CN116307249A - Biogas yield prediction method and device based on self-learning training data set - Google Patents
Biogas yield prediction method and device based on self-learning training data set Download PDFInfo
- Publication number
- CN116307249A CN116307249A CN202310385348.6A CN202310385348A CN116307249A CN 116307249 A CN116307249 A CN 116307249A CN 202310385348 A CN202310385348 A CN 202310385348A CN 116307249 A CN116307249 A CN 116307249A
- Authority
- CN
- China
- Prior art keywords
- biogas yield
- data
- model
- yield prediction
- biogas
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E50/00—Technologies for the production of fuel of non-fossil origin
- Y02E50/30—Fuel from waste, e.g. synthetic alcohol or diesel
Landscapes
- Processing Of Solid Wastes (AREA)
Abstract
The invention discloses a methane yield prediction method and device based on a self-learning training data set. Acquiring a historical operation parameter set of the anaerobic device; preprocessing the acquired historical operation parameter set, and screening out an operation parameter set in a stable operation stage; sorting the screened operation parameter sets to form a sample set of a least square support vector machine model; establishing a least square support vector machine model, and training the model by using a sample set to obtain a biogas yield prediction model; and predicting the biogas yield of the anaerobic device by using the biogas yield prediction model. The invention can better reflect the relevance of each operation parameter and the biogas yield, and improve the prediction accuracy of the biogas yield of the anaerobic device.
Description
Technical Field
The invention relates to a biogas yield prediction method and device of an anaerobic device in a biogas preparation process by anaerobic fermentation of kitchen waste, and belongs to the field of kitchen waste resource utilization.
Background
Kitchen waste is a renewable resource with rich organic matter content and huge potential, and biogas generated in the kitchen waste treatment process is clean biomass energy. At present, the biogas production capacity of the kitchen waste unit raw materials in China is 50-120 cubic meters per ton. According to statistics of the national institutional kitchen waste treatment project of the Chinese urban environmental sanitation co-society of organic solid waste of the specialized committee, 2019, the national construction kitchen waste treatment project is 7.2 ten thousand tons per day, wherein the anaerobic treatment capacity of the kitchen waste is 5.9 ten thousand tons per day, and the annual biogas yield is 16.8 hundred million cubic meters according to 80 cubic meters of biogas produced per ton of kitchen waste; the biogas utilization rates of the kitchen wastes in China are estimated to be 80%, 90% and 90% in 2025, 2030 and 2060, and the average biogas production capacities of the kitchen wastes are respectively calculated according to 80, 150 and 200 cubic meters per ton, and the biogas production potential is about 27 hundred million cubic meters, 85.1 hundred million cubic meters and 166 hundred million cubic meters. Therefore, the effective treatment and utilization of the kitchen waste has great significance for recycling economy and carbon emission reduction.
The anaerobic treatment method of the kitchen waste generally adopts the technological processes of sorting, impurity removal, pulping, oil extraction and dehydration, an anaerobic reactor, biogas desulfurization, biogas decarbonization and dehydration, a biogas storage cabinet and biogas utilization. As shown in fig. 1, large sundries, metals, plastics and the like which are unsuitable for biochemical treatment are screened out by crushing and sorting in the pretreatment process, and then grease is extracted by pulping; then enters an anaerobic reaction tank to be subjected to anaerobic digestion by microorganisms to generate biogas; the biogas can be used for power generation or can be sold after a series of purification processes such as desulfurization and the like; the biogas residue can be used for preparing organic fertilizer or fuel.
Anaerobic fermentation biogas production is a key link of a kitchen waste treatment system. Anaerobic fermentation technology is a process of degrading organic substances by utilizing anaerobic or facultative anaerobic microorganisms under anaerobic conditions to obtain methane and carbon dioxide. Anaerobic digestion has many influencing factors such as temperature, pH, C/N ratio, organic volume load, oil content, oxidation-reduction potential and the like, and various influencing factors must be controlled within an optimal range in order to make the gas production efficiency of anaerobic digestion high. Because the material components after the pretreatment of the kitchen waste inevitably have fluctuation, the biogas yield changes along with the fluctuation, and the biogas yield can be accurately predicted, so that the advanced response of the subsequent production steps is facilitated.
