Straw feed fermentation treatment control system and method

Abstract

The invention discloses a straw feed fermentation treatment control system and method, particularly relates to the technical field of production control, and is used for solving the problem of insufficient identification and regulation of an imbalance phenomenon in a straw fermentation pile caused by non-uniform gas diffusion in the existing fermentation process. The method comprises the following steps: acquiring environmental parameters of a fermentation heap, performing three-dimensional gas concentration field reconstruction processing, identifying a layered air mass region in combination with a fuzzy clustering algorithm, measuring heap pressure distribution and deformation characteristics, analyzing a heap body structure abnormal region, and marking a risk analysis region; through a three-dimensional tensor model and a fractal analysis model, the time dependency and the gas diffusion equilibrium degree of the gas exchange and metabolism process are evaluated respectively, and finally fermentation pile structure parameters and ventilation device operation parameters are dynamically adjusted based on a closed-loop control system; through accurate region identification and a dynamic regulation and control mechanism, the uniformity of the fermentation process and the quality consistency of the straw feed are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of production control, and more specifically, to a straw feed fermentation processing control system and method. Background Art

[0002] In large-scale straw fermentation piles, due to the influence of local pile pressure and pile deformation, gas diffusion is often difficult to achieve uniform distribution, which may form special areas similar to "stratified air masses". These stratified air mass areas will significantly affect the spatial distribution of microbial communities, resulting in obvious differences in oxygen, carbon dioxide concentrations and humidity in the fermentation pile between different areas. These differences further affect the utilization efficiency of nitrogen, organic acids and trace elements by microorganisms, resulting in nutritional gradients and quality differences in the upper, middle and lower areas of the fermentation products.

[0003] In the prior art, there are deficiencies in the identification and regulation of the internal imbalance phenomenon of the straw fermentation pile caused by uneven gas diffusion during the fermentation process, which will lead to low fermentation efficiency and thus affect the uniformity and quality consistency of the straw feed. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a straw feed fermentation processing control system and method to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: A straw feed fermentation treatment control method comprises the following steps: Collect fermentation pile environmental parameters at the straw fermentation pile, reconstruct the three-dimensional gas concentration field of the fermentation pile environmental parameters, and obtain gas distribution information at various positions inside the straw fermentation pile; Fuzzy clustering algorithm is used to classify and analyze gas distribution information and identify stratified air mass areas with gas concentration gradient characteristics. Measure the pile pressure distribution and deformation characteristics of the straw fermentation pile, analyze the potential impact of uneven gas diffusion in the straw fermentation pile, and identify abnormal areas of the pile structure; The union of the stratified gas mass area and the abnormal pile structure area is marked as the risk analysis area; The dynamic relationship between gas concentration and metabolites in the risk analysis area was analyzed by constructing a three-dimensional tensor model to evaluate the temporal dependence of gas exchange and metabolic processes. The distribution characteristics of the gas concentration field in the risk analysis area are analyzed through the fractal analysis model to evaluate the gas diffusion balance in the local area; Based on the time dependence of gas exchange and metabolic processes and the degree of gas diffusion balance in local areas, the structure of the straw fermentation pile and the parameters of the ventilation device are quantitatively adjusted through closed-loop control.

[0006] In a preferred embodiment, the fermentation pile environmental parameters are collected at the straw fermentation pile, and the fermentation pile environmental parameters are subjected to three-dimensional gas concentration field reconstruction processing to obtain gas distribution information at various positions inside the straw fermentation pile, specifically including: A plurality of collection points are set in the vertical range from the bottom to the top and the horizontal range from the center to the edge of the straw fermentation pile to collect the fermentation pile environmental parameters, including oxygen concentration, carbon dioxide concentration and humidity; Based on the geometric shape of the straw fermentation pile and the spatial distribution of the collection points, a three-dimensional coordinate system matching the straw fermentation pile is constructed; The environmental parameters of the fermentation pile are mapped to a three-dimensional coordinate system to generate gas distribution information at various positions inside the straw fermentation pile; the gas distribution information includes oxygen concentration distribution, carbon dioxide concentration distribution and humidity distribution.

[0007] In a preferred embodiment, a fuzzy clustering algorithm is used to classify and analyze the gas distribution information to identify stratified air mass areas with gas concentration gradient characteristics, specifically including: Based on the oxygen concentration distribution, carbon dioxide concentration distribution and humidity distribution of each point in the three-dimensional space, the parameter value of each spatial point in the gas distribution information is used as a clustering feature; Using fuzzy clustering algorithm, the spatial points in the gas distribution information are classified according to the gas concentration gradient characteristics of the spatial points to form multiple cluster categories; Cluster categories with significant gas concentration gradient characteristics and whose spatial distribution characteristics conform to the characteristics of stratified air masses are marked as stratified air mass areas.

[0008] In a preferred embodiment, the pile pressure distribution and deformation characteristics of the straw fermentation pile are measured, the potential impact of uneven gas diffusion in the straw fermentation pile is analyzed, and the abnormal area of ​​the pile structure is identified, which specifically includes: Multiple pressure-sensitive sensors are arranged in the vertical and horizontal directions of the straw fermentation pile to measure the pile pressure value at each position; Scan the surface shape of the straw fermentation pile using a three-dimensional scanning device to obtain three-dimensional morphological feature data of the straw fermentation pile; Compare and analyze the pile pressure value and three-dimensional morphological feature data to identify abnormal pile pressure areas and significant deformation areas; According to the locations of abnormal stack pressure areas and significant deformation areas, abnormal stack structure areas that may affect gas diffusion are identified.

[0009] In a preferred embodiment, a three-dimensional tensor model is constructed to analyze the dynamic relationship between gas concentration and metabolites in the risk analysis area and evaluate the time dependence of gas exchange and metabolic processes, specifically including: Obtain gas concentration data and metabolite concentration data at each location in the risk analysis area; The gas concentration data and metabolite concentration data are mapped to different dimensions of the three-dimensional tensor using the time series as the dimension; The three-dimensional tensor is decomposed using a time-dependent dynamic modeling algorithm to extract the main dynamic factors of gas concentration and metabolic product changes; Analyze the relationship between the main dynamic factors and calculate the time lag characteristics of changes in gas concentration and metabolite concentration; The temporal dependence of gas exchange and metabolic processes was quantitatively assessed based on time lag characteristics.

