Ecological chain type restoration system and method for urban water environment

Abstract

The invention discloses an urban water environment ecological chain type restoration system and method, and relates to the technical field of urban water environment restoration, the system comprises the following components: a monitoring unit, a data processing and analysis unit, a decision generation module and a restoration execution unit; according to the method, the water quality, the biocenosis structure and the environmental parameter change of the urban water environment are monitored in real time, and the monitored data are deeply analyzed and processed by utilizing a machine learning algorithm, so that problems and potential risks existing in the water environment can be accurately identified, and the water environment can be accurately identified on the basis of the analysis results. The system can automatically generate a restoration strategy adjustment instruction aiming at the current water environment condition, so that intelligent and precise restoration of the urban water environment is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of urban water environment restoration, and in particular to an urban water environment ecological chain restoration system and method thereof. Background Art

[0002] As an important part of the urban ecosystem, the health of the urban water environment is directly related to the quality of life of urban residents, the stability and sustainable development of the urban ecosystem. With the acceleration of urbanization, the urban water environment is facing unprecedented pressure and challenges, such as water pollution, imbalance in the structure of biological communities, and increasingly prominent problems of ecological function degradation.

[0003] There are deficiencies in traditional urban water environment restoration technologies. Traditional water environment restoration methods often cannot accurately identify problems and potential risks in the water environment.

[0004] To sum up, traditional water environment restoration methods have obvious shortcomings and cannot meet the urgent needs of current urban water environment restoration work. Therefore, it is particularly important to develop an urban water environment ecological chain restoration system and method. Summary of the invention

[0005] The purpose of the present invention is to make up for the deficiencies of the prior art and to provide an urban water environment ecological chain restoration system and method thereof, which can be achieved through.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an urban water environment ecological chain restoration system and method thereof, the system comprising the following components: a monitoring unit, a data processing and analysis unit, a decision-making generation module and a restoration execution unit;

[0007] The monitoring unit: monitors the water quality, biological community structure and environmental parameter changes of the urban water environment in real time. The monitoring unit includes a water quality sensor group, a biological monitoring module and an environmental parameter monitor. The water quality sensor group includes sensors for detecting conventional water quality indicators and sensors for specific pollutants. The biological monitoring module uses image recognition technology combined with gene sequencing technology to monitor and analyze the microbial community, aquatic plant species and distribution density, and aquatic animal population structure in the water body. The environmental parameter monitor monitors the meteorological data and hydrological and geographical parameters of the restoration area in real time;

[0008] The data processing and analysis unit analyzes and processes the data collected by the monitoring unit through a machine learning algorithm and generates a repair strategy adjustment instruction, wherein the machine learning algorithm uses an intelligent algorithm that integrates a hybrid neural network and an evolutionary algorithm, and the algorithm formula is: Where y is the predicted result, x iis the input data of the neural network, g(x i ) is the neuron activation function of the neural network, a i is the weight parameter of the neural network part, x j is the input data of the evolutionary algorithm, h(x j ) is the fitness function in the evolutionary algorithm, w j is the weight parameter of the evolutionary algorithm part, and b is the balance coefficient;

[0009] The decision generation module: based on the analysis results of the above algorithm and in combination with the preset restoration strategy library, automatically generates restoration strategy adjustment instructions for the current water environment conditions;

[0010] The restoration execution unit adjusts and optimizes the microbial community, aquatic plant community, hydrodynamic conditions and ecological habitat according to the instructions of the data processing and analysis unit. The restoration execution unit includes a microbial restoration module, an aquatic plant restoration module, a hydrodynamic regulation module and an ecological habitat construction and maintenance module.

[0011] Furthermore, the specific pollutant sensors in the water quality sensor group are integrated using microfluidic chip technology. A plurality of microchannels are constructed inside the microfluidic chip. Each microchannel is designed with a specific identification and detection unit for a specific pollutant. For the heavy metal ion detection channel, ion exchange resin is fixed in combination with electrochemical detection electrodes to achieve selective adsorption and quantitative detection of specific heavy metal ions. The size of the microchannel is optimized through fluid mechanics simulation to ensure that the flow state of the sample in the channel is stable and the detection reaction is fully carried out. At the same time, the chip is modular, which can easily replace and upgrade the sensor unit, thereby improving the sensor group's adaptability to the detection of various new pollutants and providing a comprehensive and flexible detection method for precise monitoring.

