Design method of solar condensation driven biogas fermentation system based on biogas production performance prediction

Abstract

The invention provides a solar condensation driven biogas fermentation system design method based on biogas production performance prediction, and relates to the technical field of renewable energy sources, and the method comprises the steps: building a biogas yield prediction model through obtaining design parameters, previous operation parameters, to-be-fermented material component data and biogas fermentation evaluation indexes of a plurality of solar condensation systems; the method comprises the following steps: predicting evaluation indexes such as biogas yield, waste gas emission and fermentation cost, calculating a performance index based on component data of a to-be-fermented material, generating a fermentation influence index and a condensation efficiency influence index according to an operation parameter and a design parameter, setting an effective range of the system design parameter and the operation parameter, randomly generating a plurality of particles, iterative optimization is carried out to maximize a fitness value, and a deviation degree coefficient is calculated to find an optimal fermentation system design parameter combination. According to the method, the deep learning model and the multi-target particle swarm optimization algorithm are constructed, so that intelligent optimization design of the biogas fermentation system is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of renewable energy, and in particular to a design method for a solar energy concentration-driven biogas fermentation system based on gas production performance prediction. Background Art

[0002] Amidst the global energy transition, solar energy and biogas fermentation technologies have become crucial components of renewable energy. Solar concentrating technology concentrates sunlight to generate heat, which raises the temperature of the biogas fermentation process, promoting microbial activity and increasing biogas production. Traditional biogas fermentation systems rely heavily on fossil fuels or electricity, creating an urgent need for more sustainable solutions to achieve efficient energy utilization.

[0003] Currently, solar concentrating biogas fermentation systems are rapidly developing, with technological integration and material advancements significantly improving system efficiency. Data-driven optimization methods enable real-time monitoring and dynamic adjustments, driving the commercialization of these systems. Furthermore, government policies supporting renewable energy have further spurred the development of this technology, particularly in regions with abundant sunlight. Solar concentrating biogas fermentation systems are being applied to agricultural waste treatment and renewable energy production.

[0004] Conventional biogas fermentation systems often rely on fixed operating parameters and lack methods for predicting gas production performance based on material composition. This results in an inability to effectively assess the fermentation potential of different organic waste treatment processes, thus impacting the stability and optimization of biogas production. Furthermore, existing technologies often fail to fully utilize historical data and deep learning models for gas production prediction, limiting the intelligence and flexibility of the system.

[0005] Second, existing design methods fail to fully consider the impact of solar concentrating system design parameters on biogas production, often overlooking the regulatory effects of key factors such as concentration efficiency and light intensity on system performance. Furthermore, the lack of a dynamic adjustment mechanism makes it difficult to respond to changes in the fermentation process in practice, resulting in biogas production failing to meet expectations.

[0006] Therefore, it is necessary to provide a solar energy concentration driven biogas fermentation system design method based on gas production performance prediction to solve the above problems.

[0007] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0008] The purpose of the present invention is to provide a design method for a solar energy concentration driven biogas fermentation system based on gas production performance prediction, so as to solve the problems raised in the above background technology.

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] A design method for a solar concentrating-driven biogas fermentation system based on gas production performance prediction includes the following steps:

[0011] Step 1: Obtaining design parameters of multiple solar concentrating systems, operating parameters of the systems in previous operations, composition data of the fermented material, and biogas fermentation evaluation indicators. The design parameters of the solar concentrating systems include the area of the concentrating panels and the matching angle of the concentrating panels. The operating parameters include the fermentation temperature, fermentation time, and total feed mass of the fermenter. The composition data of the fermented material include moisture content, organic carbon content, total nitrogen content, volatile solid content, total solid content, and oil content. The biogas fermentation evaluation indicators include gas production, waste gas emissions, and fermentation cost.

[0012] Step 2: Calculating performance indices for characterizing the fermentation of the material to be fermented based on previous composition data of the material to be fermented, the performance indices including a fermentability index, an anaerobic digestion potential index, and a biodegradability index; calculating a fermentation impact index based on previous operating parameters of the system; and calculating a concentration efficiency impact index based on design parameters of multiple solar concentrating systems;

[0013] Step 3: Based on the deep learning network, a biogas production prediction model is constructed, whose input is the performance index, fermentation impact index, and concentration efficiency impact index, and whose output is the biogas fermentation evaluation index. The model is trained based on the performance index, fermentation impact index, concentration efficiency impact index, and biogas fermentation evaluation index of the fermented material in the past historical data. The performance index, fermentation impact index, and concentration efficiency index of the current fermented material are input into the biogas production prediction model to obtain the biogas fermentation evaluation index.

[0014] Step 4: Set the effective range of the system's design parameters and operating parameters, establish a functional relationship between the biogas fermentation evaluation index and the biogas production fitness value, take maximizing the fitness value as the optimization goal, randomly generate multiple particles based on the multi-objective particle swarm optimization algorithm and perform iterative optimization. The particles are a combination of parameters such as the concentrator area, the concentrator matching angle, the fermentation temperature of the fermenter, the fermentation time, and the total feed mass;

[0015] Step 5: Establish the ideal threshold of biogas production and the ideal threshold of each biogas fermentation evaluation index. Based on the ideal threshold of biogas production, calculate the deviation coefficient of each solution whose biogas production fitness value is greater than the ideal threshold of biogas production. The solution with the minimum deviation coefficient is taken as the optimal fermentation system design parameter combination.

