Algae culture management method based on multi-parameter optimization

Abstract

The invention provides an algae culture management method based on multi-parameter optimization, and relates to the technical field of algae culture, and the method comprises the steps: making and executing an illumination management plan and a water quality management plan according to a key prediction result obtained by predicting illumination intensity and water quality change based on culture related data obtained by monitoring a current culture area; and dynamically adjusting the operation state of the key culture equipment according to the requirements of illumination management and water quality management in combination with the equipment operation data obtained by monitoring the current culture area. The method comprises the following steps: predicting illumination intensity and water quality change by using cultivation related data obtained by monitoring algae cultivation related parameters of a current cultivation area to obtain a key prediction result; making and executing an illumination management plan and a water quality management plan based on the key prediction result; according to the requirements of illumination management and water quality management, the operation state of the key culture equipment is dynamically adjusted in combination with the equipment operation data obtained by monitoring the operation state of the culture equipment, and the efficiency and quality of algae culture can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of algae cultivation, and particularly to an algae cultivation management method based on multi-parameter optimization. Background Art

[0002] In recent years, with the rapid development of the aquaculture industry and the urgent need for efficient and sustainable aquaculture models, aquaculture methods have faced many challenges. Among them, light and water quality, as key factors affecting the growth of aquatic organisms, the improvement of their management levels is particularly important. However, existing aquaculture systems often lack precise light control and water quality management capabilities, resulting in low aquaculture efficiency. Therefore, how to achieve real-time monitoring and intelligent control of light intensity, water quality parameters, and the operating status of aquaculture equipment to improve aquaculture efficiency has become one of the current research focuses.

[0003] Therefore, the present invention provides an algae cultivation management method based on multi-parameter optimization. Summary of the Invention

[0004] The present invention provides an algae cultivation management method based on multi-parameter optimization, which is used to predict the light intensity and water quality changes by using the aquaculture-related data obtained from monitoring the aquaculture-related parameters in the current aquaculture area, and obtain key prediction results; formulate and execute a light management plan and a water quality management plan based on the key prediction results; and dynamically adjust the operating status of key aquaculture equipment according to the light management and water quality management requirements, combined with the equipment operation data obtained from monitoring the operating status of aquaculture equipment, which can effectively improve the efficiency and quality of algae cultivation.

[0005] The present invention provides an algae cultivation management method based on multi-parameter optimization, including: Step 1: Use the set monitoring equipment to continuously monitor the aquaculture-related parameters in the current aquaculture area and the operating status of aquaculture equipment, and correspondingly obtain aquaculture-related data and equipment operation data; Step 2: Regularly predict the light intensity and water quality changes based on the aquaculture-related data to obtain key prediction results; Step 3: Formulate and execute a light management plan and a water quality management plan based on the key prediction results; Step 4: Dynamically adjust the operating status of key aquaculture equipment according to the light management and water quality management requirements, combined with the equipment operation data.

[0006] Preferably, the aquaculture-related parameters include the output power of the photovoltaic panel, the power of the energy storage system, and water quality parameters.

[0007] Preferably, regularly predicting the light intensity and water quality changes based on the aquaculture-related data to obtain key prediction results includes: Extract historical aquaculture-related data and historical meteorological data within a preset time period of the current aquaculture area from the preset aquaculture database; Screen historical water quality parameter data from the obtained historical aquaculture-related data, and perform data preprocessing on the historical water quality parameter data to obtain first analysis data; Screen historical light data from the obtained historical meteorological data, and perform data preprocessing on the historical light data to obtain second analysis data; Use the first analysis data as the input to the pre-established water quality prediction model to obtain the predicted water quality parameter change values within the first preset time period; After performing data preprocessing on the key meteorological data at the current moment, combine it with the second analysis data as the input, and input it into the pre-established light prediction model to obtain the predicted light intensity value within the first preset time period; Summarize the predicted water quality parameter change values and predicted light intensity values within the first preset time period to obtain the key prediction results and output them.

[0008] Preferably, based on the key prediction results, formulate and execute a light management plan and a water quality management plan, including: Compare and analyze the predicted light intensity value within the first preset time period with the set optimal light intensity range for algae to generate a light adjustment plan, and use the target light driving device to adjust the angle between the current photovoltaic panel and the ground according to the light adjustment plan; Compare and analyze the predicted water quality parameter change values within the first preset time period with the corresponding set parameter threshold range to generate a water quality adjustment plan, and use the target water quality driving device to automatically adjust the corresponding water quality-related equipment according to the water quality adjustment plan.