[0012] Furthermore, the image recognition technology of the biological monitoring module is based on a deep neural network architecture of multi-scale feature fusion. At the front end of the network, convolution kernels of different scales are used to process images in parallel to extract multi-scale features from microscopic biological cell structures to macroscopic biological community distributions. These multi-scale features are then fused through a feature fusion layer to enhance the expression capabilities of biological image features. During the network training process, a combination of transfer learning and incremental learning is adopted. First, a large-scale general biological image data set is used for pre-training. Then, based on the characteristics of aquatic environment biological images, a small number of labeled aquatic environment biological images are used for incremental training. The network parameters are adjusted quickly and accurately, so that the network can effectively identify changes in biological species and community characteristics in different water environments, providing an accurate data basis for ecosystem health assessment.

[0013] Furthermore, the neuron activation function g of the neural network part in the core of the machine learning algorithm of the data processing and analysis unit is ( x i) In piecewise function form: Among them, c, d, f, g, h, k, l, e1, and e2 parameters are determined by analyzing the distribution characteristics of different types of water quality data. A linear function is used for water quality indicators that change linearly in the low concentration range, a quadratic function is used for indicators that have a nonlinear change trend in the medium concentration range, and a logarithmic function is used for indicators that change relatively slowly in the high concentration range. By discussing the activation function in the form of a piecewise function, the neural network can more accurately fit the changing laws of water quality data in different concentration ranges, thereby improving the accuracy of the algorithm in predicting water quality changes.

[0014] Furthermore, the microbial cultivation reactor in the microbial remediation module of the remediation execution unit adopts a gradient temperature and gradient nutrient supply system. A plurality of temperature zones are arranged in the reactor. Different zones are separated by heat conduction isolation materials. The temperature of each zone is controlled by an independent heating and cooling device to form a gradient temperature environment from low temperature to high temperature to meet the temperature requirements of different microbial strains at different growth stages. At the same time, the nutrient supply system adopts a multi-pipeline layered supply method. Different pipelines transport nutrients of different types and concentrations. According to the distribution position and growth stage of the microorganisms in the reactor, the supply type and concentration of nutrients are precisely controlled to promote the efficient cultivation of microorganisms and the enhancement of specific functions, so as to provide suitable microbial agents for coping with different pollution conditions.

[0015] Furthermore, the aquatic plant maintenance equipment in the aquatic plant restoration module of the restoration execution unit adopts an intelligent lighting and carbon dioxide supplementation system, which monitors the light intensity and lighting time on the water surface in real time through light sensors. When the light intensity is lower than the optimal growth light requirement of aquatic plants, the intelligent lighting system automatically starts the fill light. The spectrum and light intensity of the fill light are adjusted according to the photosynthesis characteristics of different aquatic plants, thereby improving the aquatic plants' ability to absorb and purify water nutrients.

[0016] Furthermore, the agitator in the hydrodynamic control module of the repair execution unit adopts magnetic levitation shaftless stirring technology. The rotating parts inside the agitator are suspended in the water body through magnetic levitation technology. There is no traditional mechanical shaft connection, which reduces mechanical friction and energy loss and improves stirring efficiency. At the same time, the speed and stirring direction of the agitator can be precisely controlled according to the instructions of the data processing and analysis unit. The driving and regulation of the stirring parts are achieved by changing the magnetic field strength and direction. In the design of the stirring blades, the bionics principle is adopted to imitate the swimming posture of aquatic animals to design the blade shape and motion trajectory, so that the water flow generated during the stirring process is softer and has a good turbulent effect, which can not only promote the full contact between pollutants and microorganisms and aquatic plants, but also reduce mechanical damage to aquatic organisms and optimize the hydrodynamic control effect.