[0010] In a preferred embodiment, the relationship between the main dynamic factors is analyzed, and the time lag characteristics of the changes in gas concentration and metabolite concentration are calculated, specifically: For each main dynamic factor, the time difference between the change in gas concentration and the change in metabolite concentration is calculated using the following formula: ;in, Indicates The time lag value of the main dynamic factors, represents the correlation function, Indicates at a point in time Time The time variation characteristics of the main dynamic factors related to gas concentration, Indicates at a point in time Time The temporal variation characteristics of the main dynamic factors related to the concentration of metabolites, It represents the lag time of the time change of gas concentration relative to the time change of metabolite concentration. Represents a specific time point in a time series.

[0011] In a preferred embodiment, the time dependence of gas exchange and metabolic processes is quantitatively evaluated based on the time lag characteristics, specifically: Calculate the time dependency index, which is expressed as: ;in, represents the time dependence index, Indicates The weights of the main dynamic factors, greater than 0, Indicates the number of main dynamic factors extracted, is the number of the main dynamic factor.

[0012] In a preferred embodiment, the distribution characteristics of the gas concentration field in the risk analysis area are analyzed by a fractal analysis model to evaluate the gas diffusion balance degree in the local area, specifically including: The gas concentration data in the risk analysis area are sorted according to the spatial location and time dimensions to form a gas concentration distribution matrix; Use fractal analysis model to perform multi-scale decomposition of gas concentration distribution matrix; The fractal dimension of each scale is calculated, and the degree of gas diffusion equilibrium in the local area is evaluated according to the changing trend of the fractal dimension; the changing trend of the fractal dimension is calculated by comparing the changes in the fractal dimension at different decomposition scales.

[0013] In a preferred embodiment, based on the time dependence of gas exchange and metabolic process and the gas diffusion balance degree in the local area, the structure of the straw fermentation pile and the parameters of the ventilation device are quantitatively adjusted through closed-loop control, specifically including: According to the changing trends of the time dependency index and fractal dimension, the target parameters for adjusting the fermentation pile structure are set, including pile shape parameters and compaction degree parameters; According to the changing trend of the time dependency index and the fractal dimension, the ventilation device adjustment target parameters are set, including the switch state and flow parameters of the ventilation pipeline; Adjustment target parameters of the fermentation pile structure and ventilation device based on adjustment target parameters: perform fermentation pile structure adjustment through a closed-loop control system, including changing the shape and compaction degree of the fermentation pile; adjust the ventilation device through a closed-loop control system, including controlling the switch of the ventilation pipeline and the airflow rate.

[0014] On the other hand, the present invention provides a straw feed fermentation processing control system, including an environmental parameter acquisition module, a stratified air mass identification module, a pile pressure deformation measurement module, a risk area marking module, a time-dependent analysis module, a diffusion equilibrium evaluation module and a closed-loop control adjustment module; Environmental parameter acquisition module: collects fermentation pile environmental parameters at the straw fermentation pile, performs three-dimensional gas concentration field reconstruction on the fermentation pile environmental parameters, and obtains gas distribution information at various positions inside the straw fermentation pile; Layered air mass identification module: uses fuzzy clustering algorithm to classify and analyze gas distribution information and identify layered air mass areas with gas concentration gradient characteristics; Pile pressure deformation measurement module: measures the pile pressure distribution and deformation characteristics of the straw fermentation pile, analyzes the potential impact of uneven gas diffusion in the straw fermentation pile, and identifies abnormal areas of the pile structure; Risk area marking module: marks the union of the stratified air mass area and the abnormal pile structure area as the risk analysis area; Time-dependent analysis module: By constructing a three-dimensional tensor model to analyze the dynamic relationship between gas concentration and metabolites in the risk analysis area, the time dependency of gas exchange and metabolic processes is evaluated; Diffusion balance assessment module: Analyze the distribution characteristics of the gas concentration field in the risk analysis area through the fractal analysis model, and evaluate the degree of gas diffusion balance in the local area; Closed-loop control regulation module: Based on the time dependence of gas exchange and metabolic processes and the degree of gas diffusion balance in local areas, the straw fermentation pile structure and ventilation device parameters are quantitatively adjusted through closed-loop control.

[0015] The technical effects and advantages of a straw feed fermentation processing control system and method of the present invention are as follows: 1. By collecting environmental parameters in the fermentation pile and reconstructing the three-dimensional gas concentration field, the fuzzy clustering algorithm is combined to accurately identify the stratified air mass area with gas concentration gradient characteristics. At the same time, the abnormal area of ​​the pile structure is identified by measuring the pile pressure distribution and deformation characteristics, and the union of the two is marked as the risk analysis area, which improves the recognition accuracy and efficiency of the uneven gas diffusion phenomenon; by constructing a three-dimensional tensor model and a fractal analysis model, the gas concentration field and the dynamic relationship of metabolites in the risk analysis area are analyzed in multiple dimensions, and the time dependence of gas exchange and metabolic processes and the degree of gas diffusion balance are quantified, providing a scientific basis for the dynamic adjustment of the fermentation pile; this method based on dynamic analysis and partitioning processing solves the problem of insufficient identification of regional differences in traditional fermentation control, thereby improving the overall uniformity of the fermentation process and the consistency of feed quality.

[0016] 2. The present invention dynamically adjusts the structural parameters of the fermentation pile (such as pile shape, compaction degree) and the operating parameters of the ventilation device (such as ventilation pipeline switch status and flow rate) according to the evaluation results of the time dependence index of gas exchange and metabolic process and the degree of gas diffusion balance through a closed-loop control system; this precise dynamic regulation mechanism effectively optimizes the gas flow conditions and improves the balance of the microenvironment in the fermentation pile. By comprehensively considering the coupling relationship between microbial metabolism and gas distribution, the metabolic efficiency of microorganisms in the fermentation pile is significantly improved, the abnormal phenomena in local areas are reduced, and the uniformity of the nutritional quality of the products and the improvement of the overall fermentation efficiency during the straw feed fermentation process are achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of a straw feed fermentation processing control method of the present invention; Figure 2 The present invention is a schematic structural diagram of a straw feed fermentation processing control system. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Embodiment 1: Figure 1 A straw feed fermentation processing control method is provided, which comprises the following steps: The fermentation pile environmental parameters are collected at the straw fermentation pile, and the three-dimensional gas concentration field of the fermentation pile environmental parameters is reconstructed to obtain the gas distribution information at each position inside the straw fermentation pile.

[0020] The fuzzy clustering algorithm is used to classify and analyze the gas distribution information and identify stratified air mass areas with gas concentration gradient characteristics.

[0021] The pile pressure distribution and deformation characteristics of the straw fermentation pile were measured, the potential impact of uneven gas diffusion in the straw fermentation pile was analyzed, and abnormal areas of the pile structure were identified.

[0022] The union of the stratified air mass area and the abnormal pile structure area is marked as the risk analysis area.

[0023] A three-dimensional tensor model was constructed to analyze the dynamic relationship between gas concentrations and metabolites in the risk analysis area and to evaluate the temporal dependence of gas exchange and metabolic processes.

[0024] The fractal analysis model is used to analyze the distribution characteristics of the gas concentration field in the risk analysis area and to evaluate the degree of gas diffusion balance in the local area.

[0025] Based on the time dependence of gas exchange and metabolic processes and the degree of gas diffusion balance in local areas, the structure of the straw fermentation pile and the parameters of the ventilation device are quantitatively adjusted through closed-loop control.

[0026] The fermentation pile environmental parameters are collected at the straw fermentation pile, and the three-dimensional gas concentration field reconstruction processing is performed on the fermentation pile environmental parameters to obtain the gas distribution information at each position inside the straw fermentation pile, including: Multiple collection points are set within the straw fermentation pile in the vertical range from the bottom to the top and in the horizontal range from the center to the edge to collect the fermentation pile environmental parameters, including oxygen concentration, carbon dioxide concentration and humidity: Inside the straw fermentation pile, multiple collection points are evenly distributed in the vertical range from the bottom to the top of the pile and in the horizontal range from the center to the edge of the pile. The density of the collection points is adjusted according to the volume and complexity of the fermentation pile to ensure that the key areas of the fermentation pile are covered.

[0027] The following sensors are installed at each collection point: oxygen concentration sensor (used to measure the oxygen concentration in the gas); carbon dioxide concentration sensor (used to measure the carbon dioxide concentration in the gas); humidity sensor (used to measure the humidity of the local environment).

[0028] The acquisition frequency can be set to once per minute to capture the dynamic changes in gas distribution during the fermentation process; the data is recorded in the form of coordinates and timestamps, and a set of parameter values ​​is output for each acquisition point.

[0029] Based on the geometric shape of the straw fermentation pile and the spatial distribution of the collection points, a three-dimensional coordinate system matching the straw fermentation pile is constructed: According to the geometric shape of the fermentation pile and the distribution of sensor collection points, a three-dimensional coordinate system is established. The three-dimensional coordinate system takes the center point of the bottom of the fermentation pile as the origin, uses Cartesian coordinates to define the spatial distribution of the pile, and locates the spatial position of the collection point.

[0030] The geometric shape is obtained by using laser scanning equipment or 3D modeling tools to measure the overall shape and boundary dimensions of the fermentation pile, ensuring that the 3D coordinate system matches the actual pile space.

[0031] The environmental parameters of the fermentation pile are mapped to a three-dimensional coordinate system to generate the gas distribution information at each position inside the straw fermentation pile: For each collection point, its spatial location is bound to the oxygen concentration, carbon dioxide concentration and humidity values ​​recorded by the sensor.

[0032] Dot matrix data are formed in a three-dimensional coordinate system, wherein the spatial position of each point corresponds to a set of fermentation pile environmental parameters.

[0033] It is worth noting that a three-dimensional interpolation algorithm (such as nearest neighbor interpolation or cubic spline interpolation) can be used here to supplement the parameter values ​​of the locations where the collection points are not deployed. The interpolation method calculates the estimated values ​​of the unsampled points based on the parameter values ​​of the surrounding sampled points to generate a complete three-dimensional data field.

[0034] Based on the mapped and interpolated data, the gas distribution information of each position inside the fermentation pile is generated. The gas distribution information includes: Oxygen concentration distribution: The oxygen concentration value at each point in three-dimensional space shows the changes in oxygen concentration in different areas.

[0035] Carbon dioxide concentration distribution: The carbon dioxide concentration value at each point in three-dimensional space reveals the strength of gas exchange in the pile.

[0036] Humidity distribution: The humidity value of each point in three-dimensional space reflects the moisture distribution status in different areas.

[0037] The fuzzy clustering algorithm is used to classify and analyze the gas distribution information and identify the stratified air mass areas with gas concentration gradient characteristics, including: Based on the oxygen concentration distribution, carbon dioxide concentration distribution and humidity distribution of each point in the three-dimensional space, the parameter value of each spatial point in the gas distribution information is used as the clustering feature: After the gas distribution information is generated, the oxygen concentration distribution, carbon dioxide concentration distribution and humidity distribution of each point in the three-dimensional space are used as the basic data for classification analysis. The parameter values ​​of each spatial point, including oxygen concentration, carbon dioxide concentration and humidity, are used as feature data for subsequent cluster analysis.

[0038] The feature representation of each spatial point is a three-dimensional vector ,in, represents the oxygen concentration at that point, represents the carbon dioxide concentration at that point, Indicates the humidity at that point.

[0039] The coordinate information of the spatial point has been bound to the corresponding parameter value when generating the gas distribution information, and no additional processing is required.

[0040] Integrate the data of all spatial points in the gas distribution information into a feature matrix , used as input for the fuzzy clustering algorithm.

[0041] Feature Matrix The form is: ;in, It is the total number of all sampling points in the three-dimensional space. Each row represents the data of a spatial point, including oxygen concentration, carbon dioxide concentration and humidity.

[0042] Using the fuzzy clustering algorithm, the spatial points in the gas distribution information are classified according to the gas concentration gradient characteristics of the spatial points to form multiple cluster categories: Cluster analysis is performed using the fuzzy c-means clustering algorithm, whose goal is to minimize the following objective function: ;in, represents the clustering objective function; Represents the total number of all sampling points in three-dimensional space; Indicates the number of cluster categories; Indicates The spatial point belongs to The membership degree of each cluster category ranges from [0,1]; Represents the fuzzy factor, which controls the fuzziness of the membership degree, and its value range is usually [1.5,3]; Indicates The feature vector of a spatial point; Indicates The cluster centers of cluster categories; Represents the Euclidean distance between the feature vector and the cluster center.

[0043] in, ; ;in, For the The central value of oxygen concentration of cluster categories, For the The central value of carbon dioxide concentration in each cluster category, For the The humidity central value of each cluster category; the oxygen concentration central value, carbon dioxide concentration central value and humidity central value are calculated by fuzzy clustering algorithm. In the clustering process, according to the parameter values ​​of all spatial points of each category, the weighted average calculation method is adopted, and the point membership is used as the weight to obtain the weighted average of the oxygen concentration, carbon dioxide concentration and humidity of the category as the corresponding central value.

[0044] In the fuzzy clustering algorithm, the clustering process is completed by iteratively optimizing the objective function. In each iteration, the membership of each point is updated according to the distance between the feature value of the current spatial point and the cluster center of each category; at the same time, the cluster center value is recalculated based on the membership of each point. This process continues until the change in the objective function is lower than the preset threshold or the maximum number of iterations is reached.

[0045] According to the results of fuzzy clustering, the gas concentration gradient of each category is calculated: ;in, represents the gas concentration gradient, Indicates the maximum difference in gas concentration within a category. Indicates the maximum distance between spatial points within a category.

[0046] Clustering categories with significant gas concentration gradient characteristics and whose spatial distribution characteristics conform to the characteristics of stratified air masses are marked as stratified air mass areas: Set the gas concentration gradient threshold, and for each cluster category, compare its gas concentration gradient with the gas concentration gradient threshold: like , then it is determined that the cluster category has significant gas concentration gradient characteristics.

[0047] like , it is determined that the cluster category does not have significant gas concentration gradient characteristics.

[0048] in, It is the gas concentration gradient threshold. The gas concentration gradient threshold is a standard value used to determine whether the gas concentration changes significantly. It is usually determined through experiments or experience. For example, when the oxygen or carbon dioxide concentration gradient changes by more than 5% / m, the concentration gradient can be considered significant, which is suitable as a basis for determining the stratified air mass area.

[0049] The spatial distribution characteristics of the cluster categories are further analyzed to determine whether they conform to the characteristics of stratified air masses.

[0050] The spatial distribution characteristics of cluster categories are analyzed in the following ways: first, all spatial points in the cluster category are extracted, and their distribution density in the vertical direction (such as the z-axis) is calculated. The concentration of points in height and the gradient change are observed. Secondly, the three-dimensional distribution pattern of spatial points in the category is analyzed to determine whether there is an obvious stratification trend, such as whether the distribution of high-density points is concentrated in a certain vertical range, or whether the distribution changes regularly with height. In addition, the variance and center of gravity position of the category points in the vertical direction are calculated to evaluate whether the distribution has significant hierarchical characteristics. Finally, by comparing the vertical distribution characteristics within the category with those of other categories, it is further confirmed whether the category meets the definition of stratified air masses, and the categories with obvious stratified structures are marked as meeting the characteristics of stratified air masses.

[0051] When a cluster category has significant gas concentration gradient characteristics and the spatial distribution characteristics of the cluster category conform to the characteristics of a stratified air mass, it is marked as a stratified air mass area.

[0052] The pile pressure distribution and deformation characteristics of the straw fermentation pile were measured, the potential impact of uneven gas diffusion in the straw fermentation pile was analyzed, and abnormal areas of the pile structure were identified, including: Multiple pressure-sensitive sensors are arranged in the vertical and horizontal directions of the straw fermentation pile to measure the pile pressure value at each position: The sensors are arranged to cover the entire three-dimensional space of the fermentation pile, including the bottom, inside and surface of the pile, to ensure that the pile pressure at all key locations is collected; the sensor arrangement intervals are determined according to the size of the fermentation pile and the expected range of pile pressure changes. Larger fermentation piles have higher arrangement density to ensure that accurate pile pressure data is collected.

[0053] Use 3D scanning equipment to scan the surface shape of the straw fermentation pile and obtain the 3D morphological feature data of the straw fermentation pile: Use laser scanning equipment or structured light scanner to record the surface shape of the fermentation pile with high precision; cover the entire surface of the fermentation pile and perform a full-range scan from bottom to top to ensure that the pile shape is fully captured; set an appropriate scanning frequency based on the dynamic change characteristics of the fermentation pile. It is recommended to scan once every 6 hours to capture the changes in the pile over time.

[0054] The three-dimensional morphological feature data obtained by scanning include information such as the height distribution, surface flatness and inclination angle of the pile, and are saved in a digital format.

[0055] Compare and analyze the pile pressure value and three-dimensional morphological feature data to identify abnormal pile pressure areas and significant deformation areas: Based on the spatial coordinates of the sensor layout and the three-dimensional morphology, the pile pressure data and the morphological data are spatially aligned to ensure that the two sets of data can be compared in the same spatial range.

[0056] Perform regional gradient analysis on the stack pressure data to identify abnormal stack pressure areas. For example, calculate the variation range of stack pressure values ​​between different acquisition points, identify high gradient areas, and set the stack pressure gradient threshold to 20 kPa / m. Areas above the stack pressure gradient threshold are marked as abnormal stack pressure areas.

[0057] Analyze the surface height distribution and inclination angle of the pile to identify the area with significant deformation. For example, the deformation area of ​​the pile is identified by calculating the height difference between adjacent scanning points, and the surface height difference threshold is set to 5 cm. The area above the surface height difference threshold is marked as the area with significant deformation.

[0058] According to the location of abnormal stack pressure areas and significant deformation areas, identify abnormal stack structure areas that may affect gas diffusion: The abnormal stack pressure area and the significant deformation area are superimposed to generate the abnormal stack structure area. The union of the abnormal stack pressure area and the significant deformation area can be identified as the abnormal stack structure area by using a union method.

[0059] The abnormal area of ​​pile structure reflects the spatial location characteristics of the straw fermentation pile that may cause gas diffusion obstruction. This area is usually manifested as a significant change in the pile pressure gradient or an area where the pile deformation exceeds the normal range, such as a high-pressure area caused by excessive local compaction, or a significant deformation area caused by pile sedimentation or tilting. This may hinder the uniform flow of gas inside the fermentation pile, resulting in local gas flow obstruction, thereby affecting the microbial metabolism and the uniformity of the distribution of fermentation products. In addition, it may also cause the oxygen concentration in the local area to be too low or the carbon dioxide concentration to be too high, further causing an imbalance in the microbial community. By identifying these abnormal areas, it can provide a basis for optimizing the fermentation pile structure and adjusting the ventilation system to ensure the uniformity of gas distribution.

[0060] The union of stratified air mass areas and areas with abnormal pile structure is marked as the risk analysis area because the two types of areas reflect two key problems, namely uneven gas concentration distribution and abnormal pile structure. These problems often work together to cause obstruction of gas flow. There is usually a significant gas concentration gradient in the stratified air mass area, which may directly affect the metabolic efficiency and fermentation uniformity of microorganisms; the area with abnormal pile structure may hinder gas diffusion through deformation or abnormal pile pressure, thereby aggravating the stratification phenomenon. By marking the union of the two types of areas as the risk analysis area, all potential risk positions in the fermentation pile can be more comprehensively covered, providing a more targeted basis for subsequent adjustments and optimizations, avoiding risk blind spots caused by missing a single type of abnormal area, and improving the overall stability of gas flow and fermentation process.

[0061] By constructing a three-dimensional tensor model to analyze the dynamic relationship between gas concentration and metabolites in the risk analysis area, the temporal dependence of gas exchange and metabolic processes was evaluated, including: Obtain gas concentration data and metabolite concentration data at each location in the risk analysis area: At various locations in the risk analysis area, oxygen concentration and carbon dioxide concentration data are collected in real time through the deployed sensor network and recorded in time series.

[0062] The concentration data of metabolites (such as lactic acid, acetic acid, etc.) during the fermentation process are obtained through sampling and analysis methods. The collection frequency of metabolite concentrations should be consistent with the gas concentration data to ensure synchronization in the time dimension.

[0063] The collected gas concentration data and metabolite concentration data are organized into matrix form according to time and space dimensions, ready to be mapped to a three-dimensional tensor.

[0064] Using the time series as the dimension, the gas concentration data and metabolite concentration data are mapped to different dimensions of the three-dimensional tensor: Construct a three-dimensional tensor to represent the time series variation relationship between gas concentration and metabolite concentration in the risk analysis area, as follows: Tensor dimension definition: The first dimension represents the spatial position within the risk analysis area; the second dimension represents the time series, recording parameter changes at different times; the third dimension stores gas concentration data (oxygen concentration, carbon dioxide concentration) and metabolite concentration data respectively.

[0065] Mapping rules: Align gas concentration data and metabolite concentration data according to sampling position and time and then map them to tensors: Sort and align gas concentration data (including oxygen concentration and carbon dioxide concentration) and metabolite concentration data (such as lactic acid, acetic acid, etc.) according to the corresponding relationship between sampling position and time series. Arrange the data at each sampling position in chronological order, and combine the gas concentration and metabolite concentration at different time points to form a three-dimensional tensor, in which position, time and parameter category correspond to the three dimensions of the tensor, respectively, which can fully reflect the changing relationship between gas and metabolite concentrations at different positions at different times.

[0066] The three-dimensional tensor is decomposed using a time-dependent dynamic modeling algorithm to extract the main dynamic factors of gas concentration and metabolic product changes: The non-negative tensor factorization (NTF) method is used to decompose the tensor into multiple low-dimensional factor matrices.

[0067] The objective function is: ;in, is the original three-dimensional tensor; , and denote the spatial factor matrix, the temporal factor matrix and the parameter factor matrix respectively; is the rank of decomposition, indicating the number of main dynamic factors extracted; Represents the outer product operation of a tensor; is the number of the main dynamic factor; The norm of the error, usually the Euclidean norm, is used to measure the difference between the original 3D tensor and the reconstructed tensor.

[0068] Used to describe the The spatial distribution characteristics of the main dynamic factors, Used to describe the The temporal variation patterns of the main dynamic factors, Used to describe the Characteristics of the main dynamic factors in different parameter categories.

[0069] The purpose of this objective function is to find the best , and , so that their outer product combination is as close as possible to the original three-dimensional tensor, that is, the error between the reconstructed tensor and the original tensor is minimized; the decomposition result extracts the main dynamic features in the original data, corresponding to the spatial distribution ( )、Time Change( ) and parameter category relations ( ).

[0070] Analyze the relationship between the main dynamic factors and calculate the time lag characteristics of changes in gas concentration and metabolite concentration: Extract gas concentration factors and metabolite factors from the time factor matrix.

[0071] For each main dynamic factor, the time difference between the change in gas concentration and the change in metabolite concentration is calculated using the following formula: ;in, Indicates The time lag value of the main dynamic factors, represents the correlation function (used to measure the correlation between two time series), Indicates at a point in time Time The time variation characteristics of the main dynamic factors related to gas concentration, Indicates at a point in time Time The temporal variation characteristics of the main dynamic factors related to the concentration of metabolites, It represents the lag time of the time change of gas concentration relative to the time change of metabolite concentration. Represents a specific time point in a time series.

[0072] The distribution of time-lagged values ​​of all major dynamic factors is statistically analyzed to identify the factors with significant lags and their corresponding parameter relationships.

[0073] Quantitative assessment of the temporal dependence of gas exchange and metabolic processes based on time lag characteristics: Calculate the time dependency index, which is defined as the weighted average of all time lag values, and its expression is: ;in, represents the time dependence index, Indicates The weights of the main dynamic factors, Greater than 0.

[0074] The larger the time dependence index is, the stronger the time dependence of gas exchange and metabolic process is, which indicates that the change of gas concentration has a longer lag effect on the concentration of metabolites, which may reflect that the regulation between gas diffusion and microbial metabolic activities within the system is not timely enough, which may cause the generation or consumption rate of metabolites to lag behind the adjustment of gas supply, resulting in decreased metabolic efficiency, uneven fermentation process, and even inhibition of microbial activity in local areas.

[0075] Among them, the weight of the main dynamic factor represents the contribution of each dynamic factor to the overall tensor decomposition, which is usually calculated based on the norm of the factor matrix or the reduction of the reconstruction error. The weight is used to quantify the importance of each dynamic factor to the dynamic change pattern of gas concentration and metabolite concentration. Factors with higher weights reflect key dynamic characteristics.

[0076] The fractal analysis model is used to analyze the distribution characteristics of the gas concentration field in the risk analysis area and evaluate the degree of gas diffusion balance in the local area, including: The gas concentration data in the risk analysis area are sorted according to the spatial location and time dimensions to form a gas concentration distribution matrix: Obtain time series data of oxygen concentration and carbon dioxide concentration from the sensor network in the risk analysis area to ensure that the collected data covers the entire spatial range and complete time period.

[0077] According to the sampling location and time dimensions, the gas concentration data are organized into a three-dimensional data set, where each dimension represents the spatial location, time point, and gas concentration category.

[0078] The first dimension represents the sampling location, which is indexed by three-dimensional space coordinates; the second dimension represents the sampling order at the time point; the third dimension represents the gas concentration category, including oxygen concentration and carbon dioxide concentration.

[0079] The three-dimensional data is projected into a two-dimensional matrix, where each row represents the spatial position of a sampling point, and each column represents the gas concentration value at the corresponding moment in the time series. The element value of the matrix is ​​the gas concentration data.

[0080] Use the fractal analysis model to perform multi-scale decomposition of the gas concentration distribution matrix: By decomposing the gas concentration distribution matrix, the distribution characteristics of concentration data at different spatial scales are extracted.

[0081] A multi-scale analysis model based on fractal theory is adopted, and the fractal dimension is used to reflect the distribution complexity of the gas concentration field at different spatial scales.

[0082] The decomposition process includes: Divide spatial units: Divide the risk analysis area into multiple small cells, and the size of each cell corresponds to a spatial scale.

[0083] Statistical concentration distribution: In each cell, the distribution range of gas concentration values ​​(such as maximum and minimum values) and gradient changes are statistically analyzed.

[0084] Gradually reduce the cell size: continuously reduce the size of the cell (i.e., spatial scale), repeatedly count the concentration distribution characteristics, and record the concentration distribution data at different scales.

[0085] The fractal dimension of each scale is calculated, and the degree of gas diffusion balance in the local area is evaluated according to the change trend of the fractal dimension: The fractal dimension reflects the complexity of the gas concentration distribution and is used to quantify the variation of the concentration field at different spatial scales. The larger the value, the more complex the distribution of the concentration field.

[0086] Within each decomposition scale, the distribution frequency of gas concentration within the spatial unit is statistically analyzed.

[0087] The fractal dimension is calculated using the logarithmic regression method, and the formula is: ;in, represents the fractal dimension, Decomposition scale The probability of gas concentration distribution under Indicates the current decomposition scale.

[0088] The fractal dimension values ​​at different decomposition scales are recorded to form a fractal dimension change curve. If the fractal dimension changes dramatically at multiple scales, it means that the gas concentration field in the area is unevenly distributed.

[0089] The greater the change trend of the fractal dimension, the lower the degree of gas diffusion balance in the local area, indicating that the complexity of gas concentration distribution at different spatial scales is significantly different, which may lead to obstruction of gas diffusion paths, insufficient oxygen supply in local areas or accumulation of carbon dioxide, thereby affecting fermentation efficiency and microbial metabolic activity.

[0090] Among them, the change trend of the fractal dimension can be calculated by comparing the change of the fractal dimension at different decomposition scales to reflect the change of the spatial distribution complexity of the gas concentration field. The specific steps are as follows: For each decomposition scale, the corresponding fractal dimension is calculated based on the cell side length and the number of non-empty cells at the current scale, and the fractal dimension values ​​at all decomposition scales are recorded in turn.

[0091] Arrange them in order from large to small decomposition scales in order to observe and analyze the trend of fractal dimension changing with decomposition scale.

[0092] The variation of fractal dimensions at adjacent decomposition scales is calculated in turn, and these variations are used to reflect the differences in the distribution complexity of the gas concentration field.

[0093] The variation of fractal dimension is organized into a distribution curve, and the main trend of fractal dimension variation with decomposition scale is extracted from the curve. If the variation of fractal dimension increases significantly at multiple decomposition scales, it means that the distribution complexity of gas concentration field is high and the uniformity is poor; on the contrary, if the variation is small, it means that the distribution is more uniform.

[0094] Based on the time dependence of gas exchange and metabolic processes and the degree of gas diffusion balance in local areas, the structure of the straw fermentation pile and the parameters of the ventilation device are quantitatively adjusted through closed-loop control, including: The changing trends of the time dependence index and fractal dimension extracted from the risk analysis region reflect the dynamic relationship between gas exchange and metabolism and the degree of gas diffusion balance, respectively.

[0095] If the time dependence index is large, it indicates that the dynamic delay of gas exchange and metabolic product generation is significant, and it is necessary to adjust the shape of the pile in the time lag area, giving priority to increasing the gas flow path; if the time dependence index is small, it means that the gas exchange is relatively timely, and the original structure can be maintained to avoid excessive adjustment.

[0096] If the fractal dimension changes in a large trend, it indicates that the complexity of the gas concentration distribution increases, and it is necessary to optimize the pile shape, reduce the local height difference or adjust the compaction degree; if the fractal dimension changes in a small trend, it indicates that the gas diffusion uniformity is good, and the adjustment range of the shape and compaction degree can be reduced.

[0097] According to the changing trends of the time dependency index and fractal dimension, the target parameters for adjusting the fermentation pile structure are set, including pile shape parameters and compaction parameters: Pile shape parameters: For areas with a large time dependence index, the pile height or inclination angle is stretched first to reduce gas flow resistance; for areas with a large fractal dimension change trend, the pile width is adjusted to improve the local diffusion path.

[0098] Compactness parameter: For areas where diffusion is hindered, gas fluidity can be improved by reducing the compaction (such as reducing the local accumulation weight); for areas where diffusion is too fast, the compaction can be increased (such as increasing the weight) to control gas leakage.

[0099] According to the changing trend of the time dependency index and fractal dimension, the ventilation device adjustment target parameters are set, including the switch state and flow parameters of the ventilation pipeline: The time dependence index is large: it is necessary to increase the ventilation volume, shorten the delay of gas exchange, give priority to opening the ventilation ducts in the time lag area, and increase the airflow intensity.

[0100] The fractal dimension has a large variation trend: the ventilation direction needs to be adjusted for areas with uneven diffusion, and the pipelines in areas with high concentration gradients need to be opened first to reduce complexity.

[0101] Switching state: In areas with a large time dependence index, more pipelines are opened to ensure gas exchange efficiency; in areas with large fractal dimension changes, ventilation pipelines close to the center are opened first to optimize gas diffusion.

[0102] Airflow rate: The area with large time dependency index increases the airflow velocity, and the area with large fractal dimension changes accurately controls the airflow distribution of each pipeline to avoid excessive ventilation.

[0103] Adjustment target parameters of the fermentation pile structure and ventilation device based on adjustment target parameters: perform fermentation pile structure adjustment through a closed-loop control system, including changing the shape and compaction of the fermentation pile; adjust the ventilation device through a closed-loop control system, including controlling the switch of the ventilation pipeline and the airflow rate: Shape adjustment: In areas with a large time dependence index, the pile height is adjusted by a hydraulic push rod to form a smoother vertical flow channel for gas; in areas with a large fractal dimension change trend, the pile width and inclination angle are adjusted to reduce the blockage caused by uneven diffusion.

[0104] Adjustment of compaction degree: Reduce the stacking weight in high compaction areas to improve the gas diffusion path; increase the local weight or use compaction equipment in low compaction areas to improve gas retention capacity.

[0105] During the adjustment process, the pile shape and compaction degree are monitored in real time, and the adjustment parameters are dynamically corrected by comparing the sensor data with the target values.

[0106] Switch control: For areas with a large time dependence index, open the ventilation pipeline to prioritize the removal of carbon dioxide produced by metabolism; for areas with a large fractal dimension change trend, open the pipeline directly connected to the area to improve the concentration distribution.

[0107] Flow control: Increase airflow velocity in areas with large time dependence index to accelerate gas exchange; accurately control airflow in areas with large fractal dimension change trends, focusing on areas with uneven ventilation diffusion.

[0108] Equipped with flow sensors to monitor the air flow and regional concentration gradient of each pipeline in real time; compare the monitoring data with the target parameters and automatically adjust the fan power and airflow distribution ratio.

[0109] Example 2: The difference between Example 2 of the present invention and Example 1 is that this example introduces a straw feed fermentation processing control system.

[0110] Figure 2 A structural schematic diagram of a straw feed fermentation processing control system of the present invention is given, which includes an environmental parameter acquisition module, a stratified air mass identification module, a pile pressure deformation measurement module, a risk area marking module, a time-dependent analysis module, a diffusion equilibrium evaluation module and a closed-loop control adjustment module.

[0111] Environmental parameter acquisition module: collects fermentation pile environmental parameters at the straw fermentation pile, reconstructs the three-dimensional gas concentration field of the fermentation pile environmental parameters, and obtains the gas distribution information at various positions inside the straw fermentation pile.

[0112] Stratified air mass identification module: Use fuzzy clustering algorithm to classify and analyze gas distribution information and identify stratified air mass areas with gas concentration gradient characteristics.

[0113] Pile pressure deformation measurement module: measures the pile pressure distribution and deformation characteristics of the straw fermentation pile, analyzes the potential impact of uneven gas diffusion in the straw fermentation pile, and identifies abnormal areas of the pile structure.

[0114] Risk area marking module: Mark the union of the stratified air mass area and the abnormal pile structure area as the risk analysis area.

[0115] Time-dependent analysis module: By constructing a three-dimensional tensor model, the dynamic relationship between gas concentration and metabolites in the risk analysis area is analyzed to evaluate the time dependence of gas exchange and metabolic processes.

[0116] Diffusion balance assessment module: Analyze the distribution characteristics of the gas concentration field in the risk analysis area through the fractal analysis model, and evaluate the degree of gas diffusion balance in the local area.

[0117] Closed-loop control regulation module: Based on the time dependence of gas exchange and metabolic processes and the degree of gas diffusion balance in local areas, the straw fermentation pile structure and ventilation device parameters are quantitatively adjusted through closed-loop control.

[0118] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0119] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or may be transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0120] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0121] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0122] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0123] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0124] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0125] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0126] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0127] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A straw feed fermentation treatment control method, characterized in that: The steps include: Collect fermentation pile environmental parameters at the straw fermentation pile, reconstruct the three-dimensional gas concentration field of the fermentation pile environmental parameters, and obtain gas distribution information at various positions inside the straw fermentation pile; Fuzzy clustering algorithm is used to classify and analyze gas distribution information and identify stratified air mass areas with gas concentration gradient characteristics. Measure the pile pressure distribution and deformation characteristics of the straw fermentation pile, analyze the potential impact of uneven gas diffusion in the straw fermentation pile, and identify abnormal areas of the pile structure; The union of the stratified gas mass area and the abnormal pile structure area is marked as the risk analysis area; The dynamic relationship between gas concentration and metabolites in the risk analysis area was analyzed by constructing a three-dimensional tensor model to evaluate the temporal dependence of gas exchange and metabolic processes. The distribution characteristics of the gas concentration field in the risk analysis area are analyzed through the fractal analysis model to evaluate the gas diffusion balance in the local area; Based on the time dependence of gas exchange and metabolic processes and the degree of gas diffusion balance in local areas, the structure of the straw fermentation pile and the parameters of the ventilation device are quantitatively adjusted through closed-loop control.

2. A straw feed fermentation processing control method according to claim 1, characterized in that: The fermentation pile environmental parameters are collected at the straw fermentation pile, and the three-dimensional gas concentration field reconstruction processing is performed on the fermentation pile environmental parameters to obtain the gas distribution information at each position inside the straw fermentation pile, including: A plurality of collection points are set in the vertical range from the bottom to the top and the horizontal range from the center to the edge of the straw fermentation pile to collect the fermentation pile environmental parameters, including oxygen concentration, carbon dioxide concentration and humidity; Based on the geometric shape of the straw fermentation pile and the spatial distribution of the collection points, a three-dimensional coordinate system matching the straw fermentation pile is constructed; The environmental parameters of the fermentation pile are mapped to a three-dimensional coordinate system to generate gas distribution information at various positions inside the straw fermentation pile; the gas distribution information includes oxygen concentration distribution, carbon dioxide concentration distribution and humidity distribution.

3. A straw feed fermentation processing control method according to claim 2, characterized in that: The fuzzy clustering algorithm is used to classify and analyze the gas distribution information and identify the stratified air mass areas with gas concentration gradient characteristics, including: Based on the oxygen concentration distribution, carbon dioxide concentration distribution and humidity distribution of each point in the three-dimensional space, the parameter value of each spatial point in the gas distribution information is used as a clustering feature; Using fuzzy clustering algorithm, the spatial points in the gas distribution information are classified according to the gas concentration gradient characteristics of the spatial points to form multiple cluster categories; Cluster categories with significant gas concentration gradient characteristics and whose spatial distribution characteristics conform to the characteristics of stratified air masses are marked as stratified air mass areas.