[0009] Preferably, compare and analyze the predicted light intensity value within the first preset time period with the set optimal light intensity range for algae to generate a light adjustment plan, and use the target driving device to adjust the angle between the current photovoltaic panel and the ground according to the light adjustment plan, including: Step 11: Compare and analyze the predicted light intensity value within the first preset time period in the key prediction results with the set optimal light intensity range for algae in sequence according to the time sequence, and mark the corresponding moments of the predicted light intensity values that do not belong to the set optimal light intensity range for algae as abnormal moments; Step 12: Mark the corresponding abnormal moments when the predicted light intensity value is lower than the set optimal light intensity range for algae as the first abnormal moments; Mark the corresponding abnormal moments when the predicted light intensity value is higher than the set optimal light intensity range for algae as the second abnormal moments; Step 13: Using the light intensity difference between the predicted light intensity value and the set reference light intensity value as the dependent variable, and each moment within the first preset time period as the independent variable, construct a predicted light intensity change curve in chronological order; Step 14: In the predicted light intensity change curve, identify and mark the first abnormal moment and the second abnormal moment; In the predicted light intensity change curve, divide the first abnormal moment and the curve from it to the next normal moment or before the second abnormal moment into an abnormal curve, and mark the adjusted included angle direction as reducing the target included angle; Divide the second abnormal moment and the curve from it to the next normal moment or before the first abnormal moment into an abnormal curve, and mark the adjusted included angle direction as increasing the target included angle; In the predicted light intensity change curve, number all the obtained abnormal curves in the order of acquisition; Step 15: By combining the corresponding adjusted included angle direction of the first abnormal curve with the light intensity difference between the predicted light intensity value and the set reference light intensity value for analysis, optimize the angle between the current photovoltaic panel and the ground to obtain the optimal angle; Among them, the calculation formula for the optimal angle is as follows: ; In the formula, represents the optimal angle between the current photovoltaic panel and the ground; represents the maximum value of the angle between the current photovoltaic panel and the ground when the light intensity value within the preset time belongs to the set optimal light intensity range for algae; represents the minimum value of the angle between the current photovoltaic panel and the ground when the light intensity value within the preset time belongs to the set optimal light intensity range for algae; represents the corresponding predicted light intensity value at the first abnormal moment in the current abnormal curve; represents the set reference light intensity value; e represents a constant with a value of 2.7; ln represents the natural logarithm; Step 16: Generate a light intensity adjustment plan using the optimal angle and the first abnormal moment in the first abnormal curve, and use the target light intensity driving device to actually adjust the angle between the current photovoltaic panel and the ground according to the light intensity adjustment plan; Step 17: After the angle between the photovoltaic panel and the ground is adjusted, re-acquire the historical light intensity data within the preset time period, and combine it with the light intensity prediction model to obtain the new predicted light intensity value within the new first preset time period; Based on the new predicted light intensity, repeat steps 11 - 16 to adjust the angle between the photovoltaic panel and the ground.

[0010] Preferably, compare and analyze the predicted water quality parameter change values within the first preset time period with the corresponding set parameter threshold ranges to generate a water quality adjustment plan, and use the target water quality drive device to automatically adjust the corresponding water quality-related equipment according to the water quality adjustment plan, including: Step 21: Use the predicted water quality parameter change values within the first preset time period of the current water quality parameters as the dependent variable, and according to the parameter prediction change curve of the current water quality parameters in time sequence; Step 23: In the parameter prediction change curve, mark the corresponding moments when the predicted water quality parameter change values exceed or are lower than the corresponding set parameter threshold ranges as parameter abnormal moments, and mark the equipment adjustment directions; Step 24: If there are parameter abnormal moments in the parameter prediction change curve, then in the parameter prediction change curve, divide the curve from the parameter abnormal moment closest to the current moment to the next normal moment or before the parameter abnormal moment with a different equipment adjustment direction into a parameter sub-abnormal curve; Step 25: Through combined analysis of the corresponding equipment adjustment direction of the parameter sub-abnormal curve and the difference between the predicted water quality parameter change value and the set parameter threshold range, obtain an equipment adjustment strategy; Step 26: Combine the equipment adjustment strategy with the corresponding abnormal moment data of the parameter sub-abnormal curve to generate a water quality management plan, and use the target water quality drive device to automatically adjust the corresponding water quality-related equipment according to the water quality adjustment plan; Step 27: After the water quality-related equipment is adjusted, re-obtain the historical water quality parameter data within the preset time period of the current water quality parameters, and combine with the water quality prediction model to obtain the new predicted water quality parameter change values within the new first preset time period of the current water quality parameters; Based on the predicted water quality parameter change values, repeat Steps 21-26 to achieve the management of water quality.

[0011] Preferably, through combined analysis of the corresponding equipment adjustment direction of the parameter sub-abnormal curve and the difference between the predicted water quality parameter change value and the set parameter threshold range, obtain an equipment adjustment strategy, including: Determine the set reference parameter threshold according to the set parameter threshold range; Compare the predicted water quality parameter change value in the parameter sub-abnormal curve with the set reference parameter threshold to obtain a parameter difference score; Use the parameter difference score and the corresponding water quality parameters of the current parameter sub-abnormal curve as matching conditions to screen out a key equipment adjustment plan from the set water quality adjustment database; When there are no adjustable parameters in the key equipment adjustment plan, output the current key equipment adjustment plan as the equipment adjustment strategy; When there are adjustable parameters in the key equipment adjustment plan, extract the predicted water quality parameter change value at the first parameter abnormal moment from the current parameter sub-abnormal curve, and mark it as the key value; By analyzing the numerical difference between the key value and the set reference parameter threshold, obtain the optimization coefficient; Combine the optimization coefficient with the equipment adjustment direction, optimize the adjustable parameters of the key equipment adjustment plan, and then generate and output the equipment adjustment strategy.

