Deep-sea mining ecological restoration and restoration potential evaluation system based on efficient substratum

Abstract

The invention relates to the technical field of deep-sea ecological restoration, in particular to a deep-sea mining ecological restoration and restoration potential evaluation system based on an efficient substratum, which comprises an environmental data acquisition module, an efficient substratum design and laying module, a deep-sea noise identification and biological adhesion prediction module, a restoration strategy generation module and a restoration effect evaluation module. Wherein; the environment data acquisition module acquires environment data; the high-efficiency substratum design and laying module is used for designing a high-efficiency substratum for a deep sea environment; the deep sea noise identification and biological attachment prediction module predicts attachment behavior characteristics of the surface of an attachment base; the repair strategy generation module is used for generating a targeted repair strategy; and the restoration effect evaluation module quantitatively analyzes the restoration progress of the ecological system. According to the invention, data acquisition precision and processing capability in a complex deep sea environment are enhanced, and reliable guarantee is provided for deep sea substratum laying and ecological restoration.

Description

Technical Field

[0001] The present invention relates to the technical field of deep sea ecological restoration, and in particular to a deep sea mining ecological restoration and recovery potential assessment system based on an efficient attachment base. Background Art

[0002] Deep-sea mining activities are gradually emerging around the world, providing new prospects for the development of metal resources. However, the deep-sea ecological environment is uniquely complex and fragile. Mining activities can easily destroy the structure and function of the seabed ecosystem, including the loss of attached biological habitats, the reduction of biodiversity, and the disturbance of the sediment environment. The restoration of the deep-sea ecosystem has become a key technical link in achieving sustainable development of mining activities. However, due to the particularity of the deep-sea environment, such as high pressure, low temperature, and complex water flow and sedimentation characteristics, strict requirements are placed on the restoration technology.

[0003] Existing deep-sea ecological restoration technologies are mostly centered on artificially placed substrates, supplemented by environmental monitoring and limited effect evaluation. However, these technologies have many shortcomings. First, existing restoration strategies are insufficiently responsive to the dynamic changes of the deep-sea environment, and the dimensions and accuracy of collected data are limited, which cannot fully support the design and placement optimization of attachment substrates. Secondly, deep-sea ecological restoration lacks accurate prediction methods for the behavior of attached organisms, and restoration layout and effects often rely on experience rather than data-driven. Finally, the effect evaluation method of the restoration process lacks quantification and dynamic feedback mechanisms, making it difficult to optimize restoration strategies in a timely manner, thereby reducing restoration efficiency and the long-term stability of ecological restoration.

[0004] In response to the shortcomings of the existing technology, the present invention proposes a deep-sea mining ecological restoration and recovery potential assessment system based on a high-efficiency attachment base, which aims to significantly improve the restoration efficiency and sustainability of the effect through precise environmental data analysis, prediction of attached biological behavior, and generation and evaluation of dynamic restoration strategies, thereby providing scientific support for the stable restoration of deep-sea ecosystems and the sustainable development of mining activities. Summary of the invention

[0005] The present invention provides a deep-sea mining ecological restoration and recovery potential assessment system based on a highly efficient attachment base.

[0006] The deep-sea mining ecological restoration and recovery potential assessment system based on efficient attachment base includes an environmental data acquisition module, an efficient attachment base design and deployment module, a deep-sea noise identification and biological attachment prediction module, a restoration strategy generation module, and a restoration effect assessment module, among which; The environmental data acquisition module collects environmental data of the deep-sea restoration area in real time through multiple types of sensors, including water temperature, dissolved oxygen, pH value, nutrient concentration, sediment characteristics, current speed and direction; The efficient attachment base design and deployment module designs efficient attachment bases for deep-sea environments based on the collected environmental data, and deploys them in the target restoration area; The deep-sea noise identification and biological attachment prediction module collects noise data by deploying an underwater noise sensor array, analyzes acoustic signal parameters related to biological attachment behavior, and predicts the attachment behavior characteristics of the attachment base surface, including attachment rate, attachment species type and distribution area, specifically including: Noise data collection: By deploying an underwater noise sensor array, the noise data of the deep-sea restoration area is collected in real time, including the sound of water flow, biological activity and sediment movement, and the collected noise data is preliminarily processed, including denoising and signal enhancement; Acoustic signal extraction: Extracting acoustic signal parameters related to biological attachment behavior from the preliminarily processed noise data, including frequency range, signal intensity, signal duration, and repetition rate; Prediction of biological attachment behavior: Based on the extracted acoustic signal parameters, the biological attachment behavior characteristics on the attachment substrate surface are predicted, including attachment rate, attachment species type and distribution area; The repair strategy generation module dynamically evaluates the growth status of the actual attached organisms based on the predicted results of the attachment behavior characteristics of the attachment substrate surface, and generates a targeted repair strategy in combination with the repair target; The restoration effect evaluation module evaluates the ecological restoration effect and quantitatively analyzes the restoration progress of the ecosystem by comparing the actual restoration effect with the expected target.

[0007] Optionally, the environmental data acquisition module includes: Water quality parameter collection: water quality parameters are collected through water quality sensors, including water temperature, dissolved oxygen, pH value and nutrient concentration; Collection of sediment characteristic parameters: The sediment distribution in the restoration area (the spatial distribution and accumulation state of the sediment in the target area) is collected through physical sensors, the particle size distribution (the size of the sediment particles and their distribution ratio) is collected through a laser particle size analyzer, the sediment density is collected through a pressure sensor, and the organic matter content is collected through a chemical sensor; Ocean current parameter collection: Ocean current parameters, including ocean current speed and direction, are collected through fluid dynamic sensors.

[0008] Optionally, the efficient attachment base design and deployment module includes: Optimization of attachment base design: Based on the collected environmental data, optimize the design of the attachment base, including shape design (adjusting the geometry of the attachment base to adapt to the water flow and sediment environment and enhance stability), material selection (selecting corrosion-resistant, eco-friendly and suitable materials for target biological attachment), and surface structure optimization (designing the microstructure or texture of the attachment base surface to improve the biological attachment effect and population diversity); Attachment base deployment: Use underwater deployment equipment to transport and deploy the designed high-efficiency attachment base to the target restoration area; Positioning and stabilization adjustment: After the attachment base is laid out, the position of the attachment base is calibrated using the positioning unit and fixed using the anchoring device.

[0009] Optionally, the noise data collection includes: Noise signal collection: By deploying an underwater noise sensor array, real-time noise data is collected in the deep-sea restoration area, including the sound of water flow, biological activity, and sediment movement; Denoising: Denoising the collected noise data, removing background noise and sensor self-noise through frequency domain filters; Signal enhancement: Short-time Fourier transform (STFT) is used to enhance the noisy data in the time and frequency domains.

[0010] Optionally, the acoustic signal extraction includes: Frequency range extraction: Perform frequency domain analysis on the noise data after preliminary processing and extract the frequency range through fast Fourier transform (FFT); Signal strength calculation: Use the amplitude of time domain and frequency domain signals to calculate the strength of the noise signal; Signal duration extraction: Determine the duration of biological activity sounds based on envelope detection of time domain signals; Repetition rate calculation: Use the autocorrelation function to analyze the periodicity of the signal and calculate the repetition rate.

[0011] Optionally, the biological attachment behavior prediction includes: Attachment rate prediction: Based on the extracted signal intensity and repetition rate, the number of organisms attached to the surface of the attachment substrate per unit time, i.e., the attachment rate, is calculated; Prediction of attached species type: Based on the extracted frequency range and signal duration, the attached biological species are identified through the Softmax classification model; Prediction of attachment distribution area: Based on the spatial characteristics of the sound source, the spatial distribution of the attachment behavior on the attachment substrate surface is estimated through the signal strength and directionality data of the multi-sensor array.

[0012] Optionally, the repair strategy generation module includes: Dynamic evaluation of biological growth: Based on the output data of the attachment behavior prediction module (attachment rate, species type and distribution area), the growth status of the actual attached organisms is dynamically evaluated in combination with real-time environmental data; Restoration strategy generation: Generate targeted restoration strategies by combining the results of biological growth dynamic assessment and preset restoration goals (improving attachment efficiency and maintaining species diversity).

[0013] Optionally, the biological growth dynamics assessment includes: Attachment growth rate assessment: Calculate the growth rate of organisms on the attachment substrate surface based on attachment rate and environmental data ; Biodiversity assessment: Calculate the biodiversity index D of the restoration area based on the distribution data of the attached species type c; Assessment of the health status of the restoration area: Comprehensive biological growth rate and biodiversity index are used to assess the ecological health status H of the restoration area.

[0014] Optionally, the repair strategy generation includes: Target matching and optimization: Based on the evaluation results of attached organism growth rate, biodiversity index and ecological health status, an objective function is established to optimize the restoration strategy to maximize the comprehensive benefits of ecological restoration; Generate repair strategy: Generate the optimal repair strategy through objective function optimization, including: Adhesion base management: adjust the placement, quantity or surface structure of the adhesion base; Environmental parameter regulation: optimize water quality or adjust the placement area by adding nutrients.

[0015] Optionally, the repair effect evaluation module includes: Comparison of restoration effects: Quantify the degree of restoration effect by calculating the difference between the actual status indicators (average attachment rate, biodiversity index) of the restoration area and the expected targets; Restoration Progress Score: The restoration progress score is calculated based on the relative closeness between the actual restoration effect and the expected target. ; Integrated Ecosystem Health Assessment: Comprehensive restoration progress score and dynamic indicators of current restoration areas to assess the overall health of the ecosystem .

[0016] Beneficial effects of the present invention: The present invention ensures the scientificity and efficiency of deep-sea ecological restoration by integrating environmental data collection, efficient attachment base design and deployment, deep-sea noise identification and biological attachment prediction, restoration strategy generation and restoration effect evaluation, and closed-loop feedback from data collection to restoration effect. It also provides high-quality support for the design and deployment of attachment bases through real-time collection and precise analysis of deep-sea environmental data, including multi-dimensional information such as water quality, sediments and ocean currents, and significantly improves the adaptability and sustainability of restoration strategies.

[0017] The present invention, through a deep-sea noise recognition and biological attachment prediction module, utilizes noise signal denoising, enhancement and acoustic parameter extraction technology, combined with frequency range, signal strength, duration and repetition rate, effectively solves the problem of complex deep-sea signals and strong interference, and realizes accurate prediction of attachment rate, species type and distribution area, providing a scientific basis for the optimized layout of restoration areas, and through a system architecture combining software and hardware, enhances data acquisition accuracy and processing capabilities in complex deep-sea environments, providing reliable guarantees for the deployment of deep-sea attachment bases and ecological restoration.

[0018] The present invention dynamically adjusts the restoration plan through a restoration strategy generation module, combines attachment behavior prediction and real-time environmental changes to generate a goal-oriented restoration strategy, and quantitatively analyzes the restoration progress and ecosystem health status through a restoration effect evaluation module. This method can not only optimize the attachment base deployment and environmental regulation strategy in real time, but also continuously evaluate the effect and stability of the restoration process, greatly improving the pertinence and scientific nature of the restoration strategy, and providing technical support and decision-making basis for achieving stable recovery of deep-sea ecosystems. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A schematic diagram of system function modules according to an embodiment of the present invention; Figure 2 Schematic diagram of a deep-sea noise recognition and biological attachment prediction module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0022] like Figure 1-Figure 2 As shown, the deep-sea mining ecological restoration and recovery potential assessment system based on efficient attachment base includes an environmental data acquisition module, an efficient attachment base design and deployment module, a deep-sea noise identification and biological attachment prediction module, a restoration strategy generation module and a restoration effect assessment module, among which; The environmental data acquisition module collects environmental data of the deep-sea restoration area in real time through multiple types of sensors, including water temperature, dissolved oxygen, pH value, nutrient concentration, sediment characteristics, current speed and direction; The high-efficiency attachment base design and deployment module designs high-efficiency attachment bases for deep-sea environments based on the collected environmental data and deploys them in the target restoration area; The deep-sea noise identification and biological attachment prediction module collects noise data by deploying an underwater noise sensor array, analyzes the acoustic signal parameters related to biological attachment behavior, and predicts the attachment behavior characteristics of the attachment substrate surface, including attachment rate, attachment species type and distribution area, including: Noise data collection: By deploying an underwater noise sensor array, the noise data of the deep-sea restoration area is collected in real time, including the sound of water flow, biological activity and sediment movement, and the collected noise data is preliminarily processed, including denoising and signal enhancement; Acoustic signal extraction: Extracting acoustic signal parameters related to biological attachment behavior from the preliminarily processed noise data, including frequency range, signal intensity, signal duration, and repetition rate; Prediction of biological attachment behavior: Based on the extracted acoustic signal parameters, the biological attachment behavior characteristics on the attachment substrate surface are predicted, including attachment rate, attachment species type and distribution area; The repair strategy generation module dynamically evaluates the growth status of the actual attached organisms based on the predicted results of the attachment behavior characteristics of the attachment substrate surface, and generates targeted repair strategies in combination with the repair goals; The restoration effect evaluation module evaluates the ecological restoration effect and quantitatively analyzes the restoration progress of the ecosystem by comparing the actual restoration effect with the expected target; Through the above content, not only the scientificity and efficiency of the ecological restoration process are guaranteed, but also the adaptability and sustainability of the system are improved through data-driven dynamic adjustment. At the same time, combined with deep-sea noise identification and biological attachment behavior prediction technology, it provides more accurate decision-making support and technical guarantees for deep-sea mining ecological restoration.

[0023] The environmental data collection module includes: Water quality parameter collection: water quality parameters are collected through water quality sensors, including water temperature, dissolved oxygen, pH value and nutrient concentration; Collection of sediment characteristic parameters: The sediment distribution in the restoration area (the spatial distribution and accumulation state of the sediment in the target area) is collected through physical sensors, the particle size distribution (the size of the sediment particles and their distribution ratio) is collected through a laser particle size analyzer, the sediment density is collected through a pressure sensor, and the organic matter content is collected through a chemical sensor; Ocean current parameter collection: Collect ocean current parameters, including ocean current speed and direction, through fluid dynamic sensors; Through the above content, the breadth and accuracy of the data are ensured, which not only covers basic water quality information such as water temperature and dissolved oxygen, but also refines the distribution, particle size, density and organic matter content of sediments, and accurately measures the speed and direction of ocean currents, providing high-quality data support for the design, deployment and restoration strategy generation of attachment bases for deep-sea ecological restoration, greatly improving the adaptability of the system and the scientific nature of the restoration effect.

[0024] The efficient attachment base design and deployment module includes: Optimization of attachment base design: Based on the collected environmental data, optimize the design of the attachment base, including shape design (adjusting the geometry of the attachment base to adapt to the water flow and sediment environment and enhance stability), material selection (selecting corrosion-resistant, eco-friendly and suitable materials for target biological attachment), and surface structure optimization (designing the microstructure or texture of the attachment base surface to improve the biological attachment effect and population diversity); Attachment base deployment: Use underwater deployment equipment to transport and deploy the designed high-efficiency attachment base to the target restoration area; Positioning and stabilization adjustment: After the attachment base is laid, the position of the attachment base is calibrated by the positioning unit and fixed with an anchoring device to ensure the long-term stability of the attachment base in the deep-sea environment; Through the above content, the shape, material and surface structure of the attachment base are optimized to adapt to the complex deep-sea environment and the attachment needs of different organisms. At the same time, through precise deployment and stable adjustment technology, the effective positioning and long-term stability of the attachment base in the target restoration area are ensured, which not only improves the efficiency of biological attachment and ecological restoration effects, but also enhances the reliability and sustainability of the system in the deep-sea environment.

[0025] Noise data collection includes: Noise signal collection: By deploying an underwater noise sensor array, real-time noise data is collected in the deep-sea restoration area, including the sound of water flow, biological activity, and sediment movement; Denoising: Denoising is performed on the collected noise data. Background noise and sensor self-noise are removed through a frequency domain filter. The frequency response function of the filter is: ; in, is the frequency response of the filter, f is the signal frequency, is the cutoff frequency, n is the filter order, by adjusting and n, achieving effective suppression of different noise components while retaining the key frequency characteristics of biological activity sounds; Signal enhancement: Short-time Fourier transform (STFT) is used to enhance the time-frequency domain of noisy data, which can be expressed as: ; in, is the time-frequency domain signal, is the time domain signal, is a sliding window function; Through the above content, various noise signals in the deep-sea restoration area are collected in real time, including the sound of water flow, biological activity and sediment movement. The accuracy and quality of the data are improved through denoising and signal enhancement technology. The frequency domain filter is used to remove environmental interference and retain key acoustic features. The short-time Fourier transform is then used to enhance the time-frequency characteristics. This effectively solves the problems of complex signals and strong interference in the deep-sea environment, providing a scientific and reliable data collection method for deep-sea ecological restoration.

[0026] Acoustic signal extraction includes: Frequency range extraction: Perform frequency domain analysis on the noise data after preliminary processing, and extract the frequency range through fast Fourier transform (FFT), which is expressed as: ; in, is the frequency domain signal, is the time domain signal, f is the frequency; Signal strength calculation: The strength of the noise signal is calculated using the amplitude of the time domain and frequency domain signals, expressed as: ; Where I is the signal strength, T is the time window length of the signal; Signal duration extraction: Based on the envelope detection of the time domain signal, the duration of the biological activity sound is determined, which is expressed as: ; in, is the signal envelope, is a time domain signal; Repetition rate calculation: Use the autocorrelation function to analyze the periodicity of the signal and calculate the repetition rate, including: (1) Calculation of autocorrelation function: Calculate the autocorrelation function of the signal , analyzing the signal at different time delays The similarity under is expressed as: ; in, is the value of the autocorrelation function, indicating that the signal is delayed in time The correlation with itself is used to describe the periodicity or repetitive nature of a signal. is the value of the input signal at time t, representing the original time domain signal, For input signal In time The value of (2) Find the periodic peak: Find the first main peak position in the calculated autocorrelation function (remove The main peak of the signal), which corresponds to the period T of the signal; (3) Definition of repetition rate: The repetition rate is calculated based on the period T of the signal. , expressed as: ; in, is the period determined by the position of the main peak of the autocorrelation function; Through the above content, not only can the frequency and intensity of biological activities be accurately identified, but also the persistence and periodic characteristics of the behavior can be revealed, which greatly improves the reliability and scientificity of subsequent attachment behavior predictions, provides high-quality data support for deep-sea ecological restoration, and significantly enhances the adaptability and application value of the system in complex acoustic environments.

[0027] Biofouling behavior prediction includes: Attachment rate prediction: Based on the extracted signal intensity and repetition rate, the number of organisms attached to the surface of the attachment substrate per unit time is calculated, that is, the attachment rate, which is expressed as: ; in, is the attachment rate (number of organisms / unit time), I is the signal intensity, is the repetition rate, k is the empirical correction coefficient; Attached species type prediction: Based on the extracted frequency range and signal duration, the attached biological species are identified through the Softmax classification model, expressed as: ; in, is the predicted probability of biological species c, x is the extracted acoustic signal parameter feature vector, and is the weight and bias of the classifier, C is the total number of classification categories, is the category index, and Respectively The weights and biases of Prediction of attachment distribution area: Based on the spatial characteristics of the sound source, the spatial distribution of the attachment behavior on the attachment base surface is estimated through the signal strength and directionality data of the multi-sensor array, which is expressed as: ; in, The surface position of the attachment base The adhesion strength, is the signal strength of the ith sensor, Position of the sensor to the substrate surface The spatial attenuation function of , N is the total number of sensors; ; in, is the absorption coefficient of the medium, in units of , is the position of sensor i to the surface of the substrate The distance is the surface area for spherical wave propagation, is the attenuation factor of the signal caused by medium absorption during propagation; Through the above content, a comprehensive prediction of attachment rate, attached species type and distribution area is achieved. The attachment rate prediction accurately quantifies the number of biological attachments per unit time and provides dynamic attachment characteristics. The species type prediction uses classification models to effectively identify specific attached organisms, thereby improving the biological targeting of restoration strategies. The distribution area prediction uses sensor array signals and spatial attenuation functions to accurately estimate the spatial distribution characteristics of attachment intensity, providing a scientific basis for the optimal layout of restoration areas and greatly improving the accuracy and applicability of attachment behavior prediction in deep-sea ecological restoration.

[0028] The repair strategy generation module includes: Dynamic evaluation of biological growth: Based on the output data of the attachment behavior prediction module (attachment rate, species type and distribution area), the growth status of the actual attached organisms is dynamically evaluated in combination with real-time environmental data; Restoration strategy generation: Generate targeted restoration strategies based on the biological growth dynamics assessment results and preset restoration goals (improving attachment efficiency and maintaining species diversity); Through the above content, a full-process closed loop from attachment behavior analysis to precise strategy formulation has been achieved, and real-time monitoring of biological attachment and growth status is carried out. Combined with environmental changes and limiting factor analysis, a scientific basis is provided for strategy optimization, and restoration plans are dynamically adjusted based on evaluation results, including attachment base deployment optimization and environmental management measures, to ensure the adaptability and goal orientation of the restoration process. This not only improves the pertinence and sustainability of restoration strategies, but also greatly improves the efficiency and effectiveness of ecological restoration.

[0029] Biological growth dynamics assessment includes: Attachment growth rate assessment: Calculate the growth rate of organisms on the attachment substrate surface based on attachment rate and environmental data , expressed as: ; in, The surface position of the attachment base The biological growth rate at time t, For location The attachment rate, is the environment correction function, representing the environment parameters The combined impact of ; in, is the i-th environmental data, is the optimal value of the i-th environmental data, is the weight factor; Biodiversity assessment: Based on the distribution data of the attached species type c, the biodiversity index D of the restoration area is calculated, expressed as: ; Where D is the biodiversity index of the restoration area, is the occurrence probability of species c, and C is the total number of species in the restoration area; Assessment of the health status of the restoration area: The ecological health status H of the restoration area is assessed by combining the biological growth rate and biodiversity index, expressed as: ; Among them, H is the ecological health status score of the restoration area, is the average biological growth rate of all locations in the restoration area, D is the biodiversity index, , are the corresponding weight factors respectively; Through the above content, the environmental correction function is used to accurately reflect the nonlinear impact of environmental factors, the stability of the ecosystem is measured by the diversity index, and the health status score is used to provide a comprehensive evaluation result. It not only improves the real-time monitoring capability of the biological growth process, but also provides a scientific basis for the optimization of the restoration strategy, ensuring the targetedness and adaptability of the restoration process, and effectively promoting the sustainable recovery of the deep-sea ecosystem.

[0030] Repair strategy generation includes: Target matching and optimization: Based on the evaluation results of attached organism growth rate, biodiversity index and ecological health status, an objective function is established to optimize the restoration strategy to maximize the comprehensive benefits of ecological restoration, which is expressed as: ; Among them, S is a set of repair strategy solutions, is the average growth rate, D is the biodiversity index, is the implementation cost of the repair strategy, , , are the corresponding weight factors respectively; Generate repair strategy: Generate the optimal repair strategy through objective function optimization, including: Adhesion base management: adjust the placement, quantity or surface structure of the adhesion base to improve adhesion efficiency; Environmental parameter regulation: optimize water quality or adjust the deployment area through nutrient salt injection to reduce the interference of ocean currents; Through the above contents, the attachment efficiency is improved, the interference of ocean currents is reduced, and the scientific and operability of the restoration strategy is ensured by optimizing the attachment base deployment plan and improving water quality conditions. At the same time, by adjusting the weight factor, it can flexibly adapt to different restoration goals and actual application scenarios, providing strong technical support for achieving the stability and sustainability of the ecosystem.

[0031] The restoration effect assessment module includes: Comparison of restoration effects: By calculating the difference between the actual status indicators (average attachment rate, biodiversity index) of the restoration area and the expected targets, the degree of restoration effect is quantified, expressed as: ; in, is the difference value of the repair effect, indicating the overall deviation between the actual and the target. is the kth actual indicator value (actual biodiversity index, growth rate) of the restoration area, is the kth target value of the repair target, is the weight factor of the kth indicator, and m is the total number of indicators involved in the calculation; Restoration Progress Score: The restoration progress score is calculated based on the relative closeness between the actual restoration effect and the expected target. , expressed as: ; in, Score the progress of repair, ranging from , is the maximum allowable deviation value of the repair effect; Integrated Ecosystem Health Assessment: Comprehensive restoration progress score and dynamic indicators of current restoration areas to assess the overall health of the ecosystem , expressed as: ; in, Scoring the health of ecosystems, Score the progress of the repair, is the average attachment rate, D is the biodiversity index, , , are the corresponding weight factors respectively; Through the above content, it can not only flexibly adapt to different restoration goals, but also provide refined feedback on restoration effects. By dynamically evaluating the health of the ecosystem, it provides a scientific basis for the optimization of restoration strategies, ensures the effectiveness and sustainability of the restoration process, and significantly improves the accuracy and reliability of deep-sea ecological restoration work.

[0032] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0033] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A deep-sea mining ecological restoration and recovery potential assessment system based on an efficient attachment base, characterized in that: It includes environmental data acquisition module, efficient attachment base design and deployment module, deep-sea noise identification and biological attachment prediction module, restoration strategy generation module and restoration effect evaluation module, among which; The environmental data acquisition module collects environmental data of the deep-sea restoration area in real time through multiple types of sensors, including water temperature, dissolved oxygen, pH value, nutrient concentration, sediment characteristics, current speed and direction; The efficient attachment base design and deployment module designs efficient attachment bases for deep-sea environments based on the collected environmental data, and deploys them in the target restoration area; The deep-sea noise identification and biological attachment prediction module collects noise data by deploying an underwater noise sensor array, analyzes acoustic signal parameters related to biological attachment behavior, and predicts the attachment behavior characteristics of the attachment base surface, including attachment rate, attachment species type and distribution area, specifically including: Noise data collection: By deploying an underwater noise sensor array, the noise data of the deep-sea restoration area is collected in real time, including the sound of water flow, biological activity and sediment movement, and the collected noise data is preliminarily processed, including denoising and signal enhancement; Acoustic signal extraction: Extracting acoustic signal parameters related to biological attachment behavior from the preliminarily processed noise data, including frequency range, signal strength, signal duration, and repetition rate; Prediction of biological attachment behavior: Based on the extracted acoustic signal parameters, the biological attachment behavior characteristics on the attachment substrate surface are predicted, including attachment rate, attachment species type and distribution area; The repair strategy generation module dynamically evaluates the growth status of the actual attached organisms based on the predicted results of the attachment behavior characteristics of the attachment substrate surface, and generates a targeted repair strategy in combination with the repair target; The restoration effect evaluation module evaluates the ecological restoration effect and quantitatively analyzes the restoration progress of the ecosystem by comparing the actual restoration effect with the expected target.

2. The deep-sea mining ecological restoration and recovery potential assessment system based on an efficient attachment base according to claim 1 is characterized in that: The environmental data acquisition module comprises: Water quality parameter collection: water quality parameters are collected through water quality sensors, including water temperature, dissolved oxygen, pH value and nutrient concentration; Collection of sediment characteristic parameters: The sediment distribution in the restoration area is collected through physical sensors, the particle size distribution is collected through a laser particle size analyzer, the sediment density is collected through a pressure sensor, and the organic matter content is collected through a chemical sensor; Ocean current parameter collection: Ocean current parameters, including ocean current speed and direction, are collected through fluid dynamic sensors.

3. The deep-sea mining ecological restoration and recovery potential assessment system based on an efficient attachment base according to claim 1 is characterized in that: The high-efficiency attachment base design and deployment module includes: Optimization of attachment base design: Based on the collected environmental data, optimize the design of the attachment base, including shape design, material selection, and surface structure optimization; Attachment base deployment: Use underwater deployment equipment to transport and deploy the designed high-efficiency attachment base to the target restoration area; Positioning and stabilization adjustment: After the attachment base is laid out, the position of the attachment base is calibrated using the positioning unit and fixed using the anchoring device.

4. The deep-sea mining ecological restoration and recovery potential assessment system based on an efficient attachment base according to claim 1 is characterized in that: The noise data collection includes: Noise signal collection: By deploying an underwater noise sensor array, real-time noise data is collected in the deep-sea restoration area, including the sound of water flow, biological activity, and sediment movement; Denoising: Denoising the collected noise data, removing background noise and sensor self-noise through frequency domain filters; Signal enhancement: Use short-time Fourier transform to enhance the noisy data in the time and frequency domain.

5. The deep-sea mining ecological restoration and recovery potential assessment system based on efficient attachment base according to claim 4 is characterized in that: The acoustic signal extraction comprises: Frequency range extraction: Perform frequency domain analysis on the noise data after preliminary processing and extract the frequency range through fast Fourier transform; Signal strength calculation: Use the amplitude of time domain and frequency domain signals to calculate the strength of the noise signal; Signal duration extraction: Determine the duration of biological activity sounds based on envelope detection of time domain signals; Repetition rate calculation: Use the autocorrelation function to analyze the periodicity of the signal and calculate the repetition rate.

6. The deep-sea mining ecological restoration and recovery potential assessment system based on efficient attachment base according to claim 5 is characterized in that: The biological attachment behavior prediction includes: Attachment rate prediction: Based on the extracted signal intensity and repetition rate, the number of organisms attached to the surface of the attachment substrate per unit time, i.e., the attachment rate, is calculated; Prediction of attached species type: Based on the extracted frequency range and signal duration, the attached biological species are identified through the Softmax classification model; Prediction of attachment distribution area: Based on the spatial characteristics of the sound source, the spatial distribution of the attachment behavior on the attachment substrate surface is estimated through the signal strength and directionality data of the multi-sensor array.

7. The deep-sea mining ecological restoration and recovery potential assessment system based on efficient attachment base according to claim 6 is characterized in that: The repair strategy generation module includes: Dynamic evaluation of biological growth: Based on the output of the attachment behavior prediction module, the growth status of the actual attached organisms is dynamically evaluated in combination with real-time environmental data; Restoration strategy generation: Combine the biological growth dynamic assessment results with the preset restoration goals to generate targeted restoration strategies.

8. The deep-sea mining ecological restoration and recovery potential assessment system based on efficient attachment base according to claim 7 is characterized in that: The biological growth dynamics assessment includes: Attachment growth rate assessment: Calculate the growth rate of organisms on the attachment substrate surface based on attachment rate and environmental data ; Biodiversity assessment: Calculate the biodiversity index D of the restoration area based on the distribution data of the attached species type c; Assessment of the health status of the restoration area: Comprehensive biological growth rate and biodiversity index are used to assess the ecological health status H of the restoration area.

9. The deep-sea mining ecological restoration and recovery potential assessment system based on efficient attachment base according to claim 8 is characterized in that: The repair strategy generation includes: Target matching and optimization: Based on the evaluation results of attached organism growth rate, biodiversity index and ecological health status, an objective function is established to optimize the restoration strategy to maximize the comprehensive benefits of ecological restoration; Generate repair strategy: Generate the optimal repair strategy through objective function optimization, including: Adhesion base management: adjust the placement, quantity or surface structure of the adhesion base; Environmental parameter regulation: optimize water quality or adjust the placement area by adding nutrients.

10. The deep-sea mining ecological restoration and recovery potential assessment system based on efficient attachment base according to claim 1 is characterized in that: The repair effect evaluation module includes: Comparison of restoration effects: Quantify the degree of restoration effect by calculating the difference between the actual status indicators of the restoration area and the expected targets; Restoration Progress Score: The restoration progress score is calculated based on the relative closeness between the actual restoration effect and the expected target. ; Integrated Ecosystem Health Assessment: Comprehensive restoration progress score and dynamic indicators of current restoration areas to assess the overall health of the ecosystem .

Images