Algae counting system and method

Abstract

The present invention relates to the technical field of water quality detection, and in particular to an algae counting system and method. The method comprises the following steps: obtaining a water sample to be tested and water sample metadata; transferring the water sample to be tested to an intelligent dyeing container with an integrated fully enclosed shell, performing sample injection volume control processing through a precision metering pump, and obtaining the original volume data of the sample; performing dyeing kinetic stability analysis through a dye configuration module according to the water sample metadata and the original volume data of the sample, and obtaining the optimal dyeing stabilization time parameter. The present invention greatly reduces the errors introduced by human operation and improves the accuracy and efficiency of counting through a fully automated and intelligent algae counting process; at the same time, through technologies such as high-resolution image acquisition, algae cell image classification, and intelligent recognition model training, the counting sample volume is expanded, and a more comprehensive and accurate algae counting result is obtained, thereby improving the accuracy, efficiency, and intelligence of algae counting.

Description

Technical Field

[0001] The present invention relates to the technical field of water quality detection, and in particular to an algae counting system and method. Background Art

[0002] The presence of a large amount of algae causes damage to the water environment and directly affects the production and supply of tap water based on surface water. In order to evaluate the water environment and understand the impact of algae on various process links of water plants, the environmental protection and water supply industries need to frequently carry out algae counting and testing projects.

[0003] The existing mainstream algae counting methods mainly refer to the 20th edition of the "Standard Test Methods for Water and Wastewater" (USA), which is suitable for counting planktonic algae in water bodies. The main operating steps are: collect 1 liter of water sample, add 10mL of Lugol's solution, and let it settle in a glass measuring cylinder in the dark for 48 hours. After 48 hours, use the siphon principle to absorb the supernatant, transfer the sedimentation concentrate to a 50mL brown volumetric flask, and quantify it with pure water. If the count is not performed in time, the concentrate can be stored in the dark. Before counting, turn the volumetric flask upside down 50 times to mix the concentrate evenly. When counting, use a micropipette to draw 0.1mL of concentrate into the counting frame, and use an optical microscope to count at a magnification of 10×40.

[0004] The traditional algae counting method has the problems of large human influence factors and small counting sample size. The settled algae are easily stirred up during siphoning, and the concentrate is easily left on the wall of the measuring cylinder during transfer. The whole operation process has large errors and too many human factors. The experimenter usually counts algae in 49 fields of view, and the counting number is small, which will also have large errors. Summary of the invention

[0005] Based on this, it is necessary to provide an algae counting system and method to solve at least one of the above technical problems.

[0006] To achieve the above-mentioned purpose, an algae counting method is applied to a fully automatic instant algae counter, which includes an intelligent dyeing container with an integrated fully enclosed shell, an intelligent pipeline module, a reverse osmosis concentration device, a weighing sensor, a reverse osmosis membrane, a concentrate tank and a sample pool, wherein the intelligent dyeing container with an integrated fully enclosed shell includes a precision metering pump, a dye configuration module and a multi-channel micro pump connected in sequence, the reverse osmosis concentration device and the weighing sensor are connected to each other, and the multi-channel micro pump, the reverse osmosis concentration device, the reverse osmosis membrane, the concentrate tank and the sample pool are connected in sequence through the intelligent pipeline module, including the following steps:

[0007] Step S1: obtaining a water sample to be tested and water sample metadata; transferring the water sample to be tested to an intelligent dyeing container with an integrated fully enclosed shell, performing sample injection volume control processing through a precision metering pump, and obtaining the original volume data of the sample; performing dyeing kinetic stability analysis through a dye configuration module according to the water sample metadata and the original volume data of the sample, and obtaining the optimal dyeing stabilization time parameter;

[0008] Step S2: Transfer the dye solution through the intelligent pipeline module and the reverse osmosis concentration device to obtain transfer volume data; perform reverse osmosis concentration of the water sample according to the water sample metadata, the transfer volume data and the optimal dye stabilization time parameter to obtain a concentration multiple curve; monitor the permeate recovery through the weighing sensor to obtain the permeate recovery efficiency data; extract the volume of the algae concentrate according to the permeate recovery efficiency data to obtain the volume of the algae concentrate; determine the concentration endpoint according to the algae concentrate volume and the concentration multiple curve to obtain the concentration endpoint state parameter;

[0009] Step S3: performing multi-stage cleaning pressure control processing on the inner wall of the reverse osmosis membrane according to the concentration endpoint state parameter, the volume of the algae concentrate and the reverse osmosis membrane to obtain multi-stage cleaning process data; performing cleaning liquid recycling on the multi-stage cleaning process data to obtain cleaning liquid recycling process data; performing cleaning recovery efficiency analysis on the cleaning liquid recycling process data to obtain cleaning recovery efficiency parameters;

[0010] Step S4: The concentrated liquid sample flows into the concentrated liquid tank for processing and the volume is measured according to the cleaning recovery efficiency parameter to obtain the effective volume data of the concentrated liquid; the homogenization process is evaluated according to the effective volume data of the concentrated liquid to obtain the homogeneity evaluation parameter; the homogenization condition multi-objective analysis is performed according to the homogeneity evaluation parameter to obtain the optimal homogenization condition data;

[0011] Step S5: extracting a homogenized water sample to a sample pool for processing according to the optimal homogenization condition data and preparing a sample slide to obtain sample slide preparation parameters; classifying algae cell images using the sample slide preparation parameters to obtain algae cell image classification mask data; performing three-dimensional analysis of algae cell morphology and single cell tracking and identification according to the algae cell image classification mask data to obtain single-cell algae morphological characteristic parameters;

[0012] Step S6: construct an algae feature library according to the morphological characteristic parameters of single-cell algae to obtain algae feature library data; perform automatic classification and statistics of algae cells according to the algae feature library data to obtain algae cell quantity distribution data of different genera and species; perform algae biomass conversion calculation according to the morphological characteristic parameters of single-cell algae and the algae cell quantity distribution data of different genera and species to obtain algae biomass composition data; perform algae cell density and biomass calculation and analysis according to the algae cell quantity distribution data of different genera and species and the algae biomass composition data to obtain a comprehensive analysis report of algae cell density and biomass.

[0013] The present invention collects water samples by using a special water sampler and a standardized process, and records detailed metadata to ensure the representativeness and traceability of the samples. At the same time, the use of fully enclosed intelligent dyeing containers, precision metering pumps, intelligent pipeline modules and other automated equipment realizes the automated operation of dyeing, concentration, cleaning and other steps, minimizes human intervention, avoids human errors, and greatly improves the experimental efficiency. According to information such as the type and concentration of the water sample, the type and concentration of the dye are intelligently selected, and the dyeing time is accurately controlled by real-time monitoring of the dyeing kinetics to ensure the best dyeing effect. During the concentration process, the appropriate membrane component is selected according to the water sample situation, and the concentration process is monitored in real time to ensure efficient and gentle concentration effects and minimize damage to algae cells. The multi-stage cleaning strategy and intelligent cleaning process can be used to efficiently and thoroughly remove membrane pollutants, extend the service life of the reverse osmosis membrane, and reduce the use of cleaning agents, which is more environmentally friendly. At the same time, by real-time monitoring of the turbidity of the cleaning solution and the membrane flux recovery data, the cleaning effect can be intuitively evaluated, and the refined control of the cleaning process can be achieved, further improving the cleaning efficiency and reducing the experimental cost. According to the type of algae cells and the volume of concentrated liquid, appropriate homogenization equipment and parameters are selected, and by optimizing and combining the parameters of various homogenization methods, efficient and gentle homogenization effects are achieved, the integrity of algae cells is maintained to the greatest extent, and the uniform distribution of samples on the slide is ensured, providing high-quality samples for subsequent image analysis. Multispectral imaging technology and high-resolution image acquisition are used to obtain rich morphological information of algae cells, providing richer and more reliable data for subsequent analysis. The algae feature library and intelligent recognition model are constructed using artificial intelligence technologies such as deep learning, which realizes the automatic classification, counting and biomass calculation of algae, greatly improving the analysis efficiency and accuracy of the results. Through the fully automated and intelligent algae counting process, the errors introduced by human operation are greatly reduced, and the accuracy and efficiency of counting are improved. At the same time, through technologies such as high-resolution image acquisition, algae cell image classification and intelligent recognition model training, the counting sample size is expanded, and more comprehensive and accurate algae counting results are obtained. The accuracy, efficiency and intelligence of algae counting are improved.

[0014] Therefore, the present invention provides an algae counting method, which is an optimization process of a traditional algae counting method. It solves the problems of large human influence factors and small counting sample size in algae counting in the traditional algae counting method, reduces the influence of human factors and increases the counting sample size, thereby improving the accuracy, efficiency and intelligence of algae counting.

[0015] Preferably, step S1 comprises the following steps:

[0016] Step S11: Collect water samples from the water body through a special water sampler and record the data to obtain the water sample to be tested and the water sample metadata;

[0017] Step S12: transferring the water sample to be tested into an intelligent dyeing container with an integrated fully enclosed shell, and performing sample injection volume control processing through a precision metering pump to obtain the original volume data of the sample;

[0018] Step S13: Automatically configure the dye through the dye configuration module according to the water sample metadata and the original volume data of the sample to obtain dye dosage data; intelligently add the dye through the multi-channel micro pump according to the dye dosage data to obtain dyeing start time data;

[0019] Step S14: acquiring dyeing process data; performing dyeing liquid optical analysis on the dyeing process data and performing dyeing kinetic modeling to obtain a dyeing kinetic model; performing dyeing rate and equilibrium analysis according to the dyeing kinetic model to obtain a dyeing rate constant and a dyeing equilibrium constant;

[0020] Step S15: Perform dyeing endpoint judgment according to the dyeing kinetics model. If the dyeing progress value is less than the preset dyeing endpoint threshold, return to step S13; if the dyeing progress value is greater than or equal to the preset dyeing endpoint threshold, generate a dyeing stable state flag and execute step S16;

[0021] Step S16: Optimize the stabilization time parameters based on the dyeing start time data, the dyeing rate constant and the dyeing equilibrium constant to obtain the optimal dyeing stabilization time parameters.

[0022] The present invention collects water samples and records water sample metadata using a special water sampler, thereby ensuring the representativeness and traceability of water samples, and providing an accurate and reliable data basis for subsequent analysis. The water sample to be tested is transferred to a fully enclosed intelligent dyeing container and the injection volume is accurately controlled, thereby avoiding external environmental pollution and human operation errors, and improving the accuracy and reliability of the experimental results. The dye is automatically configured and intelligently added according to the water sample metadata and sample volume, thereby realizing the standardization and automation of dyeing, improving experimental efficiency, and reducing the errors caused by human operation. The dyeing process data is monitored in real time and a dyeing kinetic model is established, which can accurately describe the dyeing process, and provides a scientific basis for dyeing endpoint judgment and stabilization time optimization. The dyeing endpoint judgment is performed according to the dyeing kinetic model, thereby avoiding the subjective errors caused by the traditional method relying on empirical judgment, and improving the accuracy and repeatability of the dyeing results. The stabilization time is optimized based on the dyeing kinetic parameters, thereby shortening the dyeing time, improving the experimental efficiency, and ensuring the stability of the dyeing effect, providing high-quality samples for subsequent analysis and testing.

[0023] Preferably, step S3 comprises the following steps:

[0024] Step S31: configuring the cleaning liquid according to the concentration end state parameter and the volume of the algae concentrate to obtain cleaning liquid formula data; setting the cleaning pressure according to the cleaning liquid formula data to obtain the cleaning pressure parameter;

[0025] Step S32: performing multi-stage cleaning control processing on the inner wall of the reverse osmosis membrane through the reverse osmosis membrane according to the cleaning pressure parameter to obtain multi-stage cleaning process data; performing cleaning liquid circulation processing on the multi-stage cleaning process data to obtain cleaning liquid circulation dynamic parameters;

[0026] Step S33: recovering the cleaning liquid according to the multi-stage cleaning process data and the dynamic parameters of the cleaning liquid circulation to obtain a cleaning liquid recovery turbidity curve; obtaining cleaning liquid recovery process data; monitoring the membrane flux of the cleaning liquid recovery process data to obtain membrane flux recovery data;

[0027] Step S34: determining the cleaning endpoint according to the cleaning liquid recovery turbidity curve and the membrane flux recovery data, and obtaining the cleaning endpoint state parameters;

[0028] Step S35: Calculate the efficiency parameters based on the multi-stage cleaning process data, the cleaning liquid circulation dynamic parameters, the cleaning liquid recovery turbidity curve and the cleaning endpoint state parameters to obtain the cleaning recovery efficiency parameters.

