Odor decomposition optimization method and device adopting enzymatic reaction

Abstract

The invention provides a peculiar smell decomposition optimization method and device adopting an enzymatic reaction, and relates to the technical field of peculiar smell decomposition, and the method comprises the following steps: detecting and obtaining peculiar smell concentration information and peculiar smell component information; optimizing the enzyme type and enzyme concentration in the enzymatic reaction to obtain the optimal enzyme type and optimal enzyme concentration, and preparing to obtain a basic enzymatic reaction solution; predicting the pH of an odor source according to the odor concentration information and the odor component information to obtain the pH information of the odor source; according to the pH information of the peculiar smell source, adjusting and optimizing the pH of the basic enzymatic reaction solution to obtain an optimal pH value, adjusting the pH of the basic enzymatic reaction solution to obtain an enzymatic reaction solution, and decomposing the peculiar smell of the peculiar smell source. According to the method, the technical problem of low reaction efficiency caused by lack of systematic optimization schemes due to the fact that enzymatic reaction conditions are determined based on experience in the prior art can be solved, and the technical effect of improving the accuracy and efficiency of peculiar smell decomposition is achieved.

Description

Technical Field

[0001] This application relates to the technical field of odor decomposition, and particularly to an optimized method and device for odor decomposition using enzymatic reactions. Background Art

[0002] Common odors on clothing (such as cigarette smell, shoe odor, etc.) not only affect the comfort of the wearer but may also have a negative impact on the senses of others. Traditional cleaning methods usually rely on chemical cleaners. Although they can remove odors to a certain extent, they may damage the clothing and also cause certain pollution to the environment.

[0003] In recent years, the application of biological enzymes in the cleaning industry has gradually received attention. Due to its high efficiency and specificity, enzymatic reactions can degrade specific odor components, showing good deodorization effects. However, the activity of enzymes is affected by various factors, especially the pH value and the reaction environment. Different odor components and concentrations also have different requirements for enzymatic reactions.

[0004] Existing methods mostly rely on experience to determine the conditions of enzymatic reactions and lack a systematic optimization scheme, resulting in low reaction efficiency. Summary of the Invention

[0005] The purpose of this application is to provide an optimized method and device for odor decomposition using enzymatic reactions to solve the technical problem in the prior art that due to mostly relying on experience to determine the conditions of enzymatic reactions and lacking a systematic optimization scheme, the reaction efficiency is low.

[0006] In view of the above problems, this application provides an optimized method and device for odor decomposition using enzymatic reactions.

[0007] In the first aspect, this application provides an optimized method for odor decomposition using enzymatic reactions. The optimized method for odor decomposition using enzymatic reactions is implemented through an optimized device for odor decomposition using enzymatic reactions. Among them, the optimized method for odor decomposition using enzymatic reactions includes: receiving odor characteristic information obtained by detecting the odor to be decomposed currently, where the odor characteristic information includes odor concentration information and odor component information; optimizing the enzyme type and enzyme concentration in the enzymatic reaction according to the odor concentration information and odor component information to obtain the optimal enzyme type and the optimal enzyme concentration, and configuring to obtain a basic enzymatic reaction solution; predicting the pH of the odor source according to the odor concentration information and odor component information to obtain odor source pH information; optimizing the pH adjustment of the basic enzymatic reaction solution according to the odor source pH information to obtain the optimal pH value, adjusting the pH of the basic enzymatic reaction solution to obtain an enzymatic reaction solution, and decomposing the odor of the odor source.

[0008] Second aspect, the present application also provides an odor decomposition optimization device using enzymatic reactions, which is used to execute an odor decomposition optimization method using enzymatic reactions as described in the first aspect. Among them, the odor decomposition optimization device using enzymatic reactions includes: an odor feature acquisition module, which is used to receive odor feature information obtained by detecting the odor to be decomposed currently. Among them, the odor feature information includes odor concentration information and odor component information; a first optimization module, which is used to optimize the enzyme type and enzyme concentration in the enzymatic reaction according to the odor concentration information and odor component information, obtain the optimal enzyme type and the optimal enzyme concentration, and configure to obtain a basic enzymatic reaction solution; an odor source pH prediction module, which is used to predict the pH of the odor source according to the odor concentration information and odor component information, and obtain the odor source pH information; a second optimization module, which is used to optimize the pH adjustment of the basic enzymatic reaction solution according to the odor source pH information, obtain the optimal pH value, adjust the pH of the basic enzymatic reaction solution, obtain an enzymatic reaction solution, and decompose the odor of the odor source.

[0009] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0010] Receiving odor feature information obtained by detecting the odor to be decomposed currently. Among them, the odor feature information includes odor concentration information and odor component information; optimizing the enzyme type and enzyme concentration in the enzymatic reaction according to the odor concentration information and odor component information, obtaining the optimal enzyme type and the optimal enzyme concentration, and configuring to obtain a basic enzymatic reaction solution; predicting the pH of the odor source according to the odor concentration information and odor component information, and obtaining the odor source pH information; optimizing the pH adjustment of the basic enzymatic reaction solution according to the odor source pH information, obtaining the optimal pH value, adjusting the pH of the basic enzymatic reaction solution, obtaining an enzymatic reaction solution, and decomposing the odor of the odor source. By detecting the concentration and component information of the odor to be processed currently, the optimization of the enzyme type and concentration is realized, the optimal enzyme configuration is obtained. Furthermore, by predicting the pH information of the odor source, the pH value of the basic enzymatic reaction solution is optimized to ensure the best activity of the enzyme, achieving the technical effect of improving the accuracy and efficiency of odor decomposition.