[0017] Furthermore, the ecological habitat construction in the ecological habitat construction and maintenance module of the restoration execution unit is customized and manufactured using 3D printing technology. According to the terrain, water flow conditions and biological community needs of different waters, 3D printing technology is used to manufacture ecological habitat models with complex internal structures and different surface roughness. In terms of maintenance, regular non-destructive testing of the ecological habitat structure is performed to promptly detect damage or blockage of the structure. The repairability of 3D printing is used to quickly manufacture and replace damaged parts to ensure the long-term stability and effectiveness of the ecological habitat and promote the recovery and maintenance of biodiversity.

[0018] On the other hand, a method for ecological chain restoration of urban water environment is characterized in that the method comprises the following specific steps:

[0019] S1, monitoring step: real-time monitoring of water quality, biological community structure and environmental parameter changes of urban water environment, wherein the monitoring unit includes a water quality sensor group, a biological monitoring module and an environmental parameter monitor, wherein the water quality sensor group includes sensors for detecting conventional water quality indicators and sensors for specific pollutants, the biological monitoring module uses image recognition technology combined with gene sequencing technology to monitor and analyze microbial communities, aquatic plant species and distribution density, and aquatic animal population structure in the water body, and the environmental parameter monitor monitors the meteorological data and hydrological and geographical parameters of the restoration area in real time;

[0020] S2, data processing and analysis step: Analyze and process the data collected by the monitoring unit through a machine learning algorithm and generate repair strategy adjustment instructions. The machine learning algorithm uses an intelligent algorithm that combines a hybrid neural network and an evolutionary algorithm. The algorithm formula is: Where y is the predicted result, x i is the input data of the neural network, g(x i is the neuron activation function of the neural network, a iis the weight parameter of the neural network part, x j is the input data of the evolutionary algorithm, h(x j ) is the fitness function in the evolutionary algorithm, w j is the weight parameter of the evolutionary algorithm part, and b is the balance coefficient;

[0021] S3, decision making step: based on the analysis results of the above algorithm and in combination with the preset restoration strategy library, automatically generate restoration strategy adjustment instructions for the current water environment conditions;

[0022] S4, restoration execution step: adjust and optimize the microbial community, aquatic plant community, hydrodynamic conditions and ecological habitat according to the instructions of the data processing and analysis unit, and the restoration execution unit includes a microbial restoration module, an aquatic plant restoration module, a hydrodynamic regulation module and an ecological habitat construction and maintenance module.

[0023] Compared with the prior art, the urban water environment ecological chain restoration system and method thereof have the following beneficial effects:

[0024] 1. The system monitors the water quality, biological community structure and environmental parameter changes of the urban water environment in real time, and uses machine learning algorithms to conduct in-depth analysis and processing of the monitoring data. It can accurately identify problems and potential risks in the water environment. Based on these analysis results, the system can automatically generate repair strategy adjustment instructions for the current water environment conditions, thereby realizing intelligent and precise repair of the urban water environment.

[0025] 2. The system adopts ecological restoration technologies and means, including microbial restoration, aquatic plant restoration, hydrodynamic regulation, and ecological habitat construction and maintenance. These technologies and means work together to form a complete ecological chain restoration system, which can comprehensively restore and optimize the urban water environment from multiple aspects. By adjusting and optimizing microbial communities, aquatic plant communities, hydrodynamic conditions and key ecological elements of ecological habitats, the system can effectively restore and enhance the ecological functions of the urban water environment, promote the restoration and maintenance of biodiversity, and thus build a healthier and more stable urban water ecosystem. This comprehensive ecological restoration method is of great significance to the protection and improvement of the urban water environment.

[0026] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 It is a process operation diagram of an urban water environment ecological chain restoration system;

[0029] Figure 2 This is a process operation diagram of an urban water environment ecological chain restoration method. DETAILED DESCRIPTION

[0030] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation mode, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0031] Embodiment 1

[0032] This embodiment describes the ecological chain restoration of urban landscape lakes.

