Prediction method for photocatalytic degradation efficiency of photocatalyst, and related product and application thereof

Abstract

The invention discloses a method for predicting the photocatalytic degradation efficiency of a photocatalyst as well as a related product and application thereof, and relates to the field of design and preparation of semiconductor photocatalysts. The preparation conditions and doped ion characteristics of the metal ion-doped gamma-Bi2MoO6 photocatalyst are used as the input characteristics of the model, the photocatalytic degradation efficiency is used as the output, the prediction model of the photocatalytic degradation rate of the metal ion-doped gamma-Bi2MoO6 photocatalyst is constructed, and it is verified that the model has the excellent prediction capability and can be used for predicting the photocatalytic degradation rate of the metal ion-doped gamma-Bi2MoO6 photocatalyst. The design period and the preparation cost of the photocatalyst can be effectively shortened, the method is green and environment-friendly, and a new way is provided for design and preparation of the high-performance gamma-Bi2MoO6 photocatalyst.

Description

Technical Field

[0001] The present invention relates to the field of design and preparation of semiconductor photocatalysts, and in particular to a method for predicting the photocatalytic degradation efficiency of photocatalysts and related products and applications thereof. Background Art

[0002] Bi2MoO6 is a common N-type direct bandgap semiconductor material. It has three crystalline phases with the general formula (Bi2O3)-(Mo n O 3n When n=1, n=2 and n=3, the structure shows γ phase (γ-Bi2MoO6), β phase (β-Bi2Mo2O9) and α phase (α-Bi2Mo3O 12 ). Bismuth molybdate crystals with three structures can be used in pollution degradation, batteries and capacitors, and gas-sensitive response. Among them, γ-Bi2MoO6 exhibits excellent photocatalytic performance due to its unique Orville-type layered compound structure, physical and chemical properties, good thermal stability, and low color permeation rate.

[0003] In order to improve the photocatalytic performance of γ-Bi2MoO6, common methods include element doping, precious metal loading, quantum dot modification and heterostructure construction. The element doping modification method is characterized by good controllability, wide applicability and low processing cost, and has been widely used in the modification of γ-Bi2MoO6. For example, the effect of transition metal doping on the photocatalytic activity of γ-Bi2MoO6 was explored. The samples showed high degradation performance under visible light, which was attributed to the reduced nanoparticle size, reduced band gap, enhanced visible light absorption and effective photogenerated carrier separation. Since intuitive judgment and "trial and error" experiments are still the main methods, but their disadvantages are many influencing factors, long test cycle and high cost, it is challenging to effectively and controllably improve the photocatalytic performance.

[0004] In view of this, the present invention is proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a method for predicting the photocatalytic degradation efficiency of a photocatalyst and related products and applications thereof.

[0006] The present invention is achieved in that:

[0007] In a first aspect, an embodiment of the present invention provides a method for training a prediction model of the photocatalytic degradation efficiency of a photocatalyst, wherein the photocatalyst comprises a γ-Bi2MoO6 photocatalyst doped with metal ions, comprising:

[0008] Obtaining the preparation conditions and doping ion characteristics of the training samples and their corresponding annotation results; the annotation results include labels representing the photocatalytic degradation efficiency of the samples;

[0009] Inputting the preparation conditions and doping ion characteristics of the training samples into a pre-built machine learning model to obtain prediction results;

[0010] Based on the prediction results and the annotation results, the parameters of the machine learning model are updated to obtain a prediction model.

[0011] In a second aspect, an embodiment of the present invention provides a method for predicting the photocatalytic degradation efficiency of a photocatalyst, which comprises:

[0012] Obtaining the preparation conditions and doping ion characteristics of the sample to be tested; the preparation conditions and doping ion characteristics are the preparation conditions and doping ion characteristics described in the above embodiment;

[0013] The preparation conditions and doping ion characteristics of the sample to be tested are input into the prediction model trained by the training method described in the above embodiment to obtain a prediction result.

[0014] In a third aspect, embodiments of the present invention provide application of the method for predicting the photocatalytic degradation efficiency of a photocatalyst as described in the aforementioned embodiments in the preparation or screening of photocatalysts.

[0015] In a fourth aspect, an embodiment of the present invention provides a device for predicting the photocatalytic degradation efficiency of a photocatalyst, comprising:

[0016] An acquisition module, used to acquire the preparation conditions and doping ion characteristics of the sample to be tested; the preparation conditions and doping ion characteristics are the preparation conditions and doping ion characteristics described in the above embodiment;

[0017] The prediction module is used to input the preparation conditions and doping ion characteristics of the sample to be tested into the prediction model trained by the training method described in the above embodiment to obtain the prediction result of the sample to be tested.

[0018] In a fifth aspect, an embodiment of the present invention provides an electronic device, which includes a processor and a memory, wherein the memory is used to store a program, and when the program is executed by the processor, the processor implements the prediction method described in the above embodiment.

[0019] In a sixth aspect, an embodiment of the present invention provides a computer-readable medium having a computer program stored thereon, and when the computer program is executed by a processor, the prediction method described in the foregoing embodiment is implemented.

[0020] The present invention has the following beneficial effects:

[0021] By taking the preparation conditions and doping ion characteristics of metal ion-doped γ-Bi2MoO6 photocatalysts as the input features of the model and the photocatalytic degradation efficiency as the output, a prediction model for the photocatalytic degradation rate of metal ion-doped γ-Bi2MoO6 photocatalysts was constructed. It has been verified that the model has excellent predictive ability, can effectively shorten the design cycle and preparation cost of photocatalysts, is green and environmentally friendly, and provides a new way for the design and preparation of high-performance γ-Bi2MoO6 photocatalysts. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 It is a summary diagram of all input feature parameters;

[0024] Figure 2 It is a diagram of a photocatalytic reactor and a light meter;

[0025] Figure 3 (a) shows the experimental and model-predicted results for 2% Er doping 3+ (a) Comparison of the degradation efficiency of γ-Bi2MoO6 photocatalyst for RhB solution; (b) Er-doped γ-Bi2MoO6 with different doping ratios (n(Er):n(Bi)=0.5%, 1%, 1.5%, 2% and 2.5%) 3+ The degradation efficiency of γ-Bi2MoO6 photocatalyst on RhB solution after 70 minutes of illumination;

[0026] Figure 4 (a) shows Cu doped with different doping ratios (n(Cu):n(Bi)=2%, 4%, 6%, 8% and 10%) 2+ The degradation efficiency of γ-Bi2MoO6 photocatalyst for RhB solution under experimental and model prediction conditions; (b) 8% Cu doped 2 + The degradation efficiency of γ-Bi2MoO6 photocatalyst for RhB solution at different precursor pH values ​​(pH = 3, 5, 8, 10) is shown in the figure. The experimental results and model prediction results both show the degradation efficiency after 70 minutes of illumination.

[0027] Figure 5 (a) shows Nd doped with different doping ratios (n(Nd):n(Bi)=2%, 4%, 6%, 8% and 10%) 3+The degradation efficiency of γ-Bi2MoO6 photocatalyst for RhB solution under experimental and model prediction conditions; (b) 4% Nd doped 3 + Degradation efficiency of RhB solution by γ-Bi2MoO6 photocatalyst at different catalyst / pollutant mass ratios. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the technical scheme in the embodiments of the present invention will be described clearly and completely below. If the specific conditions are not specified in the embodiments, they are carried out according to conventional conditions or conditions recommended by the manufacturer. If the manufacturer of the reagents or instruments used is not specified, they are all conventional products that can be purchased commercially.

[0029] In order to solve the problems of low efficiency, high cost and complex preparation of photocatalysts in the prior art, the inventors of the present invention have carefully designed and selected 806 data points covering different experimental conditions and doping ion properties, and built a comprehensive photocatalyst performance database. Based on these data, a photocatalytic degradation rate prediction model of γ-Bi2MoO6 photocatalysts doped with transition metals and rare earth metal ions was developed using machine learning technology. The model has good predictive performance for the photocatalytic degradation efficiency of metal-doped γ-Bi2MoO6 photocatalysts, can predict the behavior of photocatalytic materials in different environments, and provide guidance for experimental optimization. The present invention uses machine learning algorithms combined with materials science to simplify the investment of resources and time and accelerate the innovation process.

[0030] In one aspect, an embodiment of the present invention provides a method for training a prediction model of the photocatalytic degradation efficiency of a photocatalyst, wherein the photocatalyst comprises a γ-Bi2MoO6 photocatalyst doped with metal ions, comprising:

[0031] Obtaining the preparation conditions and doping ion characteristics of the training samples and their corresponding annotation results; the annotation results include labels representing the photocatalytic degradation efficiency of the samples;

[0032] Inputting the preparation conditions and doping ion characteristics of the training samples into a pre-built machine learning model to obtain prediction results;

[0033] Based on the prediction results and the annotation results, the parameters of the machine learning model are updated to obtain a prediction model.

[0034] In some embodiments, the preparation conditions include any one or more of doping ratio, temperature, time, pollutant type, mass ratio of catalyst to pollutant, pH value, band gap, light wavelength and illumination time.

[0035] Specifically, the doping ratio is the molar ratio of the doping ion to the Bi element. The pH value is the acidity or alkalinity of the precursor solution of the photocatalyst during the preparation process. The time is the time of different stages in the preparation process, including the time of all steps, such as solution mixing, reaction, cooling, etc. The illumination time refers to the time that the catalyst treats pollutants under illumination conditions in the photocatalytic degradation experiment. Specifically, it is the time interval from the start of illumination to the end of illumination.

[0036] The temperature includes any one or more of the preparation temperature, mixing temperature and reaction temperature of the precursor during the preparation process.

[0037] The preparation temperature includes: the temperature of the metal salt precursor and the doping element precursor during the preparation process. Metal salt precursor, for example, Bi(NO3)3·5H2O and MoO3 as metal salt precursors of Bi and Mo. Doping element precursor: according to the metal ions to be doped (such as Sc, Ti, V, La, Ce, Pr, etc.), select the corresponding metal salt. For example, Er(NO3)3·6H2O is used to dope Er 3 +.

[0038] The mixing temperature includes: the temperature during the mixing process of the metal salt precursor and the doping element precursor.

[0039] The reaction temperature includes: the reaction temperature at which a mixed solution of a metal salt precursor and a doping element precursor further reacts to generate a photocatalyst.

[0040] In some embodiments, taking the preparation method of Er-doped γ-Bi2MoO6 photocatalyst as an example, the preparation method is described, which includes the following steps.

[0041] (1) Dissolve the precursor:

[0042] Dissolve Bi(NO3)3·5H2O and MoO3 in appropriate amount of deionized water respectively and stir until completely dissolved.

[0043] Dissolve the precursor of the doping element (such as Er(NO3)3·6H2O) in an appropriate amount of deionized water and stir until it is completely dissolved.

[0044] (2) Mixed solution:

[0045] Mix the dissolved Bi(NO3)3·5H2O and MoO3 solutions and stir evenly.

[0046] According to the required doping ratio, the precursor solution of the doping element is added to the Bi-Mo mixed solution and stirred until uniform.

[0047] Use a magnetic stirrer or mechanical agitator to ensure that the solution is thoroughly mixed to avoid localized high or low concentrations.

[0048] (3) Adjust pH value:

[0049] Use dilute hydrochloric acid or ammonia to adjust the pH of the solution. The pH range is usually between 1-13, and the specific value is determined according to the experimental design. Stir the solution to ensure that the pH is evenly distributed.

[0050] (4) Reaction process:

[0051] Refers to the step of chemical reaction in the mixed solution to form the target compound (such as γ-Bi2MoO6). This step usually involves hydrolysis, condensation, precipitation and other reactions, and finally forms a uniform gel or precipitate.

[0052] 4.1. Hydrolysis and condensation reaction:

[0053] In the mixed solution, metal ions (such as Bi 3+ and Mo 6+ ) will undergo hydrolysis reaction with water to generate precursors of metal hydroxides or oxides.

[0054] These precursors further undergo condensation reactions to form a uniform gel network structure. The reaction temperature is usually controlled at 60-80°C, and the specific temperature is adjusted according to the system.

[0055] 4.2. Precipitation reaction:

[0056] In some cases, it may be necessary to promote the formation of the precipitate by adding a precipitant (such as NaOH, NH3·H2O, etc.).

[0057] During the precipitation reaction, the control of temperature and pH value is crucial. Generally, it is controlled between room temperature and 60°C, and the pH value is adjusted according to the specific reaction system.

[0058] 4.3 Aging and drying:

[0059] The formed gel or precipitate needs to be aged to improve its structural stability and uniformity. The aging temperature is generally controlled at room temperature to 60°C.

[0060] The aged gel or precipitate needs to be dried to remove excess water. The drying temperature is generally controlled at 60-100° C., and the specific temperature is adjusted according to the system. In some embodiments, the doping ion characteristics include: physical and chemical property parameters of the doping ions.

[0061] In some embodiments, the doping ion characteristics include any one or more of atomic mass, radius, electronegativity, resistivity, ionization energy, binding energy, density, melting point and boiling point.

[0062] Through Shapley value analysis, the atomic masses (Cu 63.55 < Nd 144.24 < Er 167.26) and boiling points (Cu 2835 < Er 3141 < Nd 3347) of Cu, Er, and Nd three elements show a negative correlation trend with the photocatalytic degradation efficiency.

[0063] In some embodiments, the metal ions include: transition metal ions and / or rare earth metal ions.

[0064] In some embodiments, the transition metals include: any one or more of scandium (Sc), titanium (Ti), vanadium (V), chromium (Cr), manganese (Mn), iron (Fe), cobalt (Co), nickel (Ni), copper (Cu), zinc (Zn), yttrium (Y), zirconium (Zr), niobium (Nb), molybdenum (Mo), technetium (Tc), ruthenium (Ru), rhodium (Rh), palladium (Pd), silver (Ag), cadmium (Cd), lutetium (Lu), hafnium (Hf), tantalum (Ta), tungsten (W), rhenium (Re), osmium (Os), iridium (Ir), platinum (Pt), gold (Au), mercury (Hg), lawrencium (Lr), rutherfordium (Rf), dubnium (Db), seaborgium (Sg), bohrium (Bh), hassium (Hs), meitnerium (Mt), darmstadtium (Ds), roentgenium (Rg), copernicium (Cn).

[0065] In some embodiments, the rare earth metals include: any one or more of scandium (Sc), yttrium (Y), lanthanum (La), cerium (Ce), praseodymium (Pr), neodymium (Nd), promethium (Pm), samarium (Sm), europium (Eu), gadolinium (Gd), terbium (Tb), dysprosium (Dy), holmium (Ho), erbium (Er), ytterbium (Tm), lutetium (Lu), and tantalum (Ta).

[0066] In some embodiments, the machine learning model includes: any one of linear regression, partial least squares regression, Gaussian regression, decision tree, neural network, extreme gradient boosting, adaptive boosting, and gradient boosting.

[0067] It can be understood that the categories and quantities of training samples are conventionally selectable by those skilled in the art, and the total number of training samples and the number of training samples of various categories (for example, different preparation processes, different doping ion characteristics) can be any value in ≥10, 50, 100, 200, 300, 400, and 500 or the range between any two of them.

[0068] In some embodiments, the label can be a character or a string. The content of the prediction result corresponds to the content of the annotation result.

[0069] On the other hand, the embodiments of the present invention provide a method for predicting the photocatalytic degradation efficiency of a photocatalyst, which includes:

[0070] Obtaining the preparation conditions and doping ion characteristics of the sample to be tested; the preparation conditions and doping ion characteristics are the preparation conditions and doping ion characteristics described in any of the above embodiments;

[0071] The preparation conditions and doping ion characteristics of the sample to be tested are input into the prediction model trained by the training method described in any of the above embodiments to obtain a prediction result.

[0072] On the other hand, an embodiment of the present invention provides the use of the method for predicting the photocatalytic degradation efficiency of a photocatalyst as described in any of the aforementioned embodiments in the preparation or screening of photocatalysts.

[0073] On the other hand, an embodiment of the present invention provides a device for predicting the photocatalytic degradation efficiency of a photocatalyst, comprising:

[0074] An acquisition module, used to acquire the preparation conditions and doping ion characteristics of the sample to be tested; the preparation conditions and doping ion characteristics are the preparation conditions and doping ion characteristics described in any of the above embodiments;

[0075] The prediction module is used to input the preparation conditions and doping ion characteristics of the sample to be tested into the prediction model trained by the training method described in any of the above embodiments to obtain the prediction result of the sample to be tested.

[0076] The modules described in the embodiments of the present invention may be stored in a memory in the form of software or firmware or solidified in the operating system (OS) of the electronic device provided by the present application, and may be executed by a processor in the electronic device. At the same time, the data and program codes required to execute the above modules may be stored in the memory.

[0077] On the other hand, an embodiment of the present invention further provides an electronic device, which includes a processor and a memory, wherein the memory is used to store a program, and when the program is executed by the processor, the processor implements the prediction method described in the above embodiment.

[0078] An electronic device may include a memory, a processor, a bus, and a communication interface, wherein the memory, the processor, and the communication interface are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, these components may be electrically connected to each other via one or more buses or signal lines.

[0079] The memory can be, but is not limited to, random access memory (RAM), read only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable read-only memory (EEPROM), etc.

[0080] The processor can be an integrated circuit chip with signal processing capabilities. The processor 120 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0081] The electronic device can be a server, a cloud platform, a mobile phone, a tablet computer, a laptop computer, an ultra-mobile personal computer (UMPC), a handheld computer, a netbook, a personal digital assistant (PDA), a wearable electronic device, a virtual reality device, etc. Therefore, the embodiments of the present application do not limit the type of electronic device.

[0082] In addition, an embodiment of the present invention further provides a computer-readable medium, on which a computer program is stored. When the computer program is executed by a processor, the prediction method described in any of the above embodiments is implemented.

[0083] In some embodiments, the computer-readable medium may be a general storage medium, such as a mobile disk, a hard disk, etc.

[0084] The features and performance of the present invention are further described in detail below in conjunction with the embodiments.

[0085] Example 1

[0086] A method for training a prediction model for the photocatalytic degradation efficiency of a photocatalyst comprises the following steps.

[0087] S1: After extensive research on the photocatalytic performance of doped γ-Bi2MoO6 from 2011 to 2023, two key factors affecting its photocatalytic performance were identified ( Figure 1 ): preparation conditions and doping ion characteristics. Among them, the preparation conditions include: doping ratio (molar ratio of doping ions to Bi elements), temperature (including preparation temperature, mixing temperature and reaction temperature of the precursor solution, wherein the preparation temperature includes: the temperature of the metal salt precursor and the doping element precursor during the preparation process, the mixing temperature includes: the temperature of the metal salt precursor and the doping element precursor during the mixing process, and the reaction temperature includes: the reaction temperature when the mixed solution after the metal salt precursor and the doping element precursor are further reacted to generate a photocatalyst), time (including the time of all different steps), pollutant type, mass ratio of catalyst to pollutant, pH value (acidity and alkalinity of the precursor solution of the photocatalyst), band gap, light wavelength and illumination time (the time interval from the start of illumination to the end of illumination). Doping ion characteristics include: physical and chemical properties such as atomic mass, radius, electronegativity, resistivity, ionization energy, binding energy, density, melting point and boiling point. And the photocatalytic degradation efficiency is used as the output variable. With these parameters, 806 datasets were selected from 29 relevant papers to construct a comprehensive database for developing and training predictive models to optimize the design and performance of photocatalysts.

[0088] S2: Using machine learning methods, the following four steps are carried out: data collection and construction, data analysis and preprocessing, model learning and optimization, and model evaluation and application. Programming is done using the JupyterNotebook platform of Anaconda software, which supports languages ​​such as Python and R. Data preprocessing uses Python libraries NumPy, Pandas, and Scikit-learn, and categorical data is converted to numeric type through one-hot encoding. After that, the data is divided into training and test sets for training and evaluating the model. Models such as linear regression, partial least squares regression, Gaussian regression, decision tree, neural network, extreme gradient boosting, adaptive boosting, and gradient boosting are selected. When evaluating the model, indicators such as mean square error, root mean square error, mean absolute error, and determination coefficient are used, and K-fold cross validation is used to ensure the stability and accuracy of the model.

[0089] The determination coefficient of the cross-validation model was 0.942, and the residual value was controlled within ±15%.

[0090] Example 2

[0091] The model constructed in Example 1 was experimentally verified.

[0092] In order to verify the prediction ability of the improved extreme gradient lifting model, three sets of simple photocatalytic experiments were conducted in this example. 3+ , Cu 2+ and Nd 3+ The degradation efficiency of γ-Bi2MoO6 photocatalyst was compared with the model prediction results. 3+ and Cu 2+ The degradation efficiency of the doped γ-Bi2MoO6 photocatalyst under different conditions is close to the model prediction results, especially in the initial stage. The model prediction is usually higher than the experimental value, indicating that it can capture the photocatalytic efficiency under ideal conditions. 2+ and Nd 3+ The model also showed good predictive performance for doped photocatalysts. In addition, the experiment also found that the activity of the photocatalyst was affected by the pH value of the precursor and the mass ratio of catalyst to pollutant. The Shapley value analysis further confirmed the reliability of the model prediction results.

[0093] The experimental device, i.e., the photocatalytic activity test device, consists of four parts: light source, magnetic stirrer, photocatalytic reactor, and photocatalytic adjustable DC regulated power supply ( Figure 2 ). The light source is a 500W xenon lamp, which is inserted into the photocatalytic reactor to ensure that the light can directly irradiate the working electrode; the function of the magnetic stirrer is to ensure that the dye concentration remains in a relatively uniform state; the photocatalytic reactor is a quartz reflux cooling sleeve, and the quartz material is used to ensure that the ultraviolet light can effectively pass through the sleeve. During the entire reaction, condensed water is continuously introduced into the sleeve to ensure that the temperature of the entire reaction system is within a certain range.

[0094] Prepare 50mL of 10mg / L Rhodamine B solution, pour the prepared Rhodamine B solution and 50mg catalyst into the photocatalytic reactor as a simulated dye, and take 5mL of the reactor liquid with a 5mL pipette as sample #1. Do not turn on the light source, stir continuously for 30min, and first perform a 30min dark reaction to allow the dye and catalyst to reach an adsorption-desorption equilibrium state. After the dark reaction, take 5mL of the reactor liquid with a 5mL pipette as sample #2. Then, turn on a 500W xenon lamp (illumination intensity: 4.72E+04Lux, Err: 0.13E+04Lux), start the photoelectrocatalytic reaction, and the photoelectrocatalytic reaction lasts for 70min. During the entire light reaction process, take 5mL of the suspension with a 5mL pipette every 10min, and keep the suspension for a certain period of time, and then sort them into sample #3, sample #4...sample #9.

[0095] After the experiment, UV1901PC ultraviolet spectrophotometer was used to measure the supernatant of all samples within the wavelength range of 450nm-600nm, and the concentration of pollutants was recorded. The degradation rate of Rhodamine B was calculated according to formula 1. The experimental results are shown in the attached Figure 3 .

[0096] D=(A0-A t ) / A0×100% Formula 1;

[0097] In formula 1: D-degradation rate, %; A0-initial absorbance of rhodamine B; A t -The absorbance of Rhodamine B at degradation time t.

[0098] The results showed that the element-doped γ-Bi2MoO6 had no catalytic degradation effect on Rhodamine B after the dark reaction stage. In the light reaction stage, the degradation efficiency of Rhodamine B gradually increased with the extension of photocatalytic time. After the reaction, 2% Er 3+ Doped γ-Bi2MoO6 photocatalyst ( Figure 3 ), in the experiment, the degradation efficiency of Rhodamine B solution was 71.08%, and after 70 minutes of illumination, the degradation efficiency predicted by the model was 84.74%. 3+ For the doped γ-Bi2MoO6, as the doping ratio increases from 0.5% to 2.5%, the degradation efficiency increases first and then decreases, and the best degradation efficiency is achieved when the doping ratio is 2%. 2+ The doped γ-Bi2MoO6 photocatalyst showed the maximum degradation efficiency under experimental and model prediction at 8% doping ratio, indicating that Cu 2+ Ions can improve the separation efficiency of photogenerated charges and enhance degradation performance. 2+ Doped γ-Bi2MoO6 photocatalyst ( Figure 4 ), both the experiments and model predictions under different precursor pH conditions showed that the degradation efficiency of Rhodamine B was the highest at pH = 8. 3+ Doped γ-Bi2MoO6 photocatalyst ( Figure 5 ) When the doping ratio is 4%, both the experiment and the model prediction obtain the maximum degradation efficiency, but it is similar to Cu 2+ Compared with Nd 3 + Finally, 4% Nd 3+Experiments and model predictions of doped γ-Bi2MoO6 at different catalyst / pollutant mass ratios show that the photocatalytic degradation efficiency gradually increases with the increase of the mass ratio, which highlights the significant effect of catalyst dosage and pollutant concentration on the photocatalytic activity. This is because under the action of light, the valence band electrons of element-doped γ-Bi2MoO6 can be excited to the conduction band to form electrons and holes, which interact with O2 and H2O adsorbed on its surface to generate free radicals with strong oxidative decomposition ability, which, as a catalyst material, can efficiently catalyze the degradation of rhodamine B.

[0099] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for training a prediction model of the photocatalytic degradation efficiency of a photocatalyst, wherein the photocatalyst comprises a γ-Bi2MoO6 photocatalyst doped with metal ions, characterized in that: It includes: Obtaining the preparation conditions and doping ion characteristics of the training samples and their corresponding annotation results; the annotation results include labels representing the photocatalytic degradation efficiency of the samples; Inputting the preparation conditions and doping ion characteristics of the training samples into a pre-built machine learning model to obtain prediction results; Based on the prediction results and the annotation results, the parameters of the machine learning model are updated to obtain a prediction model.

2. The training method according to claim 1, characterized in that: The preparation conditions include: any one or more of doping ratio, temperature, time, pollutant type, mass ratio of catalyst to pollutant, pH value, band gap, light wavelength and illumination time; Optionally, the temperature includes: any one or more of the preparation temperature, mixing temperature and reaction temperature of the precursor solution; Optionally, the pH value includes: the pH value of the photocatalyst precursor solution; Optionally, the time includes: reaction time at different stages of the preparation process.

3. The training method according to claim 1, characterized in that: The doping ion characteristics include: physical and chemical property parameters of the doping ions.

4. The training method according to claim 3, characterized in that: The doping ion characteristics include: any one or more of atomic mass, radius, electronegativity, resistivity, ionization energy, binding energy, density, melting point and boiling point.

5. The training method according to any one of claims 1 to 4, characterized in that: The metal ions include: transition metal ions and / or rare earth metal ions; Optionally, the machine learning model includes any one of: linear regression, partial least squares regression, Gaussian regression, decision tree, neural network, extreme gradient boosting, adaptive boosting and gradient boosting.

6. A method for predicting the photocatalytic degradation efficiency of a photocatalyst, characterized in that: It includes: Obtaining the preparation conditions and doping ion characteristics of the sample to be tested; The preparation conditions and doping ion characteristics are the preparation conditions and doping ion characteristics described in any one of claims 1 to 5; The preparation conditions and doping ion characteristics of the sample to be tested are input into the prediction model trained by the training method described in any one of claims 1 to 5 to obtain a prediction result.

7. Use of the method for predicting the photocatalytic degradation efficiency of a photocatalyst as claimed in claim 6 in preparing or screening photocatalysts.

8. A device for predicting the photocatalytic degradation efficiency of a photocatalyst, characterized in that: It includes: An acquisition module, used to obtain the preparation conditions and doping ion characteristics of the sample to be tested; The preparation conditions and doping ion characteristics are the preparation conditions and doping ion characteristics described in any one of claims 1 to 5; The prediction module is used to input the preparation conditions and doping ion characteristics of the sample to be tested into the prediction model trained by the training method according to any one of claims 1 to 5 to obtain the prediction result of the sample to be tested.

9. An electronic device, characterized in that: It includes a processor and a memory, wherein the memory is used to store a program. When the program is executed by the processor, the processor implements the prediction method according to claim 6.

10. A computer-readable medium, characterized in that The computer readable medium stores a computer program, and when the computer program is executed by a processor, the prediction method according to claim 6 is implemented.

Images