[0012] Preferably, according to the requirements of light management and water quality management, dynamically adjust the operating status of key aquaculture equipment in combination with equipment operation data, including: Extract the equipment involved from the light management plan and water quality management plan, and label it as key aquaculture equipment; Obtain the operation data of the key aquaculture equipment from the equipment operation data, and label it as the first operation data; According to the first operation data, combine the performance evaluation index to evaluate the performance of the current key aquaculture equipment, and obtain the real-time performance evaluation coefficient; Input the first operation data into the pre-established equipment operation prediction model to obtain the predicted operation data of the current key aquaculture equipment within the first preset time period; According to the predicted operation data, combine the performance evaluation index to evaluate the performance of the current key aquaculture equipment, and obtain the predicted performance evaluation coefficient; Perform weighted averaging on the real-time performance evaluation coefficient and the predicted performance evaluation coefficient to calculate the comprehensive equipment performance evaluation coefficient; When the comprehensive performance equipment evaluation coefficient is less than the set performance threshold, determine that the current key aquaculture equipment is operating abnormally, and mark it as an abnormal equipment; Use the comprehensive performance equipment evaluation coefficient and the abnormal equipment as screening conditions to screen out the corresponding equipment optimization strategy from the pre-set equipment adjustment database; Use the equipment optimization strategy to adjust and optimize the current abnormal equipment.

[0013] Compared with the prior art, the beneficial effects of this application are as follows: By using the aquaculture-related data obtained by monitoring the algae aquaculture-related parameters in the current aquaculture area to predict the light intensity and water quality changes, key prediction results are obtained; based on the key prediction results, a light management plan and a water quality management plan are formulated and implemented; according to the requirements of light management and water quality management, combined with the equipment operation data obtained by monitoring the operating status of aquaculture equipment, the operating status of key aquaculture equipment is dynamically adjusted, which can effectively improve the efficiency and quality of algae aquaculture.

[0014] Other features and advantages of the present invention will be described in the following specification, and in part will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be realized and obtained by the structure specifically pointed out in the written specification and the drawings.

[0015] The technical solution of the present invention will be further described in detail below with reference to the drawings and embodiments. Description of the Drawings

[0016] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention. In the drawings: Figure 1 It is a flowchart of a method for algae cultivation management based on multi-parameter optimization in an embodiment of the present invention. Detailed Embodiments

[0017] The following describes the preferred embodiments of the present invention with reference to the drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0018] An embodiment of the present invention provides a method for algae cultivation management based on multi-parameter optimization, as Figure 1 shown, including: Step 1: Use the set monitoring equipment to continuously monitor the parameters related to algae cultivation in the current cultivation area and the operating status of the cultivation equipment, and correspondingly obtain the cultivation-related data and equipment operation data; Step 2: Regularly predict the light intensity and water quality changes based on the cultivation-related data to obtain key prediction results; Step 3: Based on the key prediction results, formulate and execute a light management plan and a water quality management plan; Step 4: Dynamically adjust the operating status of the key cultivation equipment according to the light management and water quality management requirements, combined with the equipment operation data.

[0019] In this embodiment, the monitoring device refers to a series of sensors specially configured to monitor in real time the parameters related to algae cultivation in the current cultivation area and the operating status of cultivation equipment, such as a light intensity sensor and a pressure sensor; the parameters related to algae cultivation include the output power of the photovoltaic panel, the power of the energy storage system, and water quality parameters (such as pH value, dissolved oxygen, nitrate, phosphate, etc.); the equipment operation data refers to the operating status and performance data of various equipment related to algae cultivation, such as the equipment operation data when the equipment is a photovoltaic panel: real-time output power, working voltage, working current, temperature; the key prediction result refers to the specific values of light intensity and water quality parameters in a future period obtained through a prediction model based on historical data and current monitoring data; the light management plan is an adjustment strategy for the angle between the photovoltaic panel and the ground formulated to optimize the photosynthesis of algae based on the light intensity prediction result; the water quality management plan is a management strategy formulated to maintain the water quality in the cultivation area within an appropriate range based on the water quality parameter prediction result; the key cultivation equipment refers to the cultivation equipment involved in the light management plan and the water quality management plan, such as photovoltaic panels, aerators, water pumps, filters, etc.

[0020] The beneficial effects of the above technical solution are: by using the cultivation-related data obtained from monitoring the parameters related to algae cultivation in the current cultivation area to predict the changes in light intensity and water quality, key prediction results are obtained; based on the key prediction results, a light management plan and a water quality management plan are formulated and implemented; according to the light management and water quality management requirements, combined with the equipment operation data obtained from monitoring the operating status of the cultivation equipment, the operating status of the key cultivation equipment is dynamically adjusted, which can effectively improve the efficiency and quality of algae cultivation.

[0021] An embodiment of the present invention provides a method for managing algae cultivation based on multi-parameter optimization, which regularly predicts the changes in light intensity and water quality based on the cultivation-related data to obtain key prediction results, including: Extract historical cultivation-related data and historical meteorological data within a preset time period of the current cultivation area from the preset cultivation database; Screen out historical water quality parameter data from the obtained historical cultivation-related data, and perform data preprocessing on the historical water quality parameter data to obtain first analysis data; Screen out historical light data from the obtained historical meteorological data, and perform data preprocessing on the historical light data to obtain second analysis data; Take the first analysis data as the input side and input it into a pre-established water quality prediction model to obtain the predicted change values of water quality parameters within a first preset time period; After performing data preprocessing on the key meteorological data at the current moment, combine it with the second analysis data as the input side and input it into a pre-established light prediction model to obtain the predicted light intensity value within a first preset time period; Summarize the predicted water quality parameter change values and predicted light intensity values within the first preset time period to obtain a key prediction result and output it.