At present, biogas yield prediction of an anaerobic device mainly depends on an empirical formula and historical data statistics of the device, and the data processing workload in the process is large and the accuracy is low. In addition, preprocessing links for collecting data are generally lacking in the biogas yield prediction method based on the self-learning model, so that a few data sets with poor correlation participate in model learning, and model prediction accuracy is reduced.
Disclosure of Invention
The invention aims to provide a biogas yield prediction method and device based on a self-learning training data set, so as to solve the problems of large workload and low accuracy caused by imperfect biogas yield prediction method of the existing anaerobic device.
In order to achieve the above purpose, the invention adopts the following technical scheme:
in one aspect, the invention provides a biogas yield prediction method based on a self-learning training data set, comprising the following steps:
acquiring a historical operation parameter set of the anaerobic device;
preprocessing the acquired historical operation parameter set, and screening out an operation parameter set in a stable operation stage;
sorting the screened operation parameter sets to form a sample set of a least square support vector machine model;
establishing a least square support vector machine model, and training the model by using a sample set to obtain a biogas yield prediction model;
and predicting the biogas yield of the anaerobic device by using the biogas yield prediction model.
Further, the acquiring the historical operating parameter set of the anaerobic device includes:
collecting the historical operation parameters of the normal operation of the anaerobic device, including the T, pH value of the reaction temperature, the C/N ratio and the inlet flow Q 0 COD concentration at inlet c 0 The solid content TS at the inlet, the oil content O at the inlet, the oxidation-reduction potential ORP, the residence time t and the biogas yield G form a historical operation parameter set P= { P i |=1, 2,3, … n }, where P i ＝(T i ,pH i ,C/N i ,Q 0i ,c 0i ,TS％ i ,O％ i ,ORP i ,t i ,G i |＝1,2,3,…n)，P i For the i-th group of data collected, data are collected at the same time interval, the data collected at the same time are a group, n is the number of the collected data groups, and the data of each group are arranged in time sequence.
Further, the preprocessing the obtained historical operation parameter set, and screening the operation parameter set in the stable operation stage includes:
calculating each parameter A of the ith group of data in the historical operating parameter set P according to the following formula qi The same parameter A relative to the previous set of data q(i-1) Rate of change K of (2) i ：
Wherein q is the parameter sequence number of the ith group of data, and q=1, 2,3 and … … 10;
if |K i And (3) deleting the data of the ith group from the data set, wherein the rest data set is the screened operation parameter set.
Further, the sorting the screened operation parameter set to form a sample set of the least square support vector machine model includes:
for each set of data in the screened operating parameter set, the simulation is performedFix x i ＝(T i ,pH i ,C/N i ,Q 0i ,c 0i ,TS％ i ,O％ i ,ORP i ,t i |i＝1,2,3,…k)，y i ＝(G i I=1, 2,3, … k) to form a data sample set D 0 ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),(x 3 ,y 3 )…(x k ,y k )},x i ∈R l ,y i ∈R m Wherein k is the number of training samples, x i For input l-dimensional training samples, y i For input m-dimensional training samples, R l For a l-dimensional sample dataset, R m Is an m-dimensional sample dataset.
Further, the building a least squares support vector machine model includes:
selecting an objective function:
wherein w is a weight, C is a penalty parameter, b is a bias value,
is a nonlinear mapping function, ζ i Is a relaxation variable;
converting the objective function into an unconstrained objective function through a Lagrangian method:
wherein: y= [ y ] 1 ,…,y k ] T ；I v ＝[1,…,1] T ；x＝[x 1 ,…,x k ] T ；a＝[a 1 ,…,a k ] T A is the Lagrangian multiplier; i isA k x k unit array; Ω= { Ω ij |i,j＝1…k}，
Is a radial basis kernel function, and sigma is a kernel width;
after solving a and b, obtaining a least square support vector machine model as
Further, the biogas yield prediction method based on the self-learning training data set further comprises the following steps:
based on the monitoring data of the factory-level information system, a training set of the biogas yield prediction model is updated, and the biogas yield prediction model is optimized in real time.