[0029] The present invention can remove membrane pollutants in a targeted manner, improve cleaning efficiency, and extend the service life of the reverse osmosis membrane by intelligently configuring the cleaning liquid according to the concentration endpoint state and the volume of the algae concentrate, and setting a suitable cleaning pressure according to the cleaning liquid formula. The multi-stage cleaning control process can gradually remove membrane pollutants, avoid the problem of low efficiency of a single cleaning method, and improve the cleaning effect. At the same time, the cleaning liquid circulation process can reduce the consumption of the cleaning liquid, reduce the experimental cost, and is more environmentally friendly. Real-time monitoring of the cleaning liquid recovery turbidity and membrane flux recovery data can intuitively reflect the cleaning effect and provide a basis for the cleaning endpoint determination. The cleaning endpoint determination based on the cleaning liquid recovery turbidity curve and membrane flux recovery data can avoid damage to the reverse osmosis membrane caused by excessive cleaning and extend the service life of the membrane. Based on the calculation of the cleaning recovery efficiency parameters based on multiple indicators, the cleaning effect can be comprehensively evaluated, data support can be provided for optimizing the cleaning strategy, the cleaning efficiency can be further improved, and the experimental cost can be reduced.

[0030] Preferably, step S4 comprises the following steps:

[0031] Step S41: The concentrated liquid sample flows into the concentrated liquid tank for processing and the volume is measured according to the cleaning recovery efficiency parameter to obtain the effective volume data of the concentrated liquid;

[0032] Step S42: acquiring algae cell type information data; selecting a homogenizing device according to the effective volume data of the concentrate and the algae cell type information data to obtain configuration parameters of the homogenizing device; optimizing stirring parameters using the configuration parameters of the homogenizing device to obtain optimal stirring process parameters;

[0033] Step S43: performing a shake-even mixing process using the configuration parameters of the homogenizing equipment according to the optimal stirring process parameters to obtain the optimal shake-even mixing parameters; performing high-pressure homogenization optimization using the configuration parameters of the homogenizing equipment according to the optimal stirring process parameters and the optimal shake-even mixing parameters to obtain the optimal high-pressure homogenization parameters;

[0034] Step S44: acquiring homogenization process data; performing dynamic particle size monitoring on the homogenization process data to obtain dynamic particle size distribution data; performing homogeneity evaluation according to the dynamic particle size distribution data to obtain homogeneity evaluation parameters;

[0035] Step S45: performing energy consumption optimization analysis according to the optimal stirring process parameters, the optimal shaking mixing parameters and the optimal high-pressure homogenization parameters to obtain energy consumption optimization data; performing homogenization endpoint determination according to the homogeneity evaluation parameters and the energy consumption optimization data to obtain homogenization endpoint state parameters;

[0036] Step S46: Determine the optimal homogenization conditions through a multi-objective optimization algorithm based on the optimal stirring process parameters, the optimal shaking mixing parameters, the optimal high-pressure homogenization parameters, the homogeneity evaluation parameters, the energy consumption optimization data and the homogenization endpoint state parameters to obtain the optimal homogenization condition data.

[0037] The present invention evaluates the cleaning effect through the cleaning recovery efficiency parameter. After confirming that the cleaning is sufficient, the concentrated liquid water sample flows into the concentrated liquid tank and performs volume measurement, that is, the volume is directly measured by the sensor to obtain the effective volume data of the concentrated liquid. By analyzing the turbidity curve of the cleaning liquid recovery and the membrane flux recovery rate data, it can be judged whether the cleaning is thorough. Only when the cleaning efficiency reaches the preset standard can the concentrated liquid volume measurement result be considered to be accurate and reliable, and the stability of the homogenization effect is guaranteed. According to the algae cell type information and the concentrated liquid volume, the appropriate homogenization equipment and configuration parameters are selected, and personalized homogenization treatment can be performed for different types of algae samples, the homogenization efficiency is improved, and the damage to the cell structure caused by excessive homogenization is avoided. By optimizing the parameters of different homogenization methods such as stirring, shaking and mixing, and high-pressure homogenization, the best combination can be found to achieve efficient and gentle homogenization effects, and the integrity of algae cells is maintained to the greatest extent. Real-time monitoring of homogenization process data and dynamic particle size distribution can intuitively reflect the homogenization effect, provide a basis for the determination of the homogenization endpoint, and provide data support for optimizing the homogenization parameters. By comprehensively considering the homogenization effect and energy consumption, we can find the best balance point that can achieve the ideal homogenization effect and reduce energy consumption, improve the experimental efficiency, and reduce the experimental cost. Through the multi-objective optimization algorithm, we can comprehensively consider multiple factors to determine the best homogenization conditions, such as stirring speed, time, shaking frequency, homogenization pressure and number of cycles, to achieve efficient, low-cost and stable homogenization effects, and provide high-quality samples for subsequent image analysis.

[0038] Preferably, step S5 comprises the following steps:

[0039] Step S51: extracting a homogenized water sample into a sample pool for processing according to the optimal homogenization condition data and preparing a sample slide to obtain sample slide preparation parameters;

[0040] Step S52: performing intelligent focusing optimization of the microscope using the sample slide preparation parameters to obtain intelligent focusing optimization data; performing multispectral imaging according to the intelligent focusing optimization data to obtain a multispectral image data set;

[0041] Step S53: performing high-resolution image acquisition according to the intelligent focusing optimization data and the multispectral image data set to obtain a high-resolution algae cell image library;

[0042] Step S54: performing image preprocessing optimization on the high-resolution algae cell image library to obtain an optimized preprocessed image set; performing algae cell image classification according to the optimized preprocessed image set to obtain algae cell image classification mask data;

[0043] Step S55: extracting morphological features according to the algae cell image classification mask data to obtain an algae cell morphological feature vector; performing three-dimensional reconstruction of the algae cell according to the algae cell image classification mask data to obtain three-dimensional morphological parameters of the algae cell;

[0044] Step S56: performing single cell trajectory tracking and identification according to the algae cell morphological feature vector and the algae cell three-dimensional morphological parameters to obtain single cell trajectory data;

[0045] Step S57: extracting morphological characteristic parameters according to the algae cell morphological characteristic vector, the algae cell three-dimensional morphological parameters and the single cell trajectory data to obtain the single cell algae morphological characteristic parameters.

[0046] The present invention can ensure the uniform distribution of samples on the slides by extracting homogenized water samples according to the optimal homogenization conditions and preparing sample slides, reduce the counting errors caused by uneven sample distribution, and provide high-quality samples for subsequent microscopic observation and image analysis. By optimizing the intelligent focusing of the microscope using the sample slide preparation parameters, the optimal imaging focal plane can be found quickly and accurately, the imaging quality can be improved, and a clear image basis can be provided for multispectral imaging. Multispectral imaging is performed under the optimal focal plane, and high-resolution image acquisition is performed to obtain multidimensional information of algae cells, including morphology, structure, pigment, etc., providing richer and more reliable data for subsequent image analysis and algae identification. Preprocessing and optimizing the high-resolution algae cell image library can remove image noise, enhance image contrast, improve image quality, and provide clearer and more accurate image data for subsequent image classification and feature extraction. Morphological feature extraction and three-dimensional reconstruction are performed according to the algae cell image classification mask data, and the morphological feature vector and three-dimensional morphological parameters of the algae cells can be obtained, providing more comprehensive feature information for algae identification and classification. Through single-cell trajectory tracking and identification, the same algae cell in images at different time points or different focal planes can be associated, providing data support for analyzing the movement trajectory and behavioral characteristics of algae cells. By comprehensively utilizing algae cell morphological feature vectors, three-dimensional morphological parameters, and single-cell trajectory data, more comprehensive and detailed single-cell algae morphological feature parameters can be extracted, providing a richer and more reliable basis for subsequent algae identification, classification, and ecological analysis.

[0047] Preferably, step S6 comprises the following steps:

[0048] Step S61: constructing an algae feature library according to the morphological characteristic parameters of the single-cell algae to obtain algae feature library data;

[0049] Step S62: Perform intelligent recognition model training according to the algae feature library data to obtain algae recognition model parameters; perform multi-classifier integration optimization using the algae recognition model parameters to obtain an optimized multi-classifier integration model;

[0050] Step S63: inputting the morphological characteristic parameters of the single-cell algae into the optimized multi-classifier integrated model to automatically identify and classify the algae, and obtaining the genus and species classification data of the algae cells;

[0051] Step S64: performing algae cell counting statistics according to the algae cell genus and species classification data to obtain algae cell quantity distribution data of different genera and species; performing algae cell size estimation according to the morphological characteristic parameters of single-cell algae to obtain algae cell size estimation data;

[0052] Step S65: performing algae biomass conversion modeling according to the algae cell size estimation data and the algae cell quantity distribution data of different genera and species to obtain an algae biomass conversion model; performing biomass conversion according to the algae biomass conversion model to obtain an algae biomass conversion factor;

[0053] Step S66: Calculate the algae biomass using the algae cell number distribution data of different genera and species, the algae cell size estimation data, and the algae biomass conversion factor to obtain the algae biomass composition data;

[0054] Step S67: Calculate the algae cell density according to the algae cell quantity distribution data of different genera and species and the original volume data of the sample to obtain the algae cell density data;

[0055] Step S68: Perform comprehensive data analysis based on the algae cell genus and species classification data, the algae cell quantity distribution data of different genera and species, the algae biomass composition data and the algae cell density data to obtain a comprehensive analysis report on the algae cell density and biomass.

[0056] The present invention provides sufficient data basis for the training of subsequent algae intelligent recognition model by constructing a feature library containing rich algae morphological feature information, thereby improving the accuracy and generalization ability of the model. By using the algae feature library data to train the intelligent recognition model, and by optimizing the integration of multiple classifiers, the recognition accuracy and robustness of the model for different types of algae can be improved, and automatic and efficient algae classification can be achieved. The extracted unicellular algae morphological feature parameters are input into the optimized intelligent recognition model, and the algae can be quickly and accurately classified into genus and species, providing a reliable data basis for subsequent algae counting, biomass calculation, etc. By counting the number distribution of algae cells of different genera and species, the algae community structure in the sample can be understood, and by estimating the size of algae cells, data support can be provided for subsequent biomass calculation. By establishing an algae biomass conversion model, the number of algae cells can be converted into biomass, which more accurately reflects the biomass level of algae in water bodies and provides a more reliable indicator for water environment evaluation. By calculating the algae biomass composition data, the contribution of different types of algae to the total biomass can be understood, providing data support for analyzing the succession of algae communities and changes in water environment. Calculating algae cell density can help us understand the number of algae per unit volume of water sample, providing an important basis for assessing the degree of eutrophication of water bodies. Integrating data such as algae genus and species classification, quantity distribution, biomass composition and cell density to generate a comprehensive analysis report can comprehensively and intuitively display the algae analysis results, providing a scientific basis for water environment monitoring, evaluation and management.