[0022] In this embodiment, the preset aquaculture database refers to a database that stores a large amount of aquaculture-related data, including historical aquaculture records, water quality parameters, meteorological data, etc.; the preset time period refers to the time period selected when extracting historical data from the preset aquaculture database before prediction; historical aquaculture-related data refers to data directly related to aquaculture activities in the aquaculture area during a past period of time, such as historical water quality parameters; historical meteorological data refers to meteorological information during a past period of time, such as light intensity, temperature, humidity, rainfall, etc.; the first analysis data is the historical water quality parameter data after data preprocessing, where data preprocessing includes data cleaning (removing outliers, filling missing values, etc.) and data transformation (such as standardization, normalization, etc.) to improve the quality of the data and the accuracy of the prediction model; historical light data is data directly related to the light intensity in the aquaculture area, selected from historical meteorological data; the second analysis data is the historical light data after data preprocessing; the water quality prediction model is a model obtained by pre-training a neural network for predicting the change trend and specific values of water quality parameters in the future for a period of time; the light prediction model is a model obtained by pre-training a neural network for predicting the change of light intensity in the aquaculture area in the future for a period of time; the first preset time period refers to the future time period set during prediction, that is, the time range covered by the prediction result; the key prediction result is the result obtained by summarizing the predicted water quality parameter change values and predicted light intensity values within the first preset time period, and is an important basis for formulating and implementing the light management plan and water quality management plan.

[0023] The beneficial effects of the above technical solution are: By comprehensively applying technical means such as data analysis, prediction models, and intelligent management, accurate prediction and management of water quality and light conditions in the aquaculture area are achieved, providing an important data basis for subsequent formulation and implementation of the light management plan and water quality management plan.

[0024] An embodiment of the present invention provides an algae aquaculture management method based on multi-parameter optimization. Based on the key prediction result, formulate and implement a light management plan and a water quality management plan, including: Compare and analyze the predicted light intensity value within the first preset time period with the set optimal light intensity range for algae to generate a light adjustment plan, and use the target light drive device to adjust the angle between the current photovoltaic panel and the ground according to the light adjustment plan; Compare and analyze the predicted water quality parameter change values within the first preset time period with the corresponding set parameter threshold ranges to generate a water quality adjustment plan, and use the target water quality drive device to automatically adjust the corresponding water quality-related equipment according to the water quality adjustment plan.

[0025] In this embodiment, the light adjustment plan is formulated based on the comparison and analysis results of the predicted light intensity values and the set optimal light intensity range for algae, aiming to ensure that the light conditions in the aquaculture area are always maintained within the optimal range for algae growth; the target light drive device is a mechanical device used to execute the light adjustment plan, and automatically adjusts the angle of the photovoltaic panel according to the instructions in the light adjustment plan; the water quality adjustment plan is formulated based on the comparison and analysis results of the predicted water quality parameter change values and the set parameter threshold ranges, and is the specific time and parameter settings for automatically adjusting the water quality-related equipment according to the predicted water quality parameter changes; the target water quality drive device is a mechanical device used to execute the water quality adjustment plan, and automatically adjusts the parameter settings of the water quality-related equipment according to the instructions in the water quality adjustment plan; the water quality-related equipment refers to various mechanical devices and instruments used to adjust and improve the water quality in the aquaculture area, such as aeration equipment (used to increase the dissolved oxygen content in the water), filtration equipment (used to remove suspended solids and impurities in the water), pH regulators (used to adjust the acidity and alkalinity of the water quality), etc.

[0026] The beneficial effects of the above technical solution are: By formulating and implementing the light management plan and water quality management plan, the precise management and optimal adjustment of the light intensity and water quality conditions in the aquaculture area are achieved, which helps to improve the efficiency of algae cultivation and management efficiency.