In another aspect, the present invention provides a biogas yield prediction apparatus based on a self-learning training data set, comprising:
the acquisition module is used for acquiring a historical operation parameter set of the anaerobic device;
the preprocessing module is used for preprocessing the acquired historical operation parameter set and screening out the operation parameter set in the stable operation stage;
the sorting module is used for sorting the screened operation parameter sets to form a sample set of the least square support vector machine model;
the model construction module is used for building a least square support vector machine model, and training the model by utilizing a sample set to obtain a biogas yield prediction model;
and the prediction module is used for predicting the biogas yield of the anaerobic device by using the biogas yield prediction model.
Further, the biogas yield prediction device based on the self-learning training data set further comprises:
the model optimization module is used for updating the training set of the biogas yield prediction model based on the monitoring data of the factory-level information system and optimizing the biogas yield prediction model in real time.
In another aspect, the present invention provides a computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform the aforementioned biogas production prediction method based on a self-learning training data set.
In another aspect, the invention provides a computing device comprising: one or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, the one or more programs including means for performing the aforementioned biogas production prediction method based on the self-learning training data set.
The invention achieves the beneficial technical effects that:
(1) The biogas yield prediction method based on the empirical formula and the historical data statistics avoids the prior biogas yield prediction method based on the empirical formula and the historical data statistics, has higher accuracy, and is beneficial to improving the intelligent operation management capability of the kitchen waste recycling system.
(2) According to the method, the data set with poor correlation generated in the unstable operation stage of the anaerobic device is eliminated through pretreatment of the data set, so that the accuracy of model prediction is further improved.
Drawings
FIG. 1 is a system diagram of a process for preparing methane from kitchen waste;
FIG. 2 is a flow chart of the method of the present invention;
FIG. 3 is another flow chart of a biogas yield prediction method based on a self-learning training data set according to an embodiment of the invention;
FIG. 4 is a schematic view of the structure of the device of the present invention;
FIG. 5 is a schematic view of another construction of the apparatus of the present invention; .
Detailed Description
The invention is further described below in connection with specific embodiments. The following examples are only for more clearly illustrating the technical aspects of the present invention, and are not intended to limit the scope of the present invention.
As shown in fig. 2 and 3, the biogas yield prediction method based on the self-learning training data set comprises the following steps:
step S1, acquiring a historical operation parameter set of an anaerobic device;
collecting operation parameters of the anaerobic device during 2 years of normal operation, including a reaction temperature T, pH value, a C/N ratio and an inlet flow Q 0 COD concentration at inlet c 0 The solid content TS at the inlet, the oil content O at the inlet, the oxidation-reduction potential ORP, the residence time t and the biogas yield G to form a data set P= { P i I=1, 2,3, … n, where P i ＝(T i ,pH i ,C/N i ,Q 0i ,c 0i ,TS％ i ,O％ i ,ORP i ,t i ,G i |i＝1,2,3,…n)，P i For the i-th group of data, the data collection interval is 2h, the data collected at the same time is a group, the data are arranged according to the time sequence, and n is the number of the collected data groups.
Step S2, preprocessing the acquired historical operation parameter set, and screening out an operation parameter set in a stable operation stage;
calculating each parameter A for the ith group of data in the data set P according to the following formula qi Relative to the same parameter A of the previous group q(i-1) Rate of change K of (2) i ：
Wherein q is the parameter sequence number of the ith group of data, and q=1, 2,3 and … … 10;
when |K i When the I is more than 0.1, the group of data is regarded as unsteady data, the unsteady data is deleted from the data set P, and the data set left after the data preprocessing is used as a sample set P' for model learning.
The purpose of this step is to screen out the set of operating parameters during steady operation of the device. Since the change of the biogas yield has a certain time lag compared with the adjustment of the inlet parameter, the data of the inlet parameter and the biogas yield collected at the same time in the stage with larger parameter adjustment amplitude have little correlation, so the data are omitted. The screened data set is a sample of the anaerobic device which stably operates under different parameter conditions, and is used as an input sample set of the model.