[0033] Multiple monitoring points are arranged in urban landscape lakes, and water quality sensor groups are installed. Conventional water quality indicator sensors monitor water temperature, pH value, dissolved oxygen, chemical oxygen demand (COD), and ammonia nitrogen parameters. Specific pollutant sensors use microfluidic chip technology to detect heavy metals and organic pollutants that may exist in lakes. For example, the ion exchange resin stationary phase and electrochemical detection electrodes in the microfluidic chip can accurately detect the copper ion concentration in the lake water at 0.05 mg / L and the lead ion concentration at 0.02 mg / L.

[0034] The biological monitoring module uses image recognition technology combined with gene sequencing technology to monitor the microbial communities, aquatic plant species and distribution density, and aquatic animal population structure in the lake. Through a deep neural network architecture with multi-scale feature fusion, the changes in the distribution density of green algae and diatoms in the lake water, as well as changes in the population size of carp and crucian carp are identified. Gene sequencing technology is used to analyze the structure of microbial communities, and it is found that the abundance of some beneficial microorganisms is low.

[0035] The environmental parameter monitor monitors meteorological data and hydrological and geographical parameters in real time. For example, when the temperature rises in summer, it detects that the lake water level drops by 0.5 meters and the water flow speed slows down to 0.1m / s.

[0036] The data acquisition and transmission subunit collects monitoring data and transmits it to the machine learning algorithm core, which uses an intelligent algorithm that combines a hybrid neural network and an evolutionary algorithm for analysis. Where y is the predicted result, x i is the input data of the neural network, g(x i ) is the neuron activation function of the neural network, a i is the weight parameter of the neural network part, x j is the input data of the evolutionary algorithm, h(x j ) is the fitness function in the evolutionary algorithm, w j is the weight parameter of the evolutionary algorithm part, b is the balance coefficient, the input data of the neural network part includes water quality monitoring data, the neuron activation function adopts a piecewise function form, and the appropriate function form is selected for calculation according to the concentration range of different water quality indicators. The input data of the evolutionary algorithm part is the biological community monitoring data, and the fitness function is set according to the health status and stability of the biological community.

[0037] Combined with the preset remediation strategy library, remediation strategy adjustment instructions are generated according to the algorithm analysis results. For example, when it is found that the ammonia nitrogen concentration in the water is high and the abundance of beneficial microorganisms is low, instructions are generated to increase the amount of nitrifying bacteria in the microbial remediation module.

[0038] The microbial cultivation reactor adopts a gradient temperature and gradient nutrient supply system to cultivate beneficial microorganisms such as nitrifying bacteria in the reactor. Temperature zones are set in the reactor to control the temperature of the low-temperature zone at 20°C, the temperature of the medium-temperature zone at 25°C, and the temperature of the high-temperature zone at 30°C to promote the growth of microorganisms. According to the growth stage of the microorganisms, a multi-channel layered supply method is used to provide high-concentration nitrogen source nutrients in the initial stage, and then adjust to low-concentration nitrogen source and appropriate amount of carbon source nutrients in the later stage.

[0039] The intelligent lighting and carbon dioxide replenishment system of the aquatic plant maintenance equipment starts the fill light on cloudy days or when there is insufficient light based on the light sensor data. For lotus aquatic plants, the fill light spectrum is adjusted to a red light and blue light ratio of 3:1 and a light intensity of 2000-3000 lux to meet their photosynthesis needs. At the same time, carbon dioxide is replenished regularly to promote the growth of aquatic plants, absorb nutrients in the water, and improve water quality.

[0040] The magnetic levitation shaftless agitator adjusts the stirring speed and direction according to instructions. In the high temperature of summer, the stirring speed is increased to 100rpm to enhance the fluidity of the water, prevent local overheating of the water and excessive growth of algae. The stirring blades imitate the swimming posture of fish, improve the stirring efficiency, promote the contact between lake water and oxygen, and increase the dissolved oxygen content.

[0041] 3D printing technology is used to customize the manufacture of ecological habitats. According to the lake terrain and biological community needs, artificial fish reefs with porous structures and appropriate roughness are printed and placed in the shallow waters of the lake to provide habitats and breeding places for fish. The ecological habitats are regularly tested for non-destructive purposes using underwater robots. When the fish reefs are found to be slightly damaged, 3D printing technology is used to quickly manufacture and replace the damaged parts to ensure the stability of the ecological habitat.

[0042] Embodiment 2

[0043] This embodiment describes the ecological chain restoration of an urban river.

[0044] A monitoring point is set up every 500 meters along the city's rivers. The conventional water quality indicator sensors in the water quality sensor group monitor the turbidity, conductivity, total phosphorus and total nitrogen indicators of the river water in real time. The specific pollutant sensors detect cyanide and volatile phenol pollutants that may exist in industrial wastewater. For example, the total phosphorus concentration in a certain section of river water was detected to be 0.3 mg / L, and the total nitrogen concentration was 2.5 mg / L, which exceeded the fourth category standard for surface water.

[0045] The biological monitoring module uses image recognition technology to analyze changes in the coverage area of ​​aquatic plants, gene sequencing technology to monitor changes in the types and numbers of microorganisms that decompose organic pollutants in the microbial community, and observes the activities of aquatic animals. It was found that the number of some microorganisms in the microbial community that can degrade organic pollutants is relatively small, which affects the self-purification ability of the river water.

[0046] Environmental parameter monitors monitor changes in inland river water levels, water flow speeds, and surrounding meteorological data.

[0047] The data acquisition and transmission subunit transmits the monitoring data to the core of the machine learning algorithm. Where y is the predicted result, x i is the input data of the neural network, g(x i ) is the neuron activation function of the neural network, a i is the weight parameter of the neural network part, x j is the input data of the evolutionary algorithm, h(x j ) is the fitness function in the evolutionary algorithm, w j is the weight parameter of the evolutionary algorithm, b is the balance coefficient, the neural network inputs the water quality monitoring data, and the neuron activation function is calculated according to the characteristics of different indicators. The parameters c, d, f, g, h, k, l, e1, and e2 are determined by analyzing the distribution characteristics of different types of water quality data. The evolutionary algorithm part inputs the biological community monitoring data, and the fitness function evaluates the contribution of the biological community to water purification.

[0048] Instructions are generated based on the algorithm analysis results and the restoration strategy library. For example, when it is found that total phosphorus and total nitrogen exceed the standard and degradation microorganisms are insufficient, instructions are given to increase the release of specific microbial agents and adjust the aquatic plant planting strategy.

[0049] The microbial cultivation reactor cultivates microbial flora that can efficiently degrade organic pollutants and absorb nitrogen and phosphorus. Through the gradient temperature and gradient nutrient supply system, the reactor temperature is controlled between 22-28°C, and high-phosphorus and high-nitrogen nutrients are provided in the early stage of microbial growth. In the later stage, it is adjusted to low-phosphorus and low-nitrogen nutrients to promote microorganisms to adapt to the inland river water quality environment and enhance their ability to degrade pollutants. The cultivated microbial agents are then released into the river water.

[0050] Aquatic plant maintenance equipment adjusts light according to light sensor data. For duckweed plants, the fill light is turned on when light is insufficient, and the light intensity is adjusted to 1500-2000 lux to promote their growth and reproduction. The aquatic plant planting area is reasonably planned, and water hyacinths and other plants with strong absorption capacity are planted in heavily polluted areas. The plants absorb nitrogen and phosphorus nutrients in the water to purify the water quality.

[0051] During the dry season, the magnetic levitation shaftless agitator speeds up to 80rpm according to instructions, improves hydrodynamic conditions, increases the dissolved oxygen content in the water, promotes the decomposition of pollutants by microorganisms and the growth of aquatic plants. The shape and movement trajectory of the stirring blades imitate the swimming pattern of aquatic animals, improves the stirring effect, and prevents sedimentation.

[0052] 3D printing technology is used to manufacture ecological habitats based on the shape of inland river channels and biological needs. For example, ecological bricks with complex cave structures are printed in river bends to provide habitats and breeding places for aquatic animals such as river shrimps and river crabs. The ecological habitats are inspected regularly. If the ecological bricks are found to be blocked by silt, 3D printing technology is used to manufacture parts with the same structure for replacement, thus ensuring the normal function of the ecological habitat.

[0053] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An urban water environment ecological chain restoration system, characterized in that: The system includes a monitoring unit, a data processing and analysis unit, a decision-making module and a repair execution unit: The monitoring unit: monitors the water quality, biological community structure and environmental parameter changes of the urban water environment in real time. The monitoring unit includes a water quality sensor group, a biological monitoring module and an environmental parameter monitor. The water quality sensor group includes sensors for detecting conventional water quality indicators and sensors for specific pollutants. The biological monitoring module uses image recognition technology combined with gene sequencing technology to monitor and analyze the microbial community, aquatic plant species and distribution density, and aquatic animal population structure in the water body. The environmental parameter monitor monitors the meteorological data and hydrological and geographical parameters of the restoration area in real time; The data processing and analysis unit analyzes and processes the data collected by the monitoring unit through a machine learning algorithm and generates a repair strategy adjustment instruction, wherein the machine learning algorithm uses an intelligent algorithm that integrates a hybrid neural network and an evolutionary algorithm, and the algorithm formula is: Where y is the predicted result, x i is the input data of the neural network, g(x i ) is the neuron activation function of the neural network, a i is the weight parameter of the neural network part, x j is the input data of the evolutionary algorithm, h(x j ) is the fitness function in the evolutionary algorithm, w j is the weight parameter of the evolutionary algorithm part, and b is the balance coefficient; The decision generation module: based on the analysis results of the above algorithm and in combination with the preset restoration strategy library, automatically generates restoration strategy adjustment instructions for the current water environment conditions; The restoration execution unit adjusts and optimizes the microbial community, aquatic plant community, hydrodynamic conditions and ecological habitat according to the instructions of the data processing and analysis unit. The restoration execution unit includes a microbial restoration module, an aquatic plant restoration module, a hydrodynamic regulation module and an ecological habitat construction and maintenance module.

2. The urban water environment ecological chain restoration system according to claim 1 is characterized in that: The specific pollutant sensors in the water quality sensor group are integrated using microfluidic chip technology. A plurality of microchannels are constructed inside the microfluidic chip. Each microchannel is designed with a specific identification and detection unit for a specific pollutant. For the heavy metal ion detection channel, ion exchange resin is fixed in combination with electrochemical detection electrodes to achieve selective adsorption and quantitative detection of specific heavy metal ions. The size of the microchannel is optimized through fluid mechanics simulation. At the same time, the chip is modularized, so the sensor unit can be easily replaced and upgraded.

3. The urban water environment ecological chain restoration system according to claim 1 is characterized in that: The image recognition technology of the biological monitoring module is based on a deep neural network architecture of multi-scale feature fusion. At the front end of the network, convolution kernels of different scales are used to process images in parallel to extract multi-scale features from microscopic biological cell structures to macroscopic biological community distributions. These multi-scale features are then fused through a feature fusion layer. During the network training process, a combination of transfer learning and incremental learning is adopted. First, a large-scale general biological image data set is used for pre-training. Then, based on the characteristics of aquatic environment biological images, a small number of labeled aquatic environment biological images are used for incremental training. The network parameters are adjusted quickly and accurately, so that the network can effectively identify changes in biological species and community characteristics in different water environments.

4. The urban water environment ecological chain restoration system according to claim 1 is characterized in that: The neuron activation function g(x) of the neural network part in the core of the machine learning algorithm of the data processing and analysis unit i ) is in piecewise function form: The parameters c, d, f, g, h, k, l, e1, and e2 are determined by analyzing the distribution characteristics of different types of water quality data. A linear function is used for water quality indicators that change linearly in the low concentration range, a quadratic function is used for indicators that have a nonlinear change trend in the medium concentration range, and a logarithmic function is used for indicators that change relatively slowly in the high concentration range.

5. The urban water environment ecological chain restoration system according to claim 1 is characterized in that: The microbial cultivation reactor in the microbial remediation module of the remediation execution unit adopts a gradient temperature and gradient nutrient supply system. A plurality of temperature zones are arranged in the reactor. Different zones are separated by heat conduction isolation materials. The temperature of each zone is controlled by an independent heating and cooling device to form a gradient temperature environment from low temperature to high temperature. At the same time, the nutrient supply system adopts a multi-pipeline layered supply method. Different pipelines transport nutrients of different types and concentrations. According to the distribution position and growth stage of the microorganisms in the reactor, the supply type and concentration of nutrients are precisely controlled to promote the efficient cultivation of microorganisms and the enhancement of specific functions.

6. The urban water environment ecological chain restoration system according to claim 1 is characterized in that: The aquatic plant maintenance equipment in the aquatic plant restoration module of the restoration execution unit adopts an intelligent lighting and carbon dioxide supplementation system, and monitors the light intensity and lighting time on the water surface in real time through a light sensor. When the light intensity is lower than the optimal growth light requirement of aquatic plants, the intelligent lighting system automatically starts the fill light, and the spectrum and light intensity of the fill light are adjusted according to the photosynthesis characteristics of different aquatic plants.

7. The urban water environment ecological chain restoration system according to claim 1 is characterized in that: The agitator in the hydrodynamic control module of the repair execution unit adopts magnetic levitation shaftless stirring technology. The rotating parts inside the agitator are suspended in the water body through magnetic levitation technology, without traditional mechanical shaft connection. At the same time, the rotation speed and stirring direction of the agitator can be precisely controlled according to the instructions of the data processing and analysis unit. The driving and control of the stirring parts are achieved by changing the magnetic field strength and direction. In the design of the stirring blades, the bionics principle is adopted to imitate the swimming posture of aquatic animals to design the blade shape and motion trajectory.

8. The urban water environment ecological chain restoration system according to claim 1 is characterized in that: The ecological habitat construction in the ecological habitat construction and maintenance module of the restoration execution unit is customized and manufactured using 3D printing technology. According to the terrain, water flow conditions and biological community needs of different waters, 3D printing technology is used to manufacture ecological habitat models with complex internal structures and different surface roughness. In terms of maintenance, regular non-destructive testing of the ecological habitat structure is performed to promptly detect damage or blockage of the structure. The repairability of 3D printing is used to quickly manufacture and replace damaged parts, thereby ensuring the long-term stability and effectiveness of the ecological habitat and promoting the recovery and maintenance of biodiversity.

9. A method for ecological chain restoration of urban water environment, characterized in that: The specific steps of this method are: S1, monitoring step: real-time monitoring of water quality, biological community structure and environmental parameter changes of urban water environment, wherein the monitoring unit includes a water quality sensor group, a biological monitoring module and an environmental parameter monitor, wherein the water quality sensor group includes sensors for detecting conventional water quality indicators and sensors for specific pollutants, the biological monitoring module uses image recognition technology combined with gene sequencing technology to monitor and analyze microbial communities, aquatic plant species and distribution density, and aquatic animal population structure in the water body, and the environmental parameter monitor monitors the meteorological data and hydrological and geographical parameters of the restoration area in real time; S2, data processing and analysis step: Analyze and process the data collected by the monitoring unit through a machine learning algorithm and generate repair strategy adjustment instructions. The machine learning algorithm uses an intelligent algorithm that combines a hybrid neural network and an evolutionary algorithm. The algorithm formula is: Where y is the predicted result, x i is the input data of the neural network, g(x i ) is the neuron activation function of the neural network, a i is the weight parameter of the neural network part, x j is the input data of the evolutionary algorithm, h(x j ) is the fitness function in the evolutionary algorithm, w j is the weight parameter of the evolutionary algorithm part, and b is the balance coefficient; S3, decision making step: based on the analysis results of the above algorithm and in combination with the preset restoration strategy library, automatically generate restoration strategy adjustment instructions for the current water environment conditions; S4, restoration execution step: adjust and optimize the microbial community, aquatic plant community, hydrodynamic conditions and ecological habitat according to the instructions of the data processing and analysis unit, and the restoration execution unit includes a microbial restoration module, an aquatic plant restoration module, a hydrodynamic regulation module and an ecological habitat construction and maintenance module.

Images