[0016] Furthermore, the performance index for characterizing the fermentation of the material to be fermented is calculated based on the previous composition data of the material to be fermented, and the method is as follows:

[0017] The fermentability index is calculated based on the organic carbon content and total nitrogen content of the fermentation material, and the formula is:

[0018]

[0019] Wherein, FI represents fermentability index, C represents organic carbon content, and N represents total nitrogen content;

[0020] The anaerobic digestion potential index is calculated based on the volatile solid content and total solid content of the fermentation material, and the formula is:

[0021]

[0022] Among them, ADPI represents anaerobic digestibility potential index, VS represents volatile solid content, and TS represents total solid content;

[0023] The biodegradability index is calculated based on the moisture content, oil content, organic carbon content and total nitrogen content of the fermentation material, and the formula is:

[0024]

[0025] Where BI represents the biodegradability index, W oil is the fat content, W water is the organic carbon content.

[0026] Furthermore, the fermentation impact index is calculated based on the system's previous operating parameters, according to the following formula:

[0027] Based on the design operating parameters of the fermentation tank obtained during the past operation of the system, including fermentation temperature, fermentation time and total feed mass, where fermentation temperature includes optimal fermentation temperature and actual fermentation temperature, fermentation time includes optimal fermentation time and actual fermentation time, and total feed mass includes the mass of organic matter input and the mass of material in the fermentation tank, the fermentation impact index that affects the fermentation degree of the material is calculated based on the following formula:

[0028]

[0029] Among them, FII represents the fermentation impact index, T opt 、T actual are the optimal fermentation temperature and the actual fermentation temperature, t fer , t actual are the optimal fermentation time and the actual fermentation time, M in 、M totalare the total mass of organic matter input and the mass of material in the fermentation tank respectively.

[0030] Furthermore, the concentration efficiency impact index is calculated based on the design parameters of multiple solar concentrating systems, and the formula is as follows:

[0031]

[0032] Among them, ε represents the concentration efficiency impact index, S m is the area of the concentrator in the mth solar concentrating system, θ m is the concentrator panel matching angle in the mth solar concentrating system, m is the index of multiple solar concentrating systems, i∈[1,n], and n is the number of solar concentrating systems obtained.

[0033] Furthermore, a biogas production prediction model is constructed based on the deep learning network, with the input being the performance index and the output being the biogas content grade index, so as to obtain the corresponding biogas content grade index. The method is as follows:

[0034] The biogas production prediction model adopts a neural network convolution structure, including an input layer, a hidden layer and an output layer. The input layer is responsible for receiving the extracted performance index, fermentation impact index and focusing efficiency index; the hidden layer is used to process the extracted index data. By applying multiple convolution kernels and using the ReLU activation function, nonlinear relationships are introduced to enable the model to fit complex feature relationships; an independent neuron is set in the output layer, which is responsible for converting the performance index representation extracted by the hidden layer into the final prediction result, that is, the output biogas fermentation evaluation indicators include gas production Q1, waste gas emissions Q2 and fermentation cost Q3.

[0035] Furthermore, the effective ranges of the system's design parameters and operating parameters are set based on the following method:

[0036] The optimization constraints of the solar concentrating drive system are set, including: the value interval of the concentrating plate area is set to [10m 2 ,50m 2 ]; the value range of the focusing plate matching angle is set to [30°, 60°]; the value range of the fermentation temperature is set to [35℃, 55℃]; the value range of the fermentation time is set to 15 days to 20 days; the value range of the total feed mass is set to [500kg, 1000kg].

[0037] Furthermore, a functional relationship between the biogas fermentation evaluation index and the biogas production fitness value is established, with maximizing the fitness value as the optimization goal. The formula is as follows:

[0038]

[0039] Among them, F syd It represents the maximum biogas production fitness value, w1, w2, and w3 are the proportional weights of gas production, waste gas emissions, and fermentation cost in the biogas fermentation evaluation index, respectively, and w1+w2+w3=1, w1>w3>w2>0.

[0040] Furthermore, the deviation coefficient of each solution whose biogas production fitness value is greater than the ideal biogas production threshold is calculated, and the solution with the minimum deviation coefficient is taken as the optimal fermentation system design parameter combination. The method is based on:

[0041] Based on the Euclidean distance method, the optimal solution close to the optimal evaluation index is selected, and the formula is as follows:

[0042]

[0043] in, represents the deviation coefficient of the j-th biogas fermentation evaluation index in the i-th particle, is the value of the j-th biogas fermentation evaluation index in the i-th particle, The ideal threshold value of the jth biogas fermentation evaluation index in the i-th particle, j is the index of the biogas fermentation evaluation index. When j = 1, it represents the gas production index in the biogas fermentation evaluation index; when j = 2, it represents the waste gas emission index in the biogas fermentation evaluation index; when j = 3, it represents the fermentation cost index in the biogas fermentation evaluation index;

[0044] After calculating the deviation coefficients of all fitness values greater than the given ideal biogas production threshold, all calculated Compare the values and find the minimum value of each solution After determining the minimum value, the corresponding solution is the optimal combination of fermentation system design parameters.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] The present invention constructs a comprehensive biogas fermentation evaluation model, combines the design parameters of the solar concentrating system and the composition data of the fermented material, and uses deep learning technology to accurately predict key indicators such as biogas production, waste gas emissions, and fermentation costs. By calculating the performance index, fermentation impact index, and concentration efficiency impact index, the system can quantify the impact of different factors on the biogas fermentation process, thereby providing a scientific basis for optimization design. The multi-objective particle swarm optimization algorithm is used to effectively explore the optimal solution within the set parameter range, thereby improving the efficiency and effectiveness of the biogas fermentation process.

[0047] In addition, the present invention ensures the reliability and accuracy of each solution in the optimization process by establishing a functional relationship between the biogas production fitness value and the evaluation index, and introducing the Euclidean distance method to calculate the deviation coefficient. This method not only ensures the feasibility of the system design, but also can effectively reduce waste gas emissions during the fermentation process, reduce fermentation costs, and improve resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 Schematic diagram of the overall method of the present invention. DETAILED DESCRIPTION

[0049] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to specific embodiments.

[0050] It should be noted that, unless otherwise defined, the technical or scientific terms used in the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0051] Example:

[0052] See also Figure 1 A design method for a solar concentrating-driven biogas fermentation system based on gas production performance prediction is provided, and the specific steps include:

[0053] Step 1: Obtaining design parameters of multiple solar concentrating systems, operating parameters of the systems in previous operations, composition data of the fermented material, and biogas fermentation evaluation indicators. The design parameters of the solar concentrating systems include the area of the concentrating panels and the matching angle of the concentrating panels. The operating parameters include the fermentation temperature, fermentation time, and total feed mass of the fermenter. The composition data of the fermented material include moisture content, organic carbon content, total nitrogen content, volatile solid content, total solid content, and oil content. The biogas fermentation evaluation indicators include gas production, waste gas emissions, and fermentation cost.

[0054] Step 2: Calculating performance indices for characterizing the fermentation of the material to be fermented based on previous composition data of the material to be fermented, the performance indices including a fermentability index, an anaerobic digestion potential index, and a biodegradability index; calculating a fermentation impact index based on previous operating parameters of the system; and calculating a concentration efficiency impact index based on design parameters of multiple solar concentrating systems;

[0055] Step 3: Based on the deep learning network, a biogas production prediction model is constructed, whose input is the performance index, fermentation impact index, and concentration efficiency impact index, and whose output is the biogas fermentation evaluation index. The model is trained based on the performance index, fermentation impact index, concentration efficiency impact index, and biogas fermentation evaluation index of the fermented material in the past historical data. The performance index, fermentation impact index, and concentration efficiency index of the current fermented material are input into the biogas production prediction model to obtain the biogas fermentation evaluation index.

[0056] Step 4: Set the effective range of the system's design parameters and operating parameters, establish a functional relationship between the biogas fermentation evaluation index and the biogas production fitness value, take maximizing the fitness value as the optimization goal, randomly generate multiple particles based on the multi-objective particle swarm optimization algorithm and perform iterative optimization. The particles are a combination of parameters such as the concentrator area, the concentrator matching angle, the fermentation temperature of the fermenter, the fermentation time, and the total feed mass;

[0057] Step 5: Establish the ideal threshold of biogas production and the ideal threshold of each biogas fermentation evaluation index. Based on the ideal threshold of biogas production, calculate the deviation coefficient of each solution whose biogas production fitness value is greater than the ideal threshold of biogas production. The solution with the minimum deviation coefficient is taken as the optimal fermentation system design parameter combination.

[0058] It should be noted that the performance indices calculated based on the composition data of the fermented materials are crucial for optimizing the biogas fermentation process, because they provide a scientific basis for evaluating the fermentation potential of different organic materials. The fermentability index, anaerobic digestion potential index and biodegradability index together constitute a comprehensive evaluation of the fermentation characteristics of the materials, ensuring the precise adjustment of the fermentation conditions. Through these indices, the biogas production can be effectively predicted, thereby maximizing the resource utilization efficiency and the economic benefits of biogas fermentation, and promoting the sustainable development of renewable energy.

[0059] Therefore, it is necessary to calculate the performance index for characterizing the fermentation of the material to be fermented based on the component data of the material to be fermented, and the method is as follows:

[0060] The fermentability index is calculated based on the organic carbon content and total nitrogen content of the fermentation material, and the formula is:

[0061]

[0062] Among them, FI represents the fermentability index, C is the organic carbon content, and N is the total nitrogen content. In the above formula, the greater the organic carbon content C, the greater the fermentability index FI, because a higher organic carbon content means more carbon sources that can be utilized by microorganisms, thereby promoting anaerobic fermentation and increasing the potential for biogas production. An increase in the total nitrogen content N will lead to a decrease in FI, because excessive nitrogen may lead to nitrogen deposition, which has a negative impact on the environment and inhibits the metabolic activity of microorganisms. Therefore, the larger the FI, the better, indicating that the relative abundance of organic carbon in the fermented material is higher than the total nitrogen content, indicating that the material has good fermentability and potential biogas production capacity.

[0063] The anaerobic digestion potential index is calculated based on the volatile solid content and total solid content of the fermentation material, and the formula is:

[0064]

[0065] Among them, ADPI represents the anaerobic digestion potential index, VS is the volatile solids content, and TS is the total solids content. In the above formula, the higher the volatile solids content VS, the larger the anaerobic digestion potential index ADPI. This is because volatile solids mainly include organic matter that can be degraded by microorganisms, such as proteins, fats and sugars. These substances are decomposed by microbial metabolism in an anaerobic environment to produce biogas, which increases the anaerobic digestion potential index ADPI. An increase in TS will lead to a decrease in ADPI because the total solids content increases due to non-organic components, such as minerals and inorganic salts. These components cannot be degraded by microorganisms during the anaerobic digestion process, thereby affecting the efficiency and gas production of anaerobic digestion. Therefore, the larger the anaerobic digestion potential index ADPI, the better, indicating that the fermentation material can be more effectively converted into renewable energy, improving resource utilization efficiency, helping to promote sustainable agriculture and the development of clean energy, and reducing dependence on traditional fossil fuels.

[0066] The biodegradability index is calculated based on the moisture content, oil content, organic carbon content and total nitrogen content of the fermentation material, and the formula is:

[0067]

[0068] Where BI represents the biodegradability index, W oil is the fat content, W wateris the organic carbon content; in the above formula, the increase of organic carbon content C and total nitrogen content N will increase the biodegradability index BI, because the increased organic carbon content and total nitrogen content increase the substrate available for microbial decomposition, thereby increasing the potential for biodegradation. Microorganisms grow and reproduce by converting organic carbon into cell substances and metabolites; and the oil content W oil The increase of W will reduce the biodegradability index because oils are usually composed of glycerol and fatty acids, which are not easily soluble in the aqueous phase during the fermentation process, forming an oil film that hinders the contact and utilization of microorganisms, thereby affecting their metabolic activity and biodegradation efficiency, and reducing BI; W water The increase in BI will also reduce the biodegradability index. This is because as the moisture content increases, the fermentation concentration of the entire material will decrease, resulting in a decrease in the relative concentration of organic matter available for microbial utilization. Excessive moisture will dilute the substrate, affecting the saturation and effectiveness of the substrate, and ultimately reducing its biodegradation rate. Therefore, the larger the biodegradability index BI, the better, indicating that the fermented material has a strong biodegradation potential, a smaller impact on the environment, and a higher resource utilization efficiency.

[0069] It should be noted that the fermentation impact index comprehensively considers the relationship between the optimal value and the actual value of the key operating parameters in the fermentation process. Through the ratio of temperature, time and material quality, the optimization degree and efficiency of the fermentation process can be effectively evaluated. The level of FII directly reflects the degree of support of the fermentation environment for microbial metabolic activities, thereby affecting the output and quality of the final product. By analyzing and optimizing FII, a scientific basis can be provided for the improvement of fermentation processes, promoting the efficient use of resources, improving biotransformation efficiency, and achieving sustainable development goals.

[0070] Therefore, it is necessary to calculate the fermentation impact index based on the system's previous operating parameters. The formula is:

[0071] According to the obtained design operating parameters of the fermentation tank, including fermentation temperature, fermentation time and total feed mass, wherein the fermentation temperature includes the optimal fermentation temperature and the actual fermentation temperature, the fermentation time includes the optimal fermentation time and the actual fermentation time, and the total feed mass includes the mass of the organic matter input and the mass of the material in the fermentation tank, the fermentation impact index that affects the fermentation degree of the material is calculated based on the following formula:

[0072]

[0073] Among them, FII represents the fermentation impact index, T opt 、T actual are the optimal fermentation temperature and the actual fermentation temperature, t fer , t actu□□ are the optimal fermentation time and the actual fermentation time, M in 、Mtotal are the total mass of organic matter input and the mass of material in the fermentation tank respectively; in the above formula, and The ratio range is (0,1], which reflects the gap between the actual operating conditions and the ideal conditions. The closer the value is to 1, the more optimized and effective the fermentation process is. The closer the ratio is to 1, the larger the FII is, because the actual temperature is closer to the optimal temperature, which is conducive to the growth and metabolism of microorganisms, thereby enhancing the biodegradation ability and product generation efficiency. This indicates that the operating conditions of the fermentation system are more optimized and can better promote an effective biotransformation process; The closer the ratio is to 1, the greater the FII is, because the optimal fermentation time represents the ideal time for microorganisms to achieve optimal metabolic efficiency and product production. The closer the actual fermentation time is to the optimal fermentation time, the more effective the material utilization is, which promotes biodegradation and product synthesis, reduces the generation of undesirable by-products, and improves the purity and quality of the final product. The larger the FII, the greater the FII. This is because the greater the total mass of organic matter input relative to the mass of the material in the fermenter, the more substrates available in the system, and the microorganisms can metabolize more fully, thereby improving the fermentation efficiency and increasing the FII. In summary, the larger the FII, the better, indicating that the substrate utilization rate in the fermentation process is high, and the microorganisms can effectively convert organic matter, thereby producing more target products.

[0074] It should be noted that through the comprehensive calculation of the concentrating plate area and the matching angle, a quantitative indicator is provided for evaluating the overall performance of multiple solar concentrating systems. Reasonable concentrating efficiency can maximize the utilization efficiency of solar energy, thereby optimizing the heat energy supply and gas production capacity of the biogas fermentation system.

[0075] Therefore, it is necessary to calculate and generate the concentration efficiency impact index based on the design parameters of multiple solar concentrating systems. The method is as follows:

[0076]

[0077] Among them, ε represents the concentration efficiency impact index, S m is the area of the concentrator in the mth solar concentrating system, θ m is the concentrating plate matching angle in the mth solar concentrating system, m is the index of multiple solar concentrating systems, i∈[1,n], and n is the number of solar concentrating systems obtained; in the above formula, the concentration efficiency impact index is calculated in the form of mean because in practical applications, some systems may exhibit extreme concentration efficiency due to various reasons, such as design defects or improper operation. Using the mean can reduce the impact of these outliers on the overall results, making the concentration efficiency impact index more robust; It is the sum of the areas of the concentrating panels in multiple solar concentrating systems. When the concentrating panel area increases within the effective range, the concentration efficiency impact index ε also increases. This is because a larger concentrating panel area can capture more solar radiation, thereby improving the conversion efficiency of thermal energy. As the concentrating panel area increases, the system can provide a higher heat energy supply, enhance the temperature control and reaction rate during the biogas fermentation process, and ultimately improve the yield and quality of biogas. It is the sum of the matching angles of the concentrating panels in multiple solar concentrating systems. When the matching angle of the concentrating panels increases within the effective range, ε will decrease. This is because as the matching angle of the concentrating panels increases, the amount of direct solar radiation received by the concentrating panels will decrease. The increased angle will cause light reflection and scattering, which will reduce the effective light collection capacity and thus affect the thermal energy conversion efficiency. In summary, the larger ε, the better, which means that the solar concentrating system can more effectively capture and convert solar radiation, thereby generating more heat energy to facilitate fermentation.

[0078] It's important to note that by employing a convolutional neural network architecture, the model automatically extracts and learns deep features from the performance index, capturing the complex, nonlinear relationship between input data and biogas production. This highly effective prediction capability not only improves the accuracy and reliability of biogas content but also provides strong support for production decisions, promotes the development and utilization of renewable energy, and has positive implications for environmental protection and sustainable resource utilization.

[0079] Therefore, it is necessary to construct a biogas production prediction model based on a deep learning network, with the inputs being the performance index, fermentation impact index, and concentration efficiency impact index, and the output being the biogas fermentation evaluation index. The method used is as follows:

[0080] The biogas production prediction model adopts a neural network convolution structure, including an input layer, a hidden layer and an output layer. The input layer is responsible for receiving the extracted performance index, fermentation impact index and focusing efficiency index; the hidden layer is used to process the extracted index data. By applying multiple convolution kernels and using the ReLU activation function, nonlinear relationships are introduced to enable the model to fit complex feature relationships; an independent neuron is set in the output layer, which is responsible for converting the performance index representation extracted by the hidden layer into the final prediction result, that is, the output biogas fermentation evaluation indicators include gas production, waste gas emissions and fermentation cost.

[0081] The composition data of historical fermentation materials, fermentation system operating parameters and design parameters of multiple solar concentrating systems are obtained, and the performance index, fermentation impact index and concentration efficiency impact index are calculated according to expert calculations. These indices are used as the input of the model, and the biogas fermentation evaluation index is used as the output of the model. The biogas production prediction model is trained. During the training process, the mean square error function is selected as the loss function, and the loss function value is calculated according to the output result and the true label. The gradient is calculated through the back propagation algorithm, and the weights and bias of the neural network are updated. The above operations are repeated until the model reaches the predetermined number of training rounds.

[0082] It should be noted that by ensuring that key indicators such as the concentrating plate area, matching angle, fermentation temperature, fermentation time and total feed mass are within a reasonable range, the acquisition and conversion of thermal energy can be optimized, and the stability and output of the biogas fermentation process can be improved. At the same time, these constraints help designers avoid potential system failures and performance degradation, ensure the safety and economy of the system during operation, and thus achieve optimal resource utilization and environmental benefits.

[0083] Therefore, it is necessary to set the effective range of the system's design parameters and operating parameters, based on the following method:

[0084] The optimization constraints of the solar concentrating drive system are set, including: the value interval of the concentrating plate area is set to [10m 2 ,50m 2 ]; the value range of the focusing plate matching angle is set to [30°, 60°]; the value range of the fermentation temperature is set to [35℃, 55℃]; the value range of the fermentation time is set to 15 days to 20 days; the value range of the total feed mass is set to [500kg, 1000kg];

[0085] The reason why the range of the area of the concentrator is set to [10m 2 ,50m 2], because the area of the concentrator directly affects the amount of solar radiation received. An area that is too small may not be able to meet the system's demand for thermal energy, resulting in insufficient energy and affecting the process and output of biogas fermentation. Although an area that is too large can increase the light collection capacity, it will also lead to a significant increase in costs, including material costs, installation and maintenance costs; the value range of the concentrator angle is set to [30°, 60°|, because the concentrator angle directly affects the capture efficiency of solar radiation. Within this angle range, the concentrator can maximize the light collection effect. An angle that is too small may result in insufficient light reflection, while an angle that is too large may result in a large amount of light being wasted; the fermentation temperature range is set to [35℃, 55℃] and combined with a fermentation time of 15 to 20 days, because the optimal temperature for anaerobic fermentation is 35℃, 55℃. The temperature is between 35℃ and 55℃. Within this temperature range, the metabolic activity of gas-producing bacteria and anaerobic microorganisms is the strongest, which can effectively increase the production of biogas. Temperatures below 35℃ may cause the metabolic rate of microorganisms to decrease, thereby reducing biogas production; temperatures exceeding 55℃ may cause the death of certain microorganisms, especially temperature-sensitive bacteria, thereby affecting the overall fermentation effect. A fermentation period of 15 to 20 days helps to ensure that the reaction is fully carried out under suitable temperature conditions. During this time, the system can effectively convert organic matter into biogas, avoiding insufficient or excessive decomposition of organic matter that may result from long-term fermentation. The value range of the total feed mass is set to [500kg, 1000kg] because there will be no fermentation tank overload due to excessive feed or insufficient reaction due to insufficient feed.

[0086] It should be noted that by maximizing the fitness value, the relationship between biogas production, waste gas emissions and fermentation costs can be effectively balanced to achieve efficient resource utilization and minimize environmental impact. The reason why the weights w1>w3>w2>0 are set is to reflect the importance of gas production in the overall evaluation, emphasizing that while pursuing efficient fermentation, environmental and economic factors must be taken into account, and the calculated fitness values must be positive; the reason why w1 is set to the largest proportional weight is because gas production is the core goal in the biogas fermentation process, which directly determines the production efficiency and economic benefits of biogas. Therefore, giving priority to gas production can ensure the overall benefits of the fermentation process; and w3 is set to the second weight ratio because the fermentation cost It directly affects the economic feasibility of biogas production. Reasonable control of fermentation costs helps to ensure that while pursuing high gas production, it does not lead to excessive investment, thereby achieving the dual goals of economic and environmental benefits. Therefore, it is placed in the second weight ratio to take into account the needs of sustainable development; w2 is set to the lowest weight ratio because compared with the influence of gas production and fermentation cost, the impact of waste gas emissions on the biogas fermentation process is relatively small. Although waste gas management and treatment are crucial to environmental protection, in the direct economic benefits and efficiency optimization of biogas production, the impact of gas production and fermentation cost is more significant. Therefore, placing waste gas emissions in the lowest position in the weight distribution can better concentrate resources and improve biogas production and economic benefits.

[0087] Therefore, it is necessary to establish a functional relationship between the biogas fermentation evaluation index and the biogas production fitness value, with the maximization of the fitness value as the optimization goal. The formula is:

[0088]

[0089] Among them, F syd represents the maximum biogas production fitness value, w1, w2, and w3 are the weights of gas production, waste gas emissions, and fermentation cost in the biogas fermentation evaluation index, and w1+w2+w3=1, w1>w3>w2>0; in the above formula, the increase of Q1 will make F syd Increase, because the increase in gas production means more efficient resource utilization, reflecting the high conversion rate of raw materials; and the decrease in Q2 will also make F syd The increase is because in the biogas fermentation process, more organic matter is effectively converted into biogas instead of being discharged in the form of waste gas; the decrease of Q3 will also make F syd The increase is because in the process of producing biogas, the cost of raw materials or other resources required is reduced, which means that the efficiency of resource utilization is improved, unnecessary investment is reduced, and thus economic benefits are improved.

[0090] It should be noted that based on the multi-objective particle swarm optimization algorithm, multiple particles are randomly generated and iteratively optimized. The specific method is: the initial position x of the particle is randomly generated within the effective range of each optimizable parameter. a , set the number of particles to P, the maximum number of iterations to max iter , inertia weight ω, learning factors c1 and c2, when calculating the biogas production fitness value of each particle, the following formula can be used to update the particle speed and position to obtain the maximum biogas production fitness value. The formula is as follows:

[0091]

[0092] in, represents the speed of the ath particle after iterative update, ω is the inertia weight, which is used to control the influence of the current speed of the particle on the new speed, h a is the current velocity of the ath particle, c1 and c2 are the individual learning factor and the group learning factor, respectively. They are random numbers between [0,1], which are used to introduce randomness to ensure the diversity of particles in the search process. pbest a Indicates the best historical position of the a-th particle, gbest a represents the global optimal position of the a-th particle, that is, the best position found in the entire particle swarm; represents the position of the ath particle after iterative update, x a is the current position of the ath particle, a is the index of the number of particles, i∈[1,P].

[0093] It should be noted that the biogas production fitness value is calculated based on the ideal biogas production threshold, and the deviation coefficient of each solution is evaluated by the Euclidean distance method. This method can effectively identify and select the solution closest to the ideal evaluation index, ensuring that the final selected design parameter combination can be as close to the optimal state as possible in terms of key indicators such as gas production, waste gas emissions and fermentation cost, thereby maximizing system performance. This not only helps to improve biogas production efficiency, but also reduces resource waste and environmental impact, and promotes sustainable development.

[0094] Therefore, it is necessary to calculate the deviation coefficient of each solution whose biogas production fitness value is greater than the ideal biogas production threshold based on the ideal biogas production threshold, and take the solution with the minimum deviation coefficient as the optimal fermentation system design parameter combination. The method is based on:

[0095] Based on the Euclidean distance method, the optimal solution close to the optimal evaluation index is selected, and the formula is as follows:

[0096]

[0097] in, represents the deviation coefficient of the j-th biogas fermentation evaluation index in the i-th particle, is the value of the j-th biogas fermentation evaluation index in the i-th particle, The ideal threshold value of the jth biogas fermentation evaluation index in the i-th particle, j is the index of the biogas fermentation evaluation index. When j = 1, it represents the gas production index in the biogas fermentation evaluation index; when j = 2, it represents the waste gas emission index in the biogas fermentation evaluation index; when j = 3, it represents the fermentation cost index in the biogas fermentation evaluation index;

[0098] After calculating the deviation coefficients of all fitness values greater than the given ideal biogas production threshold, all calculated Compare the values and find the minimum value of each solution After determining the minimum value, the corresponding solution is the optimal combination of fermentation system design parameters.

[0099] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0100] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0101] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, and may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment as needed.

[0102] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A design method for a solar-powered biogas fermentation system based on gas production performance prediction, characterized in that: The specific steps include: Step 1: Obtaining design parameters of multiple solar concentrating systems, operating parameters of the systems in previous operations, composition data of the fermented material, and biogas fermentation evaluation indicators. The design parameters of the solar concentrating systems include the area of the concentrating panels and the matching angle of the concentrating panels. The operating parameters include the fermentation temperature, fermentation time, and total feed mass of the fermenter. The composition data of the fermented material include moisture content, organic carbon content, total nitrogen content, volatile solid content, total solid content, and oil content. The biogas fermentation evaluation indicators include gas production, waste gas emissions, and fermentation cost. Step 2: Calculating performance indices for characterizing the fermentation of the material to be fermented based on previous composition data of the material to be fermented, the performance indices including a fermentability index, an anaerobic digestion potential index, and a biodegradability index; calculating a fermentation impact index based on previous operating parameters of the system; and calculating a concentration efficiency impact index based on design parameters of multiple solar concentrating systems; Step 3: Based on the deep learning network, a biogas production prediction model is constructed, whose input is the performance index, fermentation impact index, and concentration efficiency impact index, and whose output is the biogas fermentation evaluation index. The model is trained based on the performance index, fermentation impact index, concentration efficiency impact index, and biogas fermentation evaluation index of the fermented material in the past historical data. The performance index, fermentation impact index, and concentration efficiency index of the current fermented material are input into the biogas production prediction model to obtain the biogas fermentation evaluation index. Step 4: Set the effective range of the system's design parameters and operating parameters, establish a functional relationship between the biogas fermentation evaluation index and the biogas production fitness value, take maximizing the fitness value as the optimization goal, randomly generate multiple particles based on the multi-objective particle swarm optimization algorithm and perform iterative optimization. The particles are a combination of parameters such as the concentrator area, the concentrator matching angle, the fermentation temperature of the fermenter, the fermentation time, and the total feed mass; Step 5: Establish the ideal threshold of biogas production and the ideal threshold of each biogas fermentation evaluation index. Based on the ideal threshold of biogas production, calculate the deviation coefficient of each solution whose biogas production fitness value is greater than the ideal threshold of biogas production. The solution with the minimum deviation coefficient is taken as the optimal fermentation system design parameter combination.

2. The method for designing a solar-powered biogas fermentation system based on gas production performance prediction according to claim 1, characterized in that: The performance index used to characterize the fermentation of the material to be fermented is calculated based on the previous composition data of the material to be fermented, and the method is based on: The fermentability index is calculated based on the organic carbon content and total nitrogen content of the fermentation material, and the formula is: Wherein, FI represents fermentability index, C represents organic carbon content, and N represents total nitrogen content; The anaerobic digestion potential index is calculated based on the volatile solid content and total solid content of the fermentation material, and the formula is: Among them, ADPI represents anaerobic digestibility potential index, VS represents volatile solid content, and TS represents total solid content; The biodegradability index is calculated based on the moisture content, oil content, organic carbon content and total nitrogen content of the fermentation material, and the formula is: Where BI represents the biodegradability index, W oil is the fat content, W water is the organic carbon content.

3. The method for designing a solar-powered biogas fermentation system based on gas production performance prediction according to claim 1, characterized in that: The fermentation impact index is calculated based on the system's previous operating parameters, using the following formula: Based on the design operating parameters of the fermentation tank obtained during the past operation of the system, including fermentation temperature, fermentation time and total feed mass, where fermentation temperature includes optimal fermentation temperature and actual fermentation temperature, fermentation time includes optimal fermentation time and actual fermentation time, and total feed mass includes the mass of organic matter input and the mass of material in the fermentation tank, the fermentation impact index that affects the fermentation degree of the material is calculated based on the following formula: Among them, FII represents the fermentation impact index, T opt 、T actual are the optimal fermentation temperature and the actual fermentation temperature, t fer , t actual are the optimal fermentation time and the actual fermentation time, M in 、M total are the total mass of organic matter input and the mass of material in the fermentation tank respectively.

4. The method for designing a solar-powered biogas fermentation system based on gas production performance prediction according to claim 1, characterized in that: The concentration efficiency impact index is calculated based on the design parameters of multiple solar concentrating systems, and the formula is as follows: Among them, ε represents the concentration efficiency impact index, S m is the area of the concentrator in the mth solar concentrating system, θ m is the concentrator panel matching angle in the mth solar concentrating system, m is the index of multiple solar concentrating systems, i∈[1,n], and n is the number of solar concentrating systems obtained.

5. The method for designing a solar-powered biogas fermentation system based on gas production performance prediction according to claim 1, characterized in that: Based on the deep learning network, a biogas production prediction model is constructed with the performance index as input and the biogas content grade index as output to obtain the corresponding biogas content grade index. The method is as follows: The biogas production prediction model adopts a neural network convolution structure, including an input layer, a hidden layer and an output layer. The input layer is responsible for receiving the extracted performance index, fermentation impact index and focusing efficiency index; the hidden layer is used to process the extracted index data. By applying multiple convolution kernels and using the ReLU activation function, nonlinear relationships are introduced to enable the model to fit complex feature relationships; an independent neuron is set in the output layer, which is responsible for converting the performance index representation extracted by the hidden layer into the final prediction result, that is, the output biogas fermentation evaluation indicators include gas production Q1, waste gas emissions Q2 and fermentation cost Q3.

6. The method for designing a solar-powered biogas fermentation system based on gas production performance prediction according to claim 1, characterized in that: The effective range of the system design parameters and operating parameters is set based on the following method: The optimization constraints of the solar concentrating drive system are set, including: the value interval of the concentrating plate area is set to [10m 2 ,50m 2 ]; the value range of the focusing plate matching angle is set to [30°, 60°]; the value range of the fermentation temperature is set to [35℃, 55℃]; the value range of the fermentation time is set to 15 days to 20 days; the value range of the total feed mass is set to [500kg, 1000kg].

7. The method for designing a solar-powered biogas fermentation system based on gas production performance prediction according to claim 5, characterized in that: A functional relationship between biogas fermentation evaluation index and biogas production fitness value was established, with maximizing the fitness value as the optimization goal. The formula is as follows: Among them, F syd It represents the maximum biogas production fitness value, w1, w2, and w3 are the proportional weights of gas production, waste gas emissions, and fermentation cost in the biogas fermentation evaluation index, respectively, and w1+w2+w3=1, w1>w3>w2>0.

8. The method for designing a solar-powered biogas fermentation system based on gas production performance prediction according to claim 1, characterized in that: Calculate the deviation coefficient of each solution whose biogas production fitness value is greater than the ideal biogas production threshold, and take the solution with the minimum deviation coefficient as the optimal fermentation system design parameter combination. The method is based on: Based on the Euclidean distance method, the optimal solution close to the optimal evaluation index is selected, and the formula is as follows: in, It represents the deviation coefficient of the j-th biogas fermentation evaluation index in the i-th particle, is the value of the j-th biogas fermentation evaluation index in the i-th particle, The ideal threshold value of the jth biogas fermentation evaluation index in the i-th particle, j is the index of the biogas fermentation evaluation index. When j = 1, it represents the gas production index in the biogas fermentation evaluation index; when j = 2, it represents the waste gas emission index in the biogas fermentation evaluation index; when j = 3, it represents the fermentation cost index in the biogas fermentation evaluation index; After calculating the deviation coefficients of all fitness values greater than the given ideal biogas production threshold, all calculated Compare the values and find the minimum value of each solution After determining the minimum value, the corresponding solution is the optimal combination of fermentation system design parameters.

Images