S3, sorting the screened operation parameter sets to form a sample set of a least square support vector machine model;
for each group of data in the data set P' screened in step S2, x is formulated i ＝(T i ,pH i ,C/N i ,Q 0i ,c 0i ,TS％ i ,O％ i ,ORP i ,t i |i＝1,2,3,…k)，y i ＝(G i I=1, 2,3, … k) to form a data sample set D 0 ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),(x 3 ,y 3 )…(x k ,y k )},x i ∈R l ,y i ∈R m Wherein k is the number of training samples, x i For input l-dimensional training samples, y i Training samples for the input m dimensions. R is R l For a l-dimensional sample dataset, R m Is an m-dimensional sample dataset. In the biogas production prediction model of the present application, l= 9,m =1.
The sample set is divided into a training set and a test set. Wherein the number of training sets is 90% of the sample sets, and the number of test sets is 10% of the sample sets.
S4, a least square support vector machine model is established, and training is carried out on the model by utilizing a sample set to obtain a biogas yield prediction model;
and (3) inputting the sample set sorted in the step (S3) into a least square support vector machine for modeling.
The following objective function is selected:
wherein w is a weight, C is a penalty parameter, b is a bias value,
is a nonlinear mapping function, ζ i Is a relaxation variable; converting the objective function containing the constraint condition into an unconstrained objective function through a Lagrangian method:
wherein: y= [ y ] 1 ,…,y k ] T ；I v ＝[1,…,1] T ；x＝[x 1 ,…,x k ] T ；a＝[a 1 ,…,a k ] T A is the Lagrangian multiplier; i is a k×k unit array; Ω= { Ω ij |i,j＝1…k}，
Is a radial basis kernel function, and sigma is a kernel width;
after solving a and b, obtaining a biogas yield prediction model based on a least square support vector machine as follows
And (3) training the training set obtained in the step (S3) by using the function, and establishing a biogas prediction model based on a least square support vector machine. Inputting the test set obtained in the step S3 into a model, wherein the obtained calculated value is a predicted value of the biogas yield, and when the error between the predicted result of the model and the actual biogas yield is acceptable, the model can be used as a biogas yield prediction model.
And S5, predicting the biogas yield of the anaerobic device by using the biogas yield prediction model.
In a preferred embodiment, the biogas yield prediction method based on the self-learning training data set further comprises:
and S6, updating a training set of the biogas yield prediction model based on monitoring data of the factory-level information system, and optimizing the biogas yield prediction model in real time.
As shown in fig. 3, data monitored in real time during operation of the anaerobic device are obtained, a model for predicting biogas yield of the anaerobic device based on a least square support vector machine is established, and the steps S2-S4 are repeated, so that the model can be further optimized, and the model prediction precision is improved.
The method aims at carrying out model training through continuously updated data, optimizing a prediction model and enabling output results to be more accurate.
In step S6, when the error between the prediction result of the model and the actual biogas yield is acceptable, the model can be used as a theoretical basis for guiding biogas preparation and subsequent production.
In another embodiment, the invention provides a biogas yield prediction device based on a self-learning training data set, as shown in fig. 4, comprising:
the acquisition module is used for acquiring a historical operation parameter set of the anaerobic device;
the preprocessing module is used for preprocessing the acquired historical operation parameter set and screening out the operation parameter set in the stable operation stage;
the sorting module is used for sorting the screened operation parameter sets to form a sample set of the least square support vector machine model;
the model construction module is used for building a least square support vector machine model, and training the model by utilizing a sample set to obtain a biogas yield prediction model;
and the prediction module is used for predicting the biogas yield of the anaerobic device by using the biogas yield prediction model.
In a preferred embodiment, the biogas yield prediction device based on the self-learning training data set further comprises:
the model optimization module is used for updating the training set of the biogas yield prediction model based on the monitoring data of the factory-level information system and optimizing the biogas yield prediction model in real time.
In another embodiment, the invention provides a computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform the aforementioned biogas production prediction method based on a self-learning training data set.
In another embodiment, the invention provides a computing device comprising: one or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, the one or more programs including means for performing the aforementioned biogas production prediction method based on the self-learning training data set.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The present invention has been disclosed in the preferred embodiments, but the invention is not limited thereto, and the technical solutions obtained by adopting equivalent substitution or equivalent transformation fall within the protection scope of the present invention.
