:

[0021] A flow-power mapping table stores the optimal power parameters for different flow rates;

[0022] The fuzzy PID controller dynamically adjusts the motor speed, reducing energy consumption by more than 30%.

[0023] Preferably, the intelligent early warning and maintenance module includes:

[0024] Edge computing nodes run LSTM models to predict the remaining lifespan of filter cartridges and trigger replacement reminders 7 days in advance.

[0025] The three-level response unit executes the following sequentially when the turbidity is >5 NTU: start bypass circulation flushing, send mobile alarm, and remote fault log analysis.

[0026] Preferably, the personalized interactive terminal includes:

[0027] The water quality parameter customization interface allows users to set the target TDS value range of 80-150ppm.

[0028] The blockchain evidence storage unit writes the hash value of the water quality test report into the blockchain;

[0029] The dynamic curve display interface presents the spatiotemporal variation trend of four-dimensional water quality parameters in real time.

[0030] Preferred options also include:

[0031] The mixing valve assembly, controlled by a dynamic adjustment control module, includes at least one proportional control valve;

[0032] The multi-stage filtration device transmits filter life data to the intelligent early warning and maintenance module in real time.

[0033] Compared with the prior art, the beneficial effects of this utility model are:

[0034] (1) This utility model is an intelligent water quality regulation system for direct drinking water equipment. It is the first time that UKF-BP neural network has been applied to the direct drinking water quality regulation system. By combining the advantages of uncertainty Kalman filtering and backpropagation neural network, more accurate water quality regulation can be achieved, which significantly improves the water quality regulation accuracy to ±2%. This greatly improves the stability and reliability of water quality. By dynamically analyzing water quality changes, the system can better adapt to the complex conditions of different water sources and ensure that the quality of direct drinking water is always in the best state.

[0035] (2) This utility model is an intelligent water quality adjustment system for a direct drinking water device. By setting up a four-dimensional fusion sensor, it effectively solves the problems of scattered sensor layout and excessive size in the traditional solution. By adopting an integrated sensor solution, the space utilization rate is increased by 50%, which greatly optimizes the design of the device, making the device smaller and easier to install and maintain. It not only reduces the space occupied, but also improves the overall performance of the device and the user experience.

[0036] (3) This utility model is an intelligent water quality adjustment system for direct drinking water equipment. Based on dynamic adjustment algorithm and intelligent energy consumption management, the system achieves the goal of reducing energy consumption by 30%, which not only effectively reduces energy waste, but also makes the equipment operate more efficiently. At the same time, the filter replacement frequency is reduced by 20%, which directly reduces the maintenance frequency and cost of the equipment. Users can significantly reduce the total cost of ownership in the long term.

[0037] (4) This utility model is an intelligent water quality regulation system for direct drinking water equipment. The water quality compliance rate of the system has been increased from 92% to 98%, which greatly enhances the stability and safety of water quality, significantly improves the safety of drinking water for users, reduces the risk of substandard water quality, and provides users with a healthier and safer drinking water environment. It plays a positive role in improving public health and promoting the popularization of intelligent water treatment technology. Attached Figure Description

[0038] Figure 1 This is a schematic diagram of the overall structure of this utility model. Attached image description:

[0040] 100. Four-dimensional fusion sensor module; 110. Temperature compensation circuit; 120. High-speed data acquisition unit; 200. Dynamic adjustment and control module; 210. Flow-power mapping table; 220. Fuzzy PID controller; 300. Intelligent early warning and maintenance module; 310. Edge computing node; 320. Three-level response unit; 400. Personalized interactive terminal; 410. Water quality parameter customization interface; 420. Blockchain evidence storage unit; 430. Dynamic curve display interface; 500. Mixing valve group; 600. Multi-stage filtration device. Detailed Implementation

[0041] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention.

[0042] Example

[0043] Please see Figure 1 This utility model proposes a technical solution for an intelligent water quality adjustment system for direct drinking water equipment: an intelligent water quality adjustment system for direct drinking water equipment, comprising:

[0044] The 100 four-dimensional fusion sensor module integrates a pH sensor, conductivity sensor, turbidity sensor and residual chlorine sensor into one unit. It adopts a three-dimensional spatial stacking layout and time-synchronized data acquisition. Specifically, the volume is reduced by 40% compared with the traditional solution, the data acquisition frequency is increased to 10 times / second, and the sensor has a built-in temperature compensation circuit to ensure that the measurement accuracy error is <±1% under different environments.

[0045] The dynamic adjustment and control module 200 includes an adaptive adjustment unit based on the UKF-BP neural network model and an energy consumption optimization unit based on the fuzzy PID algorithm. Specifically, it analyzes water quality data (such as pH value and conductivity) and user water usage habits in real time, dynamically adjusts the opening ratio of the mixing valve, and adjusts the power of the booster pump according to real-time flow data through the fuzzy PID algorithm, so as to reduce the system energy consumption by more than 30%.

[0046] The Intelligent Early Warning and Maintenance Module 300 incorporates an LSTM filter life prediction model and a three-level fault diagnosis mechanism. Specifically, based on the edge computing-driven LSTM model, combined with water quality data and cumulative water production, it pushes filter replacement reminders 7 days in advance with an accuracy rate of 95%. When water quality parameters are abnormal (e.g., turbidity > 5 NTU), the system automatically triggers a three-level response: ① Initiating bypass circulation flushing; ② Sending an alarm to the user terminal; ③ Remotely downloading fault logs and automatically repairing 90% of common problems.

[0047] The personalized interactive terminal 400 supports custom settings and visualization of water quality parameters. Specifically, it supports setting target water quality parameters (such as TDS value of 80-150ppm) through a mobile APP. The system automatically matches the best treatment path, and the terminal screen displays four-dimensional water quality data curves in real time, and generates weekly / monthly water quality health reports. It also supports blockchain evidence storage.

[0048] In this embodiment, the four-dimensional fusion sensor module 100 is installed at the RO membrane outlet to monitor the quality of the permeate water in real time;

[0049] The process of the dynamic adjustment algorithm is as follows: Start → Sensor data acquisition → Data preprocessing → UKF-BP model calculation → Hybrid valve opening adjustment → Energy consumption optimization → Data upload to cloud → End;

[0050] The algorithm model is deployed on an edge computing chip using the TensorFlow Lite framework, with a response time of <200ms; the cloud platform adopts Huawei Cloud IoT solution, which supports data storage, analysis and device management.

[0051] Users can set a "tea brewing mode" (TDS=120ppm) via the APP, and the system will automatically adjust the mixing ratio; the school's direct drinking water equipment will dynamically adjust the water production flow and water quality parameters according to the water demand at different times.

[0052] Furthermore, the four-dimensional fusion sensor module 100 includes:

[0053] The temperature compensation circuit 110 ensures that the measurement error of the pH sensor, conductivity sensor, turbidity sensor, and residual chlorine sensor is less than ±1% in an environment of -5℃ to 50℃.

[0054] The high-speed data acquisition unit 120 enables synchronous acquisition of multiple parameters at a rate of 10 times per second.

[0055] Furthermore, the adaptive adjustment unit executes the following control logic:

[0056] D i = [1 / (θ×Y+1)]×[α] p ×(1+β t )+γ n ×(1+δ t )+ε pn ]+C where, D i For the opening degree of the mixing valve, α p γn is the weighting coefficient between pH value and conductivity, β t δ t ε is the temperature correction factor. pn θ is the interaction coefficient, θ is the membrane module characteristic parameter, and Y is the filter cartridge usage time.

[0057] Furthermore, the energy optimization unit adjusts the booster pump power through real-time flow feedback, including:

[0058] Flow-power mapping table 210 stores the optimal power parameters under different flow rates;

[0059] The 220 fuzzy PID controller dynamically adjusts the motor speed, reducing energy consumption by more than 30%.

[0060] Furthermore, the intelligent early warning and maintenance module 300 includes:

[0061] Edge computing node 310 runs an LSTM model to predict the remaining lifespan of the filter cartridge and triggers a replacement reminder 7 days in advance.

[0062] The Level 3 Response Unit 320 executes the following sequentially when the turbidity is >5 NTU: start bypass circulation flushing, send mobile alarm, and remote fault log analysis.

[0063] Furthermore, the personalized interactive terminal 400 includes:

[0064] The 410 water quality parameter customization interface allows users to set the target TDS value range of 80-150ppm.

[0065] Blockchain storage unit 420 writes the hash value of the water quality test report into the blockchain;

[0066] The dynamic curve display interface 430 presents the spatiotemporal variation trend of four-dimensional water quality parameters in real time.

[0067] Furthermore, it also includes:

[0068] The mixing valve assembly 500, controlled by the dynamic adjustment control module 200, includes at least one proportional control valve;

[0069] The multi-stage filtration device 600 transmits its filter life data to the intelligent early warning and maintenance module 300 in real time.

[0070] In this embodiment, the mixing valve group 500 adopts a three-way structure to realize the dynamic ratio mixing of ultrafiltration water and reverse osmosis water. The intelligent interactive terminal integrates a 7-inch touch screen and a 5G communication module, supporting local control and remote management.

[0071] This invention is the first to apply a UKF-BP neural network to a direct drinking water quality regulation system. By combining the advantages of uncertain Kalman filtering and backpropagation neural networks, it achieves more precise water quality regulation, significantly improving the accuracy to ±2%, thus greatly enhancing the stability and reliability of water quality. Through dynamic analysis of water quality changes, the system can better adapt to the complex conditions of different water sources, ensuring that the quality of direct drinking water is always at its best. By setting up a four-dimensional fusion sensor, the problems of scattered sensor layout and excessive size in traditional solutions are effectively solved. The integrated sensor solution improves space utilization by 50%, greatly optimizing the equipment design, making the equipment smaller, easier to install and maintain, and reducing costs. The system reduces space requirements while improving overall equipment performance and user experience. Based on dynamic adjustment algorithms and intelligent energy management, it achieves a 30% reduction in energy consumption, effectively reducing energy waste and making the equipment operate more efficiently. Simultaneously, filter replacement frequency is reduced by 20%, directly lowering maintenance frequency and costs, allowing users to significantly reduce total cost of ownership over long-term use. The system's water quality compliance rate has increased from 92% to 98%, greatly enhancing water quality stability and safety. This significantly improves the safety of users' drinking water, reduces the risk of substandard water quality, and provides users with a healthier and safer drinking water environment. This has a positive impact on improving public health and promoting the widespread adoption of intelligent water treatment technology.

[0072] In the description of this utility model, it should be understood that the terms "coaxial", "bottom", "one end", "top", "middle", "other end", "upper", "side", "top", "inner", "front", "center", "both ends", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. They are only for the convenience of describing this utility model and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this utility model.

[0073] In this utility model, unless otherwise explicitly specified and limited, the terms "installation", "setting", "connection", "fixing", "screw connection", etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal connection of two components or the interaction between two components. Unless otherwise explicitly limited, those skilled in the art can understand the specific meaning of the above terms in this utility model according to the specific circumstances.

[0074] Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the present invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An intelligent water quality adjusting system of a direct drinking water equipment, characterized in that, include: The four-dimensional fusion sensor module (100) integrates a pH sensor, conductivity sensor, turbidity sensor and residual chlorine sensor into one unit, and adopts a three-dimensional spatial stacking layout and time-synchronized acquisition. The dynamic adjustment control module (200) includes an adaptive adjustment unit based on the UKF-BP neural network model and an energy consumption optimization unit based on the fuzzy PID algorithm; Intelligent early warning and maintenance module (300), with built-in LSTM filter life prediction model and three-level fault diagnosis mechanism; Personalized interactive terminal (400) supports custom settings and visualization of water quality parameters.

2. The intelligent water quality adjusting system of a direct drinking water equipment according to claim 1, characterized in that, The four-dimensional fusion sensor module (100) includes: The temperature compensation circuit (110) ensures that the measurement error of the pH sensor, conductivity sensor, turbidity sensor and residual chlorine sensor is less than ±1% in an environment of -5℃ to 50℃. The high-speed data acquisition unit (120) enables synchronous acquisition of multiple parameters at a rate of 10 times per second.

3. The intelligent water quality adjusting system of a direct drinking water equipment according to claim 1, characterized in that, The adaptive adjustment unit executes the following control logic: D i =[1 / (θ×Y+1)]×[α p ×(1+β t )+c n ×(1+δ t )+e pn ]+C Among them, D i For the opening degree of the mixing valve, α p γ n β is the weighting coefficient for pH value and conductivity. t δ t ε is the temperature correction factor. pn θ is the interaction coefficient, θ is the membrane module characteristic parameter, and Y is the filter cartridge usage time.

4. The intelligent water quality adjusting system of a direct drinking water equipment according to claim 1, characterized in that, The energy consumption optimization unit adjusts the booster pump power through real-time flow feedback, including: The flow-power mapping table (210) stores the optimal power parameters under different flow rates; The fuzzy PID controller (220) dynamically adjusts the motor speed, reducing energy consumption by more than 30%.

5. The intelligent water quality adjusting system of a direct drinking water equipment according to claim 1, characterized in that, The intelligent early warning and maintenance module (300) includes: Edge computing node (310) runs LSTM model to predict the remaining life of filter element and triggers replacement reminder 7 days in advance; The three-level response unit (320) performs the following actions in sequence when the turbidity is >5 NTU: start bypass circulation flushing, send mobile terminal alarm, and remote fault log analysis.

6. The intelligent water quality adjusting system of a direct drinking water equipment according to claim 1, characterized in that, The personalized interactive terminal (400) includes: The water quality parameter customization interface (410) allows users to set the target TDS value range of 80-150ppm; The blockchain evidence storage unit (420) writes the hash value of the water quality test report into the blockchain; The dynamic curve display interface (430) presents the spatiotemporal variation trend of four-dimensional water quality parameters in real time.

7. The intelligent water quality adjusting system of a direct drinking water equipment according to claim 1, characterized in that, Also includes: The mixing valve assembly (500), controlled by the dynamic adjustment control module (200), includes at least one proportional control valve; The multi-stage filtration device (600) transmits its filter life data to the intelligent early warning and maintenance module (300) in real time.

Images