[0057] Preferably, the present invention also provides an algae counting system for executing the algae counting method as described above, the algae counting system comprising:

[0058] The dyeing stabilization module is used to obtain the water sample to be tested and the water sample metadata; transfer the water sample to be tested to an intelligent dyeing container with an integrated fully enclosed shell, and perform sample injection volume control processing through a precision metering pump to obtain the sample original volume data; perform dyeing kinetic stability analysis through the dye configuration module based on the water sample metadata and the sample original volume data to obtain the optimal dyeing stabilization time parameter;

[0059] The reverse osmosis concentration module is used to transfer the dye solution through the intelligent pipeline module and the reverse osmosis concentration device to obtain the transfer volume data; to perform reverse osmosis concentration of the water sample according to the water sample metadata, the transfer volume data and the optimal dye stabilization time parameters to obtain the concentration multiple curve; to monitor the permeate recovery through the weighing sensor to obtain the permeate recovery efficiency data; to extract the volume of the algae concentrate according to the permeate recovery efficiency data to obtain the volume of the algae concentrate; to judge the concentration end point according to the algae concentrate volume and the concentration multiple curve to obtain the concentration end point state parameters;

[0060] The cleaning and recovery module is used to perform multi-stage cleaning pressure control processing on the inner wall of the reverse osmosis membrane according to the concentration end state parameters, the volume of the algae concentrate and the reverse osmosis membrane to obtain multi-stage cleaning process data; perform cleaning liquid circulation recovery on the multi-stage cleaning process data to obtain cleaning liquid recovery process data; perform cleaning recovery efficiency analysis based on the cleaning liquid recovery process data to obtain cleaning recovery efficiency parameters;

[0061] The homogenization sampling module is used to process the concentrated liquid sample into the concentrated liquid tank and measure the volume according to the cleaning recovery efficiency parameters to obtain the effective volume data of the concentrated liquid; to evaluate the homogenization process according to the effective volume data of the concentrated liquid to obtain the homogeneity evaluation parameters; to perform multi-objective analysis of the homogenization conditions according to the homogeneity evaluation parameters to obtain the optimal homogenization condition data;

[0062] The intelligent imaging module is used to extract homogenized water samples into a sample pool according to the optimal homogenization condition data and prepare sample slides to obtain sample slide preparation parameters; classify algae cell images using the sample slide preparation parameters to obtain algae cell image classification mask data; perform three-dimensional analysis of algae cell morphology and perform single-cell tracking and identification according to the algae cell image classification mask data to obtain single-cell algae morphological characteristic parameters;

[0063] The precise counting module is used to construct an algae feature library based on the morphological characteristic parameters of single-cell algae to obtain the algae feature library data; to automatically classify and count algae cells based on the algae feature library data to obtain the number distribution data of algae cells of different genera and species; to perform algae biomass conversion calculations based on the morphological characteristic parameters of single-cell algae and the number distribution data of algae cells of different genera and species to obtain the algae biomass composition data; to calculate and analyze the algae cell density and biomass based on the number distribution data of algae cells of different genera and species and the algae biomass composition data to obtain a comprehensive analysis report on algae cell density and biomass. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A schematic diagram of the steps of the algae counting method;

[0065] Figure 2 for Figure 1 Detailed implementation steps of step S1 in FIG.

[0066] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0067] Figure 4 This is a connection diagram of the various components of the fully automatic instant algae counter.

[0068] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0069] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0070] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0071] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0072] To achieve this, please refer to Figures 1 to 4 , an algae counting method is applied to a fully automatic instant algae counter, the fully automatic instant algae counter comprises an intelligent dyeing container with an integrated fully enclosed shell, an intelligent pipeline module, a reverse osmosis concentration device, a weighing sensor, a reverse osmosis membrane, a concentrate tank and a sample pool, wherein the intelligent dyeing container with an integrated fully enclosed shell comprises a precision metering pump, a dye configuration module and a multi-channel micro pump connected in sequence, the reverse osmosis concentration device and the weighing sensor are connected to each other, and the multi-channel micro pump, the reverse osmosis concentration device, the reverse osmosis membrane, the concentrate tank and the sample pool are connected in sequence through the intelligent pipeline module, comprising the following steps:

[0073] Step S1: obtaining a water sample to be tested and water sample metadata; transferring the water sample to be tested to an intelligent dyeing container with an integrated fully enclosed shell, performing sample injection volume control processing through a precision metering pump, and obtaining the original volume data of the sample; performing dyeing kinetic stability analysis through a dye configuration module according to the water sample metadata and the original volume data of the sample, and obtaining the optimal dyeing stabilization time parameter;

[0074] Step S2: Transfer the dye solution through the intelligent pipeline module and the reverse osmosis concentration device to obtain transfer volume data; perform reverse osmosis concentration of the water sample according to the water sample metadata, the transfer volume data and the optimal dye stabilization time parameter to obtain a concentration multiple curve; monitor the permeate recovery through the weighing sensor to obtain the permeate recovery efficiency data; extract the volume of the algae concentrate according to the permeate recovery efficiency data to obtain the volume of the algae concentrate; determine the concentration endpoint according to the algae concentrate volume and the concentration multiple curve to obtain the concentration endpoint state parameter;

[0075] Step S3: performing multi-stage cleaning pressure control processing on the inner wall of the reverse osmosis membrane according to the concentration endpoint state parameter, the volume of the algae concentrate and the reverse osmosis membrane to obtain multi-stage cleaning process data; performing cleaning liquid recycling on the multi-stage cleaning process data to obtain cleaning liquid recycling process data; performing cleaning recovery efficiency analysis on the cleaning liquid recycling process data to obtain cleaning recovery efficiency parameters;

[0076] Step S4: The concentrated liquid sample flows into the concentrated liquid tank for processing and the volume is measured according to the cleaning recovery efficiency parameter to obtain the effective volume data of the concentrated liquid; the homogenization process is evaluated according to the effective volume data of the concentrated liquid to obtain the homogeneity evaluation parameter; the homogenization condition multi-objective analysis is performed according to the homogeneity evaluation parameter to obtain the optimal homogenization condition data;

[0077] Step S5: extracting a homogenized water sample to a sample pool for processing according to the optimal homogenization condition data and preparing a sample slide to obtain sample slide preparation parameters; classifying algae cell images using the sample slide preparation parameters to obtain algae cell image classification mask data; performing three-dimensional analysis of algae cell morphology and single cell tracking and identification according to the algae cell image classification mask data to obtain single-cell algae morphological characteristic parameters;

[0078] Step S6: construct an algae feature library according to the morphological characteristic parameters of single-cell algae to obtain algae feature library data; perform automatic classification and statistics of algae cells according to the algae feature library data to obtain algae cell quantity distribution data of different genera and species; perform algae biomass conversion calculation according to the morphological characteristic parameters of single-cell algae and the algae cell quantity distribution data of different genera and species to obtain algae biomass composition data; perform algae cell density and biomass calculation and analysis according to the algae cell quantity distribution data of different genera and species and the algae biomass composition data to obtain a comprehensive analysis report of algae cell density and biomass.

[0079] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of the algae counting method of the present invention. In this example, the algae counting method includes the following steps:

[0080] Step S1: obtaining a water sample to be tested and water sample metadata; transferring the water sample to be tested to an intelligent dyeing container with an integrated fully enclosed shell, performing sample injection volume control processing through a precision metering pump, and obtaining the original volume data of the sample; performing dyeing kinetic stability analysis through a dye configuration module according to the water sample metadata and the original volume data of the sample, and obtaining the optimal dyeing stabilization time parameter;

[0081] In an embodiment of the present invention, a special water sampler is used to collect 1 liter of water sample in the target water body, and the water sample collection time, location, water temperature, pH value and other information are recorded as water sample metadata. The collected water sample is transferred to an intelligent dyeing container, and the injection volume is accurately controlled to be 500 ml by a precision metering pump, which is recorded as the original volume data of the sample. According to the water sample metadata and the original volume data of the sample, the dye configuration module automatically calculates the required dye dosage and automatically adds it to the intelligent dyeing container through a multi-channel micro pump. The system monitors the optical properties of the dyeing solution in real time, establishes a dyeing kinetic model, and calculates the dyeing rate constant and the dyeing equilibrium constant according to the model, and finally determines the optimal dyeing stabilization time parameter.

[0082] Step S2: Transfer the dye solution through the intelligent pipeline module and the reverse osmosis concentration device to obtain transfer volume data; perform reverse osmosis concentration of the water sample according to the water sample metadata, the transfer volume data and the optimal dye stabilization time parameter to obtain a concentration multiple curve; monitor the permeate recovery through the weighing sensor to obtain the permeate recovery efficiency data; extract the volume of the algae concentrate according to the permeate recovery efficiency data to obtain the volume of the algae concentrate; determine the concentration endpoint according to the algae concentrate volume and the concentration multiple curve to obtain the concentration endpoint state parameter;

[0083] In an embodiment of the present invention, the intelligent pipeline module transfers the dyed water sample to the reverse osmosis concentration device and records the volume of the transferred dye solution. The system selects a suitable reverse osmosis membrane assembly based on the water sample metadata and the optimal dyeing stabilization time parameters, and determines the configuration parameters of the membrane assembly. The system performs pressure initialization on the reverse osmosis concentration device, and estimates the amount of water filtered out during the concentration process based on the initial pressure data, the transfer volume data, and the membrane assembly configuration parameters. During the concentration process, the system monitors the operating status of the concentration device in real time, calculates the algae cell concentration multiple, and draws a concentration multiple curve. The weight of the permeate is monitored in real time by a weighing sensor, and the volume of the permeate is calculated, thereby obtaining the permeate recovery efficiency data. Finally, the system calculates the volume of the algae concentrate based on the filtered water volume parameters and the permeate recovery efficiency data, and determines whether the preset concentration target is reached based on the concentrate volume and the concentration multiple curve, and finally records the concentration endpoint state parameters.

[0084] Step S3: performing multi-stage cleaning pressure control processing on the inner wall of the reverse osmosis membrane according to the concentration endpoint state parameter, the volume of the algae concentrate and the reverse osmosis membrane to obtain multi-stage cleaning process data; performing cleaning liquid recycling on the multi-stage cleaning process data to obtain cleaning liquid recycling process data; performing cleaning recovery efficiency analysis on the cleaning liquid recycling process data to obtain cleaning recovery efficiency parameters;

[0085] In an embodiment of the present invention, the system automatically selects a suitable cleaning solution formula and sets the cleaning pressure according to the concentration endpoint state parameters and the volume of the algae concentrate. The system controls the reverse osmosis membrane to perform multi-stage cleaning and records the cleaning process data and the dynamic parameters of the cleaning solution circulation. During the cleaning solution recovery process, the system monitors the turbidity of the cleaning solution in real time, draws a cleaning solution recovery turbidity curve, and records the cleaning solution recovery process data. The system also monitors the membrane flux of the reverse osmosis membrane and records the membrane flux recovery data. Finally, the system determines whether the cleaning reaches the preset endpoint conditions based on the cleaning solution recovery turbidity curve and the membrane flux recovery data, and records the cleaning endpoint state parameters. The cleaning efficiency parameters are calculated based on the multi-stage cleaning process data, the cleaning solution circulation dynamic parameters, the cleaning solution recovery turbidity curve, and the cleaning endpoint state parameters, and are used to evaluate the cleaning effect.

[0086] Step S4: The concentrated liquid sample flows into the concentrated liquid tank for processing and the volume is measured according to the cleaning recovery efficiency parameter to obtain the effective volume data of the concentrated liquid; the homogenization process is evaluated according to the effective volume data of the concentrated liquid to obtain the homogeneity evaluation parameter; the homogenization condition multi-objective analysis is performed according to the homogeneity evaluation parameter to obtain the optimal homogenization condition data;

[0087] In the embodiment of the present invention, after the cleaning is qualified, the system controls the concentrated water sample to flow into the concentrate tank, and measures the volume of the concentrate, which is recorded as the effective volume data of the concentrate. The system selects a suitable homogenizing device according to the effective volume data of the concentrate and the pre-acquired algae cell species information data, and determines the configuration parameters of the homogenizing device. The system optimizes the stirring parameters, the shaking mixing parameters and the high-pressure homogenization parameters, and obtains the optimal stirring process parameters, the optimal shaking mixing parameters and the optimal high-pressure homogenization parameters respectively. During the homogenization process, the system collects the homogenization process data in real time, and performs dynamic particle size monitoring on the concentrate to obtain dynamic particle size distribution data. The system evaluates the degree of homogenization based on the dynamic particle size distribution data to obtain the homogenization evaluation parameters. Finally, the system determines whether the preset homogenization target is achieved based on the homogenization process parameters, the energy consumption model, the homogenization evaluation parameters and the preset homogenization target, and records the homogenization endpoint state parameters. Finally, the system uses a multi-objective optimization algorithm to determine the optimal homogenization condition data.

[0088] Step S5: extracting a homogenized water sample to a sample pool for processing according to the optimal homogenization condition data and preparing a sample slide to obtain sample slide preparation parameters; classifying algae cell images using the sample slide preparation parameters to obtain algae cell image classification mask data; performing three-dimensional analysis of algae cell morphology and single cell tracking and identification according to the algae cell image classification mask data to obtain single-cell algae morphological characteristic parameters;

[0089] In an embodiment of the present invention, the system controls the automated equipment to extract a certain volume of homogenized water sample from the concentrate tank according to the optimal homogenization conditions, injects it into the sample pool, and makes a sample slide, and records the preparation parameters of the sample slide. The system controls the microscope to perform intelligent focusing optimization according to the sample slide preparation parameters, and records relevant data. Then, the system controls the microscope to perform multispectral imaging at the optimal focal plane to obtain a multispectral image data set. The high-resolution algae cell image library is obtained by performing high-resolution image acquisition on the multispectral image data set. The system performs image preprocessing optimization on the acquired image library to obtain an optimized preprocessed image set, and classifies the image according to the image features to obtain algae cell image classification mask data. The system extracts the morphological features of the algae cells according to the algae cell image classification mask data, constructs a morphological feature vector, and uses a three-dimensional reconstruction algorithm to construct a three-dimensional model of the algae cells, and calculates the three-dimensional morphological parameters. Finally, the system uses a single cell tracking algorithm based on the algae cell morphological feature vector and three-dimensional morphological parameters to identify and associate the same algae cell in images at different time points or different focal planes.

[0090] Step S6: constructing an algae feature library according to the morphological characteristic parameters of single-cell algae to obtain algae feature library data; automatically classifying and counting algae cells according to the algae feature library data to obtain algae cell quantity distribution data of different genera and species; performing algae biomass conversion calculation according to the morphological characteristic parameters of single-cell algae and the algae cell quantity distribution data of different genera and species to obtain algae biomass composition data; performing algae cell density and biomass calculation and analysis according to the algae cell quantity distribution data of different genera and species and the algae biomass composition data to obtain an algae cell density and biomass comprehensive analysis report;

[0091] In an embodiment of the present invention, a system is used to automatically identify algae species and estimate their biomass using image recognition and machine learning technology. The system first establishes an algae morphological feature database and trains an intelligent recognition model. Then, the system analyzes the algae image, identifies the type of each algae cell, counts the number of cells, estimates the cell size, and finally calculates the biomass and cell density of each algae species, generating a comprehensive analysis report.

[0092] Preferably, step S1 comprises the following steps:

[0093] Step S11: Collect water samples from the water body through a special water sampler and record the data to obtain the water sample to be tested and the water sample metadata;

[0094] Step S12: transferring the water sample to be tested into an intelligent dyeing container with an integrated fully enclosed shell, and performing sample injection volume control processing through a precision metering pump to obtain the original volume data of the sample;

[0095] Step S13: Automatically configure the dye through the dye configuration module according to the water sample metadata and the original volume data of the sample to obtain dye dosage data; intelligently add the dye through the multi-channel micro pump according to the dye dosage data to obtain dyeing start time data;

[0096] Step S14: acquiring dyeing process data; performing dyeing liquid optical analysis on the dyeing process data and performing dyeing kinetic modeling to obtain a dyeing kinetic model; performing dyeing rate and equilibrium analysis according to the dyeing kinetic model to obtain a dyeing rate constant and a dyeing equilibrium constant;

[0097] Step S15: Perform dyeing endpoint judgment according to the dyeing kinetics model. If the dyeing progress value is less than the preset dyeing endpoint threshold, return to step S13; if the dyeing progress value is greater than or equal to the preset dyeing endpoint threshold, generate a dyeing stable state flag and execute step S16;

[0098] Step S16: Optimize the stabilization time parameters based on the dyeing start time data, the dyeing rate constant and the dyeing equilibrium constant to obtain the optimal dyeing stabilization time parameters.

[0099] As an example of the present invention, refer to Figure 2 As shown, in this example, step S1 includes:

[0100] Step S11: Collect water samples from the water body through a special water sampler and record the data to obtain the water sample to be tested and the water sample metadata;

[0101] In the embodiment of the present invention, a special water sampler is used to collect 1 liter of water sample in the target water body, and the water sample collection time, location, water temperature, pH value and other information are recorded and stored in the system as water sample metadata.

[0102] Step S12: transferring the water sample to be tested into an intelligent dyeing container with an integrated fully enclosed shell, and performing sample injection volume control processing through a precision metering pump to obtain the original volume data of the sample;

[0103] In the embodiment of the present invention, the collected 1 liter water sample is transferred to the intelligent dyeing container, the injection volume is accurately controlled to be 500 milliliters by a precision metering pump, and the volume data is recorded as the original volume data of the sample.

[0104] Step S13: Automatically configure the dye through the dye configuration module according to the water sample metadata and the original volume data of the sample to obtain dye dosage data; intelligently add the dye through the multi-channel micro pump according to the dye dosage data to obtain dyeing start time data;

[0105] In the embodiment of the present invention, based on the water sample metadata (e.g., water sample type, turbidity, etc.) and the sample original volume data (500 ml), the dye configuration module automatically calculates the required dye dosage data, for example, it is necessary to add 2 ml of dye A and 0.5 ml of dye B. Then, the multi-channel micro pump automatically adds dye A and dye B to the smart dyeing container according to the dye dosage data, and records the time when the dye addition is completed as the dyeing start time data.

[0106] Step S14: acquiring dyeing process data; performing dyeing liquid optical analysis on the dyeing process data and performing dyeing kinetic modeling to obtain a dyeing kinetic model; performing dyeing rate and equilibrium analysis according to the dyeing kinetic model to obtain a dyeing rate constant and a dyeing equilibrium constant;

[0107] In the embodiment of the present invention, during the dyeing process, the system monitors the optical properties of the dyeing solution in real time, such as absorbance and fluorescence intensity, and records these data as dyeing process data. Then, the system analyzes the dyeing process data and establishes a dyeing kinetic model, such as a curve of absorbance or fluorescence intensity over time. Based on the model, the dyeing rate constant and the dyeing equilibrium constant are calculated.

[0108] Step S15: Perform dyeing endpoint judgment according to the dyeing kinetics model. If the dyeing progress value is less than the preset dyeing endpoint threshold, return to step S13; if the dyeing progress value is greater than or equal to the preset dyeing endpoint threshold, generate a dyeing stable state flag and execute step S16;

[0109] In the embodiment of the present invention, the system calculates the dyeing progress value in real time according to the established dyeing kinetic model. If the dyeing progress value is less than the preset dyeing endpoint threshold (e.g., 95%), the system returns to step S13 to continue adding dye and monitoring the dyeing process. If the dyeing progress value is greater than or equal to the preset dyeing endpoint threshold, a dyeing stable state flag is generated, indicating that the dyeing process has reached a balanced state, and step S16 is executed.

[0110] Step S16: Optimizing the stabilization time parameters based on the dyeing start time data, the dyeing rate constant, and the dyeing equilibrium constant to obtain the optimal dyeing stabilization time parameters;

[0111] In an embodiment of the present invention, based on the recorded dyeing start time data, the dyeing rate constant calculated in step S14, and the dyeing equilibrium constant, the system optimizes the stabilization time parameters through an algorithm, for example, calculating the time required to continue waiting after the dyeing reaches an equilibrium state in order to ensure dyeing stability, and finally obtaining the optimal dyeing stabilization time parameters.

[0112] Preferably, step S14 comprises the following steps:

[0113] Step S141: using a micro-fiber spectrometer to monitor the spectrum of the dyeing liquid for the dyeing process data to obtain absorbance-time curve data;

[0114] Step S142: using a fluorescence spectrometer to analyze the fluorescence intensity change of the dyeing process data to obtain fluorescence intensity-time curve data;

[0115] Step S143: performing mathematical curve fitting on the absorbance-time curve data and the fluorescence intensity-time curve data and constructing a dyeing kinetic model to obtain a dyeing kinetic model;

[0116] Step S144: performing dyeing rate analysis according to the dyeing kinetics model to obtain a dyeing rate constant; performing dyeing equilibrium analysis according to the dyeing kinetics model to obtain a dyeing equilibrium constant.

[0117] In the embodiment of the present invention, during the dyeing process, at regular intervals (e.g., 30 seconds), a micro-fiber spectrometer is used to perform spectral scanning on the dyeing solution in the intelligent dyeing container, and the absorbance value of the dyeing solution at different wavelengths is obtained, and the change data of the absorbance value over time is recorded, and finally the absorbance-time curve data is obtained. During the dyeing process, at regular intervals (e.g., 30 seconds), a fluorescence spectrometer is used to excite the dyeing solution in the intelligent dyeing container, and the change data of the excited fluorescence intensity value over time is recorded, and finally the fluorescence intensity-time curve data is obtained. Absorbance-time curve data and fluorescence intensity-time curve data are respectively subjected to mathematical curve fitting, such as fitting using exponential function, polynomial function or other suitable curve models, and finally a function expression that can describe the law of absorbance or fluorescence intensity changing over time is obtained, i.e., dyeing kinetic model. According to the dyeing kinetic model, the rate of change of absorbance or fluorescence intensity in the initial stage of dyeing is analyzed, such as calculating the slope of the initial stage of the curve, and obtaining the dyeing rate constant. At the same time, the value that absorbance or fluorescence intensity tends to be stable in the later stage of dyeing is analyzed to obtain the dyeing equilibrium constant.

[0118] Preferably, step S2 comprises the following steps:

[0119] Step S21: transferring the dye solution through the intelligent pipeline module and the reverse osmosis concentration device to obtain transfer volume data; selecting the membrane component according to the water sample metadata and the optimal dye stabilization time parameter to obtain the membrane component configuration parameters;

[0120] Step S22: Initializing the pressure of the reverse osmosis concentration device to obtain initial pressure data; analyzing the filtered water output according to the initial pressure data, the transfer volume data and the membrane component configuration parameters to obtain filtered water output parameters;

[0121] Step S23: monitoring the concentration process according to the filtered water volume parameter to obtain dynamic data of the concentration process; calculating the algae cell concentration multiple according to the filtered water volume parameter and the dynamic data of the concentration process to obtain a concentration multiple curve;

[0122] Step S24: monitoring the recovery of the permeate through a weighing sensor to obtain the permeate recovery efficiency data; extracting the volume of the algae concentrate according to the filtered water volume parameter and the permeate recovery efficiency data to obtain the volume of the algae concentrate;

[0123] Step S25: judging the concentration end point according to the volume of the algae concentrate and the concentration multiple curve, and obtaining the concentration end point state parameter.

[0124] In an embodiment of the present invention, the intelligent pipeline module transfers the dyeing liquid in the intelligent dyeing container to the reverse osmosis concentration device, and records the transferred dyeing liquid volume as the transfer volume data. The system selects a suitable reverse osmosis membrane assembly according to the water sample metadata (such as water sample type, algae concentration, etc.) and the optimal dyeing stabilization time parameters, and determines the configuration parameters of the membrane assembly, such as membrane area, membrane pore size, etc. The system performs pressure initialization on the reverse osmosis concentration device, sets the initial working pressure and records the pressure value as the initial pressure data. Based on the initial pressure data, the transfer volume data and the membrane assembly configuration parameters, the system estimates the amount of water filtered out during the concentration process and uses it as the filtered water volume parameter. During the concentration process, the system monitors the operating status of the concentration device in real time, such as pressure changes, flow changes, turbidity of the permeate, etc., and records these data as dynamic data of the concentration process. According to the filtered water volume parameters and the dynamic data of the concentration process, for example, the concentration multiple is calculated based on the permeate volume, the system calculates the algae cell concentration multiple in real time, and draws a concentration multiple curve. During the outflow of the permeate, the weighing sensor monitors the weight of the permeate in real time, cooperates with the micro pump to recover, and calculates the volume of the permeate, thereby obtaining the permeate recovery efficiency data. Based on the recorded filtered water volume parameters and the calculated permeate recovery volume, the system calculates the permeate recovery efficiency data. Then, based on the filtered water volume parameters and the permeate recovery efficiency data, the system calculates the actual volume of liquid involved in algae concentration, that is, the volume of algae concentrate. The system determines whether the preset concentration target, such as the preset concentration multiple or algae concentration, is reached based on the calculated algae concentrate volume and the real-time updated concentration multiple curve. If the preset target is reached, the concentration process is considered to be over, and the concentration state parameters at this time, such as concentration time, final concentration multiple, etc., are recorded.

