Preparation method and product of cross-linking enhanced composite biological enzyme algaecide

Abstract

The invention belongs to the technical field of water environment treatment, and particularly discloses a preparation method and a product of a crosslinking enhanced composite biological enzyme algaecide. Comprising the following steps: obtaining a biological enzyme algicide data sample set according to preparation key parameters, carrying out normalization processing on data samples, and randomly dividing the data samples into a training sample set and a test sample set; using the training sample set to train a Light GBM model so as to predict algae removal efficiency, material stability and reuse rate, using a Bayesian optimization algorithm to optimize hyper-parameters of the Light GBM model, and determining an optimal parameter combination; taking a BO-Light GBM prediction model function as a fitness function of a genetic algorithm, taking algae removal efficiency, material stability and reuse rate as objective functions, and taking physical and chemical limits of parameters as constraint conditions, performing multi-objective optimization, and obtaining a Pareto optimal solution set; and preparing the biological enzyme algaecide based on the Pareto optimal solution set. The performance of the algaecide is improved, and the influence on the environment is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of water environment treatment, and more specifically, relates to a preparation method and product of a cross-linked enhanced composite bio-enzyme algaecide. Background Art

[0002] Bio-enzyme algaecide is an environmentally friendly water treatment agent, mainly used to control and reduce algae growth in water bodies, especially algae blooms. Excessive algae growth can lead to hypoxia, deterioration of water quality, and even the production of toxins, posing a threat to aquatic life and human health. Bio-enzyme algaecides inhibit or kill algae by specifically decomposing algae cell walls or cell contents. Compared with traditional chemical methods, they are highly efficient, safe, and non-toxic.

[0003] In the prior art, the paper (Smith, J., & Davis, S. (2020). The challenges of enzyme stability in natural environments for algal bloom control. Journal of Environmental Science and Technology, 54 (12), 7344-7353) proposed a method to improve enzyme stability by chemical modification to extend its effective action time in water bodies. The paper proposed a method to improve enzyme stability, but chemical modification may increase preparation costs and may affect the biodegradability of the enzyme, which limits its feasibility in large-scale applications. The paper (Johnson, D., & Black, J. (2021). Multi-objective optimization in environmental engineering: A review. Environmental Engineering Journal, 17 (2), 101-112.) discussed the application of multi-objective optimization in environmental engineering, including the trade-offs of cost, efficiency and environmental impact in the development of bio-enzyme algaecides. The paper points out that existing research often focuses on a single objective and ignores other important factors, resulting in the inability to comprehensively evaluate and optimize the performance of bio-enzyme algaecides.

[0004] Based on the above defects and shortcomings, there is an urgent need in this field to propose a preparation method of a cross-linked enhanced composite bio-enzyme algaecide based on multi-objective optimization of artificial intelligence to solve the problem that the existing technology cannot take into account the optimal balance of multiple objectives. Summary of the invention

[0005] In view of the above defects or improvement needs of the prior art, the present invention provides a preparation method and product of a cross-linked enhanced composite bio-enzyme algaecide, which realizes the intelligent optimization of the formula of the cross-linked enhanced composite bio-enzyme algaecide, and significantly improves the performance and application efficiency of the algaecide. By combining Bayesian optimization (BO) and LightGBM algorithms, the scheme can accurately adjust the model hyperparameters and optimize the prediction model of algaecide efficiency, material stability and reuse rate. Using a multi-objective loss function, the scheme simultaneously considers the three key performance indicators of algaecide efficiency, material stability and reuse rate, ensuring the efficiency and economy of the algaecide in practical applications. In addition, through the NSGA-III multi-objective optimization algorithm, the scheme can find the best trade-off between multiple objectives and achieve the Pareto optimal solution, thereby providing an efficient, environmentally friendly and cost-effective algaecide preparation method for actual production. This method not only improves the performance of the algaecide, but also reduces the impact on the environment, providing strong technical support for the protection of aquatic ecosystems and water quality management.

[0006] To achieve the above object, according to one aspect of the present invention, a method for preparing a cross-linked enhanced composite bio-enzyme algaecide is proposed, comprising the following steps:

[0007] Step 1: According to the key preparation parameters, a data sample set of the bio-enzyme algaecide is obtained, the data samples are normalized, and randomly divided into a training sample set and a test sample set;

[0008] Step 2: Use the training sample set to train the LightGBM model to predict the algae removal efficiency, material stability, and reuse rate. Use the Bayesian optimization algorithm to optimize the hyperparameters of the LightGBM model and determine the best parameter combination.

[0009] Step 3: Use the BO-LightGBM prediction model function as the fitness function of the genetic algorithm, the algae removal efficiency, material stability and reuse rate as the objective function, and the physical and chemical limitations of the parameters as constraints to perform multi-objective optimization and obtain the Pareto optimal solution set;

[0010] Step 4: Prepare bio-enzyme algaecide based on the Pareto optimal solution set.

[0011] As further preferred, in step 1, the key parameters include:

[0012] Enzyme concentration E, biological ceramsite ratio G, microbial genus ratio M, sodium alginate solution concentration A, calcium chloride solution concentration C, cross-linking reaction time T, oscillation speed O and standing time S.

[0013] As further preferred, step 2 comprises the following steps:

[0014] (21) The LightGBM model was trained using the training sample set to predict algae removal efficiency, material stability, and reuse rate, and the hyperparameters were optimized, including learning rate, minimum batch size, column sampling ratio, number of estimators, L2 regularization parameter, and maximum depth of the tree;

[0015] (22) Use the Bayesian optimization algorithm to search for the optimal hyperparameter combination, with the mean square error as the optimization target;

[0016] (23) The reliability of the model was evaluated using three performance indicators: root mean square error, mean absolute error, and mean absolute percentage error.

[0017] As further preferred, the calculation model of the root mean square error, mean absolute error and mean absolute percentage error includes:

[0018]

[0019] In the formula, n is the number of data samples, and are the experimental value and the predicted value, respectively.

[0020] As further preferred, in step 3, the objective functions of algae removal efficiency, material stability and reuse rate include:

[0021] f1(E,G,M,A,C,T,O,S)=LightGBM(E,G,M,A,C,T,O,S)

[0022] f2(E,G,M,A,C,T,O,S)=LightGBM(E,G,M,A,C,T,O,S)

[0023] f3(E,G,M,A,C,T,O,S)=LightGBM(E,G,M,A,C,T,O,S)

[0024] Among them, f1 is the algae removal efficiency predicted by the LightGBM model, f2 is the material stability predicted by the LightGBM model, and f3 is the reuse rate predicted by the LightGBM model.

[0025] As a further preferred embodiment, in step 3, the BO-LightGBM prediction model includes:

[0026]

[0027] In the formula, θ * is the optimal hyperparameter combination, and θ represents the hyperparameter.

[0028] As a further preferred embodiment, in step 3, a fuzzy decision method is used to select an optimal solution from the Pareto solution set, as follows:

[0029] Each solution is scored based on its distance to the positive ideal solution and the negative ideal solution. The scoring formula for each solution is as follows:

[0030]

[0031] In the formula, S i is the score corresponding to the ith Pareto solution, f i - is the distance from the ith Pareto solution to the negative ideal solution, f i + is the distance from the ith Pareto solution to the positive ideal solution, f i - and f i + The calculation formula is as follows:

[0032]

[0033] In the formula, m is the number of optimization objectives, x ij is the ith Pareto solution under the jth objective, and is the input value corresponding to the negative ideal solution and the positive ideal solution under the jth objective, and the calculation formula is as follows:

[0034]

[0035] Calculate the percentage improvement for each Pareto solution, where the improvement for each objective is:

[0036]

[0037] The overall improvements for each solution are:

[0038]

[0039] In the formula, Imp ij is the improvement of the jth objective of each i-th Pareto solution, Org j,ave is the original mean value of the jth target, Opt ij is the optimal value of the jth objective of each i-th Pareto solution, Impoverall i is the overall improvement of each i Pareto solution.

[0040] As a further preferred embodiment, the method further includes performing the following operations according to the obtained optimal solution:

[0041] (51) adding an enzyme to a suitable amount of water to prepare an enzyme solution, and then adding the prepared enzyme solution to the sodium alginate solution to obtain a mixed solution A;

[0042] (52) Add the sterilized bioceramsite to the microbial mixed suspension D, shake and adsorb, and let stand for a period of time to obtain a bacterial suspension mixture B;

[0043] (53) adding the bacterial solution mixture B obtained in step (2) to the mixed solution A in step (51), and mixing them to obtain a mixed solution C;

[0044] (54) Add calcium chloride solution to the mixed solution C to carry out a cross-linking reaction. After the cross-linking reaction is completed, wash with sterile water to obtain the novel bio-enzyme algaecide.

[0045] According to another aspect of the present invention, there is also provided a cross-linked enhanced composite bio-enzyme algaecide, which is prepared by the method of any one of the above embodiments or a combination of multiple embodiments.

[0046] As a further preferred embodiment, the composition and mass percentage of the cross-linked enhanced composite bio-enzyme algaecide are:

[0047] 10-15 parts of biological ceramsite, 15-25 parts of mixed bacteria, 30-40 parts of hemicellulase, 30-40 parts of hemicellulase,

[0048] The mixed bacterial genus includes at least four of the following: myxobacteria, Bacillus subtilis, yeast, phosphorus-accumulating bacteria, and ammonia-nitrogen bacteria.

[0049] In general, the above technical solution conceived by the present invention has the following technical advantages compared with the prior art:

[0050] 1. The present invention realizes the intelligent optimization of the formula of the cross-linked enhanced composite bio-enzyme algaecide, and significantly improves the performance and application efficiency of the algaecide. By combining the Bayesian optimization (BO) and LightGBM algorithms, the scheme can accurately adjust the model hyperparameters and optimize the prediction model of algaecide efficiency, material stability and reuse rate. Using the multi-objective loss function, the scheme simultaneously considers the three key performance indicators of algaecide efficiency, material stability and reuse rate, ensuring the efficiency and economy of the algaecide in practical applications. In addition, through the NSGA-III multi-objective optimization algorithm, the scheme can find the best trade-off between multiple objectives and achieve the Pareto optimal solution, thereby providing an efficient, environmentally friendly and cost-effective algaecide preparation method for actual production. This method not only improves the performance of the algaecide, but also reduces the impact on the environment, providing strong technical support for the protection of aquatic ecosystems and water quality management.

[0051] 2. The present invention uses mixed enzymes such as hemicellulase and ligninase to act on algae biological cells such as cyanobacteria, causing damage to the gelatinous sheath and cell wall of the cells, destroying the integrity of the cell structure, making it difficult for them to maintain normal life when disturbed by the external environment, and ultimately leading to cell death, thereby effectively removing algae from water bodies.

[0052] 3. The biological enzyme used in the present invention is specific and will not have adverse effects on the water body. It does not require detoxification or oxygenation after use. It is simple and easy to operate and implement. It will not kill fish, shrimps, crabs and other organisms in the water body, and can protect the integrity of the target water area to the greatest extent.

[0053] 4. The present invention uses biological ceramsite as a microbial carrier, which significantly improves the survival rate and activity of microorganisms in water bodies through its excellent adsorption and protection properties. The sterilization treatment of biological ceramsite ensures its safe application in water bodies and will not cause secondary pollution.

[0054] 5. The myxobacteria group in the mixed bacterial agent of the present invention can secrete ligninase, and the Bacillus subtilis group can secrete hemicellulase, which can not only reduce the use of biological enzymes in the new biological enzyme algaecide, but also make up for the insufficient activity of the biological enzymes in the later stage of use, thereby extending the use period of the new biological enzymes.

[0055] 6. The present invention uses sodium alginate and calcium chloride to carry out cross-linking reaction to form a stable three-dimensional network structure to embed biological enzymes and microorganisms. This cross-linking technology not only improves the stability and reuse rate of the algaecide, but also ensures the continuous action of biological enzymes and microorganisms in the water body.

[0056] 7. The yeast flora and polyphosphate bacteria in the mixed bacterial agent of the present invention can effectively reduce the content of organic matter and total phosphorus in the water body, and the ammonia nitrogen bacteria can effectively reduce the total nitrogen content in the water body, which not only improves the water quality to a certain extent, but also can effectively reduce the nutrients of algae and effectively prevent the crazy growth of algae.

[0057] 8. The materials of the present invention are easy to obtain, the preparation method is simple, the production time is short, the cost is low, the application range is wide, and it also has a certain water quality improvement effect. The biological enzyme also has multiple excellent characteristics such as high efficiency, specificity, non-toxicity, harmlessness, and reusability. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a flow chart of a method for preparing a cross-linked enhanced composite bio-enzyme algaecide according to an embodiment of the present invention;

[0059] Figure 2 This is a comparison chart of the removal effects of the novel bio-enzyme algaecide with different bacterial flora ratios in the embodiments of the present invention;

[0060] Figure 3This is a test chart of the repeated performance of the novel bio-enzyme algaecide according to an embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0062] Example 1

[0063] like Figure 1 As shown, a method for preparing a cross-linked enhanced composite bio-enzyme algaecide provided by an embodiment of the present invention comprises the following steps:

[0064] Step 1: According to the key preparation parameters, a data sample set of bio-enzyme algaecide is obtained, the data samples are normalized, and randomly divided into a training sample set and a test sample set.

[0065] In this step, the key parameters include: enzyme concentration E, biological ceramsite ratio G, microbial genus ratio M, sodium alginate solution concentration A, calcium chloride solution concentration C, cross-linking reaction time T, oscillation speed O and standing time S.

[0066] In addition, the data samples need to be normalized and randomly divided into training sample sets and test sample sets.

[0067] Step 2: Use the training sample set to train the LightGBM model to predict the algae removal efficiency, material stability, and reuse rate. The Bayesian optimization algorithm is used to optimize the hyperparameters of the LightGBM model to determine the optimal parameter combination.

[0068] In this step, (21) the LightGBM model was trained using the training sample set to predict algae removal efficiency, material stability, and reuse rate, and the hyperparameters were optimized, including learning rate, minimum batch size, column sampling ratio, number of estimators, L2 regularization parameter, and maximum depth of the tree;

[0069] (22) Use the Bayesian optimization algorithm to search for the optimal hyperparameter combination, with the mean square error as the optimization target;

[0070] (23) The reliability of the model was evaluated using three performance indicators: root mean square error, mean absolute error, and mean absolute percentage error.

[0071] As further preferred, in step 3, the objective functions of algae removal efficiency, material stability and reuse rate include:

[0072] f1(E,G,M,A,C,T,O,S)=LightGBM(E,G,M,A,C,T,O,S)

[0073] f2(E,G,M,A,C,T,O,S)=LightGBM(E,G,M,A,C,T,O,S)

[0074] f3(E,G,M,A,C,T,O,S)=LightGBM(E,G,M,A,C,T,O,S)

[0075] Among them, f1 is the algae removal efficiency predicted by the LightGBM model, f2 is the material stability predicted by the LightGBM model, and f3 is the reuse rate predicted by the LightGBM model.

[0076] As further preferred, the calculation model of the root mean square error, mean absolute error and mean absolute percentage error includes:

[0077]

[0078]

[0079] In the formula, n is the number of data samples, and are the experimental value and the predicted value, respectively.

[0080] Step 3: Use the BO-LightGBM prediction model function as the fitness function of the genetic algorithm, the algae removal efficiency, material stability and reuse rate as the objective function, and the physical and chemical limitations of the parameters as constraints to perform multi-objective optimization and obtain the Pareto optimal solution set;

[0081] Step 4: Prepare bio-enzyme algaecide based on the Pareto optimal solution set.

[0082] In this step, in order to build a specific BO-LightGBM prediction model, it is necessary to define the model architecture and optimization process. The following is the calculation formula of the BO-LightGBM prediction model:

[0083] Bayesian optimization (BO) calculation formula:

[0084] P(MSE|θ)=Normal(MSE;μ,σ 2 )

[0085] Among them, θ represents the hyperparameter, μ and σ2 are the parameters of the likelihood function.

[0086] Define the prior distribution:

[0087] P(θ)=Uniform(θ;θ min ,θ max )

[0088] Among them, θmin and θmax are the minimum and maximum values ​​of the hyperparameters.

[0089] Define the posterior distribution:

[0090] P(θ|MSE)∝P(MSE|θ)·P(θ)

[0091] Define the acquisition function:

[0092]

[0093] Typically, acquisition functions include expected improvement (EI) and Gaussian process upper confidence bound (UCB).

[0094] LightGBM prediction model calculation formula

[0095] Define the LightGBM model:

[0096]

[0097] Where y is the target variable, gk(x) is the prediction function of the kth tree, and K is the number of trees.

[0098] Define the tree structure:

[0099]

[0100] Among them, w k,j is the weight of the jth leaf node of the kth tree, I is the indicator function, and Rk,j is the region of the jth leaf node of the kth tree.

[0101] Define the learning process:

[0102] The loss of algae removal efficiency is:

[0103]

[0104] Among them, AEi is the actual algae removal efficiency of the i-th sample, and AE^i is the predicted algae removal efficiency.

[0105] Loss of material stability:

[0106]

[0107] Where SIi is the actual material stability of the i-th sample and SI^i is the predicted material stability.

[0108] Reuse rate loss:

[0109]

[0110] Among them, RRi is the actual reuse rate of the i-th sample, and RR^i is the predicted reuse rate.

[0111] Total multi-objective loss function:

[0112] Total Loss = ω1·Loss AE +ω2·Loss SI +ω3·Loss RR

[0113] Among them, ω1, ω2, and ω3 are weight coefficients used to balance the relative importance of different objectives.

[0114] In this embodiment, the specific method of integrating BO and LightGBM is as follows:

[0115] Hyperparameter Optimization:

[0116]

[0117] Among them, θ * is the optimal hyperparameter combination.

[0118] Model training:

[0119] Train(LightGBM(x;θ * ))

[0120] Using the training dataset and optimal hyperparameters θ * Train the LightGBM model. During model training, minimize the total multi-objective loss function.

[0121] predict:

[0122]

[0123] The trained LightGBM model is used to predict new samples and obtain the predicted values ​​of algae removal efficiency, material stability and reuse rate.

[0124] Bayesian optimization loop: Use the Bayesian optimization algorithm to iteratively search for the optimal hyperparameter combination until a stopping condition is met (for example, a predetermined number of iterations is reached or the performance improvement is less than a certain threshold).

[0125] Preferably, in the above embodiment,

[0126] The fuzzy decision method is used to select an optimal solution from the Pareto solution set, as follows:

[0127] Each solution is scored based on its distance to the positive ideal solution and the negative ideal solution. The scoring formula for each solution is as follows:

[0128]

[0129] In the formula, S i is the score corresponding to the ith Pareto solution, f i - is the distance from the ith Pareto solution to the negative ideal solution, f i + is the distance from the ith Pareto solution to the positive ideal solution, f i - and f i + The calculation formula is as follows:

[0130]

[0131] In the formula, m is the number of optimization objectives, x ij is the ith Pareto solution under the jth objective, and is the input value corresponding to the negative ideal solution and the positive ideal solution under the jth objective, and the calculation formula is as follows:

[0132]

[0133] Calculate the percentage improvement for each Pareto solution, where the improvement for each objective is:

[0134]

[0135] The overall improvements for each solution are:

[0136]

[0137] In the formula, Imp ij is the improvement of the jth objective of each i-th Pareto solution, Org j,ave is the original mean value of the jth target, Opt ij is the optimal value of the jth objective of each i-th Pareto solution, Impoverall i is the overall improvement of each i Pareto solution.

[0138] Preferably, based on any of the above embodiments or a combination of multiple embodiments, after obtaining the optimal ratio,

[0139] Do the following:

[0140] (51) adding an enzyme to a suitable amount of water to prepare an enzyme solution, and then adding the prepared enzyme solution to the sodium alginate solution to obtain a mixed solution A;

[0141] (52) Add the sterilized bioceramsite to the microbial mixed suspension D, shake and adsorb, and let stand for a period of time to obtain a bacterial suspension mixture B;

[0142] (53) adding the bacterial solution mixture B obtained in step (2) to the mixed solution A in step (51), and mixing them to obtain a mixed solution C;

[0143] (54) Add calcium chloride solution to the mixed solution C to carry out a cross-linking reaction. After the cross-linking reaction is completed, wash with sterile water to obtain the novel bio-enzyme algaecide.

[0144] Example 2

[0145] In this embodiment, a method for preparing a cross-linked enhanced composite bio-enzyme algaecide is provided, and the specific steps are as follows:

[0146] (1) adding an enzyme to a suitable amount of water to prepare an enzyme solution, and then adding the prepared enzyme solution to a sodium alginate solution to obtain a mixed solution A;

[0147] (2) adding the sterilized bioceramsite to the microbial mixed suspension D, shaking for adsorption, and standing for a period of time to obtain a bacterial suspension mixture B;

[0148] (3) adding the bacterial solution mixture B obtained in step (2) to the mixed solution A in step (1), and mixing them to obtain a mixed solution C;

[0149] (4) Adding calcium chloride solution to the mixed solution C to carry out a cross-linking reaction. After the cross-linking reaction is completed, washing with sterile water to obtain the novel bio-enzyme algaecide.

[0150] The enzyme solution in step (1) is composed of a mixture of at least two biological enzymes such as ligninase and hemicellulase, and the mass concentration of the sodium alginate solution is 3%-4%.

[0151] The biological ceramsite in the step (2) is a 200-mesh zeolite modified with acid; the sterilization temperature is 121° C. and the sterilization time is 15 min; the oscillation speed of the oscillation adsorption is 150 r / min and the oscillation time is 30 min; the bacterial liquid mixture B mainly comprises myxobacteria, Bacillus subtilis, yeast, polyphosphate bacteria and ammonia nitrogen bacteria; the standing time is 24 h and the standing temperature is 25° C.

[0152] The mass concentration of the calcium chloride solution in step (4) is 2%-4%, and the cross-linking reaction is carried out by placing the mixed solution C in a refrigerator at 4° C. for 24 hours.

[0153] Example 3

[0154] In this embodiment, a cross-linked enhanced composite bio-enzyme algaecide is provided, and the method of using the same is as follows:

[0155] After the novel bio-enzyme algaecide is loaded into a medicine bag, it is thrown into a fixed position in the polluted river channel. The amount of the novel bio-enzyme algaecide thrown is 500-1000g / m2.

[0156] Technical principle: Ligninase is a complex enzyme that can decompose the pectin component in the algae cell wall, thereby destroying the structure of the algae cell wall; hemicellulase is also a mixed enzyme. The various components in the hemicellulase synergistically degrade cellulose and have the effect of hydrolyzing the algae cell wall.

[0157] The combined use of ligninase and hemicellulase can also damage the algae cell wall. After being treated with ligninase, the algae cell wall is damaged, causing changes in physical and chemical factors such as osmotic pressure and electric potential in the algae cells, which in turn affects the normal physiology of the cells and inhibits their growth. Hemicellulase can also inhibit the growth of algae cells. The combination of ligninase and hemicellulase can also damage the glial sheath and cell wall of algae cells, making it difficult for them to maintain normal life when disturbed by the external environment, and ultimately leading to cell death.

[0158] The mixed bacterial agent used in the present invention is selected from at least three kinds of myxobacteria, Bacillus subtilis, yeast, polyphosphate bacteria, and ammonia nitrogen bacteria. Among them, the addition of myxobacteria in the mixed genus can secrete ligninase, which can provide ligninase, which can not only reduce the use of ligninase in the new biological enzyme algaecide, but also make up for the lack of ligninase activity in the later stage of use; the addition of Bacillus subtilis in the mixed genus can secrete hemicellulase, which can provide hemicellulase, which can not only reduce the use of hemicellulase in the new biological enzyme algaecide, but also make up for the lack of hemicellulase activity in the later stage of use; the addition of yeast and polyphosphate bacteria in the mixed genus can effectively reduce the organic matter and total phosphorus content in the water body, which can not only improve the water quality to a certain extent, but also effectively reduce the nutrients of algae, and can effectively prevent the crazy growth of algae; the addition of ammonia nitrogen bacteria in the mixed genus can effectively reduce the total nitrogen content in the water body, which can not only improve the water quality to a certain extent, but also effectively reduce the nutrients of algae, and can effectively prevent the crazy growth of algae.

[0159] Example 4

[0160] A cross-linked enhanced composite bio-enzyme algaecide and a preparation method thereof, wherein the components and mass percentages thereof are:

[0161] 10-15 parts of biological ceramsite. During the water treatment process, microorganisms can form a biofilm on the surface of the ceramsite, and remove organic pollutants in the water through biodegradation. It can replace zeolite to treat domestic sewage and some industrial sewage.

[0162] Mixed bacteria 15-25 parts

[0163] 30-40 parts of hemicellulase, which can dissolve cellulose or hemicellulose in cell walls.

[0164] The mixed bacteria include at least four of the following: myxobacteria, Bacillus subtilis, yeast, phosphate-accumulating bacteria and ammonia-nitrogen bacteria.

[0165] Example 5

[0166] (1) adding a mixed enzyme such as ligninase and hemicellulase to a suitable amount of water to prepare a mixed enzyme solution, and then adding the prepared mixed enzyme solution to a sodium alginate solution to obtain a mixed solution A;

[0167] (2) adding the sterilized bioceramsite to a microbial mixed suspension D containing myxobacteria, Bacillus subtilis, yeast, polyphosphate bacteria, and ammonia nitrogen bacteria in a mass ratio of 1:3:2:2:3, shaking for adsorption, and standing for a period of time to obtain a bacterial liquid mixture B;

[0168] (3) adding the bacterial solution mixture B obtained in step (2) to the mixed solution A in step (1), and mixing them to obtain a mixed solution C;

[0169] (4) Adding calcium chloride solution to the mixed solution C to carry out a cross-linking reaction. After the cross-linking reaction is completed, washing with sterile water to obtain the novel bio-enzyme algaecide.

[0170] The difference between this embodiment and embodiment 1 is that the mass ratio of the myxobacterium group, the Bacillus subtilis group, the yeast group, the polyphosphate-accumulating bacteria group, and the ammonia-nitrogen bacteria group in the mixed bacterial community is 1:3:2:2:3, and the other steps are the same as those in embodiment 5.

[0171] Example 6

[0172] The difference between this embodiment and embodiment 5 is that the mass ratio of the myxobacterium group, the Bacillus subtilis group, the yeast group, the polyphosphate-accumulating bacteria group, and the ammonia-nitrogen bacteria group in the mixed bacterial community is 1:1:1:1:1, and the other steps are the same as those in embodiment 5.

[0173] Example 7

[0174] The difference between this embodiment and embodiment 5 is that the mass ratio of the myxobacterium group, the Bacillus subtilis group, the yeast group, the polyphosphate-accumulating bacteria group, and the ammonia-nitrogen bacteria group in the mixed bacterial community is 2:1:2:2:3, and the other steps are the same as those in embodiment 5.

[0175] Example 8

[0176] The difference between this embodiment and embodiment 5 is that the mass ratio of the myxobacterium group, the Bacillus subtilis group, the yeast group, the polyphosphate-accumulating bacteria group, and the ammonia-nitrogen bacteria group in the mixed bacterial community is 1:2:2:2:3, and the other steps are the same as those in embodiment 5.

[0177] Example 9

[0178] The difference between this embodiment and embodiment 5 is that the mass ratio of the myxobacterium group, the Bacillus subtilis group, the yeast group, the polyphosphate-accumulating bacteria group, and the ammonia-nitrogen bacteria group in the mixed bacterial community is 1:4:2:2:3, and the other steps are the same as those in embodiment 5.

[0179] Example 10

[0180] The difference between this embodiment and embodiment 5 is that the mass ratio of the myxobacterium group, the Bacillus subtilis group, the yeast group, the polyphosphate-accumulating bacteria group, and the ammonia-nitrogen bacteria group in the mixed bacterial community is 1:5:2:2:3, and the other steps are the same as those in embodiment 5.

[0181] Comparative Example 11

[0182] The difference between this embodiment and embodiment 5 is that there is no myxobacterium group, the mass ratio of the Bacillus subtilis group, the yeast group, the polyphosphate bacteria group, and the ammonia nitrogen bacteria group is 3:2:2:3, and the other steps are the same as those in embodiment 5.

[0183] Comparative Example 12

[0184] The difference between this embodiment and embodiment 5 is that there is no Bacillus subtilis group, the mass ratio of the myxobacterium group, the yeast group, the polyphosphate bacteria group, and the ammonia nitrogen bacteria group is 1:2:2:3, and the other steps are the same as those in embodiment 5.

[0185] Comparative Example 13

[0186] The difference between this embodiment and embodiment 5 is that there are no yeast flora and polyphosphate bacteria flora, the mass ratio of myxobacterium flora, Bacillus subtilis flora, polyphosphate bacteria flora and ammonia nitrogen bacteria flora is 1:3:2:3, and the other steps are the same as those in embodiment 5.

[0187] Comparative Example 14

[0188] The difference between this embodiment and embodiment 5 is that there is no polyphosphate bacteria group, the mass ratio of the myxobacterium group, the Bacillus subtilis group, the yeast group, and the ammonia nitrogen bacteria group is 1:3:2:3, and the other steps are the same as those in embodiment 5.

[0189] Comparative Example 15

[0190] The difference between this embodiment and embodiment 5 is that there is no ammonia nitrogen bacteria group, the mass ratio of the myxobacterium group, the Bacillus subtilis group, the yeast group, and the polyphosphate bacteria group is 1:3:2:2, and the other steps are the same as those in embodiment 5.

[0191] Under laboratory conditions, 2.5g of cross-linked enhanced composite bio-enzyme algaecide immobilized particles were used to treat water with a chlorophyll concentration of 118μg / L, an ammonia nitrogen concentration of 14.10mg / L, and a total phosphorus concentration of 2.74mg / L. An equal and appropriate amount of the fixed novel bio-enzyme algaecide was added to each group of water bodies in turn. After oscillating in a constant temperature oscillator at 150r / min and 30°C for 48h, the chlorophyll concentration, ammonia nitrogen concentration, and total phosphorus concentration in the water were measured to test the removal effect of different proportions of the bacterial flora in the mixed bacterial solution of the present invention. The results are as follows: Figure 2 shown.

[0192] Depend on Figure 2 It can be seen that when the mass ratio of the myxobacteria group, the Bacillus subtilis group, the yeast group, the polyphosphate bacteria group, and the ammonia nitrogen bacteria group in the mixed bacterial community is 1:3:2:2:3, the removal effect of algae, ammonia nitrogen, and total phosphorus in the water body is the best. From the comparison of Example 5 with Comparative Examples 9 and 10, it can be concluded that the myxobacteria group and the Bacillus subtilis group in the mixed bacterial solution have a greater effect on the removal of algae in the water body; from the comparison of Example 5 with Comparative Examples 11 and 12, it can be concluded that the yeast group and the polyphosphate bacteria group in the mixed bacterial solution have a greater effect on the removal of total phosphorus in the water body; from the comparison of Example 5 with Comparative Example 13, it can be concluded that the yeast group and the polyphosphate bacteria group in the mixed bacterial solution have a greater effect on the removal of ammonia nitrogen in the water body.

[0193] The above-mentioned water body biological enzyme algaecide was washed with sterile water for 3 times, and then added into water bodies with concentrations of 118μg / L, ammonia nitrogen concentration of 14.10mg / L, and total phosphorus concentration of 2.74mg / L, respectively, and equal and appropriate amounts of the fixed new biological enzyme algaecide were added to each group of water bodies in turn. After oscillating in a constant temperature oscillator at 150r / min and 30°C for 48h, the chlorophyll concentration, ammonia nitrogen concentration, and total phosphorus concentration in the water were measured. The above steps were repeated 3 times to test the reusability of the present invention. The test results are as follows: Figure 3 shown.

[0194] Depend on Figure 3 It can be seen that the new bio-enzyme algaecide still has a certain removal rate for algae, ammonia nitrogen and total phosphorus in the water after several repeated uses. In Example 5, the algae removal rate is above 70%, and the ammonia nitrogen and total phosphorus removal rates are above 60%, ensuring the stability of the algaecide in repeated use.

[0195] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for preparing a cross-linked enhanced composite bio-enzyme algaecide, characterized in that: The following steps are involved: Step 1: According to the key preparation parameters, a data sample set of the bio-enzyme algaecide is obtained, the data samples are normalized, and randomly divided into a training sample set and a test sample set; Step 2: Use the training sample set to train the LightGBM model to predict the algae removal efficiency, material stability, and reuse rate. Use the Bayesian optimization algorithm to optimize the hyperparameters of the LightGBM model and determine the best parameter combination. Step 3: Use the BO-LightGBM prediction model function as the fitness function of the genetic algorithm, the algae removal efficiency, material stability and reuse rate as the objective function, and the physical and chemical limitations of the parameters as constraints to perform multi-objective optimization and obtain the Pareto optimal solution set; Step 4: Prepare bio-enzyme algaecide based on the Pareto optimal solution set.

2. The method for preparing a cross-linked enhanced composite bio-enzyme algaecide according to claim 1, characterized in that: In step 1, the key parameters include: Enzyme concentration E, biological ceramsite ratio G, microbial genus ratio M, sodium alginate solution concentration A, calcium chloride solution concentration C, cross-linking reaction time T, oscillation speed O and standing time S.

3. The method for preparing a cross-linked enhanced composite bio-enzyme algaecide according to claim 1, characterized in that: Step 2 includes the following steps: (21) The LightGBM model was trained using the training sample set to predict algae removal efficiency, material stability, and reuse rate, and the hyperparameters were optimized, including learning rate, minimum batch size, column sampling ratio, number of estimators, L2 regularization parameter, and maximum depth of the tree; (22) Use the Bayesian optimization algorithm to search for the optimal hyperparameter combination, with the mean square error as the optimization target; (23) The reliability of the model was evaluated using three performance indicators: root mean square error, mean absolute error, and mean absolute percentage error.

4. The method for preparing a cross-linked enhanced composite bio-enzyme algaecide according to claim 3, characterized in that: The calculation model of the root mean square error, mean absolute error and mean absolute percentage error includes: In the formula, n is the number of data samples, and are the experimental value and the predicted value, respectively.

5. The method for preparing a cross-linked enhanced composite bio-enzyme algaecide according to claim 1, characterized in that: In step 3, the objective functions of algae removal efficiency, material stability and reuse rate include: f1(E,G,M,A,C,T,O,S)=LightGBM(E,G,M,A,C,T,O,S) f2(E,G,M,A,C,T,O,S)=LightGBM(E,G,M,A,C,T,O,S) f3(E,G,M,A,C,T,O,S)=LightGBM(E,G,M,A,C,T,O,S) Among them, f1 is the algae removal efficiency predicted by the LightGBM model, f2 is the material stability predicted by the LightGBM model, and f3 is the reuse rate predicted by the LightGBM model.

6. The method for preparing a cross-linked enhanced composite bio-enzyme algaecide according to claim 5, characterized in that: In step 3, the BO-LightGBM prediction model includes: In the formula, θ * is the optimal hyperparameter combination, and θ represents the hyperparameter.

7. The method for preparing a cross-linked enhanced composite bio-enzyme algaecide according to claim 6, characterized in that: In step 3, a fuzzy decision method is used to select an optimal solution from the Pareto solution set, as follows: Each solution is scored based on its distance to the positive ideal solution and the negative ideal solution. The scoring formula for each solution is as follows: In the formula, S i is the score corresponding to the ith Pareto solution, f i - is the distance from the ith Pareto solution to the negative ideal solution, f i + is the distance from the ith Pareto solution to the positive ideal solution, f i - and f i + The calculation formula is as follows: In the formula, m is the number of optimization objectives, x ij is the ith Pareto solution under the jth objective, and is the input value corresponding to the negative ideal solution and the positive ideal solution under the jth objective, and the calculation formula is as follows: Calculate the percentage improvement of each Pareto solution, where the improvement of each objective is: The overall improvements for each solution are: In the formula, Imp ij is the improvement of the jth objective of each i-th Pareto solution, Org j,ave is the original mean value of the jth target, Opt ij is the optimal value of the jth objective of each i-th Pareto solution, Impoverall i is the overall improvement of each i Pareto solution.

8. The method for preparing a cross-linked enhanced composite bio-enzyme algaecide according to any one of claims 1 to 7, characterized in that: It also includes performing the following operations based on the obtained optimal solution: (51) adding an enzyme to a suitable amount of water to prepare an enzyme solution, and then adding the prepared enzyme solution to the sodium alginate solution to obtain a mixed solution A; (52) Add the sterilized bioceramsite to the microbial mixed suspension D, shake and adsorb, and let stand for a period of time to obtain a bacterial suspension mixture B; (53) adding the bacterial solution mixture B obtained in step (2) to the mixed solution A in step (51), and mixing them to obtain a mixed solution C; (54) Add calcium chloride solution to the mixed solution C to carry out a cross-linking reaction. After the cross-linking reaction is completed, wash with sterile water to obtain the novel bio-enzyme algaecide.

9. A cross-linked enhanced composite bio-enzyme algaecide, characterized in that: The method is prepared by the method according to any one of claims 1 to 7.

10. The cross-linked enhanced composite bio-enzyme algaecide according to claim 9, characterized in that: The components and mass percentages of the cross-linked enhanced composite bio-enzyme algaecide are as follows: 10-15 parts of biological ceramsite, 15-25 parts of mixed bacteria, 30-40 parts of hemicellulase, 30-40 parts of hemicellulase, The mixed bacteria include at least four of the following: myxobacteria, Bacillus subtilis, yeast, polyphosphate bacteria and ammonia nitrogen bacteria.

Images