[0027] An embodiment of the present invention provides an algae cultivation management method based on multi-parameter optimization. Compare and analyze the predicted light intensity values within the first preset time period with the set optimal light intensity range for algae to generate a light adjustment plan, and use the target drive device to adjust the angle between the current photovoltaic panel and the ground according to the light adjustment plan, including: Step 11: Compare and analyze the predicted light intensity values within the first preset time period in the key prediction results with the set optimal light intensity range for algae in sequence according to the time sequence, and mark the corresponding moments of the predicted light intensity values that do not belong to the set optimal light intensity range for algae as abnormal moments; Step 12: Mark the corresponding abnormal moments when the predicted light intensity value is lower than the set optimal light intensity range for algae as the first abnormal moments; Mark the corresponding abnormal moments when the predicted light intensity value is higher than the set optimal light intensity range for algae as the second abnormal moments; Step 13: Construct a predicted light intensity change curve in chronological order, with the light intensity difference between the predicted light intensity value and the set reference light intensity value as the dependent variable and each moment within the first preset time period as the independent variable; Step 14: Identify and mark the first abnormal moment and the second abnormal moment in the predicted light intensity change curve; In the predicted light intensity change curve, divide the first abnormal moment and the curve from it to the next normal moment or before the second abnormal moment into an abnormal curve, and mark the adjustment angle direction as reducing the target angle; Divide the second abnormal moment and the curve from it to the next normal moment or before the first abnormal moment into an abnormal curve, and mark the adjustment angle direction as increasing the target angle; In the predicted light intensity change curve, number all the obtained abnormal curves in the order of acquisition; Step 15: Optimize the angle between the current photovoltaic panel and the ground by combining the corresponding adjustment angle direction of the first abnormal curve with the light intensity difference between the predicted light intensity value and the set reference light intensity value to obtain the optimal angle; Among them, the calculation formula for the optimal angle is as follows: ; In the formula, represents the optimal angle between the current photovoltaic panel and the ground; represents the maximum value of the angle between the current photovoltaic panel and the ground when the light intensity value belongs to the set optimal light intensity range of algae within the preset time; represents the minimum value of the angle between the current photovoltaic panel and the ground when the light intensity value belongs to the set optimal light intensity range of algae within the preset time; represents the corresponding predicted light intensity value at the first abnormal moment in the current abnormal curve; represents the set reference light intensity value; e represents a constant with a value of 2.7; ln represents the natural logarithm; Step 16: Generate a light intensity adjustment plan using the optimal angle and the first abnormal moment in the first abnormal curve, and use the target light intensity driving device to actually adjust the angle between the current photovoltaic panel and the ground according to the light intensity adjustment plan; Step 17: After the angle between the photovoltaic panel and the ground is adjusted, re-acquire the historical light intensity data within the preset time period, and combine with the light intensity prediction model to obtain the new predicted light intensity value within the new first preset time period; Based on the new predicted light intensity, repeat steps 11 - 16 to adjust the angle between the photovoltaic panel and the ground.

[0028] In this embodiment, the first abnormal moment refers to the corresponding abnormal moment when the predicted light intensity value is lower than the set optimal light intensity range for algae; the second abnormal moment refers to the corresponding abnormal moment when the predicted light intensity value is higher than the set optimal light intensity range for algae; the predicted light intensity change curve is a curve with time as the independent variable and the light intensity difference between the predicted light intensity value and the set reference light intensity value as the dependent variable; the optimal angle is the angle between the photovoltaic panel and the ground that keeps the light conditions in the breeding area within the optimal light intensity range for algae; the light adjustment plan is a plan for guiding the target light driving device to adjust the angle between the photovoltaic panel and the ground, including specific information such as the adjustment time, angle, and direction; the new predicted light intensity value is the new predicted light intensity value for a period of time in the future calculated by re-acquiring the historical light data within a preset time period after the angle between the photovoltaic panel and the ground is adjusted and combining it with the light prediction model.

[0029] The beneficial effects of the above technical solution are: by generating a light adjustment plan and using the target driving device to adjust the angle between the current photovoltaic panel and the ground according to the light adjustment plan, the healthy growth and high yield of algae can be effectively promoted, which in turn helps to improve the algae breeding efficiency and product quality.

[0030] An embodiment of the present invention provides a method for algae breeding management based on multi-parameter optimization, which compares and analyzes the predicted water quality parameter change values within the first preset time period with the corresponding set parameter threshold ranges to generate a water quality adjustment plan, and uses the target water quality driving device to automatically adjust the corresponding water quality-related equipment according to the water quality adjustment plan, including: Step 21: Use the predicted water quality parameter change values within the first preset time period of the current water quality parameters as the dependent variable, and predict the parameter change curve of the current water quality parameters according to the time sequence; Step 23: In the parameter prediction change curve, mark the corresponding moments when the predicted water quality parameter change values exceed or are lower than the corresponding set parameter threshold ranges as parameter abnormal moments, and mark the equipment adjustment directions; Step 24: If there are parameter abnormal moments in the parameter prediction change curve, then in the parameter prediction change curve, divide the curve from the parameter abnormal moment closest to the current moment to the next normal moment or before the parameter abnormal moment with a different equipment adjustment direction into a parameter sub-abnormal curve; Step 25: By combining and analyzing the corresponding equipment adjustment directions of the parameter sub-abnormal curve and the differences between the predicted water quality parameter change values and the set parameter threshold ranges, obtain the equipment adjustment strategy; Step 26: Combine the equipment adjustment strategy with the corresponding abnormal moment data of the parameter sub-abnormal curve to generate a water quality management plan, and use the target water quality driving device to automatically adjust the corresponding water quality-related equipment according to the water quality adjustment plan; Step 27: After the water quality related equipment is adjusted, re-obtain the historical water quality parameter data within the preset time period of the current water quality parameters, and combine with the water quality prediction model to obtain the new predicted water quality parameter change values within the new first preset time period of the current water quality parameters; Based on the predicted water quality parameter change values, repeat Steps 21-26 to achieve the management of water quality.