[0125] The steps for configuring the parameters of the membrane module are as follows:

[0126] 1. Preliminary selection: Based on the water sample metadata and concentration target, the type, material and pore size range of the membrane component are preliminarily selected. You can refer to relevant literature, the information of the membrane component supplier or conduct a small-scale experiment for preliminary screening.

[0127] 2. Calculate membrane area: Calculate the required membrane area based on the target concentration multiple, water sample volume, acceptable concentration time and membrane flux of the initially selected membrane assembly.

[0128] 3. Optimize parameters: Considering factors such as equipment cost, concentration efficiency, membrane pollution risk, etc., optimize parameters such as membrane area and membrane pore size, for example:

[0129] If the equipment cost is limited, the membrane area can be appropriately reduced and the concentration time can be extended.

[0130] If the concentration rate requirement is higher, a membrane module with a larger membrane area can be selected.

[0131] If the water sample has high turbidity, you can choose a membrane component with a larger pore size or add a pretreatment step.

[0132] 4. Experimental verification: Finally, experimental verification is needed to determine the final membrane component configuration parameters and fine-tune the parameters based on the experimental results to achieve the best concentration effect.

[0133] Preferably, step S3 comprises the following steps:

[0134] Step S31: configuring the cleaning liquid according to the concentration end state parameter and the volume of the algae concentrate to obtain cleaning liquid formula data; setting the cleaning pressure according to the cleaning liquid formula data to obtain the cleaning pressure parameter;

[0135] Step S32: performing multi-stage cleaning control processing on the inner wall of the reverse osmosis membrane through the reverse osmosis membrane according to the cleaning pressure parameter to obtain multi-stage cleaning process data; performing cleaning liquid circulation processing on the multi-stage cleaning process data to obtain cleaning liquid circulation dynamic parameters;

[0136] Step S33: recovering the cleaning liquid according to the multi-stage cleaning process data and the dynamic parameters of the cleaning liquid circulation to obtain a cleaning liquid recovery turbidity curve; obtaining cleaning liquid recovery process data; monitoring the membrane flux of the cleaning liquid recovery process data to obtain membrane flux recovery data;

[0137] Step S34: determining the cleaning endpoint according to the cleaning liquid recovery turbidity curve and the membrane flux recovery data, and obtaining the cleaning endpoint state parameters;

[0138] Step S35: Calculate the efficiency parameters based on the multi-stage cleaning process data, the cleaning liquid circulation dynamic parameters, the cleaning liquid recovery turbidity curve and the cleaning endpoint state parameters to obtain the cleaning recovery efficiency parameters.

[0139] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0140] Step S31: configuring the cleaning liquid according to the concentration end state parameter and the volume of the algae concentrate to obtain cleaning liquid formula data; setting the cleaning pressure according to the cleaning liquid formula data to obtain the cleaning pressure parameter;

[0141] In the embodiment of the present invention, according to the concentration end state parameters (such as the final concentration multiple) and the volume of the algae concentrate, the system automatically selects a suitable cleaning solution formula, such as the composition and concentration of the cleaning solution, and records it as cleaning solution formula data. Then, according to the cleaning solution formula data and the characteristics of the reverse osmosis membrane, the system automatically sets the cleaning pressure and records it as the cleaning pressure parameter.

[0142] Among them, the relationship between the concentration endpoint state parameters, the volume of the algae concentrate and the cleaning solution formula: the concentration endpoint state parameters (such as the final concentration multiple) reflect the concentration degree of the algae sample. The higher the concentration multiple, the greater the algae cell density and the more algae residues attached to the reverse osmosis membrane. The volume of the algae concentrate reflects the total amount of the algae sample. The larger the volume, the larger the membrane area that needs to be cleaned, and the difficulty of cleaning may also increase. Therefore, the concentration multiple and the volume of the concentrate will affect the selection of the cleaning solution. Generally speaking, when the concentration multiple is high and the volume is large, it is necessary to select a cleaning solution formula with a higher concentration and stronger cleaning ability. When the concentration multiple is low and the volume is small, select a cleaning solution formula with a lower concentration and milder cleaning ability. The system automatically matches the concentration endpoint state parameters and the volume of the algae concentrate with the optimal cleaning solution composition and concentration according to preset rules or empirical data, thereby obtaining the cleaning solution formula data.

[0143] The relationship between cleaning fluid formula data, reverse osmosis membrane characteristics and cleaning pressure: The cleaning fluid formula data includes the composition and concentration of the cleaning fluid. Cleaning fluids with different formulas have different physical and chemical properties such as viscosity and permeability, and need to match different cleaning pressures. High-concentration, high-viscosity cleaning fluids require higher cleaning pressures to overcome liquid resistance and improve cleaning efficiency. Low-concentration, low-viscosity cleaning fluids only require lower cleaning pressures to effectively penetrate and flush the reverse osmosis membrane. For reverse osmosis membranes with high density and small pore size, higher cleaning pressures are required to overcome membrane resistance and allow the cleaning fluid to penetrate effectively. For reverse osmosis membranes with high porosity and large pore size, the cleaning pressure can be relatively low.

[0144] Step S32: performing multi-stage cleaning control processing on the inner wall of the reverse osmosis membrane through the reverse osmosis membrane according to the cleaning pressure parameter to obtain multi-stage cleaning process data; performing cleaning liquid circulation processing on the multi-stage cleaning process data to obtain cleaning liquid circulation dynamic parameters;

[0145] In the embodiment of the present invention, the system controls the reverse osmosis membrane to perform multi-stage cleaning according to the set cleaning pressure parameters, for example, using a low-concentration cleaning solution for preliminary flushing and then using a high-concentration cleaning solution for deep cleaning. During the cleaning process, the system records data such as cleaning time, cleaning pressure, and cleaning solution flow rate as multi-stage cleaning process data. At the same time, the system circulates the cleaning solution and records parameters such as the number of cycles and the circulation flow rate as dynamic parameters of the cleaning solution circulation.

[0146] Step S33: recovering the cleaning liquid according to the multi-stage cleaning process data and the dynamic parameters of the cleaning liquid circulation to obtain a cleaning liquid recovery turbidity curve; obtaining cleaning liquid recovery process data; monitoring the membrane flux of the cleaning liquid recovery process data to obtain membrane flux recovery data;

[0147] In the embodiment of the present invention, during the cleaning liquid recovery process, the system monitors the turbidity of the cleaning liquid in real time and draws a cleaning liquid recovery turbidity curve. At the same time, the system records the cleaning liquid recovery time, recovery flow rate and other data as the cleaning liquid recovery process data. In addition, the system also monitors the membrane flux of the reverse osmosis membrane, for example, measuring the volume of liquid passing through the membrane per unit time, and records the monitoring results as membrane flux recovery data.

[0148] Step S34: determining the cleaning endpoint according to the cleaning liquid recovery turbidity curve and the membrane flux recovery data, and obtaining the cleaning endpoint state parameters;

[0149] In the embodiment of the present invention, the system determines whether the cleaning reaches the preset endpoint condition based on the cleaning liquid recovery turbidity curve and the membrane flux recovery data, such as the cleaning liquid turbidity drops below the preset value, or the membrane flux recovers to above the preset ratio. If the preset conditions are met, the cleaning is determined to be completed, and the cleaning time, cleaning liquid consumption and other data are recorded as cleaning endpoint state parameters.

[0150] Step S35: Calculate the efficiency parameters based on the multi-stage cleaning process data, the cleaning liquid circulation dynamic parameters, the cleaning liquid recovery turbidity curve and the cleaning endpoint state parameters to obtain the cleaning recovery efficiency parameters;

[0151] In an embodiment of the present invention, the system calculates cleaning efficiency parameters, such as cleaning liquid utilization rate, membrane flux recovery rate, etc., based on the recorded multi-stage cleaning process data, cleaning liquid circulation dynamic parameters, cleaning liquid recovery turbidity curve, and cleaning endpoint state parameters, which are used to evaluate the cleaning effect and optimize the cleaning strategy.

[0152] Among them, the cleaning efficiency parameters include cleaning fluid utilization rate, membrane flux recovery rate and cleaning time efficiency. The cleaning efficiency parameters are calculated as follows:

[0153] Calculation of cleaning liquid utilization rate: cleaning liquid utilization rate = (total cleaning liquid volume - cleaning liquid waste volume) / total cleaning liquid volume × 100%, where the total cleaning liquid volume can be obtained from the multi-stage cleaning process data, and the cleaning liquid waste volume can be estimated based on the cleaning liquid circulation dynamic parameters and the cleaning liquid recovery turbidity curve. Specifically, the cleaning liquid volume of each cycle can be calculated based on the cleaning liquid circulation dynamic parameters, and the cleaning liquid recovery turbidity curve is combined to determine the cleaning liquid turbidity of each cycle. When the turbidity exceeds the preset threshold, the cleaning liquid volume of the cycle can be recorded as the waste liquid volume.

[0154] Calculation of membrane flux recovery rate: Membrane flux recovery rate = (membrane flux after cleaning / initial membrane flux) × 100%, where the initial membrane flux can be obtained from the multi-stage cleaning process data, that is, the membrane flux measurement value before cleaning; the membrane flux after cleaning can be obtained based on the cleaning endpoint state parameters, that is, the membrane flux measurement value at the end of cleaning.

[0155] Calculation of cleaning time efficiency: Cleaning time efficiency = theoretical minimum cleaning time / actual cleaning time × 100%, where the actual cleaning time can be obtained from the cleaning endpoint state parameters; the theoretical shortest cleaning time can be estimated based on the multi-stage cleaning process data and the cleaning liquid recovery turbidity curve, that is, based on the cleaning time of each stage and the corresponding turbidity reduction rate, the shortest time required to reach the cleaning endpoint turbidity can be calculated.

[0156] Preferably, step S4 comprises the following steps:

[0157] Step S41: The concentrated liquid sample flows into the concentrated liquid tank for processing and the volume is measured according to the cleaning recovery efficiency parameter to obtain the effective volume data of the concentrated liquid;

[0158] Step S42: acquiring algae cell type information data; selecting a homogenizing device according to the effective volume data of the concentrate and the algae cell type information data to obtain configuration parameters of the homogenizing device; optimizing stirring parameters using the configuration parameters of the homogenizing device to obtain optimal stirring process parameters;

[0159] Step S43: performing a shake-even mixing process using the configuration parameters of the homogenizing equipment according to the optimal stirring process parameters to obtain the optimal shake-even mixing parameters; performing high-pressure homogenization optimization using the configuration parameters of the homogenizing equipment according to the optimal stirring process parameters and the optimal shake-even mixing parameters to obtain the optimal high-pressure homogenization parameters;

[0160] Step S44: acquiring homogenization process data; performing dynamic particle size monitoring on the homogenization process data to obtain dynamic particle size distribution data; performing homogeneity evaluation according to the dynamic particle size distribution data to obtain homogeneity evaluation parameters;

[0161] Step S45: performing energy consumption optimization analysis according to the optimal stirring process parameters, the optimal shaking mixing parameters and the optimal high-pressure homogenization parameters to obtain energy consumption optimization data; performing homogenization endpoint determination according to the homogeneity evaluation parameters and the energy consumption optimization data to obtain homogenization endpoint state parameters;

[0162] Step S46: Determine the optimal homogenization conditions through a multi-objective optimization algorithm based on the optimal stirring process parameters, the optimal shaking mixing parameters, the optimal high-pressure homogenization parameters, the homogeneity evaluation parameters, the energy consumption optimization data and the homogenization endpoint state parameters to obtain the optimal homogenization condition data.

[0163] In an embodiment of the present invention, the system evaluates the cleaning effect according to the cleaning recovery efficiency parameter, and after confirming that the cleaning is sufficient, the concentrated liquid water sample flows into the concentrated liquid tank and performs volume measurement, that is, directly measures its volume through the sensor and records it as the effective volume data of the concentrated liquid. The system obtains the algae cell type information data contained in the water sample, for example, by pre-input or other detection means. Then, the system selects a suitable homogenizing device, such as a magnetic stirrer, a shaker or a high-pressure homogenizer, according to the effective volume data of the concentrated liquid and the algae cell type information data, and determines the configuration parameters of the homogenizing device, such as the stirring speed, shaking frequency or homogenizing pressure. Finally, the system optimizes the stirring parameters according to the selected homogenizing device and configuration parameters, for example, by determining the optimal stirring speed and time through simulation or experiment, and obtaining the optimal stirring process parameters. According to the optimal stirring process parameters, the system controls the homogenizing device to shake and mix the concentrated liquid, and fine-tunes the shaking and mixing parameters according to the actual operating conditions, such as the viscosity and homogenization degree of the concentrated liquid, such as adjusting the amplitude and frequency of the shaking table, and finally obtains the optimal shaking and mixing parameters. If high-pressure homogenization is required, the system determines the optimal high-pressure homogenization parameters, such as homogenization pressure, number of cycles and time, based on the optimal stirring process parameters and the optimal shaking and mixing parameters, as well as the characteristics of the concentrate, such as cell wall thickness and toughness. During the homogenization process, the system collects homogenization process data in real time, such as stirring speed, temperature, pressure, etc. At the same time, the system performs dynamic particle size monitoring on the concentrate, such as using a laser particle size analyzer to measure the particle size distribution of algae cells to obtain dynamic particle size distribution data. Based on the dynamic particle size distribution data, the system evaluates the degree of homogenization, such as calculating the coefficient of variation or other indicators to obtain homogenization evaluation parameters. The system calculates the energy consumption of the homogenization process based on the recorded optimal stirring process parameters, optimal shaking and mixing parameters and optimal high-pressure homogenization parameters, as well as the energy consumption model of the equipment, and obtains energy consumption optimization data. Then, the system determines whether the preset homogenization target is achieved based on the homogenization evaluation parameters and energy consumption optimization data, such as whether the homogenization reaches the preset value or the energy consumption reaches the preset limit, and finally obtains the homogenization end state parameters. Based on the recorded optimal stirring process parameters, optimal shaking and mixing parameters, optimal high-pressure homogenization parameters, homogeneity evaluation parameters, energy consumption optimization data and homogenization endpoint state parameters, the system uses multi-objective optimization algorithms, such as genetic algorithms or particle swarm algorithms, to reduce energy consumption while ensuring the homogenization effect, and ultimately determines the optimal homogenization condition data, such as optimal stirring speed, time, shaking frequency, homogenization pressure and number of cycles.

[0164] Preferably, step S5 comprises the following steps:

[0165] Step S51: extracting a homogenized water sample into a sample pool for processing according to the optimal homogenization condition data and preparing a sample slide to obtain sample slide preparation parameters;

[0166] Step S52: performing intelligent focusing optimization of the microscope using the sample slide preparation parameters to obtain intelligent focusing optimization data; performing multispectral imaging according to the intelligent focusing optimization data to obtain a multispectral image data set;

[0167] Step S53: performing high-resolution image acquisition according to the intelligent focusing optimization data and the multispectral image data set to obtain a high-resolution algae cell image library;

[0168] Step S54: performing image preprocessing optimization on the high-resolution algae cell image library to obtain an optimized preprocessed image set; performing algae cell image classification according to the optimized preprocessed image set to obtain algae cell image classification mask data;

[0169] Step S55: extracting morphological features according to the algae cell image classification mask data to obtain an algae cell morphological feature vector; performing three-dimensional reconstruction of the algae cell according to the algae cell image classification mask data to obtain three-dimensional morphological parameters of the algae cell;

[0170] Step S56: performing single cell trajectory tracking and identification according to the algae cell morphological feature vector and the algae cell three-dimensional morphological parameters to obtain single cell trajectory data;

[0171] Step S57: extracting morphological characteristic parameters according to the algae cell morphological characteristic vector, the algae cell three-dimensional morphological parameters and the single cell trajectory data to obtain the single cell algae morphological characteristic parameters.

[0172] In an embodiment of the present invention, the system controls the automated equipment to extract a certain volume of homogenized water sample from the concentrate tank and inject it into the sample pool according to the optimal homogenization conditions determined in step S46. Then, the system controls the sample slide preparation device, such as an automatic dripping device and a drying device, to make the water sample in the sample pool into a sample slide, and records the preparation parameters of the sample slide, such as the water sample volume, drying time, etc. According to the sample slide preparation parameters, such as the water sample thickness, the cover glass type, etc., the system controls the microscope to perform intelligent focus optimization, such as automatically adjusting the focal plane and the objective lens magnification, finding the optimal imaging focal plane, and recording the relevant data of the intelligent focus optimization, such as the focal plane position, the objective lens magnification, etc. Then, the system controls the microscope to perform multispectral imaging at the optimal focal plane, such as using light sources of different wavelengths to illuminate the sample, and collect multi-channel image data to obtain a multispectral image data set containing rich spectral information. According to the intelligent focus optimization data, the system selects the optimal objective lens magnification and exposure time and other parameters, performs high-resolution image acquisition on each channel in the multispectral image data set, and obtains a high-resolution algae cell image library containing multiple channels. The system performs image preprocessing optimization on the collected high-resolution algae cell image library, such as image noise reduction, contrast enhancement, and correction of uneven illumination, to obtain an optimized preprocessed image set. Then, the system classifies the images based on the features in the optimized preprocessed image set, such as color, texture, shape, etc., using image classification algorithms, such as support vector machines, random forests, or deep learning algorithms, to segment the algae cells from the background and obtain algae cell image classification mask data. The system extracts the morphological features of the algae cells, such as area, perimeter, roundness, rectangularity, shape factor, etc., based on the algae cell image classification mask data, and combines these features into a feature vector as the algae cell morphological feature vector. At the same time, the system constructs a three-dimensional model of the algae cells based on the algae cell image classification mask data using a three-dimensional reconstruction algorithm, such as point cloud reconstruction or triangular mesh reconstruction, and calculates the three-dimensional morphological parameters of the algae cells, such as volume, surface area, length, width, and height. Based on the algae cell morphological feature vectors and three-dimensional morphological parameters of algae cells, the system uses single-cell tracking algorithms, such as the nearest neighbor algorithm or the Hungarian algorithm, to identify and associate the same algae cell in images at different time points or different focal planes, and obtain single-cell trajectory data, such as the position information of each algae cell at different time points or different focal planes. Based on the algae cell morphological feature vectors, three-dimensional morphological parameters of algae cells, and single-cell trajectory data, the system extracts more comprehensive single-cell algae morphological feature parameters, such as the movement speed, movement trajectory, morphological changes, etc. of algae cells, for subsequent algae identification, classification, and analysis.

[0173] Preferably, step S6 comprises the following steps:

[0174] Step S61: constructing an algae feature library according to the morphological characteristic parameters of the single-cell algae to obtain algae feature library data;

[0175] Step S62: Perform intelligent recognition model training according to the algae feature library data to obtain algae recognition model parameters; perform multi-classifier integration optimization using the algae recognition model parameters to obtain an optimized multi-classifier integration model;

[0176] Step S63: inputting the morphological characteristic parameters of the single-cell algae into the optimized multi-classifier integrated model to automatically identify and classify the algae, and obtaining the genus and species classification data of the algae cells;

[0177] Step S64: performing algae cell counting statistics according to the algae cell genus and species classification data to obtain algae cell quantity distribution data of different genera and species; performing algae cell size estimation according to the morphological characteristic parameters of single-cell algae to obtain algae cell size estimation data;

[0178] Step S65: performing algae biomass conversion modeling according to the algae cell size estimation data and the algae cell quantity distribution data of different genera and species to obtain an algae biomass conversion model; performing biomass conversion according to the algae biomass conversion model to obtain an algae biomass conversion factor;

[0179] Step S66: Calculate the algae biomass using the algae cell number distribution data of different genera and species, the algae cell size estimation data, and the algae biomass conversion factor to obtain the algae biomass composition data;

[0180] Step S67: Calculate the algae cell density according to the algae cell quantity distribution data of different genera and species and the original volume data of the sample to obtain the algae cell density data;

[0181] Step S68: Perform comprehensive data analysis based on the algae cell genus and species classification data, the algae cell quantity distribution data of different genera and species, the algae biomass composition data and the algae cell density data to obtain a comprehensive analysis report on the algae cell density and biomass.

[0182] In an embodiment of the present invention, the system uses the pre-collected morphological characteristic parameter data of different types of algae, such as cell size, shape, texture, etc., to construct an algae feature library. Each algae species corresponds to a set of characteristic parameters and is stored as algae feature library data. The system uses the constructed algae feature library data to train an intelligent recognition model, such as a support vector machine, a random forest or a deep learning model, to map the morphological characteristic parameters of the algae to the corresponding algae species, and obtain algae recognition model parameters. In order to improve the recognition accuracy and generalization ability, the system uses a variety of classifiers, such as a support vector machine, a random forest and a deep learning model, to perform multi-classifier integration optimization, and obtain an optimized multi-classifier integration model. The system inputs the morphological characteristic parameters of the unicellular algae extracted in step S57 into the optimized multi-classifier integration model trained in step S62, performs automatic identification and classification of algae, determines the algae species to which each algae cell belongs, and obtains the algae cell genus and species classification data. According to the algae cell genus and species classification data, the system counts the number of cells of each algae species and obtains the distribution data of the number of algae cells of different genera and species. At the same time, the system estimates the size of each algae cell according to the morphological characteristic parameters of the single-cell algae, such as cell length, width and volume, and obtains the algae cell size estimation data. According to the relationship between the morphological characteristics and biomass of different algae species, the system uses the algae cell size estimation data and the algae cell number distribution data of different genera and species to establish an algae biomass conversion model, such as a linear model, an exponential model or other nonlinear model, for converting the number of algae cells into biomass. Then, according to the established algae biomass conversion model, the system calculates the biomass conversion factor of each algae species, such as the biomass corresponding to the number of cells per unit. The system calculates the total biomass of each algae species using the algae cell number distribution data of different genera and species, the algae cell size estimation data and the algae biomass conversion factor calculated in step S65, and obtains the algae biomass composition data. According to the algae cell number distribution data of different genera and species and the original volume data of the sample, the system calculates the cell density of each algae species, such as the number of cells of a certain algae species per milliliter of water sample, and obtains the algae cell density data. The system integrates the data on the classification of algal cell genus and species, the distribution data on the number of algal cells of different genera and species, the data on the composition of algal biomass and the data on the density of algal cells, conducts a comprehensive data analysis, and generates a comprehensive analysis report on the density and biomass of algal cells, such as displaying information such as the number of cells, biomass and density of different algal species in the form of tables or charts.

[0183] Preferably, in step S67, the algae cell density data is obtained by a calculation formula for algae cell density calculation, wherein the calculation formula for algae cell density calculation is specifically:

[0184]

[0185] Where N is the number of algae per liter of water sample, A is the area of ​​the sample pool, and Ac V is the photo counting area, s V is the volume of the water sample after concentration and fixation, a is the volume of the sample pool, n is the number of algae counted, and L is the volume of the original water sample.

[0186] The present invention constructs a calculation formula for calculating algae cell density, wherein N is the final result, which is used to evaluate the density of algae in water. is the ratio of the sample pool area to the photographed counting area. A represents the area of ​​the entire sample pool. c Represents the area actually photographed and counted under the microscope. The ratio of this part is used to "scale" the number of algae in the counting area to the number of algae in the entire sample pool. V is the ratio of the volume of the concentrated water sample to the volume of the sample pool. s Represents the final volume of the water sample after concentration, V a Represents the volume of water sample added to the sample pool. This ratio is used to "convert" the amount of algae in the sample pool to the amount of algae in the concentrated water sample. It is the ratio of the number of algae counted to the volume of the original water sample. n represents the number of algae actually counted under the microscope, and L represents the volume of the original water sample initially collected. This ratio is used to "convert" the number of algae in the concentrated water sample to the number of algae in the original water sample. This formula uses three proportional factors to gradually expand the algae counting results in a limited area under the microscope to the entire sample pool, and then to the concentrated water sample, and finally accurately reflects the density of algae in the original water sample. Each part is indispensable and together ensures the accuracy and reliability of the final result.

[0187] Preferably, the present invention also provides an algae counting system for executing the algae counting method as described above, the algae counting system comprising:

[0188] The dyeing stabilization module is used to obtain the water sample to be tested and the water sample metadata; transfer the water sample to be tested to an intelligent dyeing container with an integrated fully enclosed shell, and perform sample injection volume control processing through a precision metering pump to obtain the sample original volume data; perform dyeing kinetic stability analysis through the dye configuration module based on the water sample metadata and the sample original volume data to obtain the optimal dyeing stabilization time parameter;

[0189] The reverse osmosis concentration module is used to transfer the dye solution through the intelligent pipeline module and the reverse osmosis concentration device to obtain the transfer volume data; to perform reverse osmosis concentration of the water sample according to the water sample metadata, the transfer volume data and the optimal dye stabilization time parameters to obtain the concentration multiple curve; to monitor the permeate recovery through the weighing sensor to obtain the permeate recovery efficiency data; to extract the volume of the algae concentrate according to the permeate recovery efficiency data to obtain the volume of the algae concentrate; to judge the concentration end point according to the algae concentrate volume and the concentration multiple curve to obtain the concentration end point state parameters;

[0190] The cleaning and recovery module is used to perform multi-stage cleaning pressure control processing on the inner wall of the reverse osmosis membrane according to the concentration end state parameters, the volume of the algae concentrate and the reverse osmosis membrane to obtain multi-stage cleaning process data; perform cleaning liquid circulation recovery on the multi-stage cleaning process data to obtain cleaning liquid recovery process data; perform cleaning recovery efficiency analysis based on the cleaning liquid recovery process data to obtain cleaning recovery efficiency parameters;

[0191] The homogenization sampling module is used to process the concentrated liquid sample into the concentrated liquid tank and measure the volume according to the cleaning recovery efficiency parameters to obtain the effective volume data of the concentrated liquid; to evaluate the homogenization process according to the effective volume data of the concentrated liquid to obtain the homogeneity evaluation parameters; to perform multi-objective analysis of the homogenization conditions according to the homogeneity evaluation parameters to obtain the optimal homogenization condition data;

[0192] The intelligent imaging module is used to extract homogenized water samples into a sample pool according to the optimal homogenization condition data and prepare sample slides to obtain sample slide preparation parameters; classify algae cell images using the sample slide preparation parameters to obtain algae cell image classification mask data; perform three-dimensional analysis of algae cell morphology and perform single-cell tracking and identification according to the algae cell image classification mask data to obtain single-cell algae morphological characteristic parameters;

[0193] The precise counting module is used to construct an algae feature library based on the morphological characteristic parameters of single-cell algae to obtain the algae feature library data; to automatically classify and count algae cells based on the algae feature library data to obtain the number distribution data of algae cells of different genera and species; to perform algae biomass conversion calculations based on the morphological characteristic parameters of single-cell algae and the number distribution data of algae cells of different genera and species to obtain the algae biomass composition data; to calculate and analyze the algae cell density and biomass based on the number distribution data of algae cells of different genera and species and the algae biomass composition data to obtain a comprehensive analysis report on algae cell density and biomass.

[0194] refer to Figure 4 The connection diagram of each component of the fully automatic instant algae counter is as follows:

[0195] 1. Sample pretreatment stage:

[0196] After the dedicated water sampler collects the water sample, it is transferred to the intelligent dyeing container with an integrated fully enclosed shell. The precision metering pump accurately controls the injection volume and collects the original volume data of the sample. The dye configuration module in the container automatically configures the dye according to the water sample metadata and volume data and accurately adds it to the water sample through a multi-channel micro pump.

[0197] The micro-fiber spectrometer and fluorescence spectrometer monitor the dyeing process in real time, obtain spectral data, and establish a dyeing kinetic model to predict the optimal dyeing time to ensure sufficient and stable dyeing.

[0198] 2. Algae concentration stage:

[0199] After dyeing is completed, the dyeing liquid is transported to the reverse osmosis concentration device through the intelligent pipeline module. The reverse osmosis concentration device selects the appropriate reverse osmosis membrane according to the water sample information and preset parameters and starts the concentration process. The weighing sensor monitors the quality of the permeate in real time, calculates the recovery efficiency of the permeate, and accurately controls the concentration end point according to the preset concentration multiple to obtain the algae concentrate of the target concentration.

[0200] 3. Cleaning and homogenization stage: After concentration is completed, the system automatically configures the cleaning liquid according to the concentrated liquid parameters, and performs multi-stage cleaning on the reverse osmosis membrane. The cleaning liquid circulation treatment device recycles the cleaning liquid to improve utilization rate.

[0201] After cleaning, the concentrated algae liquid is transported to the concentrate tank, and the system automatically measures its volume. The system selects the appropriate homogenization equipment and parameters according to the algae species and concentrate volume, and performs sufficient homogenization to ensure the accuracy of subsequent imaging analysis.

[0202] 4. Imaging and analysis stage:

[0203] The homogenized algae liquid is sent to the sample pool and made into sample slides. The intelligent imaging module performs multi-spectral imaging on the slides, and the intelligent focus optimization function of the microscope ensures image clarity. The system pre-processes, classifies, and 3D reconstructs the acquired high-resolution algae cell images to extract the morphological characteristic parameters of single-cell algae.

[0204] 5. Counting and report generation phase:

[0205] The system uses the algae feature library and intelligent recognition model to automatically identify, classify and count algae cells, and count the number and distribution of algae cells of different genera and species. The algae cell size is estimated based on the algae cell morphological characteristic parameters, and the algae biomass composition is calculated in combination with the pre-established algae biomass conversion model. Finally, the system integrates and analyzes the data to generate a comprehensive analysis report on algae cell density and biomass.

[0206] The intelligent pipeline module is the key hub connecting the various components of the fully automatic instant algae counter. It is responsible for the precise transmission and switching of liquids such as samples, dyes, and cleaning solutions. Its components and connection methods are as follows:

[0207] 1. Components:

[0208] Micro pump: provides power for liquid transmission. Micro pumps of different types and flow rates can be selected according to needs, such as peristaltic pumps, syringe pumps, etc.

[0209] Multi-way valve: realizes the switching of different flow paths, such as transporting samples to staining containers, concentrators or sample pools.

[0210] Sensor: monitors liquid flow, pressure, temperature and other parameters to ensure the stability and accuracy of liquid transmission.

[0211] Pipeline: The channel connecting the various components. Pipes of different materials and specifications are selected according to the characteristics of different liquids.

[0212] Control system: Controls the operation of micro pumps, multi-way valves and sensors to achieve automation and intelligence of liquid transmission according to preset programs or real-time feedback information.

[0213] 2. Connection method: The intelligent pipeline module connects the following components through pipelines:

[0214] Intelligent dyeing container: transport the water sample, dye, etc. to be tested to the dyeing container.

[0215] Reverse osmosis concentration device: The dyed sample is transported to the concentration device.

[0216] Reverse osmosis membrane: connects the concentration device and the cleaning system to transport the concentrate and cleaning solution.

[0217] Concentrated liquid tank: The concentrated algae liquid is transported to the concentrated liquid tank.

[0218] Sample pool: The homogenized algae solution is transported to the sample pool for imaging analysis.

[0219] Cleaning system: connects various components and cleaning liquid containers, and delivers cleaning liquid for cleaning operations.

[0220] 3. Working principle:

[0221] The control system of the intelligent pipeline module controls the operation of the micro pump and multi-way valve according to the preset program and sensor feedback information to achieve the following functions:

[0222] Precise control of liquid transmission: Precisely control the flow rate, flow rate and delivery time of different liquids (samples, dyes, cleaning solutions, etc.) as needed.

[0223] Flexible flow path switching: Flexibly switch the flow paths between different components according to different experimental steps, such as staining, concentration, washing, homogenization, imaging, etc.

[0224] Prevent cross contamination: Through reasonable pipeline design and cleaning process, cross contamination between different liquids can be prevented to ensure the accuracy of experimental results.

[0225] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0226] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for counting algae, characterized in that: The invention is applied to a fully automatic instant algae counter, which includes an intelligent dyeing container with an integrated fully enclosed shell, an intelligent pipeline module, a reverse osmosis concentration device, a weighing sensor, a reverse osmosis membrane, a concentrate tank and a sample pool, wherein the intelligent dyeing container with an integrated fully enclosed shell includes a precision metering pump, a dye configuration module and a multi-channel micro pump connected in sequence, the reverse osmosis concentration device and the weighing sensor are connected to each other, and the multi-channel micro pump, the reverse osmosis concentration device, the reverse osmosis membrane, the concentrate tank and the sample pool are connected in sequence through the intelligent pipeline module. The algae counting method includes the following steps: Step S1: obtaining a water sample to be tested and water sample metadata; transferring the water sample to be tested to an intelligent dyeing container with an integrated fully enclosed shell, performing sample injection volume control processing through a precision metering pump, and obtaining the original volume data of the sample; performing dyeing kinetic stability analysis through a dye configuration module according to the water sample metadata and the original volume data of the sample, and obtaining the optimal dyeing stabilization time parameter, wherein step S1 is specifically as follows: Step S11: Collect water samples from the water body through a special water sampler and record the data to obtain the water sample to be tested and the water sample metadata; Step S12: transferring the water sample to be tested into an intelligent dyeing container with an integrated fully enclosed shell, and performing sample injection volume control processing through a precision metering pump to obtain the original volume data of the sample; Step S13: Automatically configure the dye through the dye configuration module according to the water sample metadata and the original volume data of the sample to obtain dye dosage data; intelligently add the dye through the multi-channel micro pump according to the dye dosage data to obtain dyeing start time data; Step S14: acquiring dyeing process data; performing dyeing liquid optical analysis on the dyeing process data and performing dyeing kinetic modeling to obtain a dyeing kinetic model; performing dyeing rate and equilibrium analysis according to the dyeing kinetic model to obtain a dyeing rate constant and a dyeing equilibrium constant, wherein step S14 is specifically as follows: Step S141: using a micro-fiber spectrometer to monitor the spectrum of the dyeing liquid for the dyeing process data to obtain absorbance-time curve data; Step S142: using a fluorescence spectrometer to analyze the fluorescence intensity change of the dyeing process data to obtain fluorescence intensity-time curve data; Step S143: performing mathematical curve fitting on the absorbance-time curve data and the fluorescence intensity-time curve data and constructing a dyeing kinetic model to obtain a dyeing kinetic model; Step S144: performing dyeing rate analysis according to the dyeing kinetics model to obtain a dyeing rate constant; performing dyeing equilibrium analysis according to the dyeing kinetics model to obtain a dyeing equilibrium constant; Step S15: Perform dyeing endpoint judgment according to the dyeing kinetics model. If the dyeing progress value is less than the preset dyeing endpoint threshold, return to step S13; if the dyeing progress value is greater than or equal to the preset dyeing endpoint threshold, generate a dyeing stable state flag and execute step S16; Step S16: Optimizing the stabilization time parameters based on the dyeing start time data, the dyeing rate constant, and the dyeing equilibrium constant to obtain the optimal dyeing stabilization time parameters; Step S2: transfer the dye solution through the intelligent pipeline module and the reverse osmosis concentration device to obtain the transfer volume data; perform reverse osmosis concentration of the water sample according to the water sample metadata, the transfer volume data and the optimal dye stabilization time parameter to obtain the concentration multiple curve; monitor the permeate recovery through the weighing sensor to obtain the permeate recovery efficiency data; extract the algae concentrate volume according to the permeate recovery efficiency data to obtain the algae concentrate volume; judge the concentration end point according to the algae concentrate volume and the concentration multiple curve to obtain the concentration end point state parameter, wherein step S2 is specifically as follows: Step S21: transferring the dye solution through the intelligent pipeline module and the reverse osmosis concentration device to obtain transfer volume data; selecting the membrane component according to the water sample metadata and the optimal dye stabilization time parameter to obtain the membrane component configuration parameters; Step S22: Initializing the pressure of the reverse osmosis concentration device to obtain initial pressure data; analyzing the filtered water output according to the initial pressure data, the transfer volume data and the membrane component configuration parameters to obtain filtered water output parameters; Step S23: monitoring the concentration process according to the filtered water volume parameter to obtain dynamic data of the concentration process; calculating the algae cell concentration multiple according to the filtered water volume parameter and the dynamic data of the concentration process to obtain a concentration multiple curve; Step S24: monitoring the recovery of the permeate through a weighing sensor to obtain the permeate recovery efficiency data; extracting the volume of the algae concentrate according to the filtered water volume parameter and the permeate recovery efficiency data to obtain the volume of the algae concentrate; Step S25: judging the concentration end point according to the volume of the algae concentrate and the concentration multiple curve, and obtaining the concentration end point state parameter; Step S3: performing multi-stage cleaning pressure control processing on the inner wall of the reverse osmosis membrane according to the concentration endpoint state parameter, the volume of the algae concentrate and the reverse osmosis membrane to obtain multi-stage cleaning process data; performing cleaning liquid recycling on the multi-stage cleaning process data to obtain cleaning liquid recycling process data; performing cleaning recovery efficiency analysis on the cleaning liquid recycling process data to obtain cleaning recovery efficiency parameters; Step S4: The concentrated liquid sample flows into the concentrated liquid tank for processing and the volume is measured according to the cleaning recovery efficiency parameter to obtain the effective volume data of the concentrated liquid; the homogenization process is evaluated according to the effective volume data of the concentrated liquid to obtain the homogeneity evaluation parameter; the homogenization condition multi-objective analysis is performed according to the homogeneity evaluation parameter to obtain the optimal homogenization condition data, wherein step S4 is specifically as follows: Step S41: The concentrated liquid sample flows into the concentrated liquid tank for processing and the volume is measured according to the cleaning recovery efficiency parameter to obtain the effective volume data of the concentrated liquid; Step S42: Acquire algae cell type information data; select a homogenizing device according to the effective volume data of the concentrate and the algae cell type information data to obtain configuration parameters of the homogenizing device; optimize stirring parameters using the configuration parameters of the homogenizing device to obtain optimal stirring process parameters; Step S43: performing a shake-even mixing process using the configuration parameters of the homogenizing equipment according to the optimal stirring process parameters to obtain the optimal shake-even mixing parameters; performing high-pressure homogenization optimization using the configuration parameters of the homogenizing equipment according to the optimal stirring process parameters and the optimal shake-even mixing parameters to obtain the optimal high-pressure homogenization parameters; Step S44: acquiring homogenization process data; performing dynamic particle size monitoring on the homogenization process data to obtain dynamic particle size distribution data; performing homogeneity evaluation according to the dynamic particle size distribution data to obtain homogeneity evaluation parameters; Step S45: performing energy consumption optimization analysis according to the optimal stirring process parameters, the optimal shaking mixing parameters and the optimal high-pressure homogenization parameters to obtain energy consumption optimization data; performing homogenization endpoint determination according to the homogeneity evaluation parameters and the energy consumption optimization data to obtain homogenization endpoint state parameters; Step S46: determining the optimal homogenization conditions through a multi-objective optimization algorithm according to the optimal stirring process parameters, the optimal shaking mixing parameters, the optimal high-pressure homogenization parameters, the homogeneity evaluation parameters, the energy consumption optimization data and the homogenization end state parameters, and obtaining the optimal homogenization condition data; Step S5: extracting a homogenized water sample to a sample pool for processing according to the optimal homogenization condition data and preparing a sample slide to obtain sample slide preparation parameters; performing algae cell image classification using the sample slide preparation parameters to obtain algae cell image classification mask data; performing algae cell morphology three-dimensional analysis and single cell tracking and identification according to the algae cell image classification mask data to obtain single-cell algae morphology characteristic parameters, wherein step S5 is specifically as follows: Step S51: extracting a homogenized water sample into a sample pool for processing according to the optimal homogenization condition data and preparing a sample slide to obtain sample slide preparation parameters; Step S52: performing intelligent focusing optimization of the microscope using the sample slide preparation parameters to obtain intelligent focusing optimization data; performing multispectral imaging according to the intelligent focusing optimization data to obtain a multispectral image data set; Step S53: performing high-resolution image acquisition according to the intelligent focusing optimization data and the multispectral image data set to obtain a high-resolution algae cell image library; Step S54: performing image preprocessing optimization on the high-resolution algae cell image library to obtain an optimized preprocessed image set; performing algae cell image classification according to the optimized preprocessed image set to obtain algae cell image classification mask data; Step S55: extracting morphological features according to the algae cell image classification mask data to obtain an algae cell morphological feature vector; performing three-dimensional reconstruction of the algae cell according to the algae cell image classification mask data to obtain three-dimensional morphological parameters of the algae cell; Step S56: performing single cell trajectory tracking and identification according to the algae cell morphological feature vector and the algae cell three-dimensional morphological parameters to obtain single cell trajectory data; Step S57: extracting morphological characteristic parameters according to the algae cell morphological characteristic vector, the algae cell three-dimensional morphological parameters and the single cell trajectory data to obtain the single cell algae morphological characteristic parameters; Step S6: construct an algae feature library according to the morphological characteristic parameters of single-cell algae to obtain algae feature library data; perform automatic classification and statistics of algae cells according to the algae feature library data to obtain algae cell quantity distribution data of different genera and species; perform algae biomass conversion calculation according to the morphological characteristic parameters of single-cell algae and the algae cell quantity distribution data of different genera and species to obtain algae biomass composition data; perform algae cell density and biomass calculation and analysis according to the algae cell quantity distribution data of different genera and species and the algae biomass composition data to obtain a comprehensive analysis report of algae cell density and biomass.

2. The algae counting method according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: configuring the cleaning liquid according to the concentration end state parameter and the volume of the algae concentrate to obtain cleaning liquid formula data; setting the cleaning pressure according to the cleaning liquid formula data to obtain the cleaning pressure parameter; Step S32: performing multi-stage cleaning control processing on the inner wall of the reverse osmosis membrane through the reverse osmosis membrane according to the cleaning pressure parameter to obtain multi-stage cleaning process data; performing cleaning liquid circulation processing on the multi-stage cleaning process data to obtain cleaning liquid circulation dynamic parameters; Step S33: recovering the cleaning liquid according to the multi-stage cleaning process data and the dynamic parameters of the cleaning liquid circulation to obtain a cleaning liquid recovery turbidity curve; obtaining cleaning liquid recovery process data; monitoring the membrane flux of the cleaning liquid recovery process data to obtain membrane flux recovery data; Step S34: determining the cleaning endpoint according to the cleaning liquid recovery turbidity curve and the membrane flux recovery data, and obtaining the cleaning endpoint state parameters; Step S35: Calculate the efficiency parameters based on the multi-stage cleaning process data, the cleaning liquid circulation dynamic parameters, the cleaning liquid recovery turbidity curve and the cleaning endpoint state parameters to obtain the cleaning recovery efficiency parameters.

3. The algae counting method according to claim 1, characterized in that: Step S6 includes the following steps: Step S61: constructing an algae feature library according to the morphological characteristic parameters of the single-cell algae to obtain algae feature library data; Step S62: Perform intelligent recognition model training according to the algae feature library data to obtain algae recognition model parameters; perform multi-classifier integration optimization using the algae recognition model parameters to obtain an optimized multi-classifier integration model; Step S63: inputting the morphological characteristic parameters of the single-cell algae into the optimized multi-classifier integrated model to automatically identify and classify the algae, and obtaining the genus and species classification data of the algae cells; Step S64: performing algae cell counting statistics according to the algae cell genus and species classification data to obtain algae cell quantity distribution data of different genera and species; performing algae cell size estimation according to the morphological characteristic parameters of single-cell algae to obtain algae cell size estimation data; Step S65: performing algae biomass conversion modeling according to the algae cell size estimation data and the algae cell quantity distribution data of different genera and species to obtain an algae biomass conversion model; performing biomass conversion according to the algae biomass conversion model to obtain an algae biomass conversion factor; Step S66: Calculate the algae biomass using the algae cell number distribution data of different genera and species, the algae cell size estimation data, and the algae biomass conversion factor to obtain the algae biomass composition data; Step S67: Calculate the algae cell density according to the algae cell quantity distribution data of different genera and species and the original volume data of the sample to obtain the algae cell density data; Step S68: Perform comprehensive data analysis based on the algae cell genus and species classification data, the algae cell quantity distribution data of different genera and species, the algae biomass composition data and the algae cell density data to obtain a comprehensive analysis report on the algae cell density and biomass.

4. The algae counting method according to claim 3, characterized in that: In step S67, the algae cell density data is obtained by the calculation formula for algae cell density calculation, wherein the calculation formula for algae cell density calculation is specifically: ； In the formula, is the number of algae per liter of water sample, is the sample cell area, To take photos and count the area, The volume of the water sample after concentration and fixation. is the sample cell volume, To count the number of algae obtained, is the volume of the original water sample.

5. An algae counting system, characterized in that: For executing the algae counting method as claimed in claim 1, the algae counting system comprises: The dyeing stabilization module is used to obtain the water sample to be tested and the water sample metadata; transfer the water sample to be tested to an intelligent dyeing container with an integrated fully enclosed shell, and perform sample injection volume control processing through a precision metering pump to obtain the sample original volume data; perform dyeing kinetic stability analysis through the dye configuration module based on the water sample metadata and the sample original volume data to obtain the optimal dyeing stabilization time parameter; The reverse osmosis concentration module is used to transfer the dye solution through the intelligent pipeline module and the reverse osmosis concentration device to obtain the transfer volume data; to perform reverse osmosis concentration of the water sample according to the water sample metadata, the transfer volume data and the optimal dye stabilization time parameters to obtain the concentration multiple curve; to monitor the permeate recovery through the weighing sensor to obtain the permeate recovery efficiency data; to extract the volume of the algae concentrate according to the permeate recovery efficiency data to obtain the volume of the algae concentrate; to judge the concentration end point according to the algae concentrate volume and the concentration multiple curve to obtain the concentration end point state parameters; The cleaning and recovery module is used to perform multi-stage cleaning pressure control processing on the inner wall of the reverse osmosis membrane according to the concentration end state parameters, the volume of the algae concentrate and the reverse osmosis membrane to obtain multi-stage cleaning process data; perform cleaning liquid circulation recovery on the multi-stage cleaning process data to obtain cleaning liquid recovery process data; perform cleaning recovery efficiency analysis based on the cleaning liquid recovery process data to obtain cleaning recovery efficiency parameters; The homogenization sampling module is used to process the concentrated liquid sample into the concentrated liquid tank and measure the volume according to the cleaning recovery efficiency parameters to obtain the effective volume data of the concentrated liquid; to evaluate the homogenization process according to the effective volume data of the concentrated liquid to obtain the homogeneity evaluation parameters; to perform multi-objective analysis of the homogenization conditions according to the homogeneity evaluation parameters to obtain the optimal homogenization condition data; The intelligent imaging module is used to extract homogenized water samples into a sample pool according to the optimal homogenization condition data and prepare sample slides to obtain sample slide preparation parameters; classify algae cell images using the sample slide preparation parameters to obtain algae cell image classification mask data; perform three-dimensional analysis of algae cell morphology and perform single-cell tracking and identification according to the algae cell image classification mask data to obtain single-cell algae morphological characteristic parameters; The precise counting module is used to construct an algae feature library based on the morphological characteristic parameters of single-cell algae to obtain the algae feature library data; to automatically classify and count algae cells based on the algae feature library data to obtain the number distribution data of algae cells of different genera and species; to perform algae biomass conversion calculations based on the morphological characteristic parameters of single-cell algae and the number distribution data of algae cells of different genera and species to obtain the algae biomass composition data; to calculate and analyze the algae cell density and biomass based on the number distribution data of algae cells of different genera and species and the algae biomass composition data to obtain a comprehensive analysis report on algae cell density and biomass.

Images