Anaerobic fermentation process health evaluation method and system

Through the combination of sensor module and cloud computing platform, machine learning algorithms and physical and chemical parameter evaluation are used to solve the problem of control difficulties in traditional anaerobic fermentation processes, real-time monitoring and optimization of anaerobic fermentation process is realized, and biogas production is improved. Fermentation efficiency promotes the commercialization process of biomass energy.

CN119027272APending Publication Date: 2024-11-26ENERGY & ENVIRONMENT RES INST OF HEILONGJIANG PROVINCE
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411064337.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-05
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

Traditional anaerobic fermentation processes have problems such as low gas production rate, long cycles and difficult process control, and lack systematicity, real-timeness and accuracy, making it difficult to meet the needs of modern production, and cannot timely regulate microbial activity and metabolic state, resulting in biogas production and Insufficient fermentation efficiency.

Method used

The sensor module is used to monitor data in real time and transmit it to the cloud computing platform wirelessly, and data processing and analysis is used by machine learning algorithms, fermentation control parameters are automatically adjusted, combined with physical and chemical parameter evaluation and microbial community monitoring, and PCR technology or metagenomic analysis is used. Achieve health evaluation and optimization of the anaerobic fermentation process.

Benefits of technology

Real-time response to changes in fermentation conditions is achieved, the stability and accuracy of the fermentation process is improved, the production efficiency of biomass energy is promoted, the monitoring cost is reduced, and it is suitable for various biomass fermentation projects, reducing energy consumption and environmental pollution.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119027272A_ABST
    Figure CN119027272A_ABST
Patent Text Reader

Abstract

The invention discloses an anaerobic fermentation process health evaluation method and system, and belongs to the technical field of anaerobic fermentation. The problems that in the prior art, data cannot be analyzed and predicted in real time, and parameters cannot be automatically adjusted are solved. According to the technical scheme, a sensor is adopted to capture data in real time, and the data are transmitted to a cloud computing platform through wireless communication. According to the platform, collected data are deeply analyzed by applying a machine learning algorithm, so that the health condition of the anaerobic fermentation process is accurately predicted, and the purpose of optimizing the fermentation process is achieved. The method not only can improve the timeliness and accuracy of prediction, but also can provide guarantee for the stability of the fermentation process, thereby promoting the commercialization process of biomass energy. In addition, by optimizing the fermentation process, energy consumption and environmental pollution are reduced, and the method has profound significance for achieving green and sustainable development.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of anaerobic fermentation, and in particular to a health evaluation method and system for an anaerobic fermentation process. Background Art

[0002] In today's world, energy demand is growing, and the limited traditional energy resources and environmental pollution problems are becoming increasingly prominent. Therefore, the development of sustainable and clean bioenergy has become a global focus. Biomass energy, especially biogas produced by anaerobic fermentation, is highly favored due to its renewable nature and low carbon emission characteristics. However, the traditional anaerobic fermentation process has problems such as low gas production rate, long cycle and difficult process control, which seriously restrict the commercial application of biomass energy.

[0003] Anaerobic fermentation is a complex biochemical process involving the synergistic action of multiple microorganisms. This process is very sensitive to environmental conditions such as temperature, pH value, and nutrients. Changes in these factors directly affect the fermentation effect and biogas production. In order to improve fermentation efficiency and biogas production, it is necessary to monitor the key parameters of the fermentation process in real time and adjust the fermentation conditions accordingly.

[0004] In the existing technology, the management and optimization of anaerobic fermentation process mostly rely on manual experience and limited data analysis, lacking systematicity, real-time and accuracy, and difficult to meet the needs of modern production. At the same time, due to the inability to grasp the microbial activity and metabolic state in the fermentation process in real time and unable to regulate in time, the biogas production and fermentation efficiency are low.

[0005] At present, the relevant patent CN103398746A can only realize the integration of PLC system and sensor detection means to monitor parameters in real time; it can transmit data wirelessly to avoid on-site wiring; the signal is transmitted stably and the system's anti-interference ability is improved.

[0006] The relevant patent CN116769581A can only realize the integration of multiple detection methods based on pH sensors, odor detection and biogas production, effectively making up for the problem of insufficient fermentation tank monitoring and early warning methods, and real-time online monitoring parameters and acidification early warning.

[0007] After obtaining the data, the two related patents still rely on manual experience and data analysis, and cannot quickly reflect and analyze the data, and cannot be further adjusted. Therefore, it is urgent to propose a health evaluation method and system for anaerobic fermentation process to solve the problem of automatic data analysis and health condition prediction. Summary of the invention

[0008] In view of the above facts, in order to solve the problem that data cannot be automatically analyzed and processed and cannot be predicted and adjusted, the present invention further designs a method and system for evaluating the health of an anaerobic fermentation process.

[0009] To achieve the above object, the present invention adopts the following technical solution:

[0010] Scheme 1: A method for health assessment of anaerobic fermentation process, the specific steps are as follows:

[0011] Step 1: Use the sensor module to monitor and collect data during the anaerobic fermentation process in real time;

[0012] Step 2: Send the data collected by the sensor module to the cloud computing platform via wireless transmission;

[0013] Step 3: On a cloud computing platform, the data is processed and analyzed using a machine learning algorithm to predict the health status of the anaerobic fermentation process;

[0014] Step 4: According to the analysis results, the control parameters of the fermentation process are automatically adjusted to optimize the fermentation process;

[0015] Step 5: Combine the evaluation of physicochemical parameters with the monitoring of the microbial community, and use PCR technology or metagenomic analysis to comprehensively evaluate the fermentation process.

[0016] Further: the specific implementation process of step 3 is:

[0017] A. Use the boxplot method to process the data, and view the distribution of the data in a graphical way, including the median, quartiles, maximum value, minimum value, and outliers. Delete the data marked outside the dotted line and use the Newton interpolation method to calculate the filling value for filling;

[0018] B. Using normalized data transformation, use formula (1) to perform standard deviation normalization on the collected data;

[0019]

[0020] In the formula: x′ is the normalized value, x is the value to be normalized, μ is the mean of the collected data, and δ is the standard deviation of the original data;

[0021] C. Gas production prediction is to find the optimal solution of random forest hyperparameters through Bayesian optimization algorithm. In the Bayesian optimization calculation process, the objective function of hyperparameter optimization is first set, and the optimal solution is determined by evaluating different combinations of parameters. The parameters that need to be tuned include: the number of trees, the maximum depth of the tree, the maximum number of features, the minimum number of leaf node samples, and the sample sampling ratio;

[0022] D. The prediction of the health status of the cloud computing platform is:

[0023] 30-day average daily gas production = (a1+a2+…a30) / 30, the average daily gas production of the previous 30 days;

[0024] 3-day average daily gas production = (today's predicted gas production + a1 + a2) / 3;

[0025] Health prediction index = 5-day average daily gas production / 30-day average daily gas production;

[0026] If the health prediction index is ≥0.95, it indicates that the health status is good; if 0.95>health prediction index ≥0.85, it indicates that there is a problem with the health status and it is recommended to measure the indicators of volatile fatty acids; if the health prediction index is <0.85, it indicates that the health status is poor and active intervention must be carried out.

[0027] Further: The biogas production prediction algorithm process of the improved random forest combined with Bayesian optimization is as follows:

[0028] C1. Divide the collected data into training set and test set;

[0029] C2. Build a random forest regression model and set initial hyperparameters;

[0030] C3. Define the objective function of the random forest regression model, such as root mean square error or mean absolute error;

[0031] C4. Determine the hyperparameters and value ranges of the random forest regression model to be optimized;

[0032] C5. Perform Bayesian iterative optimization within the set hyperparameter range, and evaluate the objective function and update the Bayesian optimization algorithm model in real time;

[0033] C6. Determine the optimal hyperparameter configuration based on the Bayesian optimization results;

[0034] C7. Use the best hyperparameter configuration to train the random forest model on the training set and predict the future biogas production;

[0035] Improve the performance of the random forest prediction model by adjusting the hyperparameter search range or adding features. If the preset stop condition is reached, output the hyperparameter combination corresponding to the optimal value of the current objective function; otherwise, repeat steps C5 to C6 until the prediction performance is achieved.

[0036] Solution 2: An anaerobic fermentation process health evaluation system, including a regulating tank, a reaction tank, a controller, a valve, a pipeline, a biogas pipeline, a sensor module and a cloud computing platform;

[0037] The sensor module includes a weight sensor, a flow sensor, a first temperature sensor, a second temperature sensor, a pH sensor, and an ORP sensor;

[0038] The regulating tank is connected to the reaction tank through a pipeline, and the upper end of the reaction tank is connected to the biogas pipeline;

[0039] A weight sensor is installed below the regulating tank, and a valve is installed on the pipeline;

[0040] A flow sensor is installed on the biogas pipeline, the input end of the flow sensor is connected to the biogas pipeline, and the output end wirelessly transmits data to the cloud computing platform;

[0041] The first temperature sensor, the second temperature sensor, the pH sensor, and the ORP sensor are all installed on the reaction tank, and the output ends of the first temperature sensor, the second temperature sensor, the pH sensor, and the ORP sensor are wirelessly transmitted to the cloud computing platform;

[0042] The cloud computing platform wirelessly outputs instructions to the controller;

[0043] The controller wirelessly receives the weight sensor signal, and the output end of the controller is connected to the valve.

[0044] The beneficial effects of the present invention are:

[0045] 1. The present invention is real-time and can quickly respond to changes in fermentation conditions to ensure stable operation of the fermentation process.

[0046] 2. The present invention has accuracy, combining the evaluation of physical and chemical parameters with the monitoring of microbial communities, such as using PCR technology or metagenomics analysis, to comprehensively evaluate the fermentation process. Advanced sensors and data processing algorithms are used to improve the accuracy of monitoring data.

[0047] 3. The present invention is more intelligent. Based on the cloud computing platform and machine learning model, it can realize intelligent control of the fermentation process, improve the production efficiency of biomass energy, and provide guarantee for the stability of the fermentation process, thereby promoting the commercialization of biomass energy.

[0048] 4. The present invention has lower production cost, and the selected sensors have the characteristics of high precision and low price, which effectively reduces the monitoring cost.

[0049] 5. The present invention can be widely used and is applicable to various biomass fermentation projects. It can optimize the fermentation process, reduce energy consumption and environmental pollution, and provide technical support for the development of green energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a structural schematic diagram of the present invention;

[0051] In the figure: 1-regulating tank, 2-reaction tank, 3-controller, 4-valve, 5-pipeline, 6-weight sensor, 7-flow sensor, 8-biogas pipeline, 9-first temperature sensor, 10-pH sensor, 11-ORP sensor, 12-second temperature sensor, 13-cloud computing platform. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0053] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0054] In the present application, the directions or positional relationships indicated by the terms "upper", "lower", "inner", "middle", "outer", "front", "back", etc. are based on the directions or positional relationships shown in the drawings. These terms are mainly used to better describe the present application and its embodiments, and are not used to limit the indicated devices, elements or components to have a specific direction, or to be constructed and operated in a specific direction.

[0055] In addition, some of the above terms may be used to express other meanings in addition to indicating orientation or positional relationship. For example, the term "on" may also be used to express a certain dependency or connection relationship in some cases. For those of ordinary skill in the art, the specific meanings of these terms in this application can be understood according to specific circumstances.

[0056] In addition, the terms "disposed", "connected", and "fixed" should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection, or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be an internal connection between two devices, elements, or components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0057] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0058] Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0059] Example 1: A method for evaluating the health of an anaerobic fermentation process in this example, the specific steps are as follows:

[0060] Step 1: Use the sensor module to monitor and collect key data in the anaerobic fermentation process in real time;

[0061] Step 2: Send the data collected by the sensor module to the cloud computing platform via wireless transmission;

[0062] Step 3: On a cloud computing platform, the data is processed and analyzed using a machine learning algorithm to predict the health status of the anaerobic fermentation process;

[0063] Step 4: According to the analysis results, the control parameters of the fermentation process are automatically adjusted to optimize the fermentation process;

[0064] Step 5: Combine the evaluation of physicochemical parameters with the monitoring of the microbial community, and use PCR technology or metagenomic analysis to comprehensively evaluate the fermentation process.

[0065] More specifically: the sensor module includes a weight sensor, a flow sensor, a first temperature sensor, a second temperature sensor, a pH sensor, and an ORP sensor;

[0066] More specifically: key data include but are not limited to pH, temperature, gas production;

[0067] More specifically: the control parameters are the frequency of the ultrasonic transmitter and the amount of additive added;

[0068] More specifically: the specific implementation process of step 3 is:

[0069] A. Use the box-line method to process the data, and view the distribution of the data in a graphical way, including the median, quartile, maximum value, minimum value, and outliers. Delete the data marked outside the dotted line and use the Newton interpolation method to calculate the filling value to ensure data integrity;

[0070] B. Using normalized data transformation, the data of anaerobic fermentation process has different dimensions, and the collected data needs to be standardized to avoid data distribution disorder caused by the dimensions. Formula (1) is used to standardize the standard deviation of the collected data to ensure that each parameter can participate in model training fairly;

[0071]

[0072] In the formula: x′ is the normalized value, x is the value to be normalized, μ is the mean of the collected data, and δ is the standard deviation of the original data;

[0073] C. Gas production prediction is to find the optimal solution of random forest hyperparameters through Bayesian optimization algorithm. In the Bayesian optimization calculation process, the objective function of hyperparameter optimization (model verification error) is first set, and the optimal solution is determined by evaluating different combinations of parameters; the parameters that need to be tuned include: the number of trees (n_estimators), the maximum depth of the tree (max_depth), the maximum number of features (max_features), the minimum number of leaf node samples (min_samples_leaf), and the sample sampling ratio (bootstrap);

[0074] D. The prediction of the health status of the cloud computing platform is:

[0075] 30-day average daily gas production = (a1+a2+…a30) / 30, the average daily gas production of the previous 30 days;

[0076] 3-day average daily gas production = (today's predicted gas production + a1 + a2) / 3;

[0077] Health prediction index = 5-day average daily gas production / 30-day average daily gas production;

[0078] If the health prediction index is ≥0.95, it indicates that the health status is good; if 0.95>health prediction index ≥0.85, it indicates that there is a problem with the health status and it is recommended to measure the indicators of volatile fatty acids; if the health prediction index is <0.85, it indicates that the health status is poor and active intervention must be carried out.

[0079] More specifically: The biogas production prediction algorithm process of the improved random forest combined with Bayesian optimization is as follows:

[0080] C1. Divide the collected data into training set and test set;

[0081] C2. Build a random forest regression model and set initial hyperparameters;

[0082] C3. Define the objective function f(x) of the random forest regression model, such as root mean square error (RMSE) or mean absolute error (MAE);

[0083] C4. Determine the hyperparameters and value ranges of the random forest regression model to be optimized;

[0084] C5. Perform Bayesian iterative optimization within the set hyperparameter range, and evaluate the objective function and update the Bayesian optimization algorithm model in real time;

[0085] C6. Determine the optimal hyperparameter configuration based on the Bayesian optimization results;

[0086] C7. Use the best hyperparameter configuration to train the random forest model on the training set and predict the future biogas production;

[0087] Improve the performance of the random forest prediction model by adjusting the hyperparameter search range or adding features. If the preset stop condition is reached, output the hyperparameter combination corresponding to the optimal value of the current objective function; otherwise, repeat steps C5 to C6 until the prediction performance is achieved.

[0088] More specifically: the data collected are the processed biogas production, temperature, and pH value;

[0089] More specifically: hyperparameters include the maximum depth of the tree, the minimum number of sample splits, the minimum number of sample leaf nodes, and the random sampling ratio of features;

[0090] The cloud computing platform uses machine learning models to analyze data to predict the health status of the fermentation process; based on the prediction results, the frequency of the ultrasonic transmitter and the dosage parameters of the additive are automatically adjusted to optimize the microbial growth environment; combined with the evaluation of physical and chemical parameters and the monitoring of microbial communities, PCR technology or metagenomics analysis is used to comprehensively evaluate the fermentation process.

[0091] Example 2: Combination Figure 1 , a health evaluation system for an anaerobic fermentation process, comprising: a regulating tank 1, a reaction tank 2, a controller 3, a valve 4, a pipeline 5, a weight sensor 6, a flow sensor 7, a biogas pipeline 8, a first temperature sensor 9, a pH sensor 10, an ORP sensor 11, a second temperature sensor 12, and a cloud computing platform 13.

[0092] In actual application, valve 4 is opened first, and the material enters reaction tank 2 through pipe 5 after being homogenized by regulating tank 1. During the fermentation process, sensors are used for real-time monitoring and wireless data transmission to cloud computing platform 13. Cloud computing platform 13 processes the data and predicts the health status of the fermentation process. Finally, control parameters are automatically adjusted to achieve the purpose of optimizing the fermentation process.

[0093] The sensor module includes a weight sensor 6, a flow sensor 7, a first temperature sensor 9, a second temperature sensor 12, a pH sensor 10, and an ORP sensor 11;

[0094] The regulating tank 1 is connected to the reaction tank 2 via a pipeline 5, and the upper end of the reaction tank 2 is connected to a biogas pipeline 8;

[0095] A weight sensor 6 is installed below the regulating tank 1, and a valve 4 is installed on the pipeline 5;

[0096] The flow sensor 7 is installed on the biogas pipeline 8, and the output end of the flow sensor 7 wirelessly transmits data to the cloud computing platform 13;

[0097] The first temperature sensor 9, the second temperature sensor 12, the pH sensor 10, and the ORP sensor 11 are all installed on the reaction tank 2; the output ends of the first temperature sensor 9, the second temperature sensor 12, the pH sensor 10, and the ORP sensor 11 are wirelessly transmitted to the cloud computing platform 13;

[0098] The cloud computing platform 13 wirelessly outputs instructions to the controller 3;

[0099] The controller 3 wirelessly receives the signal from the weight sensor 6 , and the output end of the controller 3 is connected to the valve 4 .

[0100] More specifically: the cloud computing platform 13 predicts gas production and health status, and automatically adjusts control parameters;

[0101] More specifically: select sensors with high precision and low cost to monitor key parameters in the fermentation process in real time and ensure data accuracy;

[0102] More specifically: using machine learning models on cloud computing platforms to process, analyze and predict collected data in real time, providing a basis for intelligent control strategies;

[0103] More specifically: based on the analysis results of the data processing center, the frequency of the ultrasonic transmitter and the dosage parameters of the additive are automatically adjusted to optimize the microbial growth environment;

[0104] More specifically: Design an intuitive and easy-to-use operating interface to facilitate users to understand the status of the fermentation process in real time and make manual adjustments to the system as needed.

[0105] The anaerobic fermentation process health assessment method and system of the present invention can timely discover and solve problems in the fermentation process, and improve the stability and biogas production of the anaerobic fermentation process. Through multifunctional sensors, cloud computing platforms and machine learning algorithms, real-time monitoring, prediction and optimization of the fermentation process are achieved to improve biogas production and the stability of the fermentation process. It has broad application prospects in the field of biomass energy and helps promote the scientific and technological progress and sustainable development of the biogas industry. At the same time, the invention can also provide reference for microbial fermentation processes in other fields and contribute to the development of the bio-industry.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, the technical solutions described in the aforementioned embodiments can still be modified, or some or all of the technical features therein can be replaced by equivalents. As long as there is no structural conflict, the various features in the specific implementation methods disclosed in this application can be combined with each other in any way, and the essence of the corresponding technical solutions will not deviate from the scope of the technical solutions of the present invention.

[0107] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A method for evaluating the health of an anaerobic fermentation process, characterized in that: The specific steps are: Step 1: Use the sensor module to monitor and collect key data in the anaerobic fermentation process in real time; Step 2: Send the data collected by the sensor module to the cloud computing platform via wireless transmission; Step 3: On a cloud computing platform, the data is processed and analyzed using a machine learning algorithm to predict the health status of the anaerobic fermentation process; Step 4: According to the analysis results, the control parameters of the fermentation process are automatically adjusted to optimize the fermentation process; Step 5: Combine the evaluation of physicochemical parameters with the monitoring of the microbial community, and use PCR technology or metagenomic analysis to comprehensively evaluate the fermentation process.

2. The method for health assessment of an anaerobic fermentation process according to claim 1, characterized in that: The specific implementation process of step 3 is as follows: A. Use the boxplot method to process the data, and view the distribution of the data in a graphical way, including the median, quartiles, maximum value, minimum value, and outliers. Delete the data marked outside the dotted line and use the Newton interpolation method to calculate the filling value for filling; B. Using normalized data transformation, use formula (1) to normalize the standard deviation of the collected data; In the formula: x′ is the normalized value, x is the value to be normalized, μ is the mean of the collected data, and δ is the standard deviation of the original data; C. Gas production prediction is to find the optimal solution of random forest hyperparameters through Bayesian optimization algorithm. In the Bayesian optimization calculation process, the objective function of hyperparameter optimization is first set, and the optimal solution is determined by evaluating different combinations of parameters. The parameters that need to be tuned include: the number of trees, the maximum depth of the tree, the maximum number of features, the minimum number of leaf node samples, and the sample sampling ratio; D. The prediction of the health status of the cloud computing platform is: 30-day average daily gas production = (a1+a2+…a30) / 30, the average daily gas production of the previous 30 days; 3-day average daily gas production = (today's predicted gas production + a1 + a2) / 3; Health prediction index = 5-day average daily gas production / 30-day average daily gas production; If the health prediction index is ≥0.95, it indicates that the health status is good; if 0.95>health prediction index ≥0.85, it indicates that there is a problem with the health status and it is recommended to measure the indicators of volatile fatty acids; if the health prediction index is <0.85, it indicates that the health status is poor and active intervention must be carried out.

3. The method for health assessment of an anaerobic fermentation process according to claim 2, characterized in that: The process of biogas production prediction algorithm based on improved random forest combined with Bayesian optimization is as follows: C1. Divide the collected data into training set and test set; C2. Build a random forest regression model and set initial hyperparameters; C3. Define the objective function of the random forest regression model, such as root mean square error or mean absolute error; C4. Determine the hyperparameters and value ranges of the random forest regression model to be optimized; C5. Perform Bayesian iterative optimization within the set hyperparameter range, and evaluate the objective function and update the Bayesian optimization algorithm model in real time; C6. Determine the optimal hyperparameter configuration based on the Bayesian optimization results; C7. Use the best hyperparameter configuration to train the random forest model on the training set and predict the future biogas production; By adjusting the hyperparameter search range or adding features, the performance of the random forest prediction model is improved. If the preset stop condition is reached, the hyperparameter combination corresponding to the optimal value of the current objective function is output; otherwise, steps C5 to C6 are repeated until the prediction performance is achieved.

4. An anaerobic fermentation process health evaluation system, characterized in that: The structure comprises a regulating tank (1), a reaction tank (2), a controller (3), a valve (4), a pipeline (5), a biogas pipeline (8), a cloud computing platform (13) and a sensor module; The sensor module comprises a weight sensor (6), a flow sensor (7), a first temperature sensor (9), a second temperature sensor (12), a pH sensor (10), and an ORP sensor (11); The regulating tank (1) is connected to the reaction tank (2) via a pipeline (5), and the upper end of the reaction tank (2) is connected to a biogas pipeline (8); A weight sensor (6) is installed below the regulating tank (1), and a valve (4) is installed on the pipeline (5); A flow sensor (7) is installed on the biogas pipeline (8), the input end of the flow sensor (7) is connected to the biogas pipeline (8), and the output end wirelessly transmits data to the cloud computing platform (13); The first temperature sensor (9), the second temperature sensor (12), the pH sensor (10), and the ORP sensor (11) are all installed on the reaction tank (2); the output ends of the first temperature sensor (9), the second temperature sensor (12), the pH sensor (10), and the ORP sensor (11) are wirelessly transmitted to the cloud computing platform (13); The cloud computing platform (13) wirelessly outputs instructions to the controller (3); The controller (3) wirelessly receives the signal from the weight sensor (6), and the output end of the controller (3) is connected to the valve (4).

Citation Information

Patent Citations

  • Method for monitoring high-temperature anerobic fermentation operation parameters through using wireless real-time monitoring system of high-temperature anerobic fermentation operation parameters

    CN103398746A

  • Biogas anaerobic fermentation state monitoring system

    CN116769581A