Fishing-light complementary regulation and control method and platform based on microbial population monitoring
Through microbial population monitoring technology, water microbial samples are obtained and change reports are generated, and a complementary fishing and light regulation strategy is constructed, which solves the problem of low accuracy and rationality caused by the complexity of water environment in complementary fishing and light regulation, and realizes fishery and photovoltaic power generation Optimization and coordination of parameters.
Patent Information
- Application Number
- CN202411562357.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-05
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-11-05
AI Technical Summary
Due to the complexity of the water environment, existing fishing and light complementary regulation technology has low accuracy and rationality, making it difficult to achieve intelligent coordination between fishery and photovoltaic power generation.
Using a method based on microbial population monitoring, microbial samples are obtained and analyzed through microbial samplers, microbial identification instruments and data processors, microbial population change reports are generated, and the fishing light complementary regulation strategies and parameter spaces are constructed to optimize the parameters of fishery and photovoltaic power generation. coordination.
The parameters accuracy and rationality of fishing light complementary regulation are improved, and the optimization of regulation effect is ensured.
Smart Images

Figure CN119066435A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent control technology, and in particular to a fishery-photovoltaic complementary control method and platform based on microbial population monitoring. Background Art
[0002] Fishery-solar complementarity is a new energy utilization model that combines photovoltaic power generation systems with fish farming, realizing a new power generation model of "generating electricity above and raising fish below". However, in practical applications, due to the complexity of the water environment, there is a mutual influence between fish farming and photovoltaic power generation. How to reasonably coordinate and optimize the relationship between the two has become an urgent problem to be solved in order to realize the intelligent regulation of fish farming and photovoltaic power generation. Summary of the invention
[0003] This application solves the technical problem of low accuracy and rationality of fishery-photovoltaic complementary regulation in the prior art due to the complexity of the water environment by providing a fishery-photovoltaic complementary regulation method and platform based on microbial population monitoring. It achieves the technical effect of achieving coordinated optimization of fishery and photovoltaic power generation parameters by monitoring the changes in microbial populations in water bodies at multiple points, improving the accuracy and rationality of complementary regulation parameters, and thus ensuring the complementary regulation effect of fishery and photovoltaic.
[0004] In view of the above problems, the present invention provides a method and platform for regulating fishery-photovoltaic complementarity based on microbial population monitoring.
[0005] In a first aspect, the present application provides a method for fishery-photovoltaic complementary regulation based on microbial population monitoring, the method comprising: obtaining a microbial population monitoring device, the microbial population monitoring device comprising a microbial sampler, a microbial identification instrument and a data processor; performing sampling point analysis on a target water body to determine a plurality of key sampling points, performing multi-time water body sampling on the plurality of key sampling points through the microbial sampler to obtain a multi-point water body microbial sample set; performing multi-dimensional identification analysis on the multi-point water body microbial sample set using the microbial identification instrument to obtain a multi-point microbial identification data stream set; performing statistical integration processing on the multi-point microbial identification data stream set based on the data processor to generate a microbial population change report; constructing a fishery-photovoltaic complementary balanced regulation strategy, matching the fishery-photovoltaic complementary balanced regulation strategy based on the microbial population change report to obtain a target fishery-photovoltaic complementary regulation strategy, and constructing a fishery-photovoltaic complementary regulation strategy parameter space according to the target fishery-photovoltaic complementary regulation strategy; performing regulation analysis on the microbial population change report based on the fishery-photovoltaic complementary regulation strategy parameter space to obtain a fishery-photovoltaic balanced regulation parameter solution library, and performing fishery-photovoltaic complementary regulation on the target water body through the fishery-photovoltaic balanced regulation parameter solution library.
[0006] On the other hand, the present application also provides a fish-light complementary regulation and control platform based on microbial population monitoring, the platform comprising: a monitoring device acquisition module, used to acquire a microbial population monitoring device, the microbial population monitoring device comprising a microbial sampler, a microbial identification instrument and a data processor; a sampling point analysis module, used to perform sampling point analysis on the target water body, determine multiple key sampling points, perform multi-time water body collection on the multiple key sampling points through the microbial sampler, and obtain a multi-point water body microbial sample set; a multi-dimensional identification analysis module, used to use the microbial identification instrument to perform multi-dimensional identification and analysis on the multi-point water body microbial sample set, and obtain a multi-point microbial identification data stream set; a population change report generation module A block is used to perform statistical integration processing on the multi-point microbial identification data stream set based on the data processor to generate a microbial population change report; a strategy parameter space construction module is used to construct a fish-light complementary balanced regulation strategy, match the microbial population change report with the fish-light complementary balanced regulation strategy, obtain the target fish-light complementary regulation strategy, and construct a fish-light complementary regulation strategy parameter space according to the target fish-light complementary regulation strategy; a fish-light complementary regulation module is used to perform regulation analysis on the microbial population change report based on the fish-light complementary regulation strategy parameter space, obtain a fish-light balanced regulation parameter solution library, and perform fish-light complementary regulation on the target water body through the fish-light balanced regulation parameter solution library.
[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: By adopting the sampling point analysis of the target water body, multiple key sampling points are determined, and the water body is collected at multiple key sampling points at multiple times by the microbial sampler to obtain a multi-point water body microbial sample set, and a microbial identification instrument is used to perform multi-dimensional identification analysis on each of them to obtain a multi-point microbial identification data stream set, and the multi-point microbial identification data stream set is statistically integrated and processed based on the data processor to generate a microbial population change report, and then the microbial population change report is matched with the fish-photovoltaic complementary balanced regulation strategy to obtain the target fish-photovoltaic complementary regulation strategy, and according to the target fish-photovoltaic complementary regulation strategy, the fish-photovoltaic complementary regulation strategy parameter space is constructed, so as to perform regulation analysis on the microbial population change report, and obtain the fish-photovoltaic balanced regulation parameter solution library to perform fish-photovoltaic complementary regulation on the target water body. Then, the technical effect of achieving the coordinated optimization of parameters of fishery and photovoltaic power generation through multi-point monitoring of the changes in microbial populations in water bodies, improving the accuracy and rationality of complementary regulation parameters, and thus ensuring the fish-photovoltaic complementary regulation effect is achieved.
[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] Figure 1 This is a schematic diagram of the process of the fishery-photovoltaic complementary regulation method based on microbial population monitoring in this application; Figure 2 A schematic diagram of the process of determining multiple key sampling points in the fishery-photovoltaic complementary regulation method based on microbial population monitoring in this application; Figure 3 This is a schematic diagram of the structure of the fishery-light complementary regulation platform based on microbial population monitoring in this application.
[0010] Explanation of the reference numerals: monitoring device acquisition module 11, sampling point analysis module 12, multi-dimensional identification analysis module 13, population change report generation module 14, strategy parameter space construction module 15, fish-light complementary control module 16. DETAILED DESCRIPTION
[0011] This application solves the technical problem of low accuracy and rationality of fishery-photovoltaic complementary regulation in the prior art due to the complexity of the water environment by providing a fishery-photovoltaic complementary regulation method and platform based on microbial population monitoring. It achieves the technical effect of achieving coordinated optimization of fishery and photovoltaic power generation parameters by monitoring the changes in microbial populations in water bodies at multiple points, improving the accuracy and rationality of complementary regulation parameters, and thus ensuring the complementary regulation effect of fishery and photovoltaic.
[0012] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0013] The present application is described below in conjunction with the drawings in the present application.
[0014] Embodiment 1 like Figure 1 As shown, the present application provides a method for regulating fishery-light complementation based on microbial population monitoring, the method comprising: Step S1: Obtain a microbial population monitoring device, wherein the microbial population monitoring device includes a microbial sampler, a microbial identification instrument and a data processor.
[0015] Specifically, in order to achieve comprehensive monitoring of the microbial population in water bodies, first obtain a microbial population monitoring device, which is a device used to monitor and evaluate the number, type and dynamic changes of microbial populations in a specific environment, including a microbial sampler, which is a special tool for collecting microbial samples from water bodies, which can automatically or manually collect microbial samples from water bodies and keep them at a specific temperature and environment to ensure the integrity and accuracy of the samples; a microbial identification instrument, which is an instrument for automatic identification and classification of microorganisms; and a data processor, which is a new generation of processors for high-performance data processing, integrating complete data center functions into a single chip. The water body is sampled, monitored and processed through the microbial population monitoring device to achieve comprehensive monitoring of the microbial population in the water body.
[0016] Step S2: Analyze the sampling points of the target water body to determine multiple key sampling points, collect water samples at multiple time points through the microbial sampler, and obtain a multi-point water body microbial sample set.
[0017] like Figure 2 As shown, further, the step of determining multiple key sampling points in this application also includes: Acquire fishery water attribute factor information, the fishery water attribute factor information includes water body geographical characteristics, water quality environmental conditions, fishery breeding conditions and pollution source distribution; based on the fishery water attribute factor information, perform multidimensional parameter collection on the target water body to obtain a fishery water multidimensional factor parameter set; based on the fishery water multidimensional factor parameter set, perform spatial overlay analysis to obtain a fishery water spatial characteristic layer set; perform key area identification on the fishery water spatial characteristic layer set to obtain a key fishery water area set, and perform coverage analysis on the key fishery water area set to determine the multiple key sampling points.
[0018] Furthermore, the step of determining the plurality of key sampling points in this application further includes: A recursive feature elimination algorithm is used to extract influencing features of the key fishery water area set to obtain a fishery water influencing feature set; feature marking is performed on the key fishery water area set based on the fishery water influencing feature set to obtain a fishery water area influencing feature set; coverage analysis is performed on the key fishery water area set based on the fishery water area influencing feature set to obtain a fishery water area initial sampling point set; cluster analysis is performed on the fishery water area initial sampling point set to obtain a water body sampling clustering result, and the multiple key sampling points are determined based on the water body sampling clustering result.
[0019] Furthermore, the steps of obtaining the fishery water body impact feature set in this application also include: Based on the multidimensional factor parameter set of the fishery water body, the associated features of the key fishery water body area set are extracted to obtain the fishery water body associated feature set; historical data mining is performed on the fishery water body associated feature set to obtain a fishery water body microbial distribution feature data set; random forest is used to perform microbial population prediction training on the fishery water body microbial distribution feature data set to obtain a fishery water body microbial population prediction model; a meta-transformer is obtained according to a recursive feature elimination algorithm, and the fishery water body associated feature set is iteratively removed by the meta-transformer, and the fishery water body microbial population prediction model after the feature removal is trained and evaluated to screen and obtain the fishery water body influencing feature set.
[0020] Specifically, in order to ensure the comprehensiveness of the sampling of water microbial populations, the sampling point analysis is performed on the target water body to be regulated. First, the fishery water attribute factor information is obtained. The fishery water attribute factor information is the type of indicator that affects the change of the water microbial population, including the geographical characteristics of the water body, the water quality and environmental conditions, the fishery breeding conditions, and the distribution of pollution sources. Based on the fishery water attribute factor information, multi-dimensional parameter collection is performed on the target water body to obtain a set of multi-dimensional factor parameters of the fishery water body. The multi-dimensional factor parameter set of the fishery water body is the multi-factor attribute parameters such as the geographical characteristics of the water body, the water quality and environmental conditions, the fishery breeding conditions, and the distribution of pollution sources of the target water body. Use GIS technology to perform spatial overlay analysis on the multi-dimensional factor parameter set of the fishery water body, superimpose data layers such as water quality parameters, breeding distribution, topography, and geomorphology, and obtain a set of spatial characteristic layers of the fishery water body. The spatial characteristic layer set of the fishery water body is used to comprehensively display the spatial distribution parameters of the water body.
[0021] According to the water body microorganism collection requirements, the key areas of the spatial feature layer set of the fishery water body are identified to obtain key areas with large differences in microbial population distribution, that is, key fishery water body area sets, such as intensive breeding areas, near pollution discharge ports, slow water flow areas, etc. The key fishery water body area set is also covered by analysis. Since there are many multidimensional factor parameters of fishery water bodies, in order to improve the processing accuracy and efficiency, it is necessary to select features that have an important impact on the distribution of microbial populations. Specifically, the recursive feature elimination algorithm is used to extract the influencing features of the key fishery water body area set. First, based on the multidimensional factor parameter set of the fishery water body, the key fishery water body area set is extracted for correlation features to obtain a fishery water body correlation feature set. The fishery water body correlation feature set is all features related to the microbial population distribution in the multidimensional factor parameters of the fishery water body, such as water area, water depth, water flow, breeding species, breeding density, etc. Then, historical data mining is performed on the fishery water body associated feature set to obtain a fishery water body microbial distribution feature data set, which includes historical fishery water body associated feature data and corresponding microbial population distribution type, quantity and other data.
[0022] The microbial population prediction training of the fishery water microbial distribution characteristic data set is performed using random forest until the preset convergence condition is reached, and the fishery water microbial population prediction model is obtained, and the fishery water microbial population prediction model is used to predict the microbial population distribution according to the fishery water associated features. A meta-transformer is obtained according to the recursive feature elimination algorithm, and the meta-transformer is a feature selection optimizer in the recursive feature elimination algorithm. The meta-transformer will iteratively remove the fishery water associated feature set. In each round of iteration, the meta-transformer will remove the least important features in the fishery water associated feature set, and retrain and evaluate the fishery water microbial population prediction model after the feature removal. After each round of iteration, the performance of the model is evaluated, and the importance score of the removed feature is used to indicate the contribution of the feature to the model performance. The removed features and their importance scores are recorded. Through multiple rounds of iterations, the meta-transformer will gradually reduce the number of features, and determine a suitable feature number threshold based on the model performance and feature importance scores. Then, based on the importance score, the features that have the greatest impact on the model performance are selected and retained to obtain a set of fishery water body influencing features that have an important impact on the distribution of microbial populations, such as temperature, dissolved oxygen, pH value, nutrient concentration, etc. Through recursive feature elimination, the features that have an important impact on the distribution of microbial populations are accurately selected, and the impact of redundant and irrelevant features on the selection of sampling points is reduced, thereby improving data processing efficiency.
[0023] Based on the fishery water body impact feature set, the key fishery water body area set is feature-marked to obtain the fishery water body area impact feature set corresponding to each key fishery water body area after feature parameter marking. Based on the fishery water body area impact feature set, the key fishery water body area set is covered by analysis to cover the areas with different levels of features in each key fishery water body area, and the sampling points of each different level of feature area are marked to obtain a corresponding large number of initial sampling point sets of fishery water body areas. Cluster analysis is performed on the initial sampling point set of the fishery water body area, and a similarity threshold is set using a clustering algorithm such as K-means and hierarchical clustering to cluster similar sampling points into one category to obtain the calculated water body sampling clustering result. According to the water body sampling clustering result, each cluster is interpreted as a specific area or sub-area in the fishery water body, and the most representative sampling point can be selected in each clustering result by the sampling point location, for example, the sampling point whose characteristic value is closest to the cluster center in the cluster is selected to determine multiple key sampling points. The microbial sampler is used to automatically collect water samples at multiple key sampling points at multiple times to obtain a multi-point water microbial sample set to ensure the integrity and accuracy of the samples. Feature extraction analysis and clustering algorithms are used to identify the most representative sampling points for each regional feature in the fishery water body to ensure that the sampling points can fully reflect the distribution and changes of the microbial population in the fishery water body, thereby achieving multi-point comprehensive monitoring of the microbial population in the fishery water body.
[0024] Step S3: Use the microbial identification instrument to perform multi-dimensional identification analysis on the multi-point water body microbial sample sets to obtain a multi-point microbial identification data stream set.
[0025] Specifically, the microbial identification instrument is used to perform multi-dimensional identification and analysis on the multi-point water body microbial sample set, including identification characteristics such as colony morphology, color, and growth rate. The microbial identification instrument is composed of a biochemical reaction plate, an instrument, an identification database, etc. The software inside the instrument automatically searches the existing database to give a result closest to the strain species, thereby obtaining a multi-point microbial identification data stream set. The multi-point microbial identification data stream set is compared and identified to obtain the number and type of microbial populations in the corresponding different collected samples, thereby improving the comprehensiveness and efficiency of microbial identification.
[0026] Step S4: Based on the data processor, the multi-point microbial identification data stream set is statistically integrated and processed to generate a microbial population change report.
[0027] Furthermore, the steps of generating a microbial population change report in this application also include: Perform microbial parameter statistics on the multi-point microbial identification data stream set to obtain a multi-point microbial parameter set, which includes microbial species, quantity and population proportion; integrate the multi-point microbial parameter set according to time series to obtain a multi-point microbial population time series distribution parameter set; use regression analysis to perform trend fitting on the multi-point microbial population time series distribution parameter set to generate a microbial population distribution change trend curve set; perform multi-point network processing on the microbial population distribution change trend curve set according to the sampling point sequence to generate the microbial population change report.
[0028] Specifically, the data processor performs statistical integration processing on the multi-point microbial identification data stream set, wherein the data processor can realize high-performance and rapid processing of microbial data. First, microbial parameter statistics are performed on the multi-point microbial identification data stream set to obtain a corresponding multi-point microbial parameter set, which includes microbial species, quantity, and population proportion. The multi-point microbial parameter set is integrated according to the time series to obtain a multi-point microbial population time series distribution parameter set in which the multi-point microbial parameter set is arranged in order from early to late according to the collection time.
[0029] The regression analysis method is used to perform trend fitting on the multi-point microbial population time series distribution parameter set, analyze the changing trend of the microbial population quantity with the time series, and generate a microbial population distribution change trend curve set through regression analysis fitting, and the microbial population distribution change trend curve set is the time change trend of the microbial population quantity. The microbial population distribution change trend curve set is processed by multi-point network connection according to the sampling point distribution position sequence, and a microbial population change report is recorded and generated. The microbial population change report includes information such as microbial species, quantity, and change trend. Improve the comprehensiveness and accuracy of the microbial population change report, ensure that the distribution and change trend of the microbial population in the fishery water body are fully reflected, and then improve the accuracy of the analysis of the subsequent fish-light complementary control parameters.
[0030] Step S5: construct a balanced regulation strategy for fishery-photovoltaic complementarity, match the microbial population change report with the balanced regulation strategy for fishery-photovoltaic complementarity, obtain a target fishery-photovoltaic complementarity regulation strategy, and construct a parameter space for the fishery-photovoltaic complementarity regulation strategy according to the target fishery-photovoltaic complementarity regulation strategy.
[0031] Specifically, the regulation strategies for fisheries and photovoltaic power generation must meet the purpose of balanced regulation, including resource utilization, environmental impact, economic benefits, etc. The expert group constructed a balanced regulation strategy for fishery and photovoltaic complementarity through the experience of fishery and photovoltaic complementarity regulation and the purpose of balanced regulation. The balanced regulation strategy for fishery and photovoltaic complementarity is a set of regulation strategies for balanced development of fishery and photovoltaic complementarity formulated according to the situation of microbial populations. Based on the similarity matching between the microbial population change report and the balanced regulation strategy for fishery and photovoltaic complementarity, a target fishery and photovoltaic complementarity regulation strategy that matches the change of the microbial population is obtained. And according to the target fishery and photovoltaic complementarity regulation strategy, big data mining is carried out to construct a parameter space of fishery and photovoltaic complementarity regulation strategy. The parameter space of fishery and photovoltaic complementarity regulation strategy is the historical fishery and photovoltaic complementarity regulation data associated with the target fishery and photovoltaic complementarity regulation strategy, including fishery and photovoltaic balanced regulation parameters and corresponding fishery and photovoltaic complementarity regulation effect data, which is used as the optimization range of subsequent fishery and photovoltaic balanced regulation parameters, thereby improving the efficiency of parameter optimization analysis.
[0032] Step S6: Based on the parameter space of the fish-light complementary regulation strategy, the microbial population change report is regulated and analyzed to obtain a fish-light balanced regulation parameter solution library, and the target water body is regulated by the fish-light balanced regulation parameter solution library.
[0033] Furthermore, the step of obtaining the fish-light balance control parameter solution library in this application also includes: A set of fish-light complementation regulation effect indicators is obtained, and the fish-light complementation regulation effect indicator set is fitted based on the fish-light complementation regulation strategy parameter space to construct a fish-light complementation regulation effect fitness function; a correlation analysis is performed on the fish-light complementation regulation strategy parameter space based on the microbial population change report to determine a regulation strategy parameter selection threshold; multiple groups of regulation strategy parameters are orthogonally selected within the regulation strategy parameter selection threshold, and the fitness of the multiple groups of regulation strategy parameters are evaluated using the fish-light complementation regulation effect fitness function to obtain multiple groups of parameter regulation effect fitness; a parameter cluster center is selected according to the multiple groups of parameter regulation effect fitness, and the multiple groups of regulation strategy parameters are optimized and analyzed based on the parameter cluster center to obtain the fish-light balance regulation parameter solution library by optimal search.
[0034] Furthermore, the optimization step to obtain the fish-light balance control parameter solution library also includes: A learning factor is set, and the remaining control parameters in the multiple groups of control strategy parameters are learned and updated toward the center of the parameter cluster according to the learning factor to obtain a control strategy learning parameter cluster; a genetic algorithm is used to perform population iterative optimization in the control strategy learning parameter cluster to obtain a control strategy optimization parameter cluster, and the control strategy optimization parameter cluster is proportionally screened and optimized to obtain the fish-light balance control parameter solution library.
[0035] Specifically, the microbial population change report is regulated and analyzed based on the parameter space of the fish-photovoltaic complementary regulation strategy. First, a set of fish-photovoltaic complementary regulation effect indicators is formulated. The set of fish-photovoltaic complementary regulation effect indicators is used to perform a multi-dimensional evaluation of the fish-photovoltaic complementary regulation effect, including photovoltaic energy utilization efficiency, fishery income, and consumption cost, etc. The fish-photovoltaic complementary regulation effect data and the set of fish-photovoltaic complementary regulation effect indicators in the parameter space of the fish-photovoltaic complementary regulation strategy are evaluated and fitted by regression analysis to construct a fish-photovoltaic complementary regulation effect fitness function. The fish-photovoltaic complementary regulation effect fitness function is a regression function of the set of fish-photovoltaic complementary regulation effect indicators, which is used to evaluate the fish-photovoltaic complementary regulation effect according to the fish-photovoltaic balanced regulation parameters. The greater the fitness, the better the fish-photovoltaic complementary regulation effect.
[0036] Based on the microbial population change report, a correlation analysis is performed on the parameter space of the fishery-photovoltaic complementary regulation strategy, and a regulation strategy parameter selection threshold that matches the population quantity change value in the microbial population change report is determined. The regulation strategy parameter selection threshold is the selectable range for fishery-photovoltaic complementary regulation. Orthogonal arrangement of parameters is performed within the regulation strategy parameter selection threshold, and multiple groups of regulation strategy parameters are selected therein. The fitness function of the fishery-photovoltaic complementary regulation effect is used to evaluate the fitness of the multiple groups of regulation strategy parameters, and the corresponding multiple groups of parameter regulation effect fitness are obtained. According to the multiple groups of parameter regulation effect fitness, the regulation strategy parameter with the largest fitness is selected as the parameter cluster center.
[0037] Based on the center of the parameter cluster, the multiple groups of control strategy parameters are optimized and analyzed. First, the learning factor is set according to the parameter optimization accuracy requirement, and the learning factor is the parameter learning step. According to the learning factor, the remaining control parameters in the multiple groups of control strategy parameters are learned and updated to the center of the parameter cluster, so that the fitness of the remaining control parameters is close to the center of the parameter cluster, and the control strategy parameter with the largest fitness after each learning is replaced as the center of the parameter cluster to obtain the control strategy learning parameter cluster after multiple learning updates. The genetic algorithm is used to perform population iterative optimization in the control strategy learning parameter cluster. According to the fitness value of the parameters in the cluster, a part of the parameter individuals are selected from the current population as the parent generation to generate the next generation population. The selected parent generation individuals are cross-operated to generate new offspring individuals. At the same time, the offspring individuals are mutated to increase the diversity of the population until the preset termination condition is reached, and the control strategy optimization parameter cluster after population iterative optimization is obtained.
[0038] According to the fitness value of the parameters in the cluster, the control strategy optimization parameter cluster is screened and optimized in proportion. For example, the fish-light balance control parameters with the fitness in the top 5% are screened to form a fish-light balance control parameter solution library. The target water body is subjected to fish-light complementary control through the fish-light balance control parameter solution library. First, the optimal parameter solution in the fish-light balance control parameter solution library is used for complementary control. When the control effect does not meet expectations, the suboptimal parameter solution in the fish-light balance control parameter solution library can be directly used for control and application, thereby reducing the optimization and analysis time of the control parameters. The coordinated optimization of the parameters of fishery and photovoltaic power generation is achieved, the accuracy and rationality of the complementary control parameters are improved, and the timeliness of the fish-light complementary control and the effect of the fish-light complementary control are ensured.
[0039] In summary, the fishery-light complementary regulation method based on microbial population monitoring provided in this application has the following technical effects: By adopting the sampling point analysis of the target water body, multiple key sampling points are determined, and the water body is collected at multiple key sampling points at multiple times by the microbial sampler to obtain a multi-point water body microbial sample set, and a microbial identification instrument is used to perform multi-dimensional identification analysis on each of them to obtain a multi-point microbial identification data stream set, and the multi-point microbial identification data stream set is statistically integrated and processed based on the data processor to generate a microbial population change report, and then the microbial population change report is matched with the fish-photovoltaic complementary balanced regulation strategy to obtain the target fish-photovoltaic complementary regulation strategy, and according to the target fish-photovoltaic complementary regulation strategy, the fish-photovoltaic complementary regulation strategy parameter space is constructed, so as to perform regulation analysis on the microbial population change report, and obtain the fish-photovoltaic balanced regulation parameter solution library to perform fish-photovoltaic complementary regulation on the target water body. Then, the technical effect of achieving the coordinated optimization of parameters of fishery and photovoltaic power generation through multi-point monitoring of the changes in microbial populations in water bodies, improving the accuracy and rationality of complementary regulation parameters, and thus ensuring the fish-photovoltaic complementary regulation effect is achieved.
[0040] Embodiment 2 Based on the same inventive concept as the fishery-photovoltaic complementary regulation method based on microbial population monitoring in the aforementioned embodiment, the present invention also provides a fishery-photovoltaic complementary regulation platform based on microbial population monitoring, such as Figure 3 As shown, the platform includes: The monitoring device acquisition module 11 is used to acquire a microbial population monitoring device, and the microbial population monitoring device includes a microbial sampler, a microbial identification instrument and a data processor; the sampling point analysis module 12 is used to perform sampling point analysis on the target water body, determine multiple key sampling points, and use the microbial sampler to perform multi-time water body collection on the multiple key sampling points to obtain a multi-point water body microbial sample set; the multi-dimensional identification analysis module 13 is used to use the microbial identification instrument to perform multi-dimensional identification analysis on the multi-point water body microbial sample set respectively to obtain a multi-point microbial identification data stream set; the population change report generation module 14 is used to analyze the multi-point water body microbial sample set based on the data processor The point microbial identification data stream set is statistically integrated and processed to generate a microbial population change report; the strategy parameter space construction module 15 is used to construct a fish-light complementary balanced regulation strategy, match the microbial population change report with the fish-light complementary balanced regulation strategy, obtain the target fish-light complementary regulation strategy, and construct the fish-light complementary regulation strategy parameter space according to the target fish-light complementary regulation strategy; the fish-light complementary regulation module 16 is used to perform regulation and analysis on the microbial population change report based on the fish-light complementary regulation strategy parameter space, obtain a fish-light balanced regulation parameter solution library, and perform fish-light complementary regulation on the target water body through the fish-light balanced regulation parameter solution library.
[0041] Furthermore, the sampling point analysis module 12 is also used for: Acquire fishery water attribute factor information, the fishery water attribute factor information includes water body geographical characteristics, water quality environmental conditions, fishery breeding conditions and pollution source distribution; based on the fishery water attribute factor information, perform multidimensional parameter collection on the target water body to obtain a fishery water multidimensional factor parameter set; based on the fishery water multidimensional factor parameter set, perform spatial overlay analysis to obtain a fishery water spatial characteristic layer set; perform key area identification on the fishery water spatial characteristic layer set to obtain a key fishery water area set, and perform coverage analysis on the key fishery water area set to determine the multiple key sampling points.
[0042] Furthermore, the sampling point analysis module 12 is also used for: A recursive feature elimination algorithm is used to extract influencing features of the key fishery water area set to obtain a fishery water influencing feature set; feature marking is performed on the key fishery water area set based on the fishery water influencing feature set to obtain a fishery water area influencing feature set; coverage analysis is performed on the key fishery water area set based on the fishery water area influencing feature set to obtain a fishery water area initial sampling point set; cluster analysis is performed on the fishery water area initial sampling point set to obtain a water body sampling clustering result, and the multiple key sampling points are determined based on the water body sampling clustering result.
[0043] Furthermore, the sampling point analysis module 12 is also used for: Based on the multidimensional factor parameter set of the fishery water body, the associated features of the key fishery water body area set are extracted to obtain the fishery water body associated feature set; historical data mining is performed on the fishery water body associated feature set to obtain a fishery water body microbial distribution feature data set; random forest is used to perform microbial population prediction training on the fishery water body microbial distribution feature data set to obtain a fishery water body microbial population prediction model; a meta-transformer is obtained according to a recursive feature elimination algorithm, and the fishery water body associated feature set is iteratively removed by the meta-transformer, and the fishery water body microbial population prediction model after the feature removal is trained and evaluated to screen and obtain the fishery water body influencing feature set.
[0044] Furthermore, the population change report generating module 14 is also used for: Perform microbial parameter statistics on the multi-point microbial identification data stream set to obtain a multi-point microbial parameter set, which includes microbial species, quantity and population proportion; integrate the multi-point microbial parameter set according to time series to obtain a multi-point microbial population time series distribution parameter set; use regression analysis to perform trend fitting on the multi-point microbial population time series distribution parameter set to generate a microbial population distribution change trend curve set; perform multi-point network processing on the microbial population distribution change trend curve set according to the sampling point sequence to generate the microbial population change report.
[0045] Furthermore, the fish-light complementary control module 16 is also used for: A set of fish-light complementation regulation effect indicators is obtained, and the fish-light complementation regulation effect indicator set is fitted based on the fish-light complementation regulation strategy parameter space to construct a fish-light complementation regulation effect fitness function; a correlation analysis is performed on the fish-light complementation regulation strategy parameter space based on the microbial population change report to determine a regulation strategy parameter selection threshold; multiple groups of regulation strategy parameters are orthogonally selected within the regulation strategy parameter selection threshold, and the fitness of the multiple groups of regulation strategy parameters are evaluated using the fish-light complementation regulation effect fitness function to obtain multiple groups of parameter regulation effect fitness; a parameter cluster center is selected according to the multiple groups of parameter regulation effect fitness, and the multiple groups of regulation strategy parameters are optimized and analyzed based on the parameter cluster center to obtain the fish-light balance regulation parameter solution library by optimal search.
[0046] Furthermore, the fish-light complementary control module 16 is also used for: A learning factor is set, and the remaining control parameters in the multiple groups of control strategy parameters are learned and updated toward the center of the parameter cluster according to the learning factor to obtain a control strategy learning parameter cluster; a genetic algorithm is used to perform population iterative optimization in the control strategy learning parameter cluster to obtain a control strategy optimization parameter cluster, and the control strategy optimization parameter cluster is proportionally screened and optimized to obtain the fish-light balance control parameter solution library.
[0047] The foregoing Figure 1 The various variations and specific examples of the fish-photovoltaic complementary regulation method based on microbial population monitoring in Example 1 are also applicable to the fish-photovoltaic complementary regulation platform based on microbial population monitoring in this example. Through the above detailed description of the fish-photovoltaic complementary regulation method based on microbial population monitoring, those skilled in the art can clearly know the implementation method of the fish-photovoltaic complementary regulation platform based on microbial population monitoring in this example. Therefore, for the sake of brevity of the specification, it will not be described in detail here.
[0048] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A method for regulating fishery-light complementation based on microbial population monitoring, characterized in that: The method comprises: Obtaining a microbial population monitoring device, wherein the microbial population monitoring device includes a microbial sampler, a microbial identification instrument, and a data processor; Perform sampling point analysis on the target water body to determine multiple key sampling points, and use the microbial sampler to collect water samples at multiple key sampling points at multiple times to obtain a multi-point water body microbial sample set; Use the microbial identification instrument to perform multi-dimensional identification analysis on the multi-point water body microbial sample sets to obtain a multi-point microbial identification data stream set; Based on the data processor, the multi-point microbial identification data stream set is statistically integrated and processed to generate a microbial population change report; Constructing a balanced regulation strategy for fishery-photovoltaic complementarity, matching the report on the change of microbial populations with the balanced regulation strategy for fishery-photovoltaic complementarity, obtaining a target fishery-photovoltaic complementarity regulation strategy, and constructing a parameter space for the fishery-photovoltaic complementarity regulation strategy according to the target fishery-photovoltaic complementarity regulation strategy; Based on the parameter space of the fish-light complementary regulation strategy, the microbial population change report is regulated and analyzed to obtain a fish-light balance regulation parameter solution library, and the target water body is regulated by the fish-light balance regulation parameter solution library.
2. The method for regulating fishery-light complementation based on microbial population monitoring according to claim 1, characterized in that: The determining of multiple key sampling points includes: Acquire fishery water attribute factor information, wherein the fishery water attribute factor information includes water body geographical characteristics, water quality and environmental conditions, fishery breeding conditions, and pollution source distribution; Based on the fishery water body attribute factor information, multi-dimensional parameter collection is performed on the target water body to obtain a multi-dimensional factor parameter set of the fishery water body; Based on the multidimensional factor parameter set of the fishery water body, a spatial superposition analysis is performed to obtain a spatial characteristic layer set of the fishery water body; The key areas of the fishery water body spatial characteristic layer set are identified to obtain a key fishery water body area set, and the key fishery water body area set is analyzed for coverage to determine the multiple key sampling points.
3. The method for regulating fishery-light complementation based on microbial population monitoring according to claim 2, characterized in that: The determining of the plurality of key sampling points comprises: Using a recursive feature elimination algorithm to extract impact features from the key fishery water body area set, to obtain a fishery water body impact feature set; Based on the fishery water body impact feature set, feature marking is performed on the key fishery water body area set to obtain a fishery water body area impact feature set; Based on the fishery water area impact feature set, a coverage analysis is performed on the key fishery water area set to obtain an initial sampling point set for the fishery water area; A cluster analysis is performed on the initial sampling point set of the fishery water area to obtain a water body sampling clustering result, and the multiple key sampling points are determined based on the water body sampling clustering result.
4. The method for regulating fishery-light complementation based on microbial population monitoring according to claim 3, characterized in that: The fishery water body impact feature set obtained includes: Extracting correlation features of the key fishery water body area set based on the fishery water body multidimensional factor parameter set to obtain a fishery water body correlation feature set; Performing historical data mining on the fishery water body associated feature set to obtain a fishery water body microbial distribution feature data set; Using random forest to perform microbial population prediction training on the fishery water microbial distribution characteristic dataset to obtain a fishery water microbial population prediction model; A meta-transformer is obtained according to a recursive feature elimination algorithm, and the fishery water body associated feature set is iteratively removed through the meta-transformer. The fishery water body microbial population prediction model after feature removal is trained and evaluated to screen and obtain the fishery water body influencing feature set.
5. The method for regulating fishery-light complementation based on microbial population monitoring according to claim 1, characterized in that: The generating of the microbial population change report includes: Performing microbial parameter statistics on the multi-point microbial identification data stream set to obtain a multi-point microbial parameter set, wherein the multi-point microbial parameter set includes microbial species, quantity, and population proportion; Integrating the multi-point microbial parameter set according to the time series to obtain a multi-point microbial population time series distribution parameter set; Using regression analysis to perform trend fitting on the multi-point microbial population time series distribution parameter set to generate a set of microbial population distribution change trend curves; The microbial population distribution change trend curve set is processed by multi-point networking according to the sampling point sequence to generate the microbial population change report.
6. The method for regulating fishery-light complementation based on microbial population monitoring according to claim 1, characterized in that: The method of obtaining a fish-light balance control parameter solution library includes: Acquire a set of fishery-photovoltaic complementation regulation effect indicators, fit the set of fishery-photovoltaic complementation regulation effect indicators based on the parameter space of the fishery-photovoltaic complementation regulation strategy, and construct a fishery-photovoltaic complementation regulation effect fitness function; Based on the microbial population change report, a correlation analysis is performed on the parameter space of the fishery-photovoltaic complementary control strategy to determine a control strategy parameter selection threshold; orthogonally selecting multiple groups of control strategy parameters within the control strategy parameter selection threshold, and using the fishery-photovoltaic complementary control effect fitness function to evaluate the fitness of the multiple groups of control strategy parameters to obtain the fitness of the control effects of the multiple groups of parameters; The center of a parameter cluster is selected according to the fitness of the multiple groups of parameter control effects, and the multiple groups of control strategy parameters are optimized and analyzed based on the center of the parameter cluster to obtain the fish-light balance control parameter solution library.
7. The method for regulating fishery-light complementation based on microbial population monitoring according to claim 6, characterized in that: The optimization step to obtain the fish-light balance control parameter solution library includes: Setting a learning factor, and learning and updating the remaining control parameters in the multiple groups of control strategy parameters toward the center of the parameter cluster according to the learning factor to obtain a control strategy learning parameter cluster; A genetic algorithm is used to perform population iterative optimization within the control strategy learning parameter cluster to obtain a control strategy optimization parameter cluster, and the control strategy optimization parameter cluster is screened and optimized in proportion to obtain the fish-light balance control parameter solution library.
8. A fishery-light complementary regulation platform based on microbial population monitoring, characterized in that: For implementing the method for regulating fishery-photovoltaic complementary development based on microbial population monitoring according to any one of claims 1 to 7, the platform comprises: A monitoring device acquisition module, used to acquire a microbial population monitoring device, wherein the microbial population monitoring device includes a microbial sampler, a microbial identification instrument and a data processor; A sampling point analysis module is used to perform sampling point analysis on the target water body, determine multiple key sampling points, collect water samples at multiple key sampling points at multiple times through the microbial sampler, and obtain a multi-point water body microbial sample set; A multi-dimensional identification and analysis module, used to use the microbial identification instrument to perform multi-dimensional identification and analysis on the multi-point water body microbial sample sets respectively, to obtain a multi-point microbial identification data stream set; A population change report generating module, used for performing statistical integration processing on the multi-point microbial identification data stream set based on the data processor to generate a microbial population change report; A strategy parameter space construction module is used to construct a balanced regulation strategy for fishery-photovoltaic complementarity, match the microbial population change report with the balanced regulation strategy for fishery-photovoltaic complementarity, obtain a target fishery-photovoltaic complementarity regulation strategy, and construct a fishery-photovoltaic complementarity regulation strategy parameter space according to the target fishery-photovoltaic complementarity regulation strategy; The fish-light complementary regulation module is used to regulate and analyze the microbial population change report based on the fish-light complementary regulation strategy parameter space, obtain the fish-light balanced regulation parameter solution library, and perform fish-light complementary regulation on the target water body through the fish-light balanced regulation parameter solution library.
Citation Information
Patent Citations
Water conservancy project regulation and control system and method for improving habitat of rare fish population
CN115152671A
Plankton in-situ culture method and culture system thereof
CN115161202A
Optimized scheduling method for water-light complementary system based on multi-target whale algorithm
CN118333345A
Intelligent control method and system of biological isolation device
CN118393898A
Self-Adaptive Optimization Framework for Water Quality Prediction
US20240295539A1
Cited By
PTSD risk prediction system based on multi-dimensional data analysis
CN119786031A
Carbon-neutralization-oriented fishery-light composite ecological system construction method and related device
CN121503298A