4. A straw feed fermentation processing control method according to claim 3, characterized in that: The pile pressure distribution and deformation characteristics of the straw fermentation pile were measured, the potential impact of uneven gas diffusion in the straw fermentation pile was analyzed, and abnormal areas of the pile structure were identified, including: Multiple pressure-sensitive sensors are arranged in the vertical and horizontal directions of the straw fermentation pile to measure the pile pressure value at each position; Scan the surface shape of the straw fermentation pile using a three-dimensional scanning device to obtain three-dimensional morphological feature data of the straw fermentation pile; Compare and analyze the pile pressure value and three-dimensional morphological feature data to identify abnormal pile pressure areas and significant deformation areas; According to the locations of abnormal stack pressure areas and significant deformation areas, abnormal stack structure areas that may affect gas diffusion are identified.

5. A straw feed fermentation processing control method according to claim 4, characterized in that: By constructing a three-dimensional tensor model to analyze the dynamic relationship between gas concentration and metabolites in the risk analysis area, the time dependence of gas exchange and metabolic processes was evaluated, including: Obtain gas concentration data and metabolite concentration data at each location in the risk analysis area; The gas concentration data and metabolite concentration data are mapped to different dimensions of the three-dimensional tensor using the time series as the dimension; The three-dimensional tensor is decomposed using a time-dependent dynamic modeling algorithm to extract the main dynamic factors of gas concentration and metabolic product changes; Analyze the relationship between the main dynamic factors and calculate the time lag characteristics of changes in gas concentration and metabolite concentration; The temporal dependence of gas exchange and metabolic processes was quantitatively assessed based on time lag characteristics.

6. A straw feed fermentation processing control method according to claim 5, characterized in that: Analyze the relationship between the main dynamic factors and calculate the time lag characteristics of the changes in gas concentration and metabolite concentration, specifically: For each main dynamic factor, the time difference between the change in gas concentration and the change in metabolite concentration is calculated using the following formula: ;in, Indicates The time lag value of the main dynamic factors, represents the correlation function, Indicates at a point in time Time The time variation characteristics of the main dynamic factors related to gas concentration, Indicates at a point in time Time The temporal variation characteristics of the main dynamic factors related to the concentration of metabolites, It represents the lag time of the time change of gas concentration relative to the time change of metabolite concentration. Represents a specific time point in a time series.

7. A straw feed fermentation processing control method according to claim 6, characterized in that: The temporal dependence of gas exchange and metabolic processes was quantitatively evaluated based on the time lag characteristics, specifically: Calculate the time dependency index, which is expressed as: ;in, represents the time dependence index, Indicates The weights of the main dynamic factors, greater than 0, Indicates the number of main dynamic factors extracted, is the number of the main dynamic factor.

8. A straw feed fermentation processing control method according to claim 7, characterized in that: The fractal analysis model is used to analyze the distribution characteristics of the gas concentration field in the risk analysis area and evaluate the degree of gas diffusion balance in the local area, including: The gas concentration data in the risk analysis area are sorted according to the spatial location and time dimensions to form a gas concentration distribution matrix; Use fractal analysis model to perform multi-scale decomposition of gas concentration distribution matrix; The fractal dimension of each scale is calculated, and the degree of gas diffusion equilibrium in the local area is evaluated according to the changing trend of the fractal dimension; the changing trend of the fractal dimension is calculated by comparing the changes in the fractal dimension at different decomposition scales.

9. A straw feed fermentation processing control method according to claim 8, characterized in that: Based on the time dependence of gas exchange and metabolic processes and the degree of gas diffusion balance in local areas, the structure of the straw fermentation pile and the parameters of the ventilation device are quantitatively adjusted through closed-loop control, including: According to the changing trends of the time dependency index and fractal dimension, the target parameters for adjusting the fermentation pile structure are set, including pile shape parameters and compaction degree parameters; According to the changing trend of the time dependency index and the fractal dimension, the ventilation device adjustment target parameters are set, including the switch state and flow parameters of the ventilation pipeline; Adjustment target parameters of the fermentation pile structure and ventilation device based on adjustment target parameters: perform fermentation pile structure adjustment through a closed-loop control system, including changing the shape and compaction degree of the fermentation pile; adjust the ventilation device through a closed-loop control system, including controlling the switch of the ventilation pipeline and the airflow rate.

10. A straw feed fermentation processing control system, used to implement a straw feed fermentation processing control method according to any one of claims 1 to 9, characterized in that: It includes an environmental parameter acquisition module, a layered air mass identification module, a pile pressure deformation measurement module, a risk area marking module, a time-dependent analysis module, a diffusion equilibrium assessment module, and a closed-loop control adjustment module; Environmental parameter acquisition module: collects fermentation pile environmental parameters at the straw fermentation pile, performs three-dimensional gas concentration field reconstruction on the fermentation pile environmental parameters, and obtains gas distribution information at various positions inside the straw fermentation pile; Layered air mass identification module: uses fuzzy clustering algorithm to classify and analyze gas distribution information and identify layered air mass areas with gas concentration gradient characteristics; Pile pressure deformation measurement module: measures the pile pressure distribution and deformation characteristics of the straw fermentation pile, analyzes the potential impact of uneven gas diffusion in the straw fermentation pile, and identifies abnormal areas of the pile structure; Risk area marking module: marks the union of the stratified air mass area and the abnormal pile structure area as the risk analysis area; Time-dependent analysis module: By constructing a three-dimensional tensor model to analyze the dynamic relationship between gas concentration and metabolites in the risk analysis area, the time dependency of gas exchange and metabolic processes is evaluated; Diffusion balance assessment module: Analyze the distribution characteristics of the gas concentration field in the risk analysis area through the fractal analysis model, and evaluate the degree of gas diffusion balance in the local area; Closed-loop control regulation module: Based on the time dependence of gas exchange and metabolic processes and the degree of gas diffusion balance in local areas, the straw fermentation pile structure and ventilation device parameters are quantitatively adjusted through closed-loop control.

Images