Claims (10)
1. The biogas yield prediction method based on the self-learning training data set is characterized by comprising the following steps of:
acquiring a historical operation parameter set of the anaerobic device;
preprocessing the acquired historical operation parameter set, and screening out an operation parameter set in a stable operation stage;
sorting the screened operation parameter sets to form a sample set of a least square support vector machine model;
establishing a least square support vector machine model, and training the model by using a sample set to obtain a biogas yield prediction model;
and predicting the biogas yield of the anaerobic device by using the biogas yield prediction model.
2. The biogas yield prediction method based on a self-learning training data set according to claim 1, wherein the acquiring a historical operating parameter set of an anaerobic device comprises:
collecting the historical operation parameters of the normal operation of the anaerobic device, including the T, pH value of the reaction temperature, the C/N ratio and the inlet flow Q 0 COD concentration at inlet c 0 The solid content TS in the inlet, the oil content O in the inlet, the oxidation-reduction potential ORP, the residence time t and the biogas yield GHistorical operating parameter set p= { P i |=1, 2,3, … n }, where P i ＝(T i ,pH i ,C/N i ,Q 0i ,c 0i ,TS％ i ,O％ i ,ORP i ,t i ,G i |＝1,2,3,…n)，P i For the i-th group of data collected, data are collected at the same time interval, the data collected at the same time are a group, n is the number of the collected data groups, and the data of each group are arranged in time sequence.
3. The biogas yield prediction method based on a self-learning training data set according to claim 2, wherein the preprocessing of the acquired historical operating parameter set and screening out the operating parameter set in the steady operation stage comprises:
calculating each parameter A of the ith group of data in the historical operating parameter set P according to the following formula qi The same parameter A relative to the previous set of data q(i-1) Rate of change K of (2) i ：
Wherein q is the parameter sequence number of the ith group of data, and q=1, 2,3 and … … 10;
if |K i And (3) deleting the data of the ith group from the data set, wherein the rest data set is the screened operation parameter set.
4. The biogas yield prediction method based on a self-learning training data set according to claim 3, wherein the sorting the screened operation parameter set to form a sample set of a least squares support vector machine model comprises:
for each group of data in the screened operation parameter set, fitting x i ＝(T i ,pH i ,C/N i ,Q 0i ,c 0i ,TS％ i ,O％ i ,ORP i ,t i |i＝1,2,3,…k)，y i ＝(G i |i＝1,2,3,…k)，Forming a data sample set D 0 ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),(x 3 ,y 3 )…(x k ,y k )},x i ∈R l ,y i ∈R m Wherein k is the number of training samples, x i For input l-dimensional training samples, y i For input m-dimensional training samples, R l For a l-dimensional sample dataset, R m Is an m-dimensional sample dataset.
5. The biogas yield prediction method based on the self-learning training data set according to claim 4, wherein the building a least squares support vector machine model comprises:
selecting an objective function:
wherein w is a weight, C is a penalty parameter, b is a bias value,
is a nonlinear mapping function, ζ i Is a relaxation variable;
converting the objective function into an unconstrained objective function through a Lagrangian method:
wherein: y= [ y ] 1 ,…,y k ] T ；I v ＝[1,…,1] T ；x＝[x 1 ,…,x k ] T ；a＝[a 1 ,…,a k ] T A is the Lagrangian multiplier; i is a k×k unit array; Ω= { Ω ij |i,j＝1…k}，
Is a radial basis kernel function, and sigma is a kernel width;
after solving a and b, obtaining a least square support vector machine model as
6. The biogas yield prediction method based on a self-learning training data set according to claim 1, further comprising:
based on the monitoring data of the factory-level information system, a training set of the biogas yield prediction model is updated, and the biogas yield prediction model is optimized in real time.
7. A biogas yield prediction device based on a self-learning training data set, comprising:
the acquisition module is used for acquiring a historical operation parameter set of the anaerobic device;
the preprocessing module is used for preprocessing the acquired historical operation parameter set and screening out the operation parameter set in the stable operation stage;
the sorting module is used for sorting the screened operation parameter sets to form a sample set of the least square support vector machine model;
the model construction module is used for building a least square support vector machine model, and training the model by utilizing a sample set to obtain a biogas yield prediction model;
and the prediction module is used for predicting the biogas yield of the anaerobic device by using the biogas yield prediction model.