[0031] In this embodiment, the parameter prediction change curve is a curve with time as the independent variable and the predicted water quality parameter change value as the dependent variable; the parameter abnormal moment refers to the moment corresponding to when the predicted water quality parameter change value exceeds or is lower than the set parameter threshold range in the parameter prediction change curve; the equipment adjustment direction is determined according to the water quality parameter change at the parameter abnormal moment, and determines the water quality related equipment to be adjusted and its adjustment direction, generally referring to increasing or decreasing; the parameter sub-abnormal curve refers to the curve segment between the parameter abnormal moment closest to the current moment and the next normal moment or the parameter abnormal moment with a different equipment adjustment direction in the parameter prediction change curve; the equipment adjustment strategy consists of the type of equipment to be adjusted, the parameter adjustment amount, and the adjustment time; the new predicted water quality parameter change value refers to the new predicted water quality parameter change value within a certain period in the future calculated by re-obtaining the historical water quality parameter data within the preset time period of the current water quality parameters and combining with the water quality prediction model after the water quality related equipment is adjusted.

[0032] The beneficial effects of the above technical solution are: By generating a water quality adjustment plan and using the target water quality drive device to automatically adjust the corresponding water quality related equipment according to the water quality adjustment plan, it can effectively avoid the adverse impact of water quality deterioration on the aquaculture environment.

[0033] The embodiment of the present invention provides a method for algae aquaculture management based on multi-parameter optimization. By combining and analyzing the corresponding equipment adjustment direction of the parameter sub-abnormal curve and the difference between the predicted water quality parameter change value and the set parameter threshold range, an equipment adjustment strategy is obtained, including: Determine the set reference parameter threshold according to the set parameter threshold range; Compare the predicted water quality parameter change value in the parameter sub-abnormal curve with the set reference parameter threshold to obtain a parameter difference score; Use the parameter difference score and the corresponding water quality parameter of the current parameter sub-abnormal curve as matching conditions to screen out a key equipment adjustment plan from the set water quality adjustment database; When there are no adjustable parameters in the key equipment adjustment plan, output the current key equipment adjustment plan as the equipment adjustment strategy; When there are adjustable parameters in the critical equipment adjustment plan, extract the predicted water quality parameter change value at the first parameter anomaly moment from the current parameter sub-anomaly curve and mark it as the critical value; Obtain the optimization coefficient by analyzing the numerical difference between the critical value and the set reference parameter threshold; Combine the optimization coefficient with the equipment adjustment direction, optimize the adjustable parameters of the critical equipment adjustment plan, and then generate and output the equipment adjustment strategy.

[0034] In this embodiment, the set reference parameter threshold refers to the reference value used to evaluate whether the water quality parameters are normal; the parameter difference score is used to reflect the degree to which the water quality parameters deviate from the normal range; the critical equipment adjustment plan refers to the equipment adjustment suggestions for specific water quality problems screened from the set water quality adjustment database according to the parameter difference score and the current water quality parameters; the set water quality adjustment database refers to the database storing the equipment adjustment plans corresponding to various water quality parameter anomalies, which can provide predefined solutions for different water quality problems based on historical experience and professional knowledge; the optimization coefficient is used to further optimize the coefficients of the adjustable parameters in the critical equipment adjustment plan, making the adjustment strategy more accurate and adaptable to the current water quality condition.

[0035] The beneficial effects of the above technical solution are: by accurately matching the adjustment plan and dynamically adjusting the adjustment plan, the adjustment strategy can be made more in line with the current water quality condition, improving the accuracy and flexibility of the adjustment.

[0036] An embodiment of the present invention provides an algae cultivation management method based on multi-parameter optimization, which dynamically adjusts the operating state of critical cultivation equipment according to the requirements of light management and water quality management, in combination with equipment operation data, including: extracting the involved equipment from the light management plan and the water quality management plan and marking it as critical cultivation equipment; Obtain the operation data of the critical cultivation equipment from the equipment operation data and mark it as the first operation data; According to the first operation data, combine the performance evaluation index to evaluate the performance of the current critical cultivation equipment to obtain the real-time performance evaluation coefficient; Input the first operation data into the pre-established equipment operation prediction model to obtain the predicted operation data of the current critical cultivation equipment within the first preset time period; According to the predicted operation data, combine the performance evaluation index to evaluate the performance of the current critical cultivation equipment to obtain the predicted performance evaluation coefficient; Perform a weighted average on the real-time performance evaluation coefficient and the predicted performance evaluation coefficient to calculate the comprehensive equipment performance evaluation coefficient; When the comprehensive performance evaluation coefficient of the equipment is less than the set performance threshold, it is determined that the current key aquaculture equipment is operating abnormally and is marked as abnormal equipment; Using the comprehensive performance evaluation coefficient of the equipment and the abnormal equipment as screening conditions, the corresponding equipment optimization strategy is screened from the pre-set equipment adjustment database; The current abnormal equipment is adjusted and optimized using the equipment optimization strategy.

[0037] In this embodiment, the key aquaculture equipment refers to the aquaculture equipment that plays a crucial role in light management and water quality management, such as photovoltaic panels, aeration equipment, etc.; the performance evaluation index refers to a series of standards or parameters used to measure the operation efficiency and effect of the key aquaculture equipment, such as the energy consumption, working efficiency, operation stability, etc. of the equipment; the real-time performance evaluation coefficient is used to reflect the current operation status of the equipment; the equipment operation prediction model refers to a model established based on historical data and machine learning algorithms, which is used to predict the operation data of the key aquaculture equipment in the next period of time; the predicted performance evaluation coefficient is used to reflect the expected operation status of the key aquaculture equipment in the next period of time; the comprehensive equipment performance evaluation coefficient is a comprehensive index calculated by weighted averaging the real-time performance evaluation coefficient and the predicted performance evaluation coefficient, which is used to comprehensively evaluate the operation status of the key aquaculture equipment; the set performance threshold is a pre-set standard value used to judge whether the key aquaculture equipment is operating normally; the abnormal equipment refers to the key aquaculture equipment determined to be operating abnormally.

[0038] The beneficial effects of the above technical solution are: by dynamically adjusting the operation status of the key aquaculture equipment according to the requirements of light management and water quality management and combining the equipment operation data, the operation efficiency of the equipment can be improved and the intelligent management of the equipment can be realized, which in turn helps to improve the efficiency and quality of algae aquaculture.

[0039] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. An algae cultivation management method based on multi-parameter optimization, characterized in that, include: Step 1: Use the set monitoring equipment to monitor the algae cultivation related parameters and the operation status of the cultivation equipment in the current cultivation area in real time, and obtain the cultivation related data and equipment operation data accordingly; Step 2: Regularly predict the changes in light intensity and water quality based on the aquaculture-related data to obtain key prediction results; Step 3: Develop and implement a light management plan and a water quality management plan based on the key prediction results; Step 4: According to the lighting management and water quality management requirements, dynamically adjust the operating status of key aquaculture equipment in combination with equipment operation data.

2. The algal culture management method based on multi-parameter optimization according to claim 1, characterized in that, The algae cultivation related parameters include the output power of the photovoltaic panel, the power of the energy storage system and the water quality parameters.

3. A method for algae culture management based on multi-parameter optimization according to claim 1, characterized in that, Regularly predict the changes in light intensity and water quality based on the aquaculture-related data to obtain key prediction results, including: Extracting historical aquaculture-related data and historical meteorological data within a preset time period of the current aquaculture area from a preset aquaculture database; Screening historical water quality parameter data from the acquired historical aquaculture related data, and performing data preprocessing on the historical water quality parameter data to obtain first analysis data; Filtering out historical illumination data from the acquired historical meteorological data, and performing data preprocessing on the historical illumination data to obtain second analysis data; Inputting the first analysis data as input into a pre-established water quality prediction model to obtain a predicted water quality parameter change value within a first preset time period; After data preprocessing of the key meteorological data at the current moment, the second analysis data is used as input, and a pre-established light prediction model is input to obtain a predicted light intensity value within a first preset time period; The predicted water quality parameter change values and the predicted light intensity values within the first preset time period are summarized to obtain the key prediction results and output them.

4. A method for algae cultivation management based on multi-parameter optimization according to claim 1, characterized in that, Based on the key prediction results, develop and implement a light management plan and a water quality management plan, including: Compare and analyze the predicted light intensity value within the first preset time period with the set algae optimal light intensity range to generate a light adjustment plan, and use the target light driving device to adjust the angle between the current photovoltaic panel and the ground according to the light adjustment plan; The predicted water quality parameter change value within the first preset time period is compared and analyzed with the corresponding set parameter threshold range to generate a water quality adjustment plan, and the target water quality driving device is used to automatically adjust the corresponding water quality related equipment according to the water quality adjustment plan.

5. The algal cultivation management method based on multi-parameter optimization according to claim 4, characterized in that, The predicted light intensity value within the first preset time period is compared and analyzed with the set algae optimal light intensity range to generate a light adjustment plan, and the target driving device is used to adjust the angle between the current photovoltaic panel and the ground according to the light adjustment plan, including: Step 11: comparing and analyzing the predicted light intensity values within the first preset time period in the key prediction results with the set algae optimal light intensity range in chronological order, and marking the corresponding moments of the predicted light intensity values that do not fall within the set algae optimal light intensity range as abnormal moments; Step 12: Mark the corresponding abnormal moment when the predicted light intensity value is lower than the set algae optimal light intensity range as the first abnormal moment; Mark the corresponding abnormal moments when the predicted light intensity value is higher than the set optimal light intensity range of algae as the second abnormal moments; Step 13: Use the light intensity difference between the predicted light intensity value and the set reference light intensity value as the dependent variable, and each moment within the first preset time period as the independent variable to construct a predicted light intensity change curve in time sequence; Step 14: Identify and mark the first abnormal moments and the second abnormal moments in the predicted light intensity change curve; In the predicted light intensity change curve, divide the first abnormal moment and the curve from it to the next normal moment or before the second abnormal moment into abnormal curves, and mark the adjusted included angle direction as reducing the target included angle; Divide the second abnormal moment and the curve from it to the next normal moment or before the first abnormal moment into abnormal curves, and mark the adjusted included angle direction as increasing the target included angle; In the predicted light intensity change curve, number all the obtained abnormal curves in the order of acquisition; Step 15: Through the combined analysis of the corresponding adjusted included angle direction of the first abnormal curve and the light intensity difference between the predicted light intensity value and the set reference light intensity value, optimize the angle between the current photovoltaic panel and the ground to obtain the optimal angle; Among them, the calculation formula for the optimal angle is as follows: ; wherein, represents the optimal angle between the current photovoltaic panel and the ground; represents the maximum value of the angle between the current photovoltaic panel and the ground when the light intensity value belongs to the set optimal light intensity range of algae within the preset time; represents the minimum value of the angle between the current photovoltaic panel and the ground when the light intensity value belongs to the set optimal light intensity range of algae within the preset time; represents the corresponding predicted light intensity value at the first abnormal moment in the current abnormal curve; represents the set reference light intensity value; e represents a constant with a value of 2.7; ln represents the natural logarithm; Step 16: Generate a light intensity adjustment plan using the optimal angle and the first abnormal moment in the first abnormal curve, and use the target light intensity driving device to actually adjust the angle between the current photovoltaic panel and the ground according to the light intensity adjustment plan; Step 17: After the angle between the photovoltaic panel and the ground is adjusted, re-acquire the historical light intensity data within the preset time period, and combine it with the light intensity prediction model to obtain the new predicted light intensity value within the new first preset time period; Based on the new predicted light intensity, repeat Steps 11-16 to adjust the angle between the photovoltaic panel and the ground.

6. The algae cultivation management method based on multi-parameter optimization according to claim 4, characterized in that Compare and analyze the predicted water quality parameter change values within the first preset time period with the corresponding set parameter threshold ranges to generate a water quality adjustment plan, and use the target water quality driving device to automatically adjust the corresponding water quality-related equipment according to the water quality adjustment plan, including: Step 21: Use the predicted water quality parameter change values within the first preset time period of the current water quality parameters as the dependent variable to predict the parameter change curve of the current water quality parameters in time sequence; Step 23: In the parameter prediction change curve, mark the corresponding moments when the predicted water quality parameter change values exceed or are lower than the corresponding set parameter threshold ranges as parameter abnormal moments, and mark the equipment adjustment direction; Step 24: If there are parameter abnormal moments in the parameter prediction change curve, then in the parameter prediction change curve, divide the parameter abnormal moment closest to the current moment and the curve from it to the next normal moment or before the parameter abnormal moment with a different equipment adjustment direction into parameter sub-abnormal curves; Step 25: Through the combined analysis of the corresponding equipment adjustment direction of the parameter sub-abnormal curve and the difference between the predicted water quality parameter change value and the set parameter threshold range, obtain the equipment adjustment strategy; Step 26: Combine the device adjustment strategy with the corresponding abnormal moment data of the parameter sub-abnormal curve to generate a water quality management plan, and use the target water quality to drive the device to automatically adjust the corresponding water quality-related devices according to the water quality adjustment plan; Step 27: After the water quality-related devices are adjusted, re-obtain the historical water quality parameter data within the preset time period of the current water quality parameters, and combine the water quality prediction model to obtain the new predicted water quality parameter change values within the new first preset time period of the current water quality parameters; Based on the predicted water quality parameter change values, repeat Steps 21-26 to achieve the management of water quality.

7. A method for algae cultivation management based on multi-parameter optimization according to claim 6, characterized in that, By combining the corresponding device adjustment direction of the parameter sub-abnormal curve with the difference between the predicted water quality parameter change values and the set parameter threshold range for analysis, obtain the device adjustment strategy, including: Determine the set reference parameter threshold according to the set parameter threshold range; Use the predicted water quality parameter change values in the parameter sub-abnormal curve to compare with the set reference parameter threshold to obtain the parameter difference score; Use the parameter difference score and the corresponding water quality parameters of the current parameter sub-abnormal curve as matching conditions to screen out the key device adjustment plans from the set water quality adjustment database; When there are no adjustable parameters in the key device adjustment plan, output the current key device adjustment plan as the device adjustment strategy; When there are adjustable parameters in the key device adjustment plan, extract the predicted water quality parameter change value at the first parameter abnormal moment from the current parameter sub-abnormal curve and mark it as the key value; Obtain the optimization coefficient by analyzing the numerical difference between the key value and the set reference parameter threshold; Combine the optimization coefficient with the device adjustment direction, optimize the adjustable parameters of the key device adjustment plan, and then generate and output the device adjustment strategy.

8. A method for algae cultivation management based on multi-parameter optimization according to claim 1, characterized in that, According to the lighting management and water quality management requirements, dynamically adjust the operating status of the key aquaculture equipment in combination with the device operation data, including: Extract the devices involved from the lighting management plan and the water quality management plan and label them as key aquaculture equipment; Obtain the operation data of the key aquaculture equipment from the device operation data and label it as the first operation data; According to the first operation data, combine the performance evaluation index to evaluate the performance of the current key aquaculture equipment to obtain the real-time performance evaluation coefficient; Input the first operation data into the pre-established device operation prediction model to obtain the predicted operation data of the current key aquaculture equipment within the first preset time period; According to the predicted operation data, combine the performance evaluation index to evaluate the performance of the current key aquaculture equipment to obtain the predicted performance evaluation coefficient; Perform weighted averaging on the real-time performance evaluation coefficient and the predicted performance evaluation coefficient to calculate the comprehensive device performance evaluation coefficient; When the comprehensive performance device evaluation coefficient is less than the set performance threshold, determine that the current key aquaculture equipment is operating abnormally and mark it as an abnormal device; Use the comprehensive performance device evaluation coefficient and the abnormal device as screening conditions to screen out the corresponding device optimization strategy from the preset device adjustment database; Use the device optimization strategy to adjust and optimize the current abnormal device.

Images