[0011] The above description is only an overview of the technical solutions of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific embodiments of the present application are given below. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easily understood through the following description. Description of the Drawings

[0012] To more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on the provided drawings.

[0013] Figure 1 It is a schematic flow diagram of an odor decomposition optimization method using enzymatic reaction in the present application;

[0014] Figure 2 It is a schematic structural diagram of an odor decomposition optimization device using enzymatic reaction in the present application.

[0015] Explanation of reference numerals:

[0016] Odor feature acquisition module 11, first optimization module 12, odor source pH prediction module 13, second optimization module 14. Detailed implementation manners

[0017] By providing an odor decomposition optimization method and device using enzymatic reaction, the present application solves the technical problem in the prior art that due to relying more on experience to determine the enzymatic reaction conditions and lacking a systematic optimization scheme, the reaction efficiency is not high. By detecting the concentration and composition information of the current odor to be treated, the optimization of the enzyme type and concentration is realized, and the optimal enzyme configuration is obtained. Furthermore, by predicting the pH information of the odor source, the pH value of the basic enzymatic reaction solution is optimized to ensure the best activity of the enzyme, achieving the technical effect of improving the accuracy and efficiency of odor decomposition.

[0018] Next, the technical solutions in the present application will be clearly and completely described with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described here. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application. Additionally, it should be noted that for the sake of description, only the parts related to the present application are shown in the drawings rather than all of them.

[0019] Embodiment 1. Please refer to the attached Figure 1 , the present application provides an odor decomposition optimization method using enzymatic reaction. Among them, the odor decomposition optimization method using enzymatic reaction is applied to an odor decomposition optimization device using enzymatic reaction. The odor decomposition optimization method using enzymatic reaction specifically includes the following steps:

[0020] Step 1: Receive the odor characteristic information obtained by detecting the odor to be decomposed currently. Among them, the odor characteristic information includes odor concentration information and odor component information.

[0021] Specifically, the odor to be decomposed currently refers to the odor on clothing, such as cigarette smell, shoe odor, etc. That is to say, the odor on clothing will spread into the air and needs to be decomposed to improve air quality. First, the odor characteristic information is obtained through detection to carry out an effective decomposition reaction. The odor characteristic information includes odor concentration information and odor component information. The odor concentration information refers to the specific concentration level of the odor to be decomposed currently, usually in milligrams per cubic meter (mg / m 3 ) or ppm (parts per million); the odor component information refers to the specific odor substance types in the odor to be decomposed currently, including volatile organic compounds (VOCs) such as ammonia and hydrogen sulfide. These components are usually identified and quantified through gas chromatography (GC) or mass spectrometry (MS) analysis. For example, by taking air samples and using existing detection instruments to detect the odor concentration and components, the experimental data shows that the sample contains ammonia (30 mg / m 3 ) and methanethiol (50 mg / m 3 ). Thus, the odor characteristic information is obtained, providing necessary data support for the subsequent enzymatic reaction, facilitating the selection of appropriate enzyme types and concentrations to ensure the best decomposition effect under different conditions.

[0022] Step 2: According to the odor concentration information and odor component information, optimize the enzyme type and enzyme concentration in the enzymatic reaction to obtain the optimal enzyme type and the optimal enzyme concentration, and configure the basic enzymatic reaction solution.

[0023] Specifically, in the odor decomposition optimization method, the second step is to optimize the enzyme type and enzyme concentration in the enzymatic reaction according to the odor concentration information and odor component information, so as to obtain the optimal enzyme type and the optimal enzyme concentration, and configure the basic enzymatic reaction solution. The optimization of the enzyme type means selecting enzymes suitable for decomposing specific odor components. For example, for the cigarette odor components containing nicotine and aldehydes, specific oxidases or hydrolases are used to improve the removal rate. The optimization of the enzyme concentration is to improve the efficiency of odor decomposition by adjusting the addition amount of the enzyme. For example, by setting different enzyme concentration gradients (such as 1%, 2%, 5%, etc.) and monitoring the removal rate of the reaction to determine the optimal concentration. Thus, the optimal enzyme type and the optimal enzyme concentration are determined, and the basic enzymatic reaction solution is configured according to the optimal enzyme type and the optimal enzyme concentration. This reaction solution contains the selected optimal enzyme type and the corresponding concentration. Thus, by optimizing the conditions of the enzymatic reaction, the efficiency of odor decomposition is effectively improved, thereby achieving rapid and thorough treatment of the odor on clothing.

[0024] Step 3: Based on the odor concentration information and odor component information, predict the pH of the odor source to obtain the odor source pH information.

[0025] Specifically, the prediction of the odor source pH is to infer the acidity or alkalinity of the odor source by establishing a model. The pH value usually ranges from 0 to 14. A pH value less than 7 indicates acidity, equal to 7 indicates neutrality, and greater than 7 indicates alkalinity. The pH value has a significant impact on the efficiency of enzymatic reactions. Therefore, accurately predicting the pH value is an important part of optimizing odor treatment. According to the predicted odor source pH information, the appropriate pH range can be determined, providing data support for the subsequent optimization of enzymatic reactions and ensuring the maximization of treatment effects.

[0026] Step 4: Based on the odor source pH information, optimize the pH adjustment of the basic enzymatic reaction solution to obtain the optimal pH value, adjust the pH of the basic enzymatic reaction solution to obtain the enzymatic reaction solution, and decompose the odor of the odor source.

[0027] Specifically, after obtaining the odor source pH information, the next step is to optimize the pH adjustment of the basic enzymatic reaction solution to obtain the optimal pH value and ensure the efficiency of the enzymatic reaction. The basic enzymatic reaction solution refers to the reaction solution that has not been adjusted for pH on the basis of the selected optimal enzyme type and optimal enzyme concentration. The activity of the enzyme in this reaction solution is significantly affected by the pH value. Different enzymes exhibit the best activity in different pH environments. According to the previously predicted odor source pH information, optimize the pH adjustment to determine a suitable pH adjustment range, that is, the optimal pH value. Within this range, adjust the pH value by adding acidic or alkaline buffer solutions. For example, if the initial pH of the basic reaction solution is 7.0, adjust the pH value by adding acetic acid or sodium hydroxide. Finally, after adjustment, the obtained enzymatic reaction solution will be used to decompose the odor source, effectively improving the efficiency of the enzymatic reaction and thus achieving rapid and thorough treatment of the odor on the clothing.

[0028] Furthermore, Step 1 of this application includes:

[0029] Receiving the odor component information obtained by detecting the components of the odor of the odor source to be decomposed currently; receiving the odor concentration information obtained by detecting the concentration of the odor; integrating the odor concentration information and odor component information to obtain the odor characteristic information.

[0030] Specifically, the detection of odor components of the odor source refers to the identification and quantification of the specific components of the odor on clothing or in the environment through existing detection technologies such as gas chromatography-mass spectrometry (GC-MS). For example, in an experiment, a piece of clothing contaminated with cigarette smell was detected, and the results showed that the odor components contained in the sample included nicotine, which caused a significant odor, thus obtaining the odor component information. The odor concentration information refers to the concentration of the odor components in the odor source, usually in milligrams per cubic meter (mg / m 3 ), for example, in the same experiment, the cigarette smell concentration of this piece of clothing was measured to be 200 mg / m 3 using a gas sensor, thus obtaining the odor concentration information. Finally, the odor concentration information and the odor component information are integrated to obtain complete odor characteristic information. By analyzing the odor components and concentrations, the nature and intensity of the odor can be clearly identified, providing data support for the subsequent optimization of the enzymatic reaction, facilitating the targeted adjustment of the reaction conditions, thereby improving the odor removal rate, not only enhancing the accuracy of the treatment, but also making the odor decomposition process more efficient and targeted.

[0031] Further, step two of this application includes:

[0032] Obtaining the enzyme type selection space and enzyme concentration adjustment space for the enzymatic reaction; randomly selecting the first enzyme type and the first enzyme concentration within the enzyme type selection space and the enzyme concentration adjustment space; predicting the odor decomposition according to the first enzyme type, the first enzyme concentration, and the odor characteristic information to obtain the first decomposition rate; continuing to optimize the enzyme type and enzyme concentration in the enzymatic reaction within the enzyme type selection space and the enzyme concentration adjustment space until the optimization converges, outputting the enzyme type and enzyme concentration with the maximum decomposition rate to obtain the optimal enzyme type and the optimal enzyme concentration; configuring the basic enzymatic reaction solution according to the optimal enzyme type and the optimal enzyme concentration.

[0033] Specifically, the enzyme type selection space refers to constructing a list of enzyme types suitable for different odor components based on known enzyme characteristics and target odor components. For example, for cigarette smell and shoe odor, multiple enzymes such as oxidase, esterase, and hydrolase are selected. The enzyme concentration adjustment space refers to adjusting the enzyme concentration within a certain range (such as 1% to 5%) to find the optimal reaction conditions. Specifically, both the enzyme type selection space and the enzyme concentration adjustment space can be constructed based on historical odor decomposition records, that is, obtaining the enzyme types known in history that can decompose various odor components to construct the enzyme type selection space, and at the same time determining the concentration range of various types of enzymes in combination with historical odor decomposition records to construct the enzyme concentration adjustment space. Next, a first enzyme type and a first enzyme concentration are randomly selected within the enzyme type selection space and the enzyme concentration adjustment space. For example, a certain oxidase is randomly selected as the first enzyme type, and the concentration is set at 3%. Further, in combination with the odor characteristic information obtained previously (such as the concentration and components of cigarette smell), odor decomposition prediction is carried out to obtain a first decomposition rate. The decomposition rate can be understood as the removal rate of the odor.

[0034] Then, within the enzyme type selection space and the enzyme concentration adjustment space, optimization iteration is continued, that is, by continuously selecting different enzyme types and concentrations, and using the prediction model to calculate the corresponding decomposition rates until optimization convergence. The enzyme type and enzyme concentration with the maximum decomposition rate are determined as the optimal enzyme type and optimal enzyme concentration. Among them, the optimization convergence can be the number of iterations, such as iteratively optimizing 200 times. Once the optimal enzyme type and optimal enzyme concentration are obtained, a basic enzymatic reaction solution can be configured. This reaction solution includes the optimal enzyme type and concentration, which can effectively improve the efficiency of odor decomposition.

[0035] Furthermore, the present application further includes the following steps:

[0036] According to the enzymatic reaction test data within the historical time, collect the sample enzyme type set, sample enzyme concentration set, and sample odor characteristic information set, and obtain the average concentration decrease ratio of odor decomposition under different sample enzyme types, sample enzyme concentrations, and sample odor characteristic information as the sample decomposition rate set; use the sample enzyme type set, sample enzyme concentration set, sample odor characteristic information set, and sample decomposition rate set as supervised training data and test data; use the supervised training data and test data to train the decomposition predictor until the test accuracy meets the requirements to obtain the decomposition predictor; input the first enzyme type, the first enzyme concentration, and the odor characteristic information into the decomposition predictor, and output to obtain the first decomposition rate.

[0037] Specifically, in the process of optimizing the enzyme type and enzyme concentration in the enzymatic reaction, it is necessary to perform odor decomposition prediction to obtain the decomposition rate. The decomposition rate is obtained through a machine learning model, namely the decomposition predictor. Before analysis, it is necessary to first construct the decomposition predictor. The decomposition predictor is constructed based on the historical enzymatic reaction test data. The enzymatic reaction test data within the historical time refers to the odor decomposition test data carried out within a certain period in the past (such as the past three months), including the sample enzyme types, sample enzyme concentrations, sample odor characteristic information used in multiple tests, and the corresponding average concentration decrease ratio of odor decomposition (the ratio of the concentration difference before and after decomposition to the odor concentration before decomposition). First, according to the enzymatic reaction test data within the historical time, extract the sample enzyme type set, sample enzyme concentration set, and sample odor characteristic information set. Among them, the data in the sample enzyme type set, sample enzyme concentration set, and sample odor characteristic information set have a one-to-one correspondence. At the same time, extract the average concentration decrease ratio of odor decomposition corresponding to the sample enzyme type set, sample enzyme concentration set, and sample odor characteristic information set from the enzymatic reaction test data within the historical time to obtain the sample decomposition rate set.

[0038] Using the sample enzyme type set, sample enzyme concentration set, sample odor characteristic information set, and sample decomposition rate set as supervised training data and test data, specifically, the sample enzyme type set, sample enzyme concentration set, sample odor characteristic information set, and sample decomposition rate set can be divided according to a preset ratio (such as 1:4) to obtain supervised training data and test data. Use the supervised training data and test data to train a decomposition predictor. The decomposition predictor is a machine learning model (such as a neural network model) that can predict the odor decomposition rate based on the input enzyme type, enzyme concentration, and odor characteristic information. By continuously adjusting the model parameters, the predictor will be trained until its accuracy on the test data reaches a predetermined requirement (for example, the accuracy exceeds 90%). Exemplarily, taking the neural network model as an example, the network structure of the decomposition predictor can be designed into the following main layers: Input layer: The input layer receives multiple feature data, including enzyme type, enzyme concentration, and odor characteristic information. The number of nodes in the input layer corresponds to the number of input features; Hidden layer: The hidden layer consists of multiple neurons, usually set to 1 to 3 layers. The specific number of layers and the number of neurons in each layer can be adjusted. Each neuron processes the input through an activation function (such as ReLU or sigmoid) to increase the non-linear ability of the network. For example, the first hidden layer can have 64 neurons, and the second layer has 32 neurons; Output layer: The number of nodes in the output layer is usually 1, representing the predicted decomposition rate. This layer can use a linear activation function, and the output value range is usually from 0 to 1, representing the percentage of the removal rate; Loss function: During the training process, a suitable loss function (such as mean squared error) is used to evaluate the difference between the predicted value and the true decomposition rate to optimize the network parameters; Optimizer: Use an optimization algorithm (such as Adam or SGD) to update the weights and biases of the network to minimize the loss function; Regularization and Dropout layer (optional): To prevent overfitting, a Dropout layer can be added between the hidden layers to randomly discard some neurons. In addition, L2 regularization can be used to constrain the complexity of the model. This structure of the neural network can effectively capture the complex relationships between different enzyme types, enzyme concentrations, and odor characteristics, thereby accurately predicting the odor decomposition rate. Through training, the model can provide effective predictions on new input data. Finally, input the first enzyme type, the first enzyme concentration, and the odor characteristic information into the decomposition predictor, and output the first decomposition rate. Through this process, the removal effect of the odor can be effectively predicted, providing model support for the optimization of enzyme types and enzyme concentrations.

[0039] Further, step three of the present application includes:

[0040] According to the historical odor decomposition data of similar odor sources, collect the sample odor concentration information set and the sample odor component information set, and collect the pH value of the odor source when collecting different sample odor concentration information and sample odor component information, as the sample odor source information set; use the sample odor concentration information set, the sample odor component information set and the sample odor source information set to train the odor source pH analyzer; input the odor concentration information and the odor component information into the odor source pH analyzer, and output to obtain the odor source pH information.

[0041] Specifically, the prediction of the odor source pH is analyzed and predicted by the odor source pH analyzer. The odor source pH analyzer is a machine learning model (such as decision tree, random forest or neural network) used to establish the relationship between odor concentration and composition and the pH value. By inputting the concentration and composition information of different samples, the model will learn how to accurately predict the pH value. First, collect the sample odor concentration information set and the sample odor component information set. These data come from the historical odor decomposition data, which records the odor concentration and composition of different odor sources (such as cigarette smell, shoe odor, etc.) under specific conditions during historical time. For example, in a certain experiment, the odor concentration of the cigarette smell sample is 200mg / m 3 , and the main components are nicotine and benzene; the odor concentration of the shoe odor sample is 150mg / m 3 , and the components include volatile fatty acids and bacterial metabolites. The historical odor decomposition data records the pH values of different samples under different odor concentration and composition conditions during historical time, forming the sample odor source information set. Among them, the data in the sample odor concentration information set, the sample odor component information set and the sample odor source information set have a one-to-one correspondence.

[0042] Subsequently, use the sample odor concentration information set, the sample odor component information set and the sample odor source information set to train the odor source pH analyzer. Specifically, divide the collected sample odor concentration information set, the sample odor component information set and the sample odor source information set into a training set and a test set (usually 70% for training and 30% for testing). Each sample should include odor concentration, odor component and the corresponding pH value. Select an existing machine learning model, such as linear regression, random forest or neural network, and use the training set to train the selected model. By inputting features (odor concentration and composition information) to learn how to predict the target variable (pH value). During the training process, the model will continuously adjust its internal parameters to minimize the gap between the predicted value and the actual pH value, usually achieved through a loss function. Then, use the test set to evaluate the trained model and calculate the difference between the predicted pH value and the true value. Common metrics include mean squared error (MSE) and coefficient of determination (R 2) According to the evaluation results, adjust the parameters of the model to improve the prediction accuracy. Once the model passes the evaluation and reaches the expected performance level, it can be deployed as an odor source pH analyzer for practical applications.

[0043] Input the odor concentration information and odor component information into the trained odor source pH analyzer for analysis and prediction, output the odor source pH information, provide support for the subsequent optimization of the enzymatic reaction, and ensure the effectiveness and pertinence of the treatment process.

[0044] Furthermore, step four of this application includes:

[0045] Obtain the pH adjustment space of the enzymatic reaction solution; randomly generate a first pH value within the pH adjustment space; according to the odor source pH information, perform compensation adjustment on the first pH value to obtain a first compensated pH value; according to the first compensated pH value, combine the odor concentration information, odor component information, optimal enzyme type, and optimal enzyme concentration to perform odor decomposition prediction to obtain a first pH impact decomposition rate; continue to perform pH adjustment optimization of the basic enzymatic reaction solution according to the odor source pH information until the optimization converges, output the pH value with the maximum pH impact decomposition rate, and obtain the optimal pH value.

[0046] Specifically, first obtain the pH adjustment space of the enzymatic reaction solution. The pH adjustment space refers to a set range of pH values, usually determined according to the historical adjustable pH values of the enzymatic reaction solution, that is, the pH range that will not cause the enzymes in the enzymatic reaction solution to completely lose their activity, and specific settings need to be combined with practical experience. Randomly generate a pH value within the pH adjustment space, denoted as the first pH value, and then perform compensation adjustment on the first pH value according to the odor source pH information. The specific compensation adjustment method is as follows: According to the pH value in the odor source pH information, the concentration of H + can be calculated. There is an inverse relationship between the pH value and the concentration of H + (hydrogen ions), [H + = 10 -pH . At the same time, calculate the concentration of H + corresponding to the first pH value, add the concentration of odor source H + to the concentration of H + corresponding to the first pH value to obtain the concentration of H + after compensation adjustment, and then convert the concentration of H + after compensation adjustment into a pH value to obtain the first compensated pH value affected by the odor source pH.

[0047] Exemplarily, if the pH value of the odor source is 6.5, then its H + concentration is: [H + 异味源 = 10 -6.5 ​≈3.16×10 - 7 mol / L. Assuming the first pH value is 7.0, then its H + concentration can also be calculated by the formula: [H + 第一pH值 =10 -7 ≈1.00×10 -7 mol / L. When superimposing the H + concentrations of the two, the two need to be added: [H + 总 =[H + 异味源 +[H + 第一pH值 =4.16×10 -7 mol / L. Furthermore, the first compensated pH value after compensation adjustment is recalculated through the H+ concentration: First compensated pH value = -log10([H + 总 )=-log10(4.16×10 -7 )≈6.38. In this way, the obtained first compensated pH value is 6.38. Through this method, based on the pH information of the original odor source and the generated first pH value, the H + concentration after compensation adjustment can be calculated, and the new compensated pH value can be further determined to optimize the conditions of the enzymatic reaction.

[0048] According to the first compensated pH value, combined with the previously collected odor concentration information, odor component information, optimal enzyme type and optimal enzyme concentration, odor decomposition prediction is carried out to predict the decomposition effect under this pH condition, that is, the first pH affects the decomposition rate, and the first pH affects the decomposition rate as the proportion of the average concentration decrease of odor decomposition under the influence of the first compensated pH value. And so on, continue to obtain the second pH value, the third pH value, etc. in the pH adjustment space, repeat the compensation adjustment and decomposition prediction until optimization convergence. Optimization convergence refers to the iteration optimization stop condition. For example, it can be the number of optimization iterations. Output the pH value with the largest pH influence on the decomposition rate as the optimal pH value, ensuring that the efficiency of odor decomposition is maximized under the best pH conditions, thereby effectively treating the odor on the clothing.

[0049] Furthermore, this application also includes the following steps:

[0050] ​​​​​According to the odor decomposition test data at different pH values, collect the sample pH set, sample odor concentration information set, sample odor component information set, sample enzyme type set, and sample enzyme concentration set, and collect the average concentration decrease ratio of odor decomposition under different conditions as the sample pH influence decomposition rate set; use the sample pH set, sample odor concentration information set, sample odor component information set, sample enzyme type set, sample enzyme concentration set, and sample pH influence decomposition rate set to train a pH influence odor decomposition predictor; input the first compensated pH value, odor concentration information, odor component information, optimal enzyme type, and optimal enzyme concentration into the pH influence odor decomposition predictor, and output the first pH influence decomposition rate.

[0051] Specifically, according to the first compensated pH value, combined with the odor concentration information, odor component information, optimal enzyme type, and optimal enzyme concentration, the specific steps for odor decomposition prediction to obtain the first pH influence decomposition rate are as follows: The odor decomposition test data at different pH values refers to the data of odor decomposition tests at different pH values within historical time, including the sample pH, sample odor concentration information, sample odor component information, sample enzyme type, and sample enzyme concentration during multiple tests, as well as the corresponding average concentration decrease ratio of odor decomposition. Based on this, sample data is collected, including the sample pH set, sample odor concentration information set, sample odor component information set, sample enzyme type set, and sample enzyme concentration set, and the corresponding sample pH influence decomposition rate set, that is, the set of average decrease rates of odor concentration under different test conditions.

[0052] Use the data in the sample pH set, sample odor concentration information set, sample odor component information set, sample enzyme type set, and sample enzyme concentration set as training inputs, and use the corresponding data in the sample pH influence decomposition rate set as the supervised true value to train a pH influence odor decomposition predictor. The pH influence odor decomposition predictor can be a machine learning model based on regression, such as a neural network or a random forest. The goal of the model is to learn the relationship between the input features (including pH value, odor concentration, composition, enzyme type, and concentration) and the decomposition rate. Through repeated training and debugging, the model will be optimized to the best state and be able to accurately predict the decomposition rate. The training of machine learning models is a commonly used technical means for those skilled in the art and will not be elaborated here. Finally, input the first compensated pH value, odor concentration information, odor component information, and the previously optimized optimal enzyme type and optimal enzyme concentration into the trained pH influence odor decomposition predictor, and the output result is the first pH influence decomposition rate, that is, the predicted decomposition efficiency under these specific conditions. For example, the pH influence odor decomposition predictor may output a decomposition rate of 92%, indicating a relatively high reaction efficiency under this pH condition. Through this process, it is possible to quickly judge the influence of different pH conditions on the decomposition efficiency and optimize the odor decomposition reaction accordingly.

[0053] In summary, the odor decomposition optimization method using enzymatic reaction provided by this application has the following technical effects:

[0054] Receiving the odor characteristic information obtained by detecting the odor to be decomposed currently, wherein the odor characteristic information includes odor concentration information and odor component information; optimizing the enzyme type and enzyme concentration in the enzymatic reaction according to the odor concentration information and odor component information to obtain the optimal enzyme type and the optimal enzyme concentration, and configuring to obtain a basic enzymatic reaction solution; predicting the pH of the odor source according to the odor concentration information and odor component information to obtain the odor source pH information; optimizing the pH adjustment of the basic enzymatic reaction solution according to the odor source pH information to obtain the optimal pH value, adjusting the pH of the basic enzymatic reaction solution to obtain an enzymatic reaction solution, and decomposing the odor of the odor source. By detecting the concentration and component information of the odor to be processed currently, the optimization of the enzyme type and concentration is realized, and the optimal enzyme configuration is obtained. Furthermore, by predicting the pH information of the odor source, the pH value of the basic enzymatic reaction solution is optimized to ensure the best activity of the enzyme, achieving the technical effects of improving the accuracy and efficiency of odor decomposition.

[0055] Embodiment 2. Based on the same inventive concept as the odor decomposition optimization method using enzymatic reaction in the foregoing embodiment, this application also provides an odor decomposition optimization device using enzymatic reaction. Please refer to the attached Figure 2 , the odor decomposition optimization device using enzymatic reaction includes:

[0056] An odor characteristic acquisition module 11, configured to receive the odor characteristic information obtained by detecting the odor to be decomposed currently, wherein the odor characteristic information includes odor concentration information and odor component information.

[0057] A first optimization module 12, configured to optimize the enzyme type and enzyme concentration in the enzymatic reaction according to the odor concentration information and odor component information to obtain the optimal enzyme type and the optimal enzyme concentration, and configure to obtain a basic enzymatic reaction solution.

[0058] An odor source pH prediction module 13, configured to predict the pH of the odor source according to the odor concentration information and odor component information to obtain the odor source pH information.

[0059] A second optimization module 14, configured to optimize the pH adjustment of the basic enzymatic reaction solution according to the odor source pH information to obtain the optimal pH value, adjust the pH of the basic enzymatic reaction solution to obtain an enzymatic reaction solution, and decompose the odor of the odor source.

[0060] Furthermore, the odor characteristic acquisition module 11 in the odor decomposition optimization device using enzymatic reaction is further configured to:

[0061] Receive the odor component information for detecting the components of the odor from the odor source to be decomposed currently; receive the odor concentration information for detecting the concentration of the odor; integrate the odor concentration information and the odor component information to obtain odor characteristic information.

[0062] Furthermore, the first optimization module 12 in the odor decomposition optimization device using enzymatic reaction is further configured to:

[0063] Obtain the enzyme type selection space and the enzyme concentration adjustment space for the enzymatic reaction; randomly select a first enzyme type and a first enzyme concentration within the enzyme type selection space and the enzyme concentration adjustment space; perform odor decomposition prediction based on the first enzyme type, the first enzyme concentration, and the odor characteristic information to obtain a first decomposition rate; continue to optimize the enzyme type and enzyme concentration in the enzymatic reaction within the enzyme type selection space and the enzyme concentration adjustment space until the optimization converges, output the enzyme type and enzyme concentration with the maximum decomposition rate, and obtain the optimal enzyme type and the optimal enzyme concentration; configure and obtain a basic enzymatic reaction solution according to the optimal enzyme type and the optimal enzyme concentration.

[0064] Furthermore, the first optimization module 12 in the odor decomposition optimization device using enzymatic reaction is further configured to:

[0065] According to the enzymatic reaction test data within the historical time, collect a set of sample enzyme types, a set of sample enzyme concentrations, and a set of sample odor characteristic information, and obtain the average odor decomposition concentration decrease ratio under different sample enzyme types, sample enzyme concentrations, and sample odor characteristic information as a set of sample decomposition rates; use the set of sample enzyme types, the set of sample enzyme concentrations, the set of sample odor characteristic information, and the set of sample decomposition rates as supervised training data and test data; use the supervised training data and the test data to train a decomposition predictor until the test accuracy meets the requirements to obtain the decomposition predictor; input the first enzyme type, the first enzyme concentration, and the odor characteristic information into the decomposition predictor, and output to obtain the first decomposition rate.

[0066] Furthermore, the odor source pH prediction module 13 in the odor decomposition optimization device using enzymatic reaction is further configured to:

[0067] According to the historical odor decomposition data of the same type of odor source, collect a set of sample odor concentration information and a set of sample odor component information, and collect the pH value of the odor source when different sample odor concentration information and sample odor component information are available as a set of sample odor source information; use the set of sample odor concentration information, the set of sample odor component information, and the set of sample odor source information to train an odor source pH analyzer; input the odor concentration information and the odor component information into the odor source pH analyzer, and output to obtain the odor source pH information.

[0068] Further, the second optimization module 14 in the odor decomposition optimization device using enzymatic reaction is further configured to:

[0069] Obtain the pH adjustment space of the enzymatic reaction solution; randomly generate a first pH value within the pH adjustment space; perform compensation adjustment on the first pH value according to the odor source pH information to obtain a first compensated pH value; according to the first compensated pH value, combine the odor concentration information, odor component information, optimal enzyme type, and optimal enzyme concentration to perform odor decomposition prediction to obtain the first pH-influenced decomposition rate; continue to perform pH adjustment optimization of the basic enzymatic reaction solution according to the odor source pH information until the optimization converges, and output the pH value with the maximum pH-influenced decomposition rate to obtain the optimal pH value.

[0070] Further, the second optimization module 14 in the odor decomposition optimization device using enzymatic reaction is further configured to:

[0071] Collect a sample pH set, a sample odor concentration information set, a sample odor component information set, a sample enzyme type set, and a sample enzyme concentration set according to the odor decomposition test data at different pH values, and collect the average concentration decrease ratio of odor decomposition under different conditions as the sample pH-influenced decomposition rate set; use the sample pH set, the sample odor concentration information set, the sample odor component information set, the sample enzyme type set, the sample enzyme concentration set, and the sample pH-influenced decomposition rate set to train a pH-influenced odor decomposition predictor; input the first compensated pH value, the odor concentration information, the odor component information, the optimal enzyme type, and the optimal enzyme concentration into the pH-influenced odor decomposition predictor, and output to obtain the first pH-influenced decomposition rate.

[0072] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The Figure 1 A method for optimizing odor decomposition using enzymatic reaction and specific examples in the first embodiment are equally applicable to the odor decomposition optimization device using enzymatic reaction in this embodiment. Through the detailed description of the method for optimizing odor decomposition using enzymatic reaction above, those skilled in the art can clearly know the odor decomposition optimization device using enzymatic reaction in this embodiment. Therefore, for the sake of simplicity of the specification, it will not be elaborated here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0073] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0074] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is also intended to include these changes and variations.

Claims

1. A method for optimizing odor decomposition using an enzymatic reaction, characterized in that: The method for optimizing odor decomposition by enzymatic reaction comprises: Receiving odor characteristic information obtained by detecting the odor to be currently decomposed, wherein the odor characteristic information includes odor concentration information and odor component information; According to the odor concentration information and the odor component information, the enzyme type and enzyme concentration in the enzymatic reaction are optimized to obtain the optimal enzyme type and the optimal enzyme concentration, and a basic enzymatic reaction solution is obtained; Predicting the pH of the odor source based on the odor concentration information and the odor component information to obtain the odor source pH information; According to the pH information of the odor source, the pH adjustment of the basic enzymatic reaction solution is optimized to obtain the optimal pH value, and the pH of the basic enzymatic reaction solution is adjusted to obtain an enzymatic reaction solution to decompose the odor of the odor source.

2. The method for optimizing odor decomposition by enzymatic reaction according to claim 1, characterized in that: Receiving odor characteristic information obtained by detecting the odor to be currently decomposed, including: Receiving odor component information for component detection of the odor of the odor source currently to be decomposed; Receiving odor concentration information of concentration detection of the odor; The odor concentration information and the odor component information are integrated to obtain odor characteristic information.

3. The method for optimizing odor decomposition by enzymatic reaction according to claim 1, characterized in that: According to the odor concentration information and the odor component information, the enzyme type and enzyme concentration in the enzymatic reaction are optimized to obtain the optimal enzyme type and the optimal enzyme concentration, and the basic enzymatic reaction solution is configured, including: Obtain the enzyme type selection space and enzyme concentration adjustment space of the enzymatic reaction; Randomly selecting a first enzyme type and a first enzyme concentration in the enzyme type selection space and the enzyme concentration adjustment space; Perform odor decomposition prediction based on the first enzyme type, the first enzyme concentration, and the odor characteristic information to obtain a first decomposition rate; Continuing to optimize the enzyme type and enzyme concentration in the enzymatic reaction within the enzyme type selection space and the enzyme concentration adjustment space until the optimization converges, outputting the enzyme type and enzyme concentration with the maximum decomposition rate, and obtaining the optimal enzyme type and optimal enzyme concentration; According to the optimal enzyme type and optimal enzyme concentration, a basic enzymatic reaction solution is prepared.

4. The method for optimizing odor decomposition by enzymatic reaction according to claim 3, characterized in that: The odor decomposition prediction is performed according to the first enzyme type, the first enzyme concentration, and the odor characteristic information to obtain a first decomposition rate, including: According to the enzymatic reaction test data in the historical time, a set of sample enzyme types, a set of sample enzyme concentrations, and a set of sample odor characteristic information are collected, and the average concentration reduction ratio of odor decomposition under different sample enzyme types, sample enzyme concentrations, and sample odor characteristic information is obtained as a set of sample decomposition rates; The sample enzyme type set, the sample enzyme concentration set, the sample odor characteristic information set and the sample decomposition rate set are used as supervised training data and test data; Using the supervised training data and the test data, training the decomposition predictor until the test accuracy meets the requirement, thereby obtaining the decomposition predictor; The first enzyme type, first enzyme concentration, and odor characteristic information are input into the decomposition predictor, and a first decomposition rate is obtained as an output.

5. The method for optimizing odor decomposition by enzymatic reaction according to claim 1, characterized in that: According to the odor concentration information and the odor component information, the pH of the odor source is predicted to obtain the odor source pH information, including: According to the historical odor decomposition data of the same odor source, a sample odor concentration information set and a sample odor component information set are collected, and the pH value of the odor source when different sample odor concentration information and sample odor component information are collected as the sample odor source information set; Using the sample odor concentration information set, the sample odor component information set and the sample odor source information set, to train an odor source pH analyzer; The odor concentration information and the odor component information are input into the odor source pH analyzer, and the odor source pH information is output to obtain.

6. The method for optimizing odor decomposition by enzymatic reaction according to claim 1, characterized in that: According to the pH information of the odor source, the pH adjustment optimization of the basic enzymatic reaction solution is performed to obtain the optimal pH value, including: Obtaining pH adjustment space for the enzymatic reaction solution; randomly generating a first pH value in the pH adjustment space; According to the pH information of the odor source, the first pH value is compensated and adjusted to obtain a first compensated pH value; According to the first compensated pH value, combined with the odor concentration information, odor component information, optimal enzyme type and optimal enzyme concentration, odor decomposition prediction is performed to obtain the first pH-affected decomposition rate; Continue to optimize the pH adjustment of the basic enzymatic reaction solution according to the pH information of the odor source until the optimization converges, output the pH value with the greatest impact on the decomposition rate, and obtain the optimal pH value.

7. The method for optimizing odor decomposition by enzymatic reaction according to claim 6, characterized in that: According to the first compensated pH value, combined with the odor concentration information, the odor component information, the optimal enzyme type and the optimal enzyme concentration, the odor decomposition prediction is performed to obtain the first pH-affected decomposition rate, including: According to the odor decomposition test data under different pH conditions, a sample pH set, a sample odor concentration information set, a sample odor component information set, a sample enzyme type set, and a sample enzyme concentration set are collected, and the average concentration reduction ratio of odor decomposition under different conditions is collected as a sample pH-affected decomposition rate set; The sample pH set, the sample odor concentration information set, the sample odor component information set, the sample enzyme type set, the sample enzyme concentration set and the sample pH effect decomposition rate set are used to train a pH effect odor decomposition predictor; The first compensated pH value, odor concentration information, odor component information, optimal enzyme type and optimal enzyme concentration are input into the pH-affected odor decomposition predictor, and the first pH-affected decomposition rate is obtained as an output.

8. An odor decomposition optimization device using enzymatic reaction, characterized in that: The steps for implementing the method for optimizing odor decomposition by enzymatic reaction according to any one of claims 1 to 7, wherein the device for optimizing odor decomposition by enzymatic reaction comprises: An odor characteristic acquisition module, used for receiving odor characteristic information obtained by detecting the odor to be currently decomposed, wherein the odor characteristic information includes odor concentration information and odor component information; A first optimization module is used to optimize the enzyme type and enzyme concentration in the enzymatic reaction according to the odor concentration information and the odor component information, obtain the optimal enzyme type and the optimal enzyme concentration, and configure a basic enzymatic reaction solution; An odor source pH prediction module is used to predict the odor source pH according to the odor concentration information and the odor component information to obtain the odor source pH information; The second optimization module is used to optimize the pH adjustment of the basic enzymatic reaction solution according to the pH information of the odor source, obtain the optimal pH value, adjust the pH of the basic enzymatic reaction solution, obtain the enzymatic reaction solution, and decompose the odor of the odor source.

Images