8. The biogas yield prediction device based on a self-learning training data set according to claim 7, further comprising:
the model optimization module is used for updating the training set of the biogas yield prediction model based on the monitoring data of the factory-level information system and optimizing the biogas yield prediction model in real time.
9. A computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform the biogas production prediction method based on the self-learning training data set of any one of claims 1-6.
10. A computing device, comprising: one or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, the one or more programs including instructions for performing the biogas production prediction method based on the self-learning training data set of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310385348.6A CN116307249A (en) | 2023-04-12 | 2023-04-12 | Biogas yield prediction method and device based on self-learning training data set |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310385348.6A CN116307249A (en) | 2023-04-12 | 2023-04-12 | Biogas yield prediction method and device based on self-learning training data set |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116307249A true CN116307249A (en) | 2023-06-23 |
Family
ID=86837999
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310385348.6A Pending CN116307249A (en) | 2023-04-12 | 2023-04-12 | Biogas yield prediction method and device based on self-learning training data set |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116307249A (en) |
-
2023
- 2023-04-12 CN CN202310385348.6A patent/CN116307249A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Deng et al. | Biogas as a sustainable energy source in China: Regional development strategy application and decision making | |
| Farhi et al. | Prediction of wastewater treatment quality using LSTM neural network | |
| Chiu et al. | Key wastes selection and prediction improvement for biogas production through hybrid machine learning methods | |
| Ren | GM (1, N) method for the prediction of anaerobic digestion system and sensitivity analysis of influential factors | |
| Yildirim et al. | Prediction of biogas production of industrial scale anaerobic digestion plant by machine learning algorithms | |
| Li et al. | Exploring available input variables for machine learning models to predict biogas production in industrial-scale biogas plants treating food waste | |
| Walid et al. | Modeling and optimization of anaerobic digestion: a review | |
| Offie et al. | Development of an artificial intelligence-based framework for biogas generation from a micro anaerobic digestion plant | |
| Ahmad et al. | A comprehensive machine learning-coupled response surface methodology approach for predictive modeling and optimization of biogas potential in anaerobic Co-digestion of organic waste | |
| Sun et al. | Prediction of biogas production in anaerobic digestion of a full‐scale wastewater treatment plant using ensembled machine learning models | |
| CN106706491B (en) | Intelligent detection method for membrane bioreactor-MBR water permeability | |
| CN116307249A (en) | Biogas yield prediction method and device based on self-learning training data set | |
| CN113849776B (en) | Optimization method for anaerobic process for kitchen waste treatment | |
| Wang | Multicriteria sustainability ranking of biohydrogen systems | |
| CN106769748B (en) | Intelligent detection system for water permeability of membrane bioreactor-MBR (Membrane bioreactor) | |
| Jeng et al. | Cradle-to-cradle zero discharge production planning system for the pulp and paper industry using a fuzzy hybrid optimization model | |
| CN109273058A (en) | A kind of composite algorism for the exceeded early warning of anaerobic processes volatile fatty acid | |
| Kang et al. | Research on forecasting method for effluent ammonia nitrogen concentration based on GRA-TCN | |
| CN111125082B (en) | Cement process parameter data analysis method based on association rule mining | |
| Li et al. | Machine learning enabled prediction and process optimization of VFA production from riboflavin-mediated sludge fermentation | |
| Enitan et al. | Multi-objective Optimization of Methane Producing UASB Reactor Using a Combined Pareto Multi–objective Differential Evolution Algorithm (CPMDE) | |
| CN114429258A (en) | Natural gas purification control method based on energy efficiency evaluation and online optimization platform | |
| Komarysta et al. | OPTIMIZING BIOGAS PRODUCTION USING ARTIFICIAL NEURAL NETWORK. | |
| CN112183642A (en) | Method and system for detecting coal consumption of cement firing based on random forest model | |
| Liu et al. | Hydrogen production from municipal solid waste: Potential prediction and